Abstract

We present an algorithm for nonrigid contour tracking in heavily cluttered background scenes. Based on the properties of nonrigid contour movements, a sequential framework for estimating contour motion and deformation is proposed. We solve the nonrigid contour tracking problem by decomposing it into three subproblems: motion estimation, deformation estimation, and shape regulation. First, we employ a particle filter to estimate the global motion parameters of the affine transform between successive frames. Then we generate a probabilistic deformation map to deform the contour. To improve robustness, multiple cues are used for deformation probability estimation. Finally, we use a shape prior model to constrain the deformed contour. This enables us to retrieve the occluded parts of the contours and accurately track them while allowing shape changes specific to the given object types. Our experiments show that the proposed algorithm significantly improves the tracker performance.

© 2007 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. M. Isard and A. Blake, "CONDENSATION: conditional density propagation for visual tracking," Int. J. Comput. Vis. 29, 5-28 (1998).
    [CrossRef]
  2. P. Li, T. Zhang, and A. E. C. Pece, "Visual contour tracking based on particle filters," Image Vis. Comput. 21, 111-123 (2003).
    [CrossRef]
  3. M. Kass, A. Witkins, and D. Terzopoulos, "Snakes: active contour models," Int. J. Comput. Vis. 1, 321-331 (1988).
    [CrossRef]
  4. F. Leymarie and M. D. Levine, "Tracking deformable objects in the plane using an active contour model," IEEE Trans. Pattern Anal. Mach. Intell. 15, 617-634 (1993).
    [CrossRef]
  5. K. P. Nikos and D. Rachid, "A PDE-based level-set approach for detection and tracking of moving objects," in Proceedings of the International Conference on Computer Vision, (IEEE Computer Society, 1998), p. 1139.
  6. M. Rousson and N. Paragios, "Shape priors for level set representations," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), pp. 78-92.
  7. G. Sapiro, Geometric Partial Differential Equations and Image Analysis (Cambridge U. Press, 2001).
    [CrossRef]
  8. A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
    [CrossRef] [PubMed]
  9. J. Jackson, A. J. Yezzi, and S. Soatto, "Tracking deformable moving objects under severe occlusions," in Proceedings of the IEEE Conference on Decision and Control (IEEE, 2004), pp. 2990-2995.
  10. Y. Rathi, N. Vaswani, A. Tannenbaum, and A. Yezzi, "Particle filtering for geometric active contours with application to tracking moving and deforming objects," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE Computer Society, 2005), Vol. 2, pp. 2-9.
  11. A. Yezzi and S. Soatto, "Deformation: deforming motion, shape average and the joint registration and approximation of structures in images," Int. J. Comput. Vis. 53, 153-167 (2003).
    [CrossRef]
  12. J. Foley, A. van Dam, S. Feiner, and J. Hughes, Computer Graphics Principles and Practice, (Addison-Wesley, 1990), Chap. 13, pp. 563-604.
  13. R. E. Kalman, "A new approach to linear filtering and prediction problems," Trans. ASME 82 Ser. D, 35-45 (1960).
  14. A. Doucet and N. de Freitas, Sequential Monte Carlo Methods in Practice (Springer-Verlag, 2001).
  15. A. C. Sankaranarayanan, R. Chellappa, and A. Srivastava, "Algorithmic and architectural design methodology for particle filters in hardware," in Proceedings of the International Conference of Computer Design (ICCD) (2005), pp. 275-280.
  16. M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Trans. Signal Process. 50, 174-188 (2002).
    [CrossRef]
  17. N. J. Gordon, D. J. Salmond, and A. Smith, "Novel approach to nonlinear/non-Gaussian Bayesian state estimation," IEEE Proc. Radar Signal Process. 140, 107-113 (1993).
    [CrossRef]
  18. S. Zhou, R. Chellappa, and B. Moghaddam, "Visual tracking and recognition using appearance-adaptive models in particle filters," IEEE Trans. Image Process. 13, 1491-1506 (2004).
    [CrossRef] [PubMed]
  19. D. Metaxas and D. Terzopouilos, "Shape and nonrigid motion estimation through physics-based synthesis," IEEE Trans. Pattern Anal. Mach. Intell. 15, 580-591 (1993).
    [CrossRef]
  20. G. Xu, E. Segawa, and S. Tsuji, "A robust active contour model with insensitive parameters," in Proceedings of the International Conference on Computer Vision (1993), pp. 562-566.
  21. P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, "The gait identification challenge problem: data sets and baseline algorithm," in Proceedings of the International Conference on Pattern Recognition (International Association for Pattern Recognition, 2002), Vol. 1, pp. 385-388.
  22. A. Jain, Fundamentals of Digital Image Processing (Prentice Hall, 1989), Chap. 9.
  23. P. Viola, M. J. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," in Proceedings of the 9th IEEE International Conference on Computer Vision (IEEE Computer Society, 2003), Vol. 2, pp. 734-741.
    [CrossRef]
  24. K. Toyama and G. Hager, "Incremental focus of attention for robust vision-based tracking," Int. J. Comput. Vis. 35, 45-63 (Jan 1999).
    [CrossRef]
  25. H. Sidenbladh, M. J. Black, and D. J. Fleet, "Stochastic tracking of 3D human figures using 2D image motion," in Proceedings of the European Conference on Computer Vision 2000 (Springer, 2000), Vol. 2, pp. 702-718.
  26. J. M. Odobez and D. Gatica-Perez, "Embedding motion in model-based stochastic tracking," in Proceedings of the International Conference on Pattern Recognition 2004 (International Society for Pattern Recognition, 2004), Vol. 2, pp. 815-818.
    [CrossRef]
  27. B. Birchfield, "Elliptical head tracking using intensity gradients and color histogram," in Proceedings of the International Conference on Pattern Recognition 1998 Computer Vision and Pattern Recognition, (International Society for Pattern Recognition, 1998), pp. 232-237.
  28. J. Triesch and C. van der Malsburg, "Democratic integration: Self-organized integration of adaptive cues," Neural Comput. 13, 2049-2074 (2001).
    [CrossRef] [PubMed]
  29. J. Vermaak, P. Pérez, M. Gangnet, and A. Blake, "Towards improved observation models for visual tracking: selective adaptation," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), Vol. 1, pp. 645-660 (2002).
  30. P. Pérez, J. Vermaak, and A. Blake, Proc. IEEE 92, 495-513 (2004).
  31. P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Trans. Pattern Anal. Mach. Intell. 12, 629-639 (1990).
    [CrossRef]
  32. Q. Zheng and R. Chellappa, "A computational vision approach to image registration," IEEE Trans. Image Process. 2, 311-326 (1993).
    [CrossRef] [PubMed]
  33. J. M. Coughlan and S. J. Ferreira, "Finding deformable shapes using loopy belief propagation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 3, pp. 453-468.
  34. D. Cremers, T. Kohlberger, and C. Schnörr, "Nonlinear shape statistics in Mumford-Shah based segmentation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 2, pp. 93-108.
  35. F. Porikli and O. Tuzel, "Bayesian background modeling for foreground detection," in Proceedings of the ACM Visual Surveillance and Sensor Network (Association for Computing Machinery, 2005), Vol. 3, pp. 55-58.
    [CrossRef]
  36. T. F. Cootes and C. J. Taylor, "Active shape models," in Proceedings of the 3rd British Machine Vision Conference, D.Hogg and R.Boyle, eds. (Springer, 1992), pp. 266-275.
  37. T. F. Cootes and C. J. Taylor, "Combining point distribution models with shape models based on finite-element analysis," in Proceedings of the 5th British Machine Vision Conference, E.Hancock, ed., (British Machine Vision Association, 1994), pp. 419-428.
  38. X. S. Zhou, D. Comaniciu, and A. Gupta, "An information fusion framework for robust shape tracking," IEEE Trans. Pattern Anal. Mach. Intell. 27, 115-129 (2005).
    [CrossRef] [PubMed]
  39. P. Hall, D. Marshall, and R. Martin, "Merging and splitting eigenspace models," IEEE Trans. Pattern Anal. Mach. Intell. 22, 1042-1048 (2000).
    [CrossRef]
  40. H. Nanda and L. Davis, "Probabilistic template based pedestrian detection in infrared videos," in Proceedings of the IEEE Intelligent Vehicle Symposium (IEEE, 2002), pp. 15-20.
  41. Y. Akgul and C. Kambhamettu, "A coarse-to-fine deformable contour optimization framework," IEEE Trans. Pattern Anal. Mach. Intell. 25, 174-186 (2003).
    [CrossRef]
  42. M. Spengler and B. Schiele, "Towards robust multi-cue integration for visual tracking," Machine Vision Appl. 4, 50-58 (2003).
    [CrossRef]

2005 (1)

X. S. Zhou, D. Comaniciu, and A. Gupta, "An information fusion framework for robust shape tracking," IEEE Trans. Pattern Anal. Mach. Intell. 27, 115-129 (2005).
[CrossRef] [PubMed]

2004 (2)

S. Zhou, R. Chellappa, and B. Moghaddam, "Visual tracking and recognition using appearance-adaptive models in particle filters," IEEE Trans. Image Process. 13, 1491-1506 (2004).
[CrossRef] [PubMed]

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

2003 (4)

A. Yezzi and S. Soatto, "Deformation: deforming motion, shape average and the joint registration and approximation of structures in images," Int. J. Comput. Vis. 53, 153-167 (2003).
[CrossRef]

P. Li, T. Zhang, and A. E. C. Pece, "Visual contour tracking based on particle filters," Image Vis. Comput. 21, 111-123 (2003).
[CrossRef]

Y. Akgul and C. Kambhamettu, "A coarse-to-fine deformable contour optimization framework," IEEE Trans. Pattern Anal. Mach. Intell. 25, 174-186 (2003).
[CrossRef]

M. Spengler and B. Schiele, "Towards robust multi-cue integration for visual tracking," Machine Vision Appl. 4, 50-58 (2003).
[CrossRef]

2002 (1)

M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Trans. Signal Process. 50, 174-188 (2002).
[CrossRef]

2001 (1)

J. Triesch and C. van der Malsburg, "Democratic integration: Self-organized integration of adaptive cues," Neural Comput. 13, 2049-2074 (2001).
[CrossRef] [PubMed]

2000 (1)

P. Hall, D. Marshall, and R. Martin, "Merging and splitting eigenspace models," IEEE Trans. Pattern Anal. Mach. Intell. 22, 1042-1048 (2000).
[CrossRef]

1999 (1)

K. Toyama and G. Hager, "Incremental focus of attention for robust vision-based tracking," Int. J. Comput. Vis. 35, 45-63 (Jan 1999).
[CrossRef]

1998 (1)

M. Isard and A. Blake, "CONDENSATION: conditional density propagation for visual tracking," Int. J. Comput. Vis. 29, 5-28 (1998).
[CrossRef]

1993 (4)

F. Leymarie and M. D. Levine, "Tracking deformable objects in the plane using an active contour model," IEEE Trans. Pattern Anal. Mach. Intell. 15, 617-634 (1993).
[CrossRef]

N. J. Gordon, D. J. Salmond, and A. Smith, "Novel approach to nonlinear/non-Gaussian Bayesian state estimation," IEEE Proc. Radar Signal Process. 140, 107-113 (1993).
[CrossRef]

Q. Zheng and R. Chellappa, "A computational vision approach to image registration," IEEE Trans. Image Process. 2, 311-326 (1993).
[CrossRef] [PubMed]

D. Metaxas and D. Terzopouilos, "Shape and nonrigid motion estimation through physics-based synthesis," IEEE Trans. Pattern Anal. Mach. Intell. 15, 580-591 (1993).
[CrossRef]

1990 (1)

P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Trans. Pattern Anal. Mach. Intell. 12, 629-639 (1990).
[CrossRef]

1988 (1)

M. Kass, A. Witkins, and D. Terzopoulos, "Snakes: active contour models," Int. J. Comput. Vis. 1, 321-331 (1988).
[CrossRef]

1960 (1)

R. E. Kalman, "A new approach to linear filtering and prediction problems," Trans. ASME 82 Ser. D, 35-45 (1960).

Akgul, Y.

Y. Akgul and C. Kambhamettu, "A coarse-to-fine deformable contour optimization framework," IEEE Trans. Pattern Anal. Mach. Intell. 25, 174-186 (2003).
[CrossRef]

Arulampalam, M. S.

M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Trans. Signal Process. 50, 174-188 (2002).
[CrossRef]

Birchfield, B.

B. Birchfield, "Elliptical head tracking using intensity gradients and color histogram," in Proceedings of the International Conference on Pattern Recognition 1998 Computer Vision and Pattern Recognition, (International Society for Pattern Recognition, 1998), pp. 232-237.

Black, M. J.

H. Sidenbladh, M. J. Black, and D. J. Fleet, "Stochastic tracking of 3D human figures using 2D image motion," in Proceedings of the European Conference on Computer Vision 2000 (Springer, 2000), Vol. 2, pp. 702-718.

Blake, A.

M. Isard and A. Blake, "CONDENSATION: conditional density propagation for visual tracking," Int. J. Comput. Vis. 29, 5-28 (1998).
[CrossRef]

J. Vermaak, P. Pérez, M. Gangnet, and A. Blake, "Towards improved observation models for visual tracking: selective adaptation," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), Vol. 1, pp. 645-660 (2002).

P. Pérez, J. Vermaak, and A. Blake, Proc. IEEE 92, 495-513 (2004).

Bowyer, K. W.

P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, "The gait identification challenge problem: data sets and baseline algorithm," in Proceedings of the International Conference on Pattern Recognition (International Association for Pattern Recognition, 2002), Vol. 1, pp. 385-388.

Chellappa, R.

S. Zhou, R. Chellappa, and B. Moghaddam, "Visual tracking and recognition using appearance-adaptive models in particle filters," IEEE Trans. Image Process. 13, 1491-1506 (2004).
[CrossRef] [PubMed]

Q. Zheng and R. Chellappa, "A computational vision approach to image registration," IEEE Trans. Image Process. 2, 311-326 (1993).
[CrossRef] [PubMed]

A. C. Sankaranarayanan, R. Chellappa, and A. Srivastava, "Algorithmic and architectural design methodology for particle filters in hardware," in Proceedings of the International Conference of Computer Design (ICCD) (2005), pp. 275-280.

Clapp, T.

M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Trans. Signal Process. 50, 174-188 (2002).
[CrossRef]

Comaniciu, D.

X. S. Zhou, D. Comaniciu, and A. Gupta, "An information fusion framework for robust shape tracking," IEEE Trans. Pattern Anal. Mach. Intell. 27, 115-129 (2005).
[CrossRef] [PubMed]

Cootes, T. F.

T. F. Cootes and C. J. Taylor, "Combining point distribution models with shape models based on finite-element analysis," in Proceedings of the 5th British Machine Vision Conference, E.Hancock, ed., (British Machine Vision Association, 1994), pp. 419-428.

T. F. Cootes and C. J. Taylor, "Active shape models," in Proceedings of the 3rd British Machine Vision Conference, D.Hogg and R.Boyle, eds. (Springer, 1992), pp. 266-275.

Coughlan, J. M.

J. M. Coughlan and S. J. Ferreira, "Finding deformable shapes using loopy belief propagation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 3, pp. 453-468.

Cremers, D.

D. Cremers, T. Kohlberger, and C. Schnörr, "Nonlinear shape statistics in Mumford-Shah based segmentation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 2, pp. 93-108.

Davis, L.

H. Nanda and L. Davis, "Probabilistic template based pedestrian detection in infrared videos," in Proceedings of the IEEE Intelligent Vehicle Symposium (IEEE, 2002), pp. 15-20.

de Freitas, N.

A. Doucet and N. de Freitas, Sequential Monte Carlo Methods in Practice (Springer-Verlag, 2001).

Doucet, A.

A. Doucet and N. de Freitas, Sequential Monte Carlo Methods in Practice (Springer-Verlag, 2001).

Feiner, S.

J. Foley, A. van Dam, S. Feiner, and J. Hughes, Computer Graphics Principles and Practice, (Addison-Wesley, 1990), Chap. 13, pp. 563-604.

Ferreira, S. J.

J. M. Coughlan and S. J. Ferreira, "Finding deformable shapes using loopy belief propagation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 3, pp. 453-468.

Fleet, D. J.

H. Sidenbladh, M. J. Black, and D. J. Fleet, "Stochastic tracking of 3D human figures using 2D image motion," in Proceedings of the European Conference on Computer Vision 2000 (Springer, 2000), Vol. 2, pp. 702-718.

Foley, J.

J. Foley, A. van Dam, S. Feiner, and J. Hughes, Computer Graphics Principles and Practice, (Addison-Wesley, 1990), Chap. 13, pp. 563-604.

Gangnet, M.

J. Vermaak, P. Pérez, M. Gangnet, and A. Blake, "Towards improved observation models for visual tracking: selective adaptation," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), Vol. 1, pp. 645-660 (2002).

Gatica-Perez, D.

J. M. Odobez and D. Gatica-Perez, "Embedding motion in model-based stochastic tracking," in Proceedings of the International Conference on Pattern Recognition 2004 (International Society for Pattern Recognition, 2004), Vol. 2, pp. 815-818.
[CrossRef]

Gordon, N.

M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Trans. Signal Process. 50, 174-188 (2002).
[CrossRef]

Gordon, N. J.

N. J. Gordon, D. J. Salmond, and A. Smith, "Novel approach to nonlinear/non-Gaussian Bayesian state estimation," IEEE Proc. Radar Signal Process. 140, 107-113 (1993).
[CrossRef]

Grother, P.

P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, "The gait identification challenge problem: data sets and baseline algorithm," in Proceedings of the International Conference on Pattern Recognition (International Association for Pattern Recognition, 2002), Vol. 1, pp. 385-388.

Gupta, A.

X. S. Zhou, D. Comaniciu, and A. Gupta, "An information fusion framework for robust shape tracking," IEEE Trans. Pattern Anal. Mach. Intell. 27, 115-129 (2005).
[CrossRef] [PubMed]

Hager, G.

K. Toyama and G. Hager, "Incremental focus of attention for robust vision-based tracking," Int. J. Comput. Vis. 35, 45-63 (Jan 1999).
[CrossRef]

Hall, P.

P. Hall, D. Marshall, and R. Martin, "Merging and splitting eigenspace models," IEEE Trans. Pattern Anal. Mach. Intell. 22, 1042-1048 (2000).
[CrossRef]

Hughes, J.

J. Foley, A. van Dam, S. Feiner, and J. Hughes, Computer Graphics Principles and Practice, (Addison-Wesley, 1990), Chap. 13, pp. 563-604.

Isard, M.

M. Isard and A. Blake, "CONDENSATION: conditional density propagation for visual tracking," Int. J. Comput. Vis. 29, 5-28 (1998).
[CrossRef]

Jackson, J.

J. Jackson, A. J. Yezzi, and S. Soatto, "Tracking deformable moving objects under severe occlusions," in Proceedings of the IEEE Conference on Decision and Control (IEEE, 2004), pp. 2990-2995.

Jain, A.

A. Jain, Fundamentals of Digital Image Processing (Prentice Hall, 1989), Chap. 9.

Jones, M. J.

P. Viola, M. J. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," in Proceedings of the 9th IEEE International Conference on Computer Vision (IEEE Computer Society, 2003), Vol. 2, pp. 734-741.
[CrossRef]

Kalman, R. E.

R. E. Kalman, "A new approach to linear filtering and prediction problems," Trans. ASME 82 Ser. D, 35-45 (1960).

Kambhamettu, C.

Y. Akgul and C. Kambhamettu, "A coarse-to-fine deformable contour optimization framework," IEEE Trans. Pattern Anal. Mach. Intell. 25, 174-186 (2003).
[CrossRef]

Kass, M.

M. Kass, A. Witkins, and D. Terzopoulos, "Snakes: active contour models," Int. J. Comput. Vis. 1, 321-331 (1988).
[CrossRef]

Kohlberger, T.

D. Cremers, T. Kohlberger, and C. Schnörr, "Nonlinear shape statistics in Mumford-Shah based segmentation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 2, pp. 93-108.

Levine, M. D.

F. Leymarie and M. D. Levine, "Tracking deformable objects in the plane using an active contour model," IEEE Trans. Pattern Anal. Mach. Intell. 15, 617-634 (1993).
[CrossRef]

Leymarie, F.

F. Leymarie and M. D. Levine, "Tracking deformable objects in the plane using an active contour model," IEEE Trans. Pattern Anal. Mach. Intell. 15, 617-634 (1993).
[CrossRef]

Li, P.

P. Li, T. Zhang, and A. E. C. Pece, "Visual contour tracking based on particle filters," Image Vis. Comput. 21, 111-123 (2003).
[CrossRef]

Li, X.

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

Malik, J.

P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Trans. Pattern Anal. Mach. Intell. 12, 629-639 (1990).
[CrossRef]

Marshall, D.

P. Hall, D. Marshall, and R. Martin, "Merging and splitting eigenspace models," IEEE Trans. Pattern Anal. Mach. Intell. 22, 1042-1048 (2000).
[CrossRef]

Martin, R.

P. Hall, D. Marshall, and R. Martin, "Merging and splitting eigenspace models," IEEE Trans. Pattern Anal. Mach. Intell. 22, 1042-1048 (2000).
[CrossRef]

Maskell, S.

M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Trans. Signal Process. 50, 174-188 (2002).
[CrossRef]

Metaxas, D.

D. Metaxas and D. Terzopouilos, "Shape and nonrigid motion estimation through physics-based synthesis," IEEE Trans. Pattern Anal. Mach. Intell. 15, 580-591 (1993).
[CrossRef]

Moghaddam, B.

S. Zhou, R. Chellappa, and B. Moghaddam, "Visual tracking and recognition using appearance-adaptive models in particle filters," IEEE Trans. Image Process. 13, 1491-1506 (2004).
[CrossRef] [PubMed]

Nanda, H.

H. Nanda and L. Davis, "Probabilistic template based pedestrian detection in infrared videos," in Proceedings of the IEEE Intelligent Vehicle Symposium (IEEE, 2002), pp. 15-20.

Nikos, K. P.

K. P. Nikos and D. Rachid, "A PDE-based level-set approach for detection and tracking of moving objects," in Proceedings of the International Conference on Computer Vision, (IEEE Computer Society, 1998), p. 1139.

Odobez, J. M.

J. M. Odobez and D. Gatica-Perez, "Embedding motion in model-based stochastic tracking," in Proceedings of the International Conference on Pattern Recognition 2004 (International Society for Pattern Recognition, 2004), Vol. 2, pp. 815-818.
[CrossRef]

Paragios, N.

M. Rousson and N. Paragios, "Shape priors for level set representations," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), pp. 78-92.

Pece, A. E. C.

P. Li, T. Zhang, and A. E. C. Pece, "Visual contour tracking based on particle filters," Image Vis. Comput. 21, 111-123 (2003).
[CrossRef]

Pérez, P.

J. Vermaak, P. Pérez, M. Gangnet, and A. Blake, "Towards improved observation models for visual tracking: selective adaptation," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), Vol. 1, pp. 645-660 (2002).

P. Pérez, J. Vermaak, and A. Blake, Proc. IEEE 92, 495-513 (2004).

Perona, P.

P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Trans. Pattern Anal. Mach. Intell. 12, 629-639 (1990).
[CrossRef]

Phillips, P. J.

P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, "The gait identification challenge problem: data sets and baseline algorithm," in Proceedings of the International Conference on Pattern Recognition (International Association for Pattern Recognition, 2002), Vol. 1, pp. 385-388.

Porikli, F.

F. Porikli and O. Tuzel, "Bayesian background modeling for foreground detection," in Proceedings of the ACM Visual Surveillance and Sensor Network (Association for Computing Machinery, 2005), Vol. 3, pp. 55-58.
[CrossRef]

Rachid, D.

K. P. Nikos and D. Rachid, "A PDE-based level-set approach for detection and tracking of moving objects," in Proceedings of the International Conference on Computer Vision, (IEEE Computer Society, 1998), p. 1139.

Rathi, Y.

Y. Rathi, N. Vaswani, A. Tannenbaum, and A. Yezzi, "Particle filtering for geometric active contours with application to tracking moving and deforming objects," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE Computer Society, 2005), Vol. 2, pp. 2-9.

Robledo, I.

P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, "The gait identification challenge problem: data sets and baseline algorithm," in Proceedings of the International Conference on Pattern Recognition (International Association for Pattern Recognition, 2002), Vol. 1, pp. 385-388.

Rousson, M.

M. Rousson and N. Paragios, "Shape priors for level set representations," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), pp. 78-92.

Salmond, D. J.

N. J. Gordon, D. J. Salmond, and A. Smith, "Novel approach to nonlinear/non-Gaussian Bayesian state estimation," IEEE Proc. Radar Signal Process. 140, 107-113 (1993).
[CrossRef]

Sankaranarayanan, A. C.

A. C. Sankaranarayanan, R. Chellappa, and A. Srivastava, "Algorithmic and architectural design methodology for particle filters in hardware," in Proceedings of the International Conference of Computer Design (ICCD) (2005), pp. 275-280.

Sapiro, G.

G. Sapiro, Geometric Partial Differential Equations and Image Analysis (Cambridge U. Press, 2001).
[CrossRef]

Sarkar, S.

P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, "The gait identification challenge problem: data sets and baseline algorithm," in Proceedings of the International Conference on Pattern Recognition (International Association for Pattern Recognition, 2002), Vol. 1, pp. 385-388.

Schiele, B.

M. Spengler and B. Schiele, "Towards robust multi-cue integration for visual tracking," Machine Vision Appl. 4, 50-58 (2003).
[CrossRef]

Schnörr, C.

D. Cremers, T. Kohlberger, and C. Schnörr, "Nonlinear shape statistics in Mumford-Shah based segmentation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 2, pp. 93-108.

Segawa, E.

G. Xu, E. Segawa, and S. Tsuji, "A robust active contour model with insensitive parameters," in Proceedings of the International Conference on Computer Vision (1993), pp. 562-566.

Shah, M.

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

Sidenbladh, H.

H. Sidenbladh, M. J. Black, and D. J. Fleet, "Stochastic tracking of 3D human figures using 2D image motion," in Proceedings of the European Conference on Computer Vision 2000 (Springer, 2000), Vol. 2, pp. 702-718.

Smith, A.

N. J. Gordon, D. J. Salmond, and A. Smith, "Novel approach to nonlinear/non-Gaussian Bayesian state estimation," IEEE Proc. Radar Signal Process. 140, 107-113 (1993).
[CrossRef]

Snow, D.

P. Viola, M. J. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," in Proceedings of the 9th IEEE International Conference on Computer Vision (IEEE Computer Society, 2003), Vol. 2, pp. 734-741.
[CrossRef]

Soatto, S.

A. Yezzi and S. Soatto, "Deformation: deforming motion, shape average and the joint registration and approximation of structures in images," Int. J. Comput. Vis. 53, 153-167 (2003).
[CrossRef]

J. Jackson, A. J. Yezzi, and S. Soatto, "Tracking deformable moving objects under severe occlusions," in Proceedings of the IEEE Conference on Decision and Control (IEEE, 2004), pp. 2990-2995.

Spengler, M.

M. Spengler and B. Schiele, "Towards robust multi-cue integration for visual tracking," Machine Vision Appl. 4, 50-58 (2003).
[CrossRef]

Srivastava, A.

A. C. Sankaranarayanan, R. Chellappa, and A. Srivastava, "Algorithmic and architectural design methodology for particle filters in hardware," in Proceedings of the International Conference of Computer Design (ICCD) (2005), pp. 275-280.

Tannenbaum, A.

Y. Rathi, N. Vaswani, A. Tannenbaum, and A. Yezzi, "Particle filtering for geometric active contours with application to tracking moving and deforming objects," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE Computer Society, 2005), Vol. 2, pp. 2-9.

Taylor, C. J.

T. F. Cootes and C. J. Taylor, "Combining point distribution models with shape models based on finite-element analysis," in Proceedings of the 5th British Machine Vision Conference, E.Hancock, ed., (British Machine Vision Association, 1994), pp. 419-428.

T. F. Cootes and C. J. Taylor, "Active shape models," in Proceedings of the 3rd British Machine Vision Conference, D.Hogg and R.Boyle, eds. (Springer, 1992), pp. 266-275.

Terzopouilos, D.

D. Metaxas and D. Terzopouilos, "Shape and nonrigid motion estimation through physics-based synthesis," IEEE Trans. Pattern Anal. Mach. Intell. 15, 580-591 (1993).
[CrossRef]

Terzopoulos, D.

M. Kass, A. Witkins, and D. Terzopoulos, "Snakes: active contour models," Int. J. Comput. Vis. 1, 321-331 (1988).
[CrossRef]

Toyama, K.

K. Toyama and G. Hager, "Incremental focus of attention for robust vision-based tracking," Int. J. Comput. Vis. 35, 45-63 (Jan 1999).
[CrossRef]

Triesch, J.

J. Triesch and C. van der Malsburg, "Democratic integration: Self-organized integration of adaptive cues," Neural Comput. 13, 2049-2074 (2001).
[CrossRef] [PubMed]

Tsuji, S.

G. Xu, E. Segawa, and S. Tsuji, "A robust active contour model with insensitive parameters," in Proceedings of the International Conference on Computer Vision (1993), pp. 562-566.

Tuzel, O.

F. Porikli and O. Tuzel, "Bayesian background modeling for foreground detection," in Proceedings of the ACM Visual Surveillance and Sensor Network (Association for Computing Machinery, 2005), Vol. 3, pp. 55-58.
[CrossRef]

van Dam, A.

J. Foley, A. van Dam, S. Feiner, and J. Hughes, Computer Graphics Principles and Practice, (Addison-Wesley, 1990), Chap. 13, pp. 563-604.

van der Malsburg, C.

J. Triesch and C. van der Malsburg, "Democratic integration: Self-organized integration of adaptive cues," Neural Comput. 13, 2049-2074 (2001).
[CrossRef] [PubMed]

Vaswani, N.

Y. Rathi, N. Vaswani, A. Tannenbaum, and A. Yezzi, "Particle filtering for geometric active contours with application to tracking moving and deforming objects," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE Computer Society, 2005), Vol. 2, pp. 2-9.

Vermaak, J.

J. Vermaak, P. Pérez, M. Gangnet, and A. Blake, "Towards improved observation models for visual tracking: selective adaptation," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), Vol. 1, pp. 645-660 (2002).

P. Pérez, J. Vermaak, and A. Blake, Proc. IEEE 92, 495-513 (2004).

Viola, P.

P. Viola, M. J. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," in Proceedings of the 9th IEEE International Conference on Computer Vision (IEEE Computer Society, 2003), Vol. 2, pp. 734-741.
[CrossRef]

Witkins, A.

M. Kass, A. Witkins, and D. Terzopoulos, "Snakes: active contour models," Int. J. Comput. Vis. 1, 321-331 (1988).
[CrossRef]

Xu, G.

G. Xu, E. Segawa, and S. Tsuji, "A robust active contour model with insensitive parameters," in Proceedings of the International Conference on Computer Vision (1993), pp. 562-566.

Yezzi, A.

A. Yezzi and S. Soatto, "Deformation: deforming motion, shape average and the joint registration and approximation of structures in images," Int. J. Comput. Vis. 53, 153-167 (2003).
[CrossRef]

Y. Rathi, N. Vaswani, A. Tannenbaum, and A. Yezzi, "Particle filtering for geometric active contours with application to tracking moving and deforming objects," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE Computer Society, 2005), Vol. 2, pp. 2-9.

Yezzi, A. J.

J. Jackson, A. J. Yezzi, and S. Soatto, "Tracking deformable moving objects under severe occlusions," in Proceedings of the IEEE Conference on Decision and Control (IEEE, 2004), pp. 2990-2995.

Yilmaz, A.

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

Zhang, T.

P. Li, T. Zhang, and A. E. C. Pece, "Visual contour tracking based on particle filters," Image Vis. Comput. 21, 111-123 (2003).
[CrossRef]

Zheng, Q.

Q. Zheng and R. Chellappa, "A computational vision approach to image registration," IEEE Trans. Image Process. 2, 311-326 (1993).
[CrossRef] [PubMed]

Zhou, S.

S. Zhou, R. Chellappa, and B. Moghaddam, "Visual tracking and recognition using appearance-adaptive models in particle filters," IEEE Trans. Image Process. 13, 1491-1506 (2004).
[CrossRef] [PubMed]

Zhou, X. S.

X. S. Zhou, D. Comaniciu, and A. Gupta, "An information fusion framework for robust shape tracking," IEEE Trans. Pattern Anal. Mach. Intell. 27, 115-129 (2005).
[CrossRef] [PubMed]

IEEE Proc. Radar Signal Process. (1)

N. J. Gordon, D. J. Salmond, and A. Smith, "Novel approach to nonlinear/non-Gaussian Bayesian state estimation," IEEE Proc. Radar Signal Process. 140, 107-113 (1993).
[CrossRef]

IEEE Trans. Image Process. (2)

S. Zhou, R. Chellappa, and B. Moghaddam, "Visual tracking and recognition using appearance-adaptive models in particle filters," IEEE Trans. Image Process. 13, 1491-1506 (2004).
[CrossRef] [PubMed]

Q. Zheng and R. Chellappa, "A computational vision approach to image registration," IEEE Trans. Image Process. 2, 311-326 (1993).
[CrossRef] [PubMed]

IEEE Trans. Pattern Anal. Mach. Intell. (7)

X. S. Zhou, D. Comaniciu, and A. Gupta, "An information fusion framework for robust shape tracking," IEEE Trans. Pattern Anal. Mach. Intell. 27, 115-129 (2005).
[CrossRef] [PubMed]

P. Hall, D. Marshall, and R. Martin, "Merging and splitting eigenspace models," IEEE Trans. Pattern Anal. Mach. Intell. 22, 1042-1048 (2000).
[CrossRef]

Y. Akgul and C. Kambhamettu, "A coarse-to-fine deformable contour optimization framework," IEEE Trans. Pattern Anal. Mach. Intell. 25, 174-186 (2003).
[CrossRef]

D. Metaxas and D. Terzopouilos, "Shape and nonrigid motion estimation through physics-based synthesis," IEEE Trans. Pattern Anal. Mach. Intell. 15, 580-591 (1993).
[CrossRef]

F. Leymarie and M. D. Levine, "Tracking deformable objects in the plane using an active contour model," IEEE Trans. Pattern Anal. Mach. Intell. 15, 617-634 (1993).
[CrossRef]

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Trans. Pattern Anal. Mach. Intell. 12, 629-639 (1990).
[CrossRef]

IEEE Trans. Signal Process. (1)

M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," IEEE Trans. Signal Process. 50, 174-188 (2002).
[CrossRef]

Image Vis. Comput. (1)

P. Li, T. Zhang, and A. E. C. Pece, "Visual contour tracking based on particle filters," Image Vis. Comput. 21, 111-123 (2003).
[CrossRef]

Int. J. Comput. Vis. (4)

M. Kass, A. Witkins, and D. Terzopoulos, "Snakes: active contour models," Int. J. Comput. Vis. 1, 321-331 (1988).
[CrossRef]

A. Yezzi and S. Soatto, "Deformation: deforming motion, shape average and the joint registration and approximation of structures in images," Int. J. Comput. Vis. 53, 153-167 (2003).
[CrossRef]

M. Isard and A. Blake, "CONDENSATION: conditional density propagation for visual tracking," Int. J. Comput. Vis. 29, 5-28 (1998).
[CrossRef]

K. Toyama and G. Hager, "Incremental focus of attention for robust vision-based tracking," Int. J. Comput. Vis. 35, 45-63 (Jan 1999).
[CrossRef]

Machine Vision Appl. (1)

M. Spengler and B. Schiele, "Towards robust multi-cue integration for visual tracking," Machine Vision Appl. 4, 50-58 (2003).
[CrossRef]

Neural Comput. (1)

J. Triesch and C. van der Malsburg, "Democratic integration: Self-organized integration of adaptive cues," Neural Comput. 13, 2049-2074 (2001).
[CrossRef] [PubMed]

Trans. ASME (1)

R. E. Kalman, "A new approach to linear filtering and prediction problems," Trans. ASME 82 Ser. D, 35-45 (1960).

Other (23)

A. Doucet and N. de Freitas, Sequential Monte Carlo Methods in Practice (Springer-Verlag, 2001).

A. C. Sankaranarayanan, R. Chellappa, and A. Srivastava, "Algorithmic and architectural design methodology for particle filters in hardware," in Proceedings of the International Conference of Computer Design (ICCD) (2005), pp. 275-280.

J. Foley, A. van Dam, S. Feiner, and J. Hughes, Computer Graphics Principles and Practice, (Addison-Wesley, 1990), Chap. 13, pp. 563-604.

G. Xu, E. Segawa, and S. Tsuji, "A robust active contour model with insensitive parameters," in Proceedings of the International Conference on Computer Vision (1993), pp. 562-566.

P. J. Phillips, S. Sarkar, I. Robledo, P. Grother, and K. W. Bowyer, "The gait identification challenge problem: data sets and baseline algorithm," in Proceedings of the International Conference on Pattern Recognition (International Association for Pattern Recognition, 2002), Vol. 1, pp. 385-388.

A. Jain, Fundamentals of Digital Image Processing (Prentice Hall, 1989), Chap. 9.

P. Viola, M. J. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," in Proceedings of the 9th IEEE International Conference on Computer Vision (IEEE Computer Society, 2003), Vol. 2, pp. 734-741.
[CrossRef]

J. Jackson, A. J. Yezzi, and S. Soatto, "Tracking deformable moving objects under severe occlusions," in Proceedings of the IEEE Conference on Decision and Control (IEEE, 2004), pp. 2990-2995.

Y. Rathi, N. Vaswani, A. Tannenbaum, and A. Yezzi, "Particle filtering for geometric active contours with application to tracking moving and deforming objects," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE Computer Society, 2005), Vol. 2, pp. 2-9.

K. P. Nikos and D. Rachid, "A PDE-based level-set approach for detection and tracking of moving objects," in Proceedings of the International Conference on Computer Vision, (IEEE Computer Society, 1998), p. 1139.

M. Rousson and N. Paragios, "Shape priors for level set representations," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), pp. 78-92.

G. Sapiro, Geometric Partial Differential Equations and Image Analysis (Cambridge U. Press, 2001).
[CrossRef]

J. Vermaak, P. Pérez, M. Gangnet, and A. Blake, "Towards improved observation models for visual tracking: selective adaptation," in Proceedings of the European Conference on Computer Vision 2002 (Springer, 2002), Vol. 1, pp. 645-660 (2002).

P. Pérez, J. Vermaak, and A. Blake, Proc. IEEE 92, 495-513 (2004).

H. Sidenbladh, M. J. Black, and D. J. Fleet, "Stochastic tracking of 3D human figures using 2D image motion," in Proceedings of the European Conference on Computer Vision 2000 (Springer, 2000), Vol. 2, pp. 702-718.

J. M. Odobez and D. Gatica-Perez, "Embedding motion in model-based stochastic tracking," in Proceedings of the International Conference on Pattern Recognition 2004 (International Society for Pattern Recognition, 2004), Vol. 2, pp. 815-818.
[CrossRef]

B. Birchfield, "Elliptical head tracking using intensity gradients and color histogram," in Proceedings of the International Conference on Pattern Recognition 1998 Computer Vision and Pattern Recognition, (International Society for Pattern Recognition, 1998), pp. 232-237.

H. Nanda and L. Davis, "Probabilistic template based pedestrian detection in infrared videos," in Proceedings of the IEEE Intelligent Vehicle Symposium (IEEE, 2002), pp. 15-20.

J. M. Coughlan and S. J. Ferreira, "Finding deformable shapes using loopy belief propagation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 3, pp. 453-468.

D. Cremers, T. Kohlberger, and C. Schnörr, "Nonlinear shape statistics in Mumford-Shah based segmentation," in Proceedings of the European Conference on Computer Vision (Springer, 2002), Vol. 2, pp. 93-108.

F. Porikli and O. Tuzel, "Bayesian background modeling for foreground detection," in Proceedings of the ACM Visual Surveillance and Sensor Network (Association for Computing Machinery, 2005), Vol. 3, pp. 55-58.
[CrossRef]

T. F. Cootes and C. J. Taylor, "Active shape models," in Proceedings of the 3rd British Machine Vision Conference, D.Hogg and R.Boyle, eds. (Springer, 1992), pp. 266-275.

T. F. Cootes and C. J. Taylor, "Combining point distribution models with shape models based on finite-element analysis," in Proceedings of the 5th British Machine Vision Conference, E.Hancock, ed., (British Machine Vision Association, 1994), pp. 419-428.

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 (17)

Fig. 1
Fig. 1

Illustration of the proposed tracking system.

Fig. 2
Fig. 2

Illustration of estimating the measurement model. (a) The red (upper) line is the contour determined by the control points. Light lines are the normal lines on the control points. The solid dots are feature points detected by the normal lines; (b) 1D measurement density along the line normal on one control point q j ; d 1 , j , d 2 , j and d 3 , j are the three distances between the feature points and the corresponding control point. The vertical axis G EDGE represents the gradient magnitude along the normal line n j .

Fig. 3
Fig. 3

Example of how to make a normal line scanning adaptive. (a) Cropped original object, (b) estimated contour, (c) the distance transformed object, (d) normal lines on control points.

Fig. 4
Fig. 4

Illustration of fusion from different visual sources, including the probability maps of (a) gradient magnitude, (b) gradient orientation, (c) shape template, (d) foreground, (e) fusion.

Fig. 5
Fig. 5

Performance comparisons on a cluttered scene. A stabilization step is applied to obtain the second set of results to obtain F I because the sequence was acquired by a moving camera.

Fig. 6
Fig. 6

Illustrations of adaptive probability shape templates for pedestrians. (1) and (2), shape training samples; (3), shape prior model; (4), (5), and (6), examples of probability shape templates in different frames.

Fig. 7
Fig. 7

Comparisons of tracking results with and without subspace regulation: (a) and (c) are without regulation, (b) and (d) are with regulation.

Fig. 8
Fig. 8

One example frame from an MRI sequence to illustrate shape alignment. The target of interest is the articular cartilage layer. (1) Detected contour pixels, (2) recovered contour pixels using the shape subspace projection, (3) contour pixel after alignment, (4) final result.

Fig. 9
Fig. 9

Example of starting tracking using a very rough initial contour. After tracking for six frames, we find that the contour has been attached to the object fairly precisely.

Fig. 10
Fig. 10

Pedestrian tracking performance with a stationary camera. The thick light (yellow online) outlines represent the final tracked contours.

Fig. 11
Fig. 11

Results of tracking a vehicle from behind. The comparison result is given in Fig. 5.

Fig. 12
Fig. 12

Comparisons of the traditional method and our proposed method on a sequence with both background and object moving. Upper: using the traditional method; Lower: using the proposed method.

Fig. 13
Fig. 13

Sequence with both background and object moving. The challenges of processing this sequence are due to the following: (1) camera motion, (2) background clutter, (3) the pants and the shirt that the pedestrian is wearing are of very different colors.

Fig. 14
Fig. 14

Sequence with both background and object moving. The background is heavily cluttered, and the intensity of the tracking pedestrian is very similar to the background color. A comparison result from the traditional approach is also given.

Fig. 15
Fig. 15

Airborne sequence with a white truck moving on the ground. The truck shows a back view in frames (1) and (2), then shows the back-right view in frame (3), a side view in frames (4) and (5) and a front-right view in frame (6). This experiment demonstrates that the contour-based tracker can give satisfactory results on sequences containing 3D object rotations.

Fig. 16
Fig. 16

Example of an occluded contour being recovered by shape subspace projection. In the last three frames, the pedestrian is partially occluded by the surrounding trees. Our tracking result recovers the partially occluded contour. Bright (red online) arrows indicate the occluded parts. We may also note that the parked cars contribute to background clutter.

Fig. 17
Fig. 17

Magnetic resonance imaging scans of human knees. The area of interest is the articular cartilage in each image. The upper row demonstrates the results from application of the traditional algorithm. The middle and bottom rows show the results from application of our proposed method.

Tables (4)

Tables Icon

Table 1 Algorithm 1: Set Center of the Normal Line Adaptive

Tables Icon

Table 2 Algorithm 2: Construct Prior Shape Model

Tables Icon

Table 3 Algorithm 3: Active Contour Tracking

Tables Icon

Table 4 Comparison of Tracking Results in Heavy-Cluttered Background Sequences and Nonrigid Object Sequences

Equations (35)

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

p ( θ t Y 1 : t ) p ( Y t θ t ) p ( θ t θ t 1 ) p ( θ t 1 Y 1 : t 1 ) d θ t 1 ,
ω t ( j ) p ( Y t θ t ( j ) ) ,
ω j ( j ) p ( Y t θ t ( j ) ) p ( θ t j θ t 1 ( j ) ) g ( θ j ( j ) θ t 1 ( j ) , Y 1 : t ) .
[ q l , t 1 1 ] = T [ q l , t 1 ] = [ T 11 T 12 T 13 T 21 T 22 T 23 0 0 1 ] [ q l , t 1 ] ,
θ t = ( T 11 T 12 T 21 T 22 T 13 T 23 ) T .
θ t = θ ̂ t 1 + v t + U t
Z t ( Q t ) = Z t 1 ( T ( θ t ) [ Q t 1 ] ) = Z t 1 ( Q ̂ t 1 ) ,
T { Z t ; θ t } T { Z t ; θ ̂ t 1 } + C t ( θ t θ ̂ t 1 ) = T { Z t ; θ ̂ t 1 } + C t v t ,
Z ̂ t 1 T { Z t ; θ ̂ t 1 } + C t v t ,
v t B t ( T { Z t ; θ ̂ t 1 } Z ̂ t 1 ) ,
Θ t 1 δ = [ θ t 1 ( 1 ) θ ̂ t 1 , , θ t 1 ( J ) θ ̂ t 1 ] ,
Z t 1 δ = [ Z t 1 ( 1 ) Z ̂ t 1 , , Z t 1 ( J ) Z ̂ t 1 ] ,
B t = ( Θ t 1 δ Z t 1 δ T ) ( Z t 1 δ Z t 1 δ T ) 1 ,
p l ( z q l ) 1 + 1 2 π σ ψ λ j = 1 N l exp [ ( z j ( l ) q l ) 2 2 σ 2 ] ,
p ( Y θ ) = l = 1 L p l ( z q l ) .
ξ ( l ) = E q l k E ( q l k ) 2 ,
u ( l ) L min log ξ ( l ) min ( ξ ( l ) ) ,
P t ( Y Q ̂ ) = i = 1 M P t ( Y i Q ̂ ) .
P t ( Y m Q ̂ ) = α m ( E I Δ I ) * G ,
P t ( Y o Q ̂ ) exp { [ O I t ( x ) ϕ ̂ t 1 ( l ) ] 2 σ o 2 } x R ( n l ) ,
R ( n l ) { y R ( n l ) : dist ( y , n l ) dist ( y , n k ) , k l } .
P t ( Y s Q ̂ ) = a t A S + ( 1 a t ) A Q ̂ ,
d i ( x ) = ( I ( x ) μ t 1 i ) T ( Σ t 1 i ) 1 ( I ( x ) μ t 1 i ) ,
P t ( Y f Q ̂ ) = α exp ( min i = 1 K d i ( x ) ) ,
x r = x 0 x ¯ Pb s .
x ¯ * = β x ¯ + ( 1 β ) x r ,
e r = x r T x r ( x 0 x ¯ ) ,
C * = β [ Λ t 0 0 T 0 ] + β ( 1 β ) [ b s b s T e r b s e r b s T e r 2 ] ,
x p , t = PP T ( x t x ¯ ) + x ¯ ,
x p , t = PP I d ( x I d , t x ¯ I d ) + x ¯ ,
P I d = ( P I d T P I d ) 1 P I d T .
MSSD = 1 K k = 1 K 1 L j = 1 L ( x k , j x k , j 0 ) 2 + ( y k , j y k , j 0 ) 2 ,
D I ( x ) = { min y r ̃ dist ( x , y ) , x Ω 0 otherwise .
u ( l ) in = min ( u ( l ) 2 , D I l d 0 ) ,
u ( l ) out = max ( u ( l ) 2 , u ( l ) [ D I l d 0 ] ) ,

Metrics