Abstract

Semantic segmentation represents a promising means to unify different detection tasks, especially pixel-wise traversability perception as the fundamental enabler in robotic vision systems aiding upper-level navigational applications. However, major research efforts are being put into earning marginal accuracy increments on semantic segmentation benchmarks, without assuring the robustness of real-time segmenters to be deployed in assistive cognition systems for the visually impaired. In this paper, we explore in a comparative study across four perception systems, including a pair of commercial smart glasses, a customized wearable prototype, and two portable red–green–blue-depth (RGB-D) cameras that are being integrated in the next generation of navigation assistance devices. More concretely, we analyze the gap between the concepts of “accuracy” and “robustness” on the critical traversability-related semantic scene understanding. A cluster of efficient deep architectures is proposed, which is built using spatial factorizations, hierarchical dilations, and pyramidal representations. Based on these architectures, this research demonstrates the augmented robustness of semantically traversable area parsing against the variations of environmental conditions in diverse RGB-D observations, and sensorial factors such as illumination, imaging quality, field of view, and detectable depth range.

© 2019 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Reducing the minimum range of a RGB-depth sensor to aid navigation in visually impaired individuals

Kailun Yang, Kaiwei Wang, Hao Chen, and Jian Bai
Appl. Opt. 57(11) 2809-2819 (2018)

Unconstrained self-calibration of stereo camera on visually impaired assistance devices

Huabing Li, Kaiwei Wang, Kailun Yang, Ruiqi Cheng, Chen Wang, and Lei Fei
Appl. Opt. 58(23) 6377-6387 (2019)

Encoder–decoder with densely convolutional networks for monocular depth estimation

Songnan Chen, Mengxia Tang, and Jiangming Kan
J. Opt. Soc. Am. A 36(10) 1709-1718 (2019)

References

  • View by:
  • |
  • |
  • |

  1. Krvision, “To tackle the challenges for the visually impaired,” 2016, http://krvision.cn .
  2. R. Girshick, “Fast R-CNN,” in International Conference on Computer Vision (IEEE, 2015), pp. 1440–1448.
  3. J. Long, E. Shelhamer, and T. Darrel, “Fully convolutional networks for semantic segmentation,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2015), pp. 3431–3440.
  4. K. Yang, L. M. Bergasa, E. Romera, R. Cheng, T. Chen, and K. Wang, “Unifying terrain awareness through real-time semantic segmentation,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1033–1038.
  5. K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
    [Crossref]
  6. M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.
  7. G. Neuhold, T. Ollmann, S. R. Bulò, and P. Kontschieder, “The mapillary vistas dataset for semantic understanding of street scenes,” in International Conference on Computer Vision (IEEE, 2017), pp. 5000–5009.
  8. K. Yang, “Panoramic annular semantic segmentation,” 2019, https://github.com/elnino9ykl/PASS .
  9. G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
    [Crossref]
  10. F. Yu and V. Koltun, “Multi-scale context aggregation by dilated convolutions,” arXiv:1511.07122 (2015).
  11. T. Pohlen, A. Hermans, M. Mathias, and B. Leibe, “Full-resolution residual networks for semantic segmentation in street scenes,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 3309–3318.
  12. L. C. Chen, Y. Zhu, G. Papandreous, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in European Conference on Computer Vision (2018), pp. 801–818.
  13. Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.
  14. K. Saleh, R. A. Zeineldin, M. Hossny, S. Nahavandi, and N. A. El-Fishawy, “Navigational path detection for the visually impaired using fully convolutional networks,” in International Conference on Systems, Man, and Cybernetics (IEEE, 2017), pp. 1399–1404.
  15. A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
    [Crossref]
  16. K. Yang, K. Wang, W. Hu, and J. Bai, “Expanding the detection of traversable area with RealSense for the visually impaired,” Sensors 16, C1 (2016).
    [Crossref]
  17. D. Pfeiffer and U. Franke, “Efficient representation of traffic scenes by means of dynamic stixels,” in Intelligent Vehicles Symposium (IEEE, 2010), pp. 217–224.
  18. M. Martinez, A. Roitberg, D. Koester, B. Stiefelhagen, and B. Schauerte, “Using technology developed for autonomous cars to help navigate blind people,” in International Conference on Computer Vision Workshops (IEEE, 2017), pp. 1424–1432.
  19. H. C. Wang, R. K. Katzschmann, S. Teng, B. Araki, L. Giarré, and D. Rus, “Enabling independent navigation for visually impaired people through a wearable vision-based feedback system,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 6533–6540.
  20. K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
    [Crossref]
  21. K. Yang, K. Wang, S. Lin, J. Bai, L. M. Bergasa, and R. Arroyo, “Long-range traversability awareness and low-lying obstacle negotiation with RealSense for the visually impaired,” in International Conference on Information Science and System (ACM, 2018), pp. 137–141.
  22. L. Deng, M. Yang, H. Li, B. Hu, and C. Wang, “Restricted deformable convolution based road scene semantic segmentation using surround view cameras,” arXiv:1801.00708 (2018).
  23. A. Sáez, L. M. Bergasa, E. Romera, E. López, R. Barea, and R. Sanz, “CNN-based fisheye image real-time semantic segmentation,” in Intelligent Vehicles Symposium (IEEE, 2018), pp. 1039–1044.
  24. K. Yang, R. Cheng, L. M. Bergasa, E. Romera, K. Wang, and N. Long, “Intersection perception through real-time semantic segmentation to assist navigation of visually impaired pedestrians,” in International Conference on Robotics and Biomimetics (IEEE, 2018), pp. 1034–1039.
  25. F. Schilling, X. Chen, J. Folkesson, and P. Jensfelt, “Geometric and visual terrain classification for autonomous mobile navigation,” in International Conference on Intelligent Robots and Systems (IEEE, 2017), pp. 2678–2684.
  26. S. Ramos, S. Gehrig, P. Pinggera, U. Franke, and C. Rother, “Detecting unexpected obstacles for self-driving cars: fusing deep learning and geometric modeling,” in IEEE Intelligent Vehicles Symposium (IEEE, 2017), pp. 1025–1032.
  27. V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: a deep convolutional encoder-decoder architecture for image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017).
    [Crossref]
  28. A. Paszke, A. Chaurasia, S. Kim, and E. Culurciello, “ENet: a deep neural network architecture for real-time semantic segmentation,” arXiv:1606.02147 (2016).
  29. A. Chaurasia and E. Culurciello, “LinkNet: exploiting encoder representations for efficient semantic segmentation,” in IEEE Visual Communications and Image Processing (IEEE, 2017), pp. 1–4.
  30. E. Romera, J. M. Alvarez, L. M. Bergasa, and R. Arroyo, “ERFNet: efficient residual factorized convnet for real-time semantic segmentation,” IEEE Trans. Intell. Transp. Syst. 19, 263–272 (2018).
    [Crossref]
  31. H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, “ICnet for real-time semantic segmentation on high-resolution images,” in European Conference on Computer Vision (2018), pp. 405–420.
  32. M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.
  33. W. Wang and Z. Pan, “DSNet for real-time driving scene semantic segmentation,” arXiv:1812.07049 (2018).
  34. R. P. Poudel, U. Bonde, S. Liwicki, and C. Zach, “ContextNet: exploring context and detail for semantic segmentation in real-time,” arXiv:1805.04554 (2018).
  35. R. P. Poudel, S. Liwicki, and R. Cipolla, “Fast-SCNN: fast semantic segmentation network,” arXiv:1902.04502 (2019).
  36. Q. Ning, J. Zhu, and C. Chen, “Very fast semantic image segmentation using hierarchical dilation and feature refining,” Cognit. Comput. 10, 62–72 (2018).
    [Crossref]
  37. L. Tang, X. Ding, H. Yin, Y. Wang, and R. Xiong, “From one to many: unsupervised traversable area segmentation in off-road environment,” in International Conference on Robotics and Biomimetics (IEEE, 2017), pp. 787–792.
  38. Y. H. Tsai, W. C. Hung, S. Schulter, K. Sohn, M. H. Yang, and M. Chandraker, “Learning to adapt structured output space for semantic segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2018), pp. 7472–7481.
  39. Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
    [Crossref]
  40. S. Mehta, H. Hajishirzi, and L. Shapiro, “Identifying most walkable direction for navigation in an outdoor environment,” arXiv:1711.08040 (2017).
  41. D. K. Kim, D. Maturana, M. Uenoyama, and S. Scherer, “Season-invariant semantic segmentation with a deep multimodal network,” in Field and Service Robotics (Springer, 2018), pp. 255–270.
  42. A. Valada, J. Vertens, A. Dhall, and W. Burgard, “AdapNet: adaptive semantic segmentation in adverse environmental conditions,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 4644–4651.
  43. K. Yang, L. M. Bergasa, E. Romera, X. Huang, and K. Wang, “Predicting polarization beyond semantics for wearable robotics,” in International Conference on Humanoid Robots (IEEE, 2018), pp. 96–103.
  44. N. Alshammari, S. Akcay, and T. P. Breckon, “On the impact of illumination-invariant image pre-transformation on contemporary automotive semantic scene understanding,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1027–1032.
  45. C. Sakaridis, D. Dai, S. Hecker, and L. Van Gool, “Model adaptation with synthetic and real data for semantic dense foggy scene understanding,” in European Conference on Computer Vision (2018), pp. 707–724.
  46. C. Sakaridis, D. Dai, and L. Van Gool, “Semantic nighttime image segmentation with synthetic stylized data, gradual adaptation and uncertainty-aware evaluation,” arXiv:1901.05946 (2019).
  47. A. Arnab, O. Miksik, and P. H. Torr, “On the robustness of semantic segmentation models to adversarial attacks,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018), pp. 888–897.
  48. G. L. Oliveira, C. Bollen, W. Burgard, and T. Brox, “Efficient and robust deep networks for semantic segmentation,” Int. J. Robot. Res. 37, 472–491 (2018).
    [Crossref]
  49. O. Zendel, K. Honauer, M. Murschitz, D. Steininger, and G. F. Dominguez, “WildDash-creating hazard-aware benchmarks,” in European Conference on Computer Vision (2018), pp. 402–416.
  50. M. Larsson, E. Stenborg, L. Hammarstrand, T. Sattler, M. Pollefeys, and F. Kahl, “A cross-season correspondence dataset for robust semantic segmentation,” arXiv:1903.06916 (2019).
  51. L. Keselman, J. Iselin Woodfill, A. Grunnet-Jepsen, and A. Bhowmik, “Intel RealSense stereoscopic depth cameras,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (IEEE, 2018), pp. 1–10.
  52. L. E. Ortiz, E. V. Cabrera, and L. M. Gonçalves, “Depth data error modeling of the ZED 3D vision sensor from stereolabs,” Electr. Lett. Comput. Vis. Image Anal. 17, 1–15 (2018).
    [Crossref]
  53. S. Giancola, M. Valenti, and R. Sala, “Metrological qualification of the intel D400TM active stereoscopy cameras,” in A Survey on 3D Cameras: Metrological Comparison of Time-of-Flight, Structured-Light and Active Stereoscopy Technologies (Springer, 2018), pp. 71–85.
  54. Stereolabs, “Meet ZED Mini: the world’s first camera for mixed-reality,” 2018, https://www.stereolabs.com/zed-mini .
  55. K. Yang, K. Wang, H. Chen, and J. Bai, “Reducing the minimum range of a RGB-depth sensor to aid navigation in visually impaired individuals,” Appl. Opt. 57, 2809–2819 (2018).
    [Crossref]
  56. K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
    [Crossref]
  57. K. Yang, “Sequential/hierarchical ERF-PSPNet,” 2018, https://github.com/elnino9ykl/ERF-PSPNet .
  58. K. Xiang, “ERF-PSPNET implemented by tensorflow” 2018, https://github.com/Katexiang/ERF-PSPNET .
  59. D. Sun, “ERF-PSPNet on TX2,” 2018, https://github.com/dongmingsun/tx2-erfpsp .
  60. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 770–778.
  61. H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 6230–6239.
  62. E. Romera, L. M. Bergasa, J. M. Alvarez, and M. Trivedi, “Train here, deploy there: robust segmentation in unseen domains,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1823–1833.
  63. K. Wang, “RGB-D-SS dataset,” 2018, http://wangkaiwei.org/downloadeg.html .
  64. D. P. Kingma and J. Ba, “Adam: a method for stochastic optimization,” arXiv:1412.6980 (2014).
  65. T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in International Conference on Computer Vision (IEEE, 2017), pp. 2990–3007.
  66. X. Y. Zhou, C. Riga, S. L. Lee, and G. Z. Yang, “Towards automatic 3D shape instantiation for deployed stent grafts: 2D multiple-class and class-imbalance marker segmentation with equally-weighted focal U-Net,” in International Conference on Intelligent Robots and Systems (IEEE, 2018), pp. 1261–1267.
  67. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
    [Crossref]
  68. K. He, J. Sun, and X. Tang, “Guided image filtering,” in European Conference on Computer Vision (2010), pp. 1–14.
  69. L. He, G. Wang, and Z. Hu, “Learning depth from single images with deep neural network embedding focal length,” IEEE Trans. Image Process. 27, 4676–4689 (2018).
    [Crossref]
  70. B. Chen, C. Gong, and J. Yang, “Importance-aware semantic segmentation for autonomous vehicles,” IEEE Trans. Intell. Transp. Syst. 20, 137–148 (2019).
    [Crossref]
  71. Y. Luo, X. Huang, J. Bai, and R. Liang, “Compact polarization-based dual-view panoramic lens,” Appl. Opt. 56, 6283–6287 (2017).
    [Crossref]
  72. K. Yang, “ZJU day and night driving dataset,” 2019, https://github.com/elnino9ykl/ZJU-Dataset .

2019 (1)

B. Chen, C. Gong, and J. Yang, “Importance-aware semantic segmentation for autonomous vehicles,” IEEE Trans. Intell. Transp. Syst. 20, 137–148 (2019).
[Crossref]

2018 (9)

L. He, G. Wang, and Z. Hu, “Learning depth from single images with deep neural network embedding focal length,” IEEE Trans. Image Process. 27, 4676–4689 (2018).
[Crossref]

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
[Crossref]

E. Romera, J. M. Alvarez, L. M. Bergasa, and R. Arroyo, “ERFNet: efficient residual factorized convnet for real-time semantic segmentation,” IEEE Trans. Intell. Transp. Syst. 19, 263–272 (2018).
[Crossref]

Q. Ning, J. Zhu, and C. Chen, “Very fast semantic image segmentation using hierarchical dilation and feature refining,” Cognit. Comput. 10, 62–72 (2018).
[Crossref]

Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
[Crossref]

G. L. Oliveira, C. Bollen, W. Burgard, and T. Brox, “Efficient and robust deep networks for semantic segmentation,” Int. J. Robot. Res. 37, 472–491 (2018).
[Crossref]

L. E. Ortiz, E. V. Cabrera, and L. M. Gonçalves, “Depth data error modeling of the ZED 3D vision sensor from stereolabs,” Electr. Lett. Comput. Vis. Image Anal. 17, 1–15 (2018).
[Crossref]

K. Yang, K. Wang, H. Chen, and J. Bai, “Reducing the minimum range of a RGB-depth sensor to aid navigation in visually impaired individuals,” Appl. Opt. 57, 2809–2819 (2018).
[Crossref]

2017 (3)

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: a deep convolutional encoder-decoder architecture for image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017).
[Crossref]

Y. Luo, X. Huang, J. Bai, and R. Liang, “Compact polarization-based dual-view panoramic lens,” Appl. Opt. 56, 6283–6287 (2017).
[Crossref]

2016 (2)

K. Yang, K. Wang, W. Hu, and J. Bai, “Expanding the detection of traversable area with RealSense for the visually impaired,” Sensors 16, C1 (2016).
[Crossref]

K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
[Crossref]

2015 (1)

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

2012 (1)

A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
[Crossref]

Adam, H.

L. C. Chen, Y. Zhu, G. Papandreous, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in European Conference on Computer Vision (2018), pp. 801–818.

Akcay, S.

N. Alshammari, S. Akcay, and T. P. Breckon, “On the impact of illumination-invariant image pre-transformation on contemporary automotive semantic scene understanding,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1027–1032.

Alcantarilla, P. F.

A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
[Crossref]

Almazán, J.

A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
[Crossref]

Alshammari, N.

N. Alshammari, S. Akcay, and T. P. Breckon, “On the impact of illumination-invariant image pre-transformation on contemporary automotive semantic scene understanding,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1027–1032.

Alvarez, J. M.

E. Romera, J. M. Alvarez, L. M. Bergasa, and R. Arroyo, “ERFNet: efficient residual factorized convnet for real-time semantic segmentation,” IEEE Trans. Intell. Transp. Syst. 19, 263–272 (2018).
[Crossref]

E. Romera, L. M. Bergasa, J. M. Alvarez, and M. Trivedi, “Train here, deploy there: robust segmentation in unseen domains,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1823–1833.

Araki, B.

H. C. Wang, R. K. Katzschmann, S. Teng, B. Araki, L. Giarré, and D. Rus, “Enabling independent navigation for visually impaired people through a wearable vision-based feedback system,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 6533–6540.

Arjona-Medina, J.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Arnab, A.

A. Arnab, O. Miksik, and P. H. Torr, “On the robustness of semantic segmentation models to adversarial attacks,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018), pp. 888–897.

Arroyo, R.

E. Romera, J. M. Alvarez, L. M. Bergasa, and R. Arroyo, “ERFNet: efficient residual factorized convnet for real-time semantic segmentation,” IEEE Trans. Intell. Transp. Syst. 19, 263–272 (2018).
[Crossref]

K. Yang, K. Wang, S. Lin, J. Bai, L. M. Bergasa, and R. Arroyo, “Long-range traversability awareness and low-lying obstacle negotiation with RealSense for the visually impaired,” in International Conference on Information Science and System (ACM, 2018), pp. 137–141.

Ba, J.

D. P. Kingma and J. Ba, “Adam: a method for stochastic optimization,” arXiv:1412.6980 (2014).

Badrinarayanan, V.

V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: a deep convolutional encoder-decoder architecture for image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017).
[Crossref]

Bai, J.

K. Yang, K. Wang, H. Chen, and J. Bai, “Reducing the minimum range of a RGB-depth sensor to aid navigation in visually impaired individuals,” Appl. Opt. 57, 2809–2819 (2018).
[Crossref]

Y. Luo, X. Huang, J. Bai, and R. Liang, “Compact polarization-based dual-view panoramic lens,” Appl. Opt. 56, 6283–6287 (2017).
[Crossref]

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

K. Yang, K. Wang, W. Hu, and J. Bai, “Expanding the detection of traversable area with RealSense for the visually impaired,” Sensors 16, C1 (2016).
[Crossref]

K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
[Crossref]

K. Yang, K. Wang, S. Lin, J. Bai, L. M. Bergasa, and R. Arroyo, “Long-range traversability awareness and low-lying obstacle negotiation with RealSense for the visually impaired,” in International Conference on Information Science and System (ACM, 2018), pp. 137–141.

Barea, R.

A. Sáez, L. M. Bergasa, E. Romera, E. López, R. Barea, and R. Sanz, “CNN-based fisheye image real-time semantic segmentation,” in Intelligent Vehicles Symposium (IEEE, 2018), pp. 1039–1044.

Benenson, R.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

Berg, A. C.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Bergasa, L. M.

E. Romera, J. M. Alvarez, L. M. Bergasa, and R. Arroyo, “ERFNet: efficient residual factorized convnet for real-time semantic segmentation,” IEEE Trans. Intell. Transp. Syst. 19, 263–272 (2018).
[Crossref]

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
[Crossref]

A. Sáez, L. M. Bergasa, E. Romera, E. López, R. Barea, and R. Sanz, “CNN-based fisheye image real-time semantic segmentation,” in Intelligent Vehicles Symposium (IEEE, 2018), pp. 1039–1044.

K. Yang, R. Cheng, L. M. Bergasa, E. Romera, K. Wang, and N. Long, “Intersection perception through real-time semantic segmentation to assist navigation of visually impaired pedestrians,” in International Conference on Robotics and Biomimetics (IEEE, 2018), pp. 1034–1039.

K. Yang, K. Wang, S. Lin, J. Bai, L. M. Bergasa, and R. Arroyo, “Long-range traversability awareness and low-lying obstacle negotiation with RealSense for the visually impaired,” in International Conference on Information Science and System (ACM, 2018), pp. 137–141.

E. Romera, L. M. Bergasa, J. M. Alvarez, and M. Trivedi, “Train here, deploy there: robust segmentation in unseen domains,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1823–1833.

K. Yang, L. M. Bergasa, E. Romera, X. Huang, and K. Wang, “Predicting polarization beyond semantics for wearable robotics,” in International Conference on Humanoid Robots (IEEE, 2018), pp. 96–103.

K. Yang, L. M. Bergasa, E. Romera, R. Cheng, T. Chen, and K. Wang, “Unifying terrain awareness through real-time semantic segmentation,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1033–1038.

Bernstein, M.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Bhowmik, A.

L. Keselman, J. Iselin Woodfill, A. Grunnet-Jepsen, and A. Bhowmik, “Intel RealSense stereoscopic depth cameras,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (IEEE, 2018), pp. 1–10.

Bollen, C.

G. L. Oliveira, C. Bollen, W. Burgard, and T. Brox, “Efficient and robust deep networks for semantic segmentation,” Int. J. Robot. Res. 37, 472–491 (2018).
[Crossref]

Bonde, U.

R. P. Poudel, U. Bonde, S. Liwicki, and C. Zach, “ContextNet: exploring context and detail for semantic segmentation in real-time,” arXiv:1805.04554 (2018).

Breckon, T. P.

N. Alshammari, S. Akcay, and T. P. Breckon, “On the impact of illumination-invariant image pre-transformation on contemporary automotive semantic scene understanding,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1027–1032.

Brox, T.

G. L. Oliveira, C. Bollen, W. Burgard, and T. Brox, “Efficient and robust deep networks for semantic segmentation,” Int. J. Robot. Res. 37, 472–491 (2018).
[Crossref]

Bulò, S. R.

G. Neuhold, T. Ollmann, S. R. Bulò, and P. Kontschieder, “The mapillary vistas dataset for semantic understanding of street scenes,” in International Conference on Computer Vision (IEEE, 2017), pp. 5000–5009.

Burgard, W.

G. L. Oliveira, C. Bollen, W. Burgard, and T. Brox, “Efficient and robust deep networks for semantic segmentation,” Int. J. Robot. Res. 37, 472–491 (2018).
[Crossref]

A. Valada, J. Vertens, A. Dhall, and W. Burgard, “AdapNet: adaptive semantic segmentation in adverse environmental conditions,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 4644–4651.

Cabrera, E. V.

L. E. Ortiz, E. V. Cabrera, and L. M. Gonçalves, “Depth data error modeling of the ZED 3D vision sensor from stereolabs,” Electr. Lett. Comput. Vis. Image Anal. 17, 1–15 (2018).
[Crossref]

Cai, X.

Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
[Crossref]

Cela, A.

A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
[Crossref]

Chandraker, M.

Y. H. Tsai, W. C. Hung, S. Schulter, K. Sohn, M. H. Yang, and M. Chandraker, “Learning to adapt structured output space for semantic segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2018), pp. 7472–7481.

Chaurasia, A.

A. Chaurasia and E. Culurciello, “LinkNet: exploiting encoder representations for efficient semantic segmentation,” in IEEE Visual Communications and Image Processing (IEEE, 2017), pp. 1–4.

A. Paszke, A. Chaurasia, S. Kim, and E. Culurciello, “ENet: a deep neural network architecture for real-time semantic segmentation,” arXiv:1606.02147 (2016).

Chen, B.

B. Chen, C. Gong, and J. Yang, “Importance-aware semantic segmentation for autonomous vehicles,” IEEE Trans. Intell. Transp. Syst. 20, 137–148 (2019).
[Crossref]

Chen, C.

Q. Ning, J. Zhu, and C. Chen, “Very fast semantic image segmentation using hierarchical dilation and feature refining,” Cognit. Comput. 10, 62–72 (2018).
[Crossref]

Chen, H.

K. Yang, K. Wang, H. Chen, and J. Bai, “Reducing the minimum range of a RGB-depth sensor to aid navigation in visually impaired individuals,” Appl. Opt. 57, 2809–2819 (2018).
[Crossref]

Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
[Crossref]

Chen, L. C.

L. C. Chen, Y. Zhu, G. Papandreous, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in European Conference on Computer Vision (2018), pp. 801–818.

Chen, T.

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

K. Yang, L. M. Bergasa, E. Romera, R. Cheng, T. Chen, and K. Wang, “Unifying terrain awareness through real-time semantic segmentation,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1033–1038.

Chen, X.

F. Schilling, X. Chen, J. Folkesson, and P. Jensfelt, “Geometric and visual terrain classification for autonomous mobile navigation,” in International Conference on Intelligent Robots and Systems (IEEE, 2017), pp. 2678–2684.

Cheng, R.

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
[Crossref]

K. Yang, L. M. Bergasa, E. Romera, R. Cheng, T. Chen, and K. Wang, “Unifying terrain awareness through real-time semantic segmentation,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1033–1038.

K. Yang, R. Cheng, L. M. Bergasa, E. Romera, K. Wang, and N. Long, “Intersection perception through real-time semantic segmentation to assist navigation of visually impaired pedestrians,” in International Conference on Robotics and Biomimetics (IEEE, 2018), pp. 1034–1039.

Choe, G.

G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
[Crossref]

Cipolla, R.

V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: a deep convolutional encoder-decoder architecture for image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017).
[Crossref]

R. P. Poudel, S. Liwicki, and R. Cipolla, “Fast-SCNN: fast semantic segmentation network,” arXiv:1902.04502 (2019).

Cordts, M.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

Culurciello, E.

A. Chaurasia and E. Culurciello, “LinkNet: exploiting encoder representations for efficient semantic segmentation,” in IEEE Visual Communications and Image Processing (IEEE, 2017), pp. 1–4.

A. Paszke, A. Chaurasia, S. Kim, and E. Culurciello, “ENet: a deep neural network architecture for real-time semantic segmentation,” arXiv:1606.02147 (2016).

Dai, D.

C. Sakaridis, D. Dai, S. Hecker, and L. Van Gool, “Model adaptation with synthetic and real data for semantic dense foggy scene understanding,” in European Conference on Computer Vision (2018), pp. 707–724.

C. Sakaridis, D. Dai, and L. Van Gool, “Semantic nighttime image segmentation with synthetic stylized data, gradual adaptation and uncertainty-aware evaluation,” arXiv:1901.05946 (2019).

Darrel, T.

J. Long, E. Shelhamer, and T. Darrel, “Fully convolutional networks for semantic segmentation,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2015), pp. 3431–3440.

Deng, J.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Deng, L.

L. Deng, M. Yang, H. Li, B. Hu, and C. Wang, “Restricted deformable convolution based road scene semantic segmentation using surround view cameras,” arXiv:1801.00708 (2018).

Dhall, A.

A. Valada, J. Vertens, A. Dhall, and W. Burgard, “AdapNet: adaptive semantic segmentation in adverse environmental conditions,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 4644–4651.

Ding, X.

L. Tang, X. Ding, H. Yin, Y. Wang, and R. Xiong, “From one to many: unsupervised traversable area segmentation in off-road environment,” in International Conference on Robotics and Biomimetics (IEEE, 2017), pp. 787–792.

Dollár, P.

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in International Conference on Computer Vision (IEEE, 2017), pp. 2990–3007.

Dominguez, G. F.

O. Zendel, K. Honauer, M. Murschitz, D. Steininger, and G. F. Dominguez, “WildDash-creating hazard-aware benchmarks,” in European Conference on Computer Vision (2018), pp. 402–416.

Durgesh, R.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

El-Fishawy, N. A.

K. Saleh, R. A. Zeineldin, M. Hossny, S. Nahavandi, and N. A. El-Fishawy, “Navigational path detection for the visually impaired using fully convolutional networks,” in International Conference on Systems, Man, and Cybernetics (IEEE, 2017), pp. 1399–1404.

Enzweiler, M.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

Folkesson, J.

F. Schilling, X. Chen, J. Folkesson, and P. Jensfelt, “Geometric and visual terrain classification for autonomous mobile navigation,” in International Conference on Intelligent Robots and Systems (IEEE, 2017), pp. 2678–2684.

Franke, U.

D. Pfeiffer and U. Franke, “Efficient representation of traffic scenes by means of dynamic stixels,” in Intelligent Vehicles Symposium (IEEE, 2010), pp. 217–224.

S. Ramos, S. Gehrig, P. Pinggera, U. Franke, and C. Rother, “Detecting unexpected obstacles for self-driving cars: fusing deep learning and geometric modeling,” in IEEE Intelligent Vehicles Symposium (IEEE, 2017), pp. 1025–1032.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

Friedmann, F.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Gao, W.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Gehrig, S.

S. Ramos, S. Gehrig, P. Pinggera, U. Franke, and C. Rother, “Detecting unexpected obstacles for self-driving cars: fusing deep learning and geometric modeling,” in IEEE Intelligent Vehicles Symposium (IEEE, 2017), pp. 1025–1032.

Giancola, S.

S. Giancola, M. Valenti, and R. Sala, “Metrological qualification of the intel D400TM active stereoscopy cameras,” in A Survey on 3D Cameras: Metrological Comparison of Time-of-Flight, Structured-Light and Active Stereoscopy Technologies (Springer, 2018), pp. 71–85.

Giarré, L.

H. C. Wang, R. K. Katzschmann, S. Teng, B. Araki, L. Giarré, and D. Rus, “Enabling independent navigation for visually impaired people through a wearable vision-based feedback system,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 6533–6540.

Girshick, R.

R. Girshick, “Fast R-CNN,” in International Conference on Computer Vision (IEEE, 2015), pp. 1440–1448.

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in International Conference on Computer Vision (IEEE, 2017), pp. 2990–3007.

Gonçalves, L. M.

L. E. Ortiz, E. V. Cabrera, and L. M. Gonçalves, “Depth data error modeling of the ZED 3D vision sensor from stereolabs,” Electr. Lett. Comput. Vis. Image Anal. 17, 1–15 (2018).
[Crossref]

Gong, C.

B. Chen, C. Gong, and J. Yang, “Importance-aware semantic segmentation for autonomous vehicles,” IEEE Trans. Intell. Transp. Syst. 20, 137–148 (2019).
[Crossref]

Goyal, P.

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in International Conference on Computer Vision (IEEE, 2017), pp. 2990–3007.

Grunnet-Jepsen, A.

L. Keselman, J. Iselin Woodfill, A. Grunnet-Jepsen, and A. Bhowmik, “Intel RealSense stereoscopic depth cameras,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (IEEE, 2018), pp. 1–10.

Hajishirzi, H.

S. Mehta, H. Hajishirzi, and L. Shapiro, “Identifying most walkable direction for navigation in an outdoor environment,” arXiv:1711.08040 (2017).

Hammarstrand, L.

M. Larsson, E. Stenborg, L. Hammarstrand, T. Sattler, M. Pollefeys, and F. Kahl, “A cross-season correspondence dataset for robust semantic segmentation,” arXiv:1903.06916 (2019).

He, K.

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in International Conference on Computer Vision (IEEE, 2017), pp. 2990–3007.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 770–778.

K. He, J. Sun, and X. Tang, “Guided image filtering,” in European Conference on Computer Vision (2010), pp. 1–14.

He, L.

L. He, G. Wang, and Z. Hu, “Learning depth from single images with deep neural network embedding focal length,” IEEE Trans. Image Process. 27, 4676–4689 (2018).
[Crossref]

He, Y.

Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
[Crossref]

Hecker, S.

C. Sakaridis, D. Dai, S. Hecker, and L. Van Gool, “Model adaptation with synthetic and real data for semantic dense foggy scene understanding,” in European Conference on Computer Vision (2018), pp. 707–724.

Hermans, A.

T. Pohlen, A. Hermans, M. Mathias, and B. Leibe, “Full-resolution residual networks for semantic segmentation in street scenes,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 3309–3318.

Heusel, M.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Hofmarcher, M.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Honauer, K.

O. Zendel, K. Honauer, M. Murschitz, D. Steininger, and G. F. Dominguez, “WildDash-creating hazard-aware benchmarks,” in European Conference on Computer Vision (2018), pp. 402–416.

Hossny, M.

K. Saleh, R. A. Zeineldin, M. Hossny, S. Nahavandi, and N. A. El-Fishawy, “Navigational path detection for the visually impaired using fully convolutional networks,” in International Conference on Systems, Man, and Cybernetics (IEEE, 2017), pp. 1399–1404.

Hu, B.

L. Deng, M. Yang, H. Li, B. Hu, and C. Wang, “Restricted deformable convolution based road scene semantic segmentation using surround view cameras,” arXiv:1801.00708 (2018).

Hu, W.

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

K. Yang, K. Wang, W. Hu, and J. Bai, “Expanding the detection of traversable area with RealSense for the visually impaired,” Sensors 16, C1 (2016).
[Crossref]

K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
[Crossref]

Hu, Z.

L. He, G. Wang, and Z. Hu, “Learning depth from single images with deep neural network embedding focal length,” IEEE Trans. Image Process. 27, 4676–4689 (2018).
[Crossref]

Huang, X.

Y. Luo, X. Huang, J. Bai, and R. Liang, “Compact polarization-based dual-view panoramic lens,” Appl. Opt. 56, 6283–6287 (2017).
[Crossref]

K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
[Crossref]

K. Yang, L. M. Bergasa, E. Romera, X. Huang, and K. Wang, “Predicting polarization beyond semantics for wearable robotics,” in International Conference on Humanoid Robots (IEEE, 2018), pp. 96–103.

Huang, Z.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Hung, W. C.

Y. H. Tsai, W. C. Hung, S. Schulter, K. Sohn, M. H. Yang, and M. Chandraker, “Learning to adapt structured output space for semantic segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2018), pp. 7472–7481.

Im, S.

G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
[Crossref]

Iselin Woodfill, J.

L. Keselman, J. Iselin Woodfill, A. Grunnet-Jepsen, and A. Bhowmik, “Intel RealSense stereoscopic depth cameras,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (IEEE, 2018), pp. 1–10.

Jensfelt, P.

F. Schilling, X. Chen, J. Folkesson, and P. Jensfelt, “Geometric and visual terrain classification for autonomous mobile navigation,” in International Conference on Intelligent Robots and Systems (IEEE, 2017), pp. 2678–2684.

Jia, H.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Jia, J.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 6230–6239.

H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, “ICnet for real-time semantic segmentation on high-resolution images,” in European Conference on Computer Vision (2018), pp. 405–420.

Kahl, F.

M. Larsson, E. Stenborg, L. Hammarstrand, T. Sattler, M. Pollefeys, and F. Kahl, “A cross-season correspondence dataset for robust semantic segmentation,” arXiv:1903.06916 (2019).

Karpathy, A.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Katzschmann, R. K.

H. C. Wang, R. K. Katzschmann, S. Teng, B. Araki, L. Giarré, and D. Rus, “Enabling independent navigation for visually impaired people through a wearable vision-based feedback system,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 6533–6540.

Kendall, A.

V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: a deep convolutional encoder-decoder architecture for image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017).
[Crossref]

Keselman, L.

L. Keselman, J. Iselin Woodfill, A. Grunnet-Jepsen, and A. Bhowmik, “Intel RealSense stereoscopic depth cameras,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (IEEE, 2018), pp. 1–10.

Khosla, A.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Kim, D. K.

D. K. Kim, D. Maturana, M. Uenoyama, and S. Scherer, “Season-invariant semantic segmentation with a deep multimodal network,” in Field and Service Robotics (Springer, 2018), pp. 255–270.

Kim, S.

A. Paszke, A. Chaurasia, S. Kim, and E. Culurciello, “ENet: a deep neural network architecture for real-time semantic segmentation,” arXiv:1606.02147 (2016).

Kim, S. H.

G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
[Crossref]

Kingma, D. P.

D. P. Kingma and J. Ba, “Adam: a method for stochastic optimization,” arXiv:1412.6980 (2014).

Koester, D.

M. Martinez, A. Roitberg, D. Koester, B. Stiefelhagen, and B. Schauerte, “Using technology developed for autonomous cars to help navigate blind people,” in International Conference on Computer Vision Workshops (IEEE, 2017), pp. 1424–1432.

Koltun, V.

F. Yu and V. Koltun, “Multi-scale context aggregation by dilated convolutions,” arXiv:1511.07122 (2015).

Kontschieder, P.

G. Neuhold, T. Ollmann, S. R. Bulò, and P. Kontschieder, “The mapillary vistas dataset for semantic understanding of street scenes,” in International Conference on Computer Vision (IEEE, 2017), pp. 5000–5009.

Krause, J.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Kweon, I. S.

G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
[Crossref]

Larsson, M.

M. Larsson, E. Stenborg, L. Hammarstrand, T. Sattler, M. Pollefeys, and F. Kahl, “A cross-season correspondence dataset for robust semantic segmentation,” arXiv:1903.06916 (2019).

Lee, J. Y.

G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
[Crossref]

Lee, S. L.

X. Y. Zhou, C. Riga, S. L. Lee, and G. Z. Yang, “Towards automatic 3D shape instantiation for deployed stent grafts: 2D multiple-class and class-imbalance marker segmentation with equally-weighted focal U-Net,” in International Conference on Intelligent Robots and Systems (IEEE, 2018), pp. 1261–1267.

Leibe, B.

T. Pohlen, A. Hermans, M. Mathias, and B. Leibe, “Full-resolution residual networks for semantic segmentation in street scenes,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 3309–3318.

Li, F.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Li, H.

L. Deng, M. Yang, H. Li, B. Hu, and C. Wang, “Restricted deformable convolution based road scene semantic segmentation using surround view cameras,” arXiv:1801.00708 (2018).

Li, Y.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Liang, R.

Lin, S.

K. Yang, K. Wang, S. Lin, J. Bai, L. M. Bergasa, and R. Arroyo, “Long-range traversability awareness and low-lying obstacle negotiation with RealSense for the visually impaired,” in International Conference on Information Science and System (ACM, 2018), pp. 137–141.

Lin, T. Y.

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in International Conference on Computer Vision (IEEE, 2017), pp. 2990–3007.

Liu, D.

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

Liwicki, S.

R. P. Poudel, U. Bonde, S. Liwicki, and C. Zach, “ContextNet: exploring context and detail for semantic segmentation in real-time,” arXiv:1805.04554 (2018).

R. P. Poudel, S. Liwicki, and R. Cipolla, “Fast-SCNN: fast semantic segmentation network,” arXiv:1902.04502 (2019).

Long, J.

J. Long, E. Shelhamer, and T. Darrel, “Fully convolutional networks for semantic segmentation,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2015), pp. 3431–3440.

Long, N.

K. Yang, R. Cheng, L. M. Bergasa, E. Romera, K. Wang, and N. Long, “Intersection perception through real-time semantic segmentation to assist navigation of visually impaired pedestrians,” in International Conference on Robotics and Biomimetics (IEEE, 2018), pp. 1034–1039.

López, E.

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

A. Sáez, L. M. Bergasa, E. Romera, E. López, R. Barea, and R. Sanz, “CNN-based fisheye image real-time semantic segmentation,” in Intelligent Vehicles Symposium (IEEE, 2018), pp. 1039–1044.

Luo, Y.

Ma, C.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Ma, S.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Martinez, M.

M. Martinez, A. Roitberg, D. Koester, B. Stiefelhagen, and B. Schauerte, “Using technology developed for autonomous cars to help navigate blind people,” in International Conference on Computer Vision Workshops (IEEE, 2017), pp. 1424–1432.

Mathias, M.

T. Pohlen, A. Hermans, M. Mathias, and B. Leibe, “Full-resolution residual networks for semantic segmentation in street scenes,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 3309–3318.

Maturana, D.

D. K. Kim, D. Maturana, M. Uenoyama, and S. Scherer, “Season-invariant semantic segmentation with a deep multimodal network,” in Field and Service Robotics (Springer, 2018), pp. 255–270.

Mayr, A.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Mehta, S.

S. Mehta, H. Hajishirzi, and L. Shapiro, “Identifying most walkable direction for navigation in an outdoor environment,” arXiv:1711.08040 (2017).

Miksik, O.

A. Arnab, O. Miksik, and P. H. Torr, “On the robustness of semantic segmentation models to adversarial attacks,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018), pp. 888–897.

Murschitz, M.

O. Zendel, K. Honauer, M. Murschitz, D. Steininger, and G. F. Dominguez, “WildDash-creating hazard-aware benchmarks,” in European Conference on Computer Vision (2018), pp. 402–416.

Nahavandi, S.

K. Saleh, R. A. Zeineldin, M. Hossny, S. Nahavandi, and N. A. El-Fishawy, “Navigational path detection for the visually impaired using fully convolutional networks,” in International Conference on Systems, Man, and Cybernetics (IEEE, 2017), pp. 1399–1404.

Narasimhan, S. G.

G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
[Crossref]

Nessler, B.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Neuhold, G.

G. Neuhold, T. Ollmann, S. R. Bulò, and P. Kontschieder, “The mapillary vistas dataset for semantic understanding of street scenes,” in International Conference on Computer Vision (IEEE, 2017), pp. 5000–5009.

Ning, Q.

Q. Ning, J. Zhu, and C. Chen, “Very fast semantic image segmentation using hierarchical dilation and feature refining,” Cognit. Comput. 10, 62–72 (2018).
[Crossref]

Oliveira, G. L.

G. L. Oliveira, C. Bollen, W. Burgard, and T. Brox, “Efficient and robust deep networks for semantic segmentation,” Int. J. Robot. Res. 37, 472–491 (2018).
[Crossref]

Ollmann, T.

G. Neuhold, T. Ollmann, S. R. Bulò, and P. Kontschieder, “The mapillary vistas dataset for semantic understanding of street scenes,” in International Conference on Computer Vision (IEEE, 2017), pp. 5000–5009.

Omran, M.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

Ortiz, L. E.

L. E. Ortiz, E. V. Cabrera, and L. M. Gonçalves, “Depth data error modeling of the ZED 3D vision sensor from stereolabs,” Electr. Lett. Comput. Vis. Image Anal. 17, 1–15 (2018).
[Crossref]

Pan, Z.

W. Wang and Z. Pan, “DSNet for real-time driving scene semantic segmentation,” arXiv:1812.07049 (2018).

Papandreous, G.

L. C. Chen, Y. Zhu, G. Papandreous, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in European Conference on Computer Vision (2018), pp. 801–818.

Paszke, A.

A. Paszke, A. Chaurasia, S. Kim, and E. Culurciello, “ENet: a deep neural network architecture for real-time semantic segmentation,” arXiv:1606.02147 (2016).

Pfeiffer, D.

D. Pfeiffer and U. Franke, “Efficient representation of traffic scenes by means of dynamic stixels,” in Intelligent Vehicles Symposium (IEEE, 2010), pp. 217–224.

Pinggera, P.

S. Ramos, S. Gehrig, P. Pinggera, U. Franke, and C. Rother, “Detecting unexpected obstacles for self-driving cars: fusing deep learning and geometric modeling,” in IEEE Intelligent Vehicles Symposium (IEEE, 2017), pp. 1025–1032.

Pohlen, T.

T. Pohlen, A. Hermans, M. Mathias, and B. Leibe, “Full-resolution residual networks for semantic segmentation in street scenes,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 3309–3318.

Pollefeys, M.

M. Larsson, E. Stenborg, L. Hammarstrand, T. Sattler, M. Pollefeys, and F. Kahl, “A cross-season correspondence dataset for robust semantic segmentation,” arXiv:1903.06916 (2019).

Poudel, R. P.

R. P. Poudel, U. Bonde, S. Liwicki, and C. Zach, “ContextNet: exploring context and detail for semantic segmentation in real-time,” arXiv:1805.04554 (2018).

R. P. Poudel, S. Liwicki, and R. Cipolla, “Fast-SCNN: fast semantic segmentation network,” arXiv:1902.04502 (2019).

Qi, X.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 6230–6239.

H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, “ICnet for real-time semantic segmentation on high-resolution images,” in European Conference on Computer Vision (2018), pp. 405–420.

Ramos, S.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

S. Ramos, S. Gehrig, P. Pinggera, U. Franke, and C. Rother, “Detecting unexpected obstacles for self-driving cars: fusing deep learning and geometric modeling,” in IEEE Intelligent Vehicles Symposium (IEEE, 2017), pp. 1025–1032.

Rehfeld, T.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

Ren, S.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 770–778.

Riga, C.

X. Y. Zhou, C. Riga, S. L. Lee, and G. Z. Yang, “Towards automatic 3D shape instantiation for deployed stent grafts: 2D multiple-class and class-imbalance marker segmentation with equally-weighted focal U-Net,” in International Conference on Intelligent Robots and Systems (IEEE, 2018), pp. 1261–1267.

Rodríguez, A.

A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
[Crossref]

Roitberg, A.

M. Martinez, A. Roitberg, D. Koester, B. Stiefelhagen, and B. Schauerte, “Using technology developed for autonomous cars to help navigate blind people,” in International Conference on Computer Vision Workshops (IEEE, 2017), pp. 1424–1432.

Romera, E.

E. Romera, J. M. Alvarez, L. M. Bergasa, and R. Arroyo, “ERFNet: efficient residual factorized convnet for real-time semantic segmentation,” IEEE Trans. Intell. Transp. Syst. 19, 263–272 (2018).
[Crossref]

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

E. Romera, L. M. Bergasa, J. M. Alvarez, and M. Trivedi, “Train here, deploy there: robust segmentation in unseen domains,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1823–1833.

A. Sáez, L. M. Bergasa, E. Romera, E. López, R. Barea, and R. Sanz, “CNN-based fisheye image real-time semantic segmentation,” in Intelligent Vehicles Symposium (IEEE, 2018), pp. 1039–1044.

K. Yang, R. Cheng, L. M. Bergasa, E. Romera, K. Wang, and N. Long, “Intersection perception through real-time semantic segmentation to assist navigation of visually impaired pedestrians,” in International Conference on Robotics and Biomimetics (IEEE, 2018), pp. 1034–1039.

K. Yang, L. M. Bergasa, E. Romera, R. Cheng, T. Chen, and K. Wang, “Unifying terrain awareness through real-time semantic segmentation,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1033–1038.

K. Yang, L. M. Bergasa, E. Romera, X. Huang, and K. Wang, “Predicting polarization beyond semantics for wearable robotics,” in International Conference on Humanoid Robots (IEEE, 2018), pp. 96–103.

Roth, S.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

Rother, C.

S. Ramos, S. Gehrig, P. Pinggera, U. Franke, and C. Rother, “Detecting unexpected obstacles for self-driving cars: fusing deep learning and geometric modeling,” in IEEE Intelligent Vehicles Symposium (IEEE, 2017), pp. 1025–1032.

Rus, D.

H. C. Wang, R. K. Katzschmann, S. Teng, B. Araki, L. Giarré, and D. Rus, “Enabling independent navigation for visually impaired people through a wearable vision-based feedback system,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 6533–6540.

Russakovsky, O.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Sáez, A.

A. Sáez, L. M. Bergasa, E. Romera, E. López, R. Barea, and R. Sanz, “CNN-based fisheye image real-time semantic segmentation,” in Intelligent Vehicles Symposium (IEEE, 2018), pp. 1039–1044.

Sakaridis, C.

C. Sakaridis, D. Dai, and L. Van Gool, “Semantic nighttime image segmentation with synthetic stylized data, gradual adaptation and uncertainty-aware evaluation,” arXiv:1901.05946 (2019).

C. Sakaridis, D. Dai, S. Hecker, and L. Van Gool, “Model adaptation with synthetic and real data for semantic dense foggy scene understanding,” in European Conference on Computer Vision (2018), pp. 707–724.

Sala, R.

S. Giancola, M. Valenti, and R. Sala, “Metrological qualification of the intel D400TM active stereoscopy cameras,” in A Survey on 3D Cameras: Metrological Comparison of Time-of-Flight, Structured-Light and Active Stereoscopy Technologies (Springer, 2018), pp. 71–85.

Saleh, K.

K. Saleh, R. A. Zeineldin, M. Hossny, S. Nahavandi, and N. A. El-Fishawy, “Navigational path detection for the visually impaired using fully convolutional networks,” in International Conference on Systems, Man, and Cybernetics (IEEE, 2017), pp. 1399–1404.

Sanz, R.

A. Sáez, L. M. Bergasa, E. Romera, E. López, R. Barea, and R. Sanz, “CNN-based fisheye image real-time semantic segmentation,” in Intelligent Vehicles Symposium (IEEE, 2018), pp. 1039–1044.

Satheesh, S.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Sattler, T.

M. Larsson, E. Stenborg, L. Hammarstrand, T. Sattler, M. Pollefeys, and F. Kahl, “A cross-season correspondence dataset for robust semantic segmentation,” arXiv:1903.06916 (2019).

Schauerte, B.

M. Martinez, A. Roitberg, D. Koester, B. Stiefelhagen, and B. Schauerte, “Using technology developed for autonomous cars to help navigate blind people,” in International Conference on Computer Vision Workshops (IEEE, 2017), pp. 1424–1432.

Scherer, S.

D. K. Kim, D. Maturana, M. Uenoyama, and S. Scherer, “Season-invariant semantic segmentation with a deep multimodal network,” in Field and Service Robotics (Springer, 2018), pp. 255–270.

Schiele, B.

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

Schilling, F.

F. Schilling, X. Chen, J. Folkesson, and P. Jensfelt, “Geometric and visual terrain classification for autonomous mobile navigation,” in International Conference on Intelligent Robots and Systems (IEEE, 2017), pp. 2678–2684.

Schroff, F.

L. C. Chen, Y. Zhu, G. Papandreous, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in European Conference on Computer Vision (2018), pp. 801–818.

Schuberth, P.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Schulter, S.

Y. H. Tsai, W. C. Hung, S. Schulter, K. Sohn, M. H. Yang, and M. Chandraker, “Learning to adapt structured output space for semantic segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2018), pp. 7472–7481.

Shapiro, L.

S. Mehta, H. Hajishirzi, and L. Shapiro, “Identifying most walkable direction for navigation in an outdoor environment,” arXiv:1711.08040 (2017).

Shelhamer, E.

J. Long, E. Shelhamer, and T. Darrel, “Fully convolutional networks for semantic segmentation,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2015), pp. 3431–3440.

Shen, X.

H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, “ICnet for real-time semantic segmentation on high-resolution images,” in European Conference on Computer Vision (2018), pp. 405–420.

Shi, J.

H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, “ICnet for real-time semantic segmentation on high-resolution images,” in European Conference on Computer Vision (2018), pp. 405–420.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 6230–6239.

Sohn, K.

Y. H. Tsai, W. C. Hung, S. Schulter, K. Sohn, M. H. Yang, and M. Chandraker, “Learning to adapt structured output space for semantic segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2018), pp. 7472–7481.

Steininger, D.

O. Zendel, K. Honauer, M. Murschitz, D. Steininger, and G. F. Dominguez, “WildDash-creating hazard-aware benchmarks,” in European Conference on Computer Vision (2018), pp. 402–416.

Stenborg, E.

M. Larsson, E. Stenborg, L. Hammarstrand, T. Sattler, M. Pollefeys, and F. Kahl, “A cross-season correspondence dataset for robust semantic segmentation,” arXiv:1903.06916 (2019).

Stiefelhagen, B.

M. Martinez, A. Roitberg, D. Koester, B. Stiefelhagen, and B. Schauerte, “Using technology developed for autonomous cars to help navigate blind people,” in International Conference on Computer Vision Workshops (IEEE, 2017), pp. 1424–1432.

Su, H.

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Sun, D.

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

Sun, J.

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 770–778.

K. He, J. Sun, and X. Tang, “Guided image filtering,” in European Conference on Computer Vision (2010), pp. 1–14.

Tang, L.

L. Tang, X. Ding, H. Yin, Y. Wang, and R. Xiong, “From one to many: unsupervised traversable area segmentation in off-road environment,” in International Conference on Robotics and Biomimetics (IEEE, 2017), pp. 787–792.

Tang, X.

K. He, J. Sun, and X. Tang, “Guided image filtering,” in European Conference on Computer Vision (2010), pp. 1–14.

Tao, L.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Teng, S.

H. C. Wang, R. K. Katzschmann, S. Teng, B. Araki, L. Giarré, and D. Rus, “Enabling independent navigation for visually impaired people through a wearable vision-based feedback system,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 6533–6540.

Torr, P. H.

A. Arnab, O. Miksik, and P. H. Torr, “On the robustness of semantic segmentation models to adversarial attacks,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018), pp. 888–897.

Treml, M.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Trivedi, M.

E. Romera, L. M. Bergasa, J. M. Alvarez, and M. Trivedi, “Train here, deploy there: robust segmentation in unseen domains,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1823–1833.

Tsai, Y. H.

Y. H. Tsai, W. C. Hung, S. Schulter, K. Sohn, M. H. Yang, and M. Chandraker, “Learning to adapt structured output space for semantic segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2018), pp. 7472–7481.

Uenoyama, M.

D. K. Kim, D. Maturana, M. Uenoyama, and S. Scherer, “Season-invariant semantic segmentation with a deep multimodal network,” in Field and Service Robotics (Springer, 2018), pp. 255–270.

Unterthiner, T.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Valada, A.

A. Valada, J. Vertens, A. Dhall, and W. Burgard, “AdapNet: adaptive semantic segmentation in adverse environmental conditions,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 4644–4651.

Valenti, M.

S. Giancola, M. Valenti, and R. Sala, “Metrological qualification of the intel D400TM active stereoscopy cameras,” in A Survey on 3D Cameras: Metrological Comparison of Time-of-Flight, Structured-Light and Active Stereoscopy Technologies (Springer, 2018), pp. 71–85.

Van Gool, L.

C. Sakaridis, D. Dai, S. Hecker, and L. Van Gool, “Model adaptation with synthetic and real data for semantic dense foggy scene understanding,” in European Conference on Computer Vision (2018), pp. 707–724.

C. Sakaridis, D. Dai, and L. Van Gool, “Semantic nighttime image segmentation with synthetic stylized data, gradual adaptation and uncertainty-aware evaluation,” arXiv:1901.05946 (2019).

Vertens, J.

A. Valada, J. Vertens, A. Dhall, and W. Burgard, “AdapNet: adaptive semantic segmentation in adverse environmental conditions,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 4644–4651.

Wang, C.

L. Deng, M. Yang, H. Li, B. Hu, and C. Wang, “Restricted deformable convolution based road scene semantic segmentation using surround view cameras,” arXiv:1801.00708 (2018).

Wang, G.

L. He, G. Wang, and Z. Hu, “Learning depth from single images with deep neural network embedding focal length,” IEEE Trans. Image Process. 27, 4676–4689 (2018).
[Crossref]

Wang, H. C.

H. C. Wang, R. K. Katzschmann, S. Teng, B. Araki, L. Giarré, and D. Rus, “Enabling independent navigation for visually impaired people through a wearable vision-based feedback system,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 6533–6540.

Wang, K.

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

K. Yang, K. Wang, H. Chen, and J. Bai, “Reducing the minimum range of a RGB-depth sensor to aid navigation in visually impaired individuals,” Appl. Opt. 57, 2809–2819 (2018).
[Crossref]

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

K. Yang, K. Wang, W. Hu, and J. Bai, “Expanding the detection of traversable area with RealSense for the visually impaired,” Sensors 16, C1 (2016).
[Crossref]

K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
[Crossref]

K. Yang, L. M. Bergasa, E. Romera, R. Cheng, T. Chen, and K. Wang, “Unifying terrain awareness through real-time semantic segmentation,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1033–1038.

K. Yang, L. M. Bergasa, E. Romera, X. Huang, and K. Wang, “Predicting polarization beyond semantics for wearable robotics,” in International Conference on Humanoid Robots (IEEE, 2018), pp. 96–103.

K. Yang, R. Cheng, L. M. Bergasa, E. Romera, K. Wang, and N. Long, “Intersection perception through real-time semantic segmentation to assist navigation of visually impaired pedestrians,” in International Conference on Robotics and Biomimetics (IEEE, 2018), pp. 1034–1039.

K. Yang, K. Wang, S. Lin, J. Bai, L. M. Bergasa, and R. Arroyo, “Long-range traversability awareness and low-lying obstacle negotiation with RealSense for the visually impaired,” in International Conference on Information Science and System (ACM, 2018), pp. 137–141.

Wang, W.

W. Wang and Z. Pan, “DSNet for real-time driving scene semantic segmentation,” arXiv:1812.07049 (2018).

Wang, X.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 6230–6239.

Wang, Y.

L. Tang, X. Ding, H. Yin, Y. Wang, and R. Xiong, “From one to many: unsupervised traversable area segmentation in off-road environment,” in International Conference on Robotics and Biomimetics (IEEE, 2017), pp. 787–792.

Widrich, M.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

Xie, X.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Xiong, R.

L. Tang, X. Ding, H. Yin, Y. Wang, and R. Xiong, “From one to many: unsupervised traversable area segmentation in off-road environment,” in International Conference on Robotics and Biomimetics (IEEE, 2017), pp. 787–792.

Yang, F.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Yang, G. Z.

X. Y. Zhou, C. Riga, S. L. Lee, and G. Z. Yang, “Towards automatic 3D shape instantiation for deployed stent grafts: 2D multiple-class and class-imbalance marker segmentation with equally-weighted focal U-Net,” in International Conference on Intelligent Robots and Systems (IEEE, 2018), pp. 1261–1267.

Yang, J.

B. Chen, C. Gong, and J. Yang, “Importance-aware semantic segmentation for autonomous vehicles,” IEEE Trans. Intell. Transp. Syst. 20, 137–148 (2019).
[Crossref]

Yang, K.

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

K. Yang, K. Wang, H. Chen, and J. Bai, “Reducing the minimum range of a RGB-depth sensor to aid navigation in visually impaired individuals,” Appl. Opt. 57, 2809–2819 (2018).
[Crossref]

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

K. Yang, K. Wang, W. Hu, and J. Bai, “Expanding the detection of traversable area with RealSense for the visually impaired,” Sensors 16, C1 (2016).
[Crossref]

K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
[Crossref]

K. Yang, L. M. Bergasa, E. Romera, R. Cheng, T. Chen, and K. Wang, “Unifying terrain awareness through real-time semantic segmentation,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1033–1038.

K. Yang, L. M. Bergasa, E. Romera, X. Huang, and K. Wang, “Predicting polarization beyond semantics for wearable robotics,” in International Conference on Humanoid Robots (IEEE, 2018), pp. 96–103.

K. Yang, R. Cheng, L. M. Bergasa, E. Romera, K. Wang, and N. Long, “Intersection perception through real-time semantic segmentation to assist navigation of visually impaired pedestrians,” in International Conference on Robotics and Biomimetics (IEEE, 2018), pp. 1034–1039.

K. Yang, K. Wang, S. Lin, J. Bai, L. M. Bergasa, and R. Arroyo, “Long-range traversability awareness and low-lying obstacle negotiation with RealSense for the visually impaired,” in International Conference on Information Science and System (ACM, 2018), pp. 137–141.

Yang, M.

L. Deng, M. Yang, H. Li, B. Hu, and C. Wang, “Restricted deformable convolution based road scene semantic segmentation using surround view cameras,” arXiv:1801.00708 (2018).

Yang, M. H.

Y. H. Tsai, W. C. Hung, S. Schulter, K. Sohn, M. H. Yang, and M. Chandraker, “Learning to adapt structured output space for semantic segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2018), pp. 7472–7481.

Yang, Y.

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

Ye, M.

Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
[Crossref]

Yebes, J. J.

A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
[Crossref]

Yin, H.

L. Tang, X. Ding, H. Yin, Y. Wang, and R. Xiong, “From one to many: unsupervised traversable area segmentation in off-road environment,” in International Conference on Robotics and Biomimetics (IEEE, 2017), pp. 787–792.

Yu, F.

F. Yu and V. Koltun, “Multi-scale context aggregation by dilated convolutions,” arXiv:1511.07122 (2015).

Zach, C.

R. P. Poudel, U. Bonde, S. Liwicki, and C. Zach, “ContextNet: exploring context and detail for semantic segmentation in real-time,” arXiv:1805.04554 (2018).

Zeineldin, R. A.

K. Saleh, R. A. Zeineldin, M. Hossny, S. Nahavandi, and N. A. El-Fishawy, “Navigational path detection for the visually impaired using fully convolutional networks,” in International Conference on Systems, Man, and Cybernetics (IEEE, 2017), pp. 1399–1404.

Zendel, O.

O. Zendel, K. Honauer, M. Murschitz, D. Steininger, and G. F. Dominguez, “WildDash-creating hazard-aware benchmarks,” in European Conference on Computer Vision (2018), pp. 402–416.

Zhang, D.

Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
[Crossref]

Zhang, X.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 770–778.

Zhang, Y.

Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
[Crossref]

Zhang, Z.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Zhao, H.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 6230–6239.

H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, “ICnet for real-time semantic segmentation on high-resolution images,” in European Conference on Computer Vision (2018), pp. 405–420.

Zhao, X.

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

Zhou, X. Y.

X. Y. Zhou, C. Riga, S. L. Lee, and G. Z. Yang, “Towards automatic 3D shape instantiation for deployed stent grafts: 2D multiple-class and class-imbalance marker segmentation with equally-weighted focal U-Net,” in International Conference on Intelligent Robots and Systems (IEEE, 2018), pp. 1261–1267.

Zhu, J.

Q. Ning, J. Zhu, and C. Chen, “Very fast semantic image segmentation using hierarchical dilation and feature refining,” Cognit. Comput. 10, 62–72 (2018).
[Crossref]

Zhu, Y.

L. C. Chen, Y. Zhu, G. Papandreous, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in European Conference on Computer Vision (2018), pp. 801–818.

Zhuang, Y.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

Appl. Opt. (2)

Cognit. Comput. (1)

Q. Ning, J. Zhu, and C. Chen, “Very fast semantic image segmentation using hierarchical dilation and feature refining,” Cognit. Comput. 10, 62–72 (2018).
[Crossref]

Electr. Lett. Comput. Vis. Image Anal. (1)

L. E. Ortiz, E. V. Cabrera, and L. M. Gonçalves, “Depth data error modeling of the ZED 3D vision sensor from stereolabs,” Electr. Lett. Comput. Vis. Image Anal. 17, 1–15 (2018).
[Crossref]

IEEE Robot. Autom. Lett. (1)

G. Choe, S. H. Kim, S. Im, J. Y. Lee, S. G. Narasimhan, and I. S. Kweon, “RANUS: RGB and NIR urban scene dataset for deep scene parsing,” IEEE Robot. Autom. Lett. 3, 1808–1815 (2018).
[Crossref]

IEEE Trans. Image Process. (1)

L. He, G. Wang, and Z. Hu, “Learning depth from single images with deep neural network embedding focal length,” IEEE Trans. Image Process. 27, 4676–4689 (2018).
[Crossref]

IEEE Trans. Intell. Transp. Syst. (2)

B. Chen, C. Gong, and J. Yang, “Importance-aware semantic segmentation for autonomous vehicles,” IEEE Trans. Intell. Transp. Syst. 20, 137–148 (2019).
[Crossref]

E. Romera, J. M. Alvarez, L. M. Bergasa, and R. Arroyo, “ERFNet: efficient residual factorized convnet for real-time semantic segmentation,” IEEE Trans. Intell. Transp. Syst. 19, 263–272 (2018).
[Crossref]

IEEE Trans. Pattern Anal. Mach. Intell. (1)

V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: a deep convolutional encoder-decoder architecture for image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017).
[Crossref]

Int. J. Comput. Vis. (1)

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. Li, “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vis. 115, 211–252 (2015).
[Crossref]

Int. J. Robot. Res. (1)

G. L. Oliveira, C. Bollen, W. Burgard, and T. Brox, “Efficient and robust deep networks for semantic segmentation,” Int. J. Robot. Res. 37, 472–491 (2018).
[Crossref]

J. Ambient Intell. Smart Environ. (1)

K. Yang, K. Wang, X. Zhao, R. Cheng, J. Bai, Y. Yang, and D. Liu, “IR stereo RealSense: decreasing minimum range of navigational assistance for visually impaired individuals,” J. Ambient Intell. Smart Environ. 9, 743–755 (2017).
[Crossref]

Neurocomputing (1)

Y. Zhang, H. Chen, Y. He, M. Ye, X. Cai, and D. Zhang, “Road segmentation for all-day outdoor robot navigation,” Neurocomputing 314, 316–325 (2018).
[Crossref]

Sensors (4)

K. Yang, K. Wang, R. Cheng, W. Hu, X. Huang, and J. Bai, “Detecting traversable area and water hazards for visually impaired with a pRGB-D sensor,” Sensors 17, 16–20 (2016).
[Crossref]

A. Rodríguez, J. J. Yebes, P. F. Alcantarilla, L. M. Bergasa, J. Almazán, and A. Cela, “Assisting the visually impaired: obstacle detection and warning system by acoustic feedback,” Sensors 12, 17467–17496 (2012).
[Crossref]

K. Yang, K. Wang, W. Hu, and J. Bai, “Expanding the detection of traversable area with RealSense for the visually impaired,” Sensors 16, C1 (2016).
[Crossref]

K. Yang, K. Wang, L. M. Bergasa, E. Romera, W. Hu, D. Sun, J. Sun, T. Chen, and E. López, “Unifying terrain awareness for the visually impaired through real-time semantic segmentation,” Sensors 16, 1–32 (2018).
[Crossref]

Other (55)

M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The Cityscapes dataset for semantic urban scene understanding,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 3213–3223.

G. Neuhold, T. Ollmann, S. R. Bulò, and P. Kontschieder, “The mapillary vistas dataset for semantic understanding of street scenes,” in International Conference on Computer Vision (IEEE, 2017), pp. 5000–5009.

K. Yang, “Panoramic annular semantic segmentation,” 2019, https://github.com/elnino9ykl/PASS .

Krvision, “To tackle the challenges for the visually impaired,” 2016, http://krvision.cn .

R. Girshick, “Fast R-CNN,” in International Conference on Computer Vision (IEEE, 2015), pp. 1440–1448.

J. Long, E. Shelhamer, and T. Darrel, “Fully convolutional networks for semantic segmentation,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2015), pp. 3431–3440.

K. Yang, L. M. Bergasa, E. Romera, R. Cheng, T. Chen, and K. Wang, “Unifying terrain awareness through real-time semantic segmentation,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1033–1038.

D. Pfeiffer and U. Franke, “Efficient representation of traffic scenes by means of dynamic stixels,” in Intelligent Vehicles Symposium (IEEE, 2010), pp. 217–224.

M. Martinez, A. Roitberg, D. Koester, B. Stiefelhagen, and B. Schauerte, “Using technology developed for autonomous cars to help navigate blind people,” in International Conference on Computer Vision Workshops (IEEE, 2017), pp. 1424–1432.

H. C. Wang, R. K. Katzschmann, S. Teng, B. Araki, L. Giarré, and D. Rus, “Enabling independent navigation for visually impaired people through a wearable vision-based feedback system,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 6533–6540.

F. Yu and V. Koltun, “Multi-scale context aggregation by dilated convolutions,” arXiv:1511.07122 (2015).

T. Pohlen, A. Hermans, M. Mathias, and B. Leibe, “Full-resolution residual networks for semantic segmentation in street scenes,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 3309–3318.

L. C. Chen, Y. Zhu, G. Papandreous, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in European Conference on Computer Vision (2018), pp. 801–818.

Y. Zhuang, F. Yang, L. Tao, C. Ma, Z. Zhang, Y. Li, H. Jia, X. Xie, and W. Gao, “Dense relation network: learning consistent and context-aware representation for semantic image segmentation,” in International Conference on Image Processing (IEEE, 2018), pp. 3698–3702.

K. Saleh, R. A. Zeineldin, M. Hossny, S. Nahavandi, and N. A. El-Fishawy, “Navigational path detection for the visually impaired using fully convolutional networks,” in International Conference on Systems, Man, and Cybernetics (IEEE, 2017), pp. 1399–1404.

K. Yang, K. Wang, S. Lin, J. Bai, L. M. Bergasa, and R. Arroyo, “Long-range traversability awareness and low-lying obstacle negotiation with RealSense for the visually impaired,” in International Conference on Information Science and System (ACM, 2018), pp. 137–141.

L. Deng, M. Yang, H. Li, B. Hu, and C. Wang, “Restricted deformable convolution based road scene semantic segmentation using surround view cameras,” arXiv:1801.00708 (2018).

A. Sáez, L. M. Bergasa, E. Romera, E. López, R. Barea, and R. Sanz, “CNN-based fisheye image real-time semantic segmentation,” in Intelligent Vehicles Symposium (IEEE, 2018), pp. 1039–1044.

K. Yang, R. Cheng, L. M. Bergasa, E. Romera, K. Wang, and N. Long, “Intersection perception through real-time semantic segmentation to assist navigation of visually impaired pedestrians,” in International Conference on Robotics and Biomimetics (IEEE, 2018), pp. 1034–1039.

F. Schilling, X. Chen, J. Folkesson, and P. Jensfelt, “Geometric and visual terrain classification for autonomous mobile navigation,” in International Conference on Intelligent Robots and Systems (IEEE, 2017), pp. 2678–2684.

S. Ramos, S. Gehrig, P. Pinggera, U. Franke, and C. Rother, “Detecting unexpected obstacles for self-driving cars: fusing deep learning and geometric modeling,” in IEEE Intelligent Vehicles Symposium (IEEE, 2017), pp. 1025–1032.

H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, “ICnet for real-time semantic segmentation on high-resolution images,” in European Conference on Computer Vision (2018), pp. 405–420.

M. Treml, J. Arjona-Medina, T. Unterthiner, R. Durgesh, F. Friedmann, P. Schuberth, A. Mayr, M. Heusel, M. Hofmarcher, M. Widrich, and B. Nessler, “Speeding up semantic segmentation for autonomous driving,” in Conference on Neural Information Processing System Workshop (2016), pp. 1–8.

W. Wang and Z. Pan, “DSNet for real-time driving scene semantic segmentation,” arXiv:1812.07049 (2018).

R. P. Poudel, U. Bonde, S. Liwicki, and C. Zach, “ContextNet: exploring context and detail for semantic segmentation in real-time,” arXiv:1805.04554 (2018).

R. P. Poudel, S. Liwicki, and R. Cipolla, “Fast-SCNN: fast semantic segmentation network,” arXiv:1902.04502 (2019).

S. Mehta, H. Hajishirzi, and L. Shapiro, “Identifying most walkable direction for navigation in an outdoor environment,” arXiv:1711.08040 (2017).

D. K. Kim, D. Maturana, M. Uenoyama, and S. Scherer, “Season-invariant semantic segmentation with a deep multimodal network,” in Field and Service Robotics (Springer, 2018), pp. 255–270.

A. Valada, J. Vertens, A. Dhall, and W. Burgard, “AdapNet: adaptive semantic segmentation in adverse environmental conditions,” in International Conference on Robotics and Automation (IEEE, 2017), pp. 4644–4651.

K. Yang, L. M. Bergasa, E. Romera, X. Huang, and K. Wang, “Predicting polarization beyond semantics for wearable robotics,” in International Conference on Humanoid Robots (IEEE, 2018), pp. 96–103.

N. Alshammari, S. Akcay, and T. P. Breckon, “On the impact of illumination-invariant image pre-transformation on contemporary automotive semantic scene understanding,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1027–1032.

C. Sakaridis, D. Dai, S. Hecker, and L. Van Gool, “Model adaptation with synthetic and real data for semantic dense foggy scene understanding,” in European Conference on Computer Vision (2018), pp. 707–724.

C. Sakaridis, D. Dai, and L. Van Gool, “Semantic nighttime image segmentation with synthetic stylized data, gradual adaptation and uncertainty-aware evaluation,” arXiv:1901.05946 (2019).

A. Arnab, O. Miksik, and P. H. Torr, “On the robustness of semantic segmentation models to adversarial attacks,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018), pp. 888–897.

K. Yang, “Sequential/hierarchical ERF-PSPNet,” 2018, https://github.com/elnino9ykl/ERF-PSPNet .

K. Xiang, “ERF-PSPNET implemented by tensorflow” 2018, https://github.com/Katexiang/ERF-PSPNET .

D. Sun, “ERF-PSPNet on TX2,” 2018, https://github.com/dongmingsun/tx2-erfpsp .

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 770–778.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 6230–6239.

E. Romera, L. M. Bergasa, J. M. Alvarez, and M. Trivedi, “Train here, deploy there: robust segmentation in unseen domains,” in IEEE Intelligent Vehicles Symposium (IEEE, 2018), pp. 1823–1833.

K. Wang, “RGB-D-SS dataset,” 2018, http://wangkaiwei.org/downloadeg.html .

D. P. Kingma and J. Ba, “Adam: a method for stochastic optimization,” arXiv:1412.6980 (2014).

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in International Conference on Computer Vision (IEEE, 2017), pp. 2990–3007.

X. Y. Zhou, C. Riga, S. L. Lee, and G. Z. Yang, “Towards automatic 3D shape instantiation for deployed stent grafts: 2D multiple-class and class-imbalance marker segmentation with equally-weighted focal U-Net,” in International Conference on Intelligent Robots and Systems (IEEE, 2018), pp. 1261–1267.

O. Zendel, K. Honauer, M. Murschitz, D. Steininger, and G. F. Dominguez, “WildDash-creating hazard-aware benchmarks,” in European Conference on Computer Vision (2018), pp. 402–416.

M. Larsson, E. Stenborg, L. Hammarstrand, T. Sattler, M. Pollefeys, and F. Kahl, “A cross-season correspondence dataset for robust semantic segmentation,” arXiv:1903.06916 (2019).

L. Keselman, J. Iselin Woodfill, A. Grunnet-Jepsen, and A. Bhowmik, “Intel RealSense stereoscopic depth cameras,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (IEEE, 2018), pp. 1–10.

A. Paszke, A. Chaurasia, S. Kim, and E. Culurciello, “ENet: a deep neural network architecture for real-time semantic segmentation,” arXiv:1606.02147 (2016).

A. Chaurasia and E. Culurciello, “LinkNet: exploiting encoder representations for efficient semantic segmentation,” in IEEE Visual Communications and Image Processing (IEEE, 2017), pp. 1–4.

L. Tang, X. Ding, H. Yin, Y. Wang, and R. Xiong, “From one to many: unsupervised traversable area segmentation in off-road environment,” in International Conference on Robotics and Biomimetics (IEEE, 2017), pp. 787–792.

Y. H. Tsai, W. C. Hung, S. Schulter, K. Sohn, M. H. Yang, and M. Chandraker, “Learning to adapt structured output space for semantic segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, 2018), pp. 7472–7481.

K. He, J. Sun, and X. Tang, “Guided image filtering,” in European Conference on Computer Vision (2010), pp. 1–14.

S. Giancola, M. Valenti, and R. Sala, “Metrological qualification of the intel D400TM active stereoscopy cameras,” in A Survey on 3D Cameras: Metrological Comparison of Time-of-Flight, Structured-Light and Active Stereoscopy Technologies (Springer, 2018), pp. 71–85.

Stereolabs, “Meet ZED Mini: the world’s first camera for mixed-reality,” 2018, https://www.stereolabs.com/zed-mini .

K. Yang, “ZJU day and night driving dataset,” 2019, https://github.com/elnino9ykl/ZJU-Dataset .

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (9)

Fig. 1.
Fig. 1. Overview of the study on the robustness of semantic traversability perception across navigation assistance systems.
Fig. 2.
Fig. 2. Overview of a wearable navigation assistance system with a semantic perception framework supporting traversability awareness and curbs negotiation.
Fig. 3.
Fig. 3. Proposed architecture. (a) Input, (b) encoder, (c) decoder, and (d) prediction.
Fig. 4.
Fig. 4. Sequential and hierarchical architectures of dilated Non-bottleneck-1D (Non-bt-1D) layers. From left to right: (a) sequential architecture, (b)  4 × 2 hierarchical architecture, and (c)  3 × 3 hierarchical architecture.
Fig. 5.
Fig. 5. Class frequency of the VISTAS dataset: (a) pixel frequency (portion of labeled pixels); (b) instance frequency (number of images with at least one labeled instance).
Fig. 6.
Fig. 6. Comparison of the pixel-wise accuracy values of traversable area parsing at different ranges across perception systems produced by (a) our sequential ERF-PSP model trained without data augmentations, (b) our model trained with all data augmentations, (c) 3D-RANSAC-F [15], and (d) FreeSpaceParse [19].
Fig. 7.
Fig. 7. Qualitative examples of the segmentation of real-world images produced by our approach (with/without data augmentations) compared with ground-truth annotation, 3D-RANSAC-F (3D-R-F) [15], FreeSpaceParse (FSP) [19], and ENet [28].
Fig. 8.
Fig. 8. Qualitative examples of the segmentation in unseen domains under challenging illumination and severe rotation conditions, which are produced by our approach with or without data augmentations. From left to right, images captured by (a) Smart Glasses, (b) pRGB-D sensor, (c) RealSense D435, and (d) ZED Mini. The first and the third rows, semantic traversability perception results without data augmentations; the second and the fourth rows, segmentation outputs with data augmentations.
Fig. 9.
Fig. 9. Diverse qualitative examples of the segmentation of cross-country images (captured in Madrid, Spain, and Hangzhou, China) produced by our semantic traversability perception approach with all augmentations. The color masks of the road, sidewalks, and curbs follow Vistas [7] style.

Tables (5)

Tables Icon

Table 1. Specifications of the Perception Systems

Tables Icon

Table 2. Layer Disposal of Our Proposed Network

Tables Icon

Table 3. Speed and Semantic Segmentation Accuracy Analysis

Tables Icon

Table 4. Accuracy Analysis using Intersection-over-UNION (IoU)

Tables Icon

Table 5. Real-World Robustness Analysis using Pixel-Wise Accuracy (PA)

Equations (5)

Equations on this page are rendered with MathJax. Learn more.

IoU = TP TP + FP + FN ,
PA = CCP LP ,
MV = 1 n i = 1 n PA i ,
CV = i = 1 n ( PA i MV ) 2 / n MV .
Focal loss = i = 1 W j = 1 H n = 0 N ( 1 P ( i , j , n ) ) 2 L ( i , j , n ) log ( P ( i , j , n ) ) ,

Metrics