Abstract

We present a method based on Bayesian estimation with prior Markov random field models for segmentation of range images of polyhedral objects. This method includes new ways to determine the confidence associated with the information given for every pixel in the image as well as an improved method for localization of the boundaries between regions. The performance of the method compares favorably with other state-of-the-art procedures when evaluated using a standard benchmark.

© 2008 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. S. Inokuchi, K. Sato, and F. Matsuda, “Range imaging system for 3-D object recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE, 1984), pp. 806-808.
  2. A. Hover, “ABW images: the camera and models, ”http://marathon.csee.usf.edu/range/seg-comp/SegComp.html.
  3. A. Hoover, D. Goldgof, and K. W. Bowyer, “The space envelope: a representation for 3D scenes,” Comput. Vision Image Understand. 69, 310-329 (1998).
    [CrossRef]
  4. D. B. Goldgof, T. S. Huang, and H. Lee, “A curvature-based approach to terrain recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 1213-1217 (1989).
    [CrossRef]
  5. X. Y. Jiang and H. Bunke “Fast segmentation of range images into planar regions by scan line grouping,” Machine Vision Appl. 7, 115-122 (1994).
    [CrossRef]
  6. E. Trucco and R. B. Fisher, “Experiments in curvature-based segmentation of range data,” IEEE Trans. Pattern Anal. Mach. Intell. 17, 177-182 (1995).
    [CrossRef]
  7. T. S. Newman, P. J. Flynn, and A. K. Jain, “Model-based classification of quadric surfaces,” CVGIP Image Understand. 58, 235-249 (1993).
    [CrossRef]
  8. A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
    [CrossRef]
  9. D. Huber, O. Carmichael, and M. Hebert, “3-D map reconstruction from range data,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00) (IEEE, 2000), pp. 891-897.
  10. J. Min, M. Powell, and K. W. Bowyer, “Automated performance evaluation of range image segmentation algorithms,” IEEE Trans. Syst. Man Cybern. Part B 34, 263-271 (2004).
    [CrossRef]
  11. X. Jiang, “An adaptive contour closure algorithm and experimental evaluation,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 1252-1265 (2000).
    [CrossRef]
  12. R. W. Taylor, M. Sarini, and A. P. Reeves, “Fast segmentation of range imagery into planar regions,” Comput. Vision Graph. Image Process. 45, 42-60 (1989).
    [CrossRef]
  13. Y. Chen and G. Medioni, “Object modeling by registration of multiple range images,” in IEEE Conference on Robotics and Automations (IEEE, 1991), pp. 2724-2729.
  14. A. W. Fitzgibbon, D. W. Eggert, and R. B. Fisher, “High-level CAD model acquisition from range images,” Comput. Aided Des. 29, 321-330 (1997).
    [CrossRef]
  15. Stan Z. Li, Markov Random Field Modeling in Image Analysis (Springer, 2001).
  16. M. Rivera, O. Ocegueda, and J. L. Marroquin, “Entropy-controlled quadratic measure field models for efficient image segmentation,” IEEE Trans. Image Process. 16, 3047-3057(2007).
    [CrossRef]
  17. http://marathon.csee.usf.edu/range/seg-comp/SegComp.html.
  18. X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
    [CrossRef]

2007 (1)

M. Rivera, O. Ocegueda, and J. L. Marroquin, “Entropy-controlled quadratic measure field models for efficient image segmentation,” IEEE Trans. Image Process. 16, 3047-3057(2007).
[CrossRef]

2004 (1)

J. Min, M. Powell, and K. W. Bowyer, “Automated performance evaluation of range image segmentation algorithms,” IEEE Trans. Syst. Man Cybern. Part B 34, 263-271 (2004).
[CrossRef]

2001 (1)

Stan Z. Li, Markov Random Field Modeling in Image Analysis (Springer, 2001).

2000 (3)

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

X. Jiang, “An adaptive contour closure algorithm and experimental evaluation,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 1252-1265 (2000).
[CrossRef]

D. Huber, O. Carmichael, and M. Hebert, “3-D map reconstruction from range data,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00) (IEEE, 2000), pp. 891-897.

1998 (1)

A. Hoover, D. Goldgof, and K. W. Bowyer, “The space envelope: a representation for 3D scenes,” Comput. Vision Image Understand. 69, 310-329 (1998).
[CrossRef]

1997 (1)

A. W. Fitzgibbon, D. W. Eggert, and R. B. Fisher, “High-level CAD model acquisition from range images,” Comput. Aided Des. 29, 321-330 (1997).
[CrossRef]

1996 (1)

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

1995 (1)

E. Trucco and R. B. Fisher, “Experiments in curvature-based segmentation of range data,” IEEE Trans. Pattern Anal. Mach. Intell. 17, 177-182 (1995).
[CrossRef]

1994 (1)

X. Y. Jiang and H. Bunke “Fast segmentation of range images into planar regions by scan line grouping,” Machine Vision Appl. 7, 115-122 (1994).
[CrossRef]

1993 (1)

T. S. Newman, P. J. Flynn, and A. K. Jain, “Model-based classification of quadric surfaces,” CVGIP Image Understand. 58, 235-249 (1993).
[CrossRef]

1991 (1)

Y. Chen and G. Medioni, “Object modeling by registration of multiple range images,” in IEEE Conference on Robotics and Automations (IEEE, 1991), pp. 2724-2729.

1989 (2)

R. W. Taylor, M. Sarini, and A. P. Reeves, “Fast segmentation of range imagery into planar regions,” Comput. Vision Graph. Image Process. 45, 42-60 (1989).
[CrossRef]

D. B. Goldgof, T. S. Huang, and H. Lee, “A curvature-based approach to terrain recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 1213-1217 (1989).
[CrossRef]

1984 (1)

S. Inokuchi, K. Sato, and F. Matsuda, “Range imaging system for 3-D object recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE, 1984), pp. 806-808.

Bock, M.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

Bowyer, K.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

Bowyer, K. W.

J. Min, M. Powell, and K. W. Bowyer, “Automated performance evaluation of range image segmentation algorithms,” IEEE Trans. Syst. Man Cybern. Part B 34, 263-271 (2004).
[CrossRef]

A. Hoover, D. Goldgof, and K. W. Bowyer, “The space envelope: a representation for 3D scenes,” Comput. Vision Image Understand. 69, 310-329 (1998).
[CrossRef]

Bunke, H.

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

X. Y. Jiang and H. Bunke “Fast segmentation of range images into planar regions by scan line grouping,” Machine Vision Appl. 7, 115-122 (1994).
[CrossRef]

Carmichael, O.

D. Huber, O. Carmichael, and M. Hebert, “3-D map reconstruction from range data,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00) (IEEE, 2000), pp. 891-897.

Chen, Y.

Y. Chen and G. Medioni, “Object modeling by registration of multiple range images,” in IEEE Conference on Robotics and Automations (IEEE, 1991), pp. 2724-2729.

du Buf., J. M. H.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

Eggert, D. W.

A. W. Fitzgibbon, D. W. Eggert, and R. B. Fisher, “High-level CAD model acquisition from range images,” Comput. Aided Des. 29, 321-330 (1997).
[CrossRef]

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

Fisher, R. B.

A. W. Fitzgibbon, D. W. Eggert, and R. B. Fisher, “High-level CAD model acquisition from range images,” Comput. Aided Des. 29, 321-330 (1997).
[CrossRef]

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

E. Trucco and R. B. Fisher, “Experiments in curvature-based segmentation of range data,” IEEE Trans. Pattern Anal. Mach. Intell. 17, 177-182 (1995).
[CrossRef]

Fitzgibbon, A.

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

Fitzgibbon, A. W.

A. W. Fitzgibbon, D. W. Eggert, and R. B. Fisher, “High-level CAD model acquisition from range images,” Comput. Aided Des. 29, 321-330 (1997).
[CrossRef]

Flynn, P. J.

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

T. S. Newman, P. J. Flynn, and A. K. Jain, “Model-based classification of quadric surfaces,” CVGIP Image Understand. 58, 235-249 (1993).
[CrossRef]

Goldgof, D.

A. Hoover, D. Goldgof, and K. W. Bowyer, “The space envelope: a representation for 3D scenes,” Comput. Vision Image Understand. 69, 310-329 (1998).
[CrossRef]

Goldgof, D. B.

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

D. B. Goldgof, T. S. Huang, and H. Lee, “A curvature-based approach to terrain recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 1213-1217 (1989).
[CrossRef]

Guerra, C.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

Hebert, M.

D. Huber, O. Carmichael, and M. Hebert, “3-D map reconstruction from range data,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00) (IEEE, 2000), pp. 891-897.

Hiura, S.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

Hoover, A.

A. Hoover, D. Goldgof, and K. W. Bowyer, “The space envelope: a representation for 3D scenes,” Comput. Vision Image Understand. 69, 310-329 (1998).
[CrossRef]

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

Hover, A.

A. Hover, “ABW images: the camera and models, ”http://marathon.csee.usf.edu/range/seg-comp/SegComp.html.

Huang, T. S.

D. B. Goldgof, T. S. Huang, and H. Lee, “A curvature-based approach to terrain recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 1213-1217 (1989).
[CrossRef]

Huber, D.

D. Huber, O. Carmichael, and M. Hebert, “3-D map reconstruction from range data,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00) (IEEE, 2000), pp. 891-897.

Inokuchi, S.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

S. Inokuchi, K. Sato, and F. Matsuda, “Range imaging system for 3-D object recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE, 1984), pp. 806-808.

Jain, A. K.

T. S. Newman, P. J. Flynn, and A. K. Jain, “Model-based classification of quadric surfaces,” CVGIP Image Understand. 58, 235-249 (1993).
[CrossRef]

Jean-Baptiste, G.

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

Jiang, X.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

X. Jiang, “An adaptive contour closure algorithm and experimental evaluation,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 1252-1265 (2000).
[CrossRef]

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

Jiang, X. Y.

X. Y. Jiang and H. Bunke “Fast segmentation of range images into planar regions by scan line grouping,” Machine Vision Appl. 7, 115-122 (1994).
[CrossRef]

Lee, H.

D. B. Goldgof, T. S. Huang, and H. Lee, “A curvature-based approach to terrain recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 1213-1217 (1989).
[CrossRef]

Li, Stan Z.

Stan Z. Li, Markov Random Field Modeling in Image Analysis (Springer, 2001).

Loke, R. E.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

Marroquin, J. L.

M. Rivera, O. Ocegueda, and J. L. Marroquin, “Entropy-controlled quadratic measure field models for efficient image segmentation,” IEEE Trans. Image Process. 16, 3047-3057(2007).
[CrossRef]

Matsuda, F.

S. Inokuchi, K. Sato, and F. Matsuda, “Range imaging system for 3-D object recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE, 1984), pp. 806-808.

Medioni, G.

Y. Chen and G. Medioni, “Object modeling by registration of multiple range images,” in IEEE Conference on Robotics and Automations (IEEE, 1991), pp. 2724-2729.

Min, J.

J. Min, M. Powell, and K. W. Bowyer, “Automated performance evaluation of range image segmentation algorithms,” IEEE Trans. Syst. Man Cybern. Part B 34, 263-271 (2004).
[CrossRef]

Morioka, Y.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

Newman, T. S.

T. S. Newman, P. J. Flynn, and A. K. Jain, “Model-based classification of quadric surfaces,” CVGIP Image Understand. 58, 235-249 (1993).
[CrossRef]

Ocegueda, O.

M. Rivera, O. Ocegueda, and J. L. Marroquin, “Entropy-controlled quadratic measure field models for efficient image segmentation,” IEEE Trans. Image Process. 16, 3047-3057(2007).
[CrossRef]

Powell, M.

J. Min, M. Powell, and K. W. Bowyer, “Automated performance evaluation of range image segmentation algorithms,” IEEE Trans. Syst. Man Cybern. Part B 34, 263-271 (2004).
[CrossRef]

Reeves, A. P.

R. W. Taylor, M. Sarini, and A. P. Reeves, “Fast segmentation of range imagery into planar regions,” Comput. Vision Graph. Image Process. 45, 42-60 (1989).
[CrossRef]

Rivera, M.

M. Rivera, O. Ocegueda, and J. L. Marroquin, “Entropy-controlled quadratic measure field models for efficient image segmentation,” IEEE Trans. Image Process. 16, 3047-3057(2007).
[CrossRef]

Sarini, M.

R. W. Taylor, M. Sarini, and A. P. Reeves, “Fast segmentation of range imagery into planar regions,” Comput. Vision Graph. Image Process. 45, 42-60 (1989).
[CrossRef]

Sato, K.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

S. Inokuchi, K. Sato, and F. Matsuda, “Range imaging system for 3-D object recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE, 1984), pp. 806-808.

Taylor, R. W.

R. W. Taylor, M. Sarini, and A. P. Reeves, “Fast segmentation of range imagery into planar regions,” Comput. Vision Graph. Image Process. 45, 42-60 (1989).
[CrossRef]

Trucco, E.

E. Trucco and R. B. Fisher, “Experiments in curvature-based segmentation of range data,” IEEE Trans. Pattern Anal. Mach. Intell. 17, 177-182 (1995).
[CrossRef]

Comput. Aided Des. (1)

A. W. Fitzgibbon, D. W. Eggert, and R. B. Fisher, “High-level CAD model acquisition from range images,” Comput. Aided Des. 29, 321-330 (1997).
[CrossRef]

Comput. Vision Graph. Image Process. (1)

R. W. Taylor, M. Sarini, and A. P. Reeves, “Fast segmentation of range imagery into planar regions,” Comput. Vision Graph. Image Process. 45, 42-60 (1989).
[CrossRef]

Comput. Vision Image Understand. (1)

A. Hoover, D. Goldgof, and K. W. Bowyer, “The space envelope: a representation for 3D scenes,” Comput. Vision Image Understand. 69, 310-329 (1998).
[CrossRef]

CVGIP Image Understand. (1)

T. S. Newman, P. J. Flynn, and A. K. Jain, “Model-based classification of quadric surfaces,” CVGIP Image Understand. 58, 235-249 (1993).
[CrossRef]

IEEE Trans. Image Process. (1)

M. Rivera, O. Ocegueda, and J. L. Marroquin, “Entropy-controlled quadratic measure field models for efficient image segmentation,” IEEE Trans. Image Process. 16, 3047-3057(2007).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell. (4)

X. Jiang, “An adaptive contour closure algorithm and experimental evaluation,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 1252-1265 (2000).
[CrossRef]

A. Hoover, G. Jean-Baptiste, X. Jiang, P. J. Flynn, H. Bunke, D. B. Goldgof, K. Bowyer, D. W. Eggert, A. Fitzgibbon, and R. B. Fisher, “An experimental comparison of range image segmentation algorithms,” IEEE Trans. Pattern Anal. Mach. Intell. 18, 673-689 (1996).
[CrossRef]

E. Trucco and R. B. Fisher, “Experiments in curvature-based segmentation of range data,” IEEE Trans. Pattern Anal. Mach. Intell. 17, 177-182 (1995).
[CrossRef]

D. B. Goldgof, T. S. Huang, and H. Lee, “A curvature-based approach to terrain recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 11, 1213-1217 (1989).
[CrossRef]

IEEE Trans. Syst. Man Cybern. Part B (1)

J. Min, M. Powell, and K. W. Bowyer, “Automated performance evaluation of range image segmentation algorithms,” IEEE Trans. Syst. Man Cybern. Part B 34, 263-271 (2004).
[CrossRef]

Machine Vision Appl. (1)

X. Y. Jiang and H. Bunke “Fast segmentation of range images into planar regions by scan line grouping,” Machine Vision Appl. 7, 115-122 (1994).
[CrossRef]

Other (7)

S. Inokuchi, K. Sato, and F. Matsuda, “Range imaging system for 3-D object recognition,” in Proceedings of the International Conference on Pattern Recognition (IEEE, 1984), pp. 806-808.

A. Hover, “ABW images: the camera and models, ”http://marathon.csee.usf.edu/range/seg-comp/SegComp.html.

D. Huber, O. Carmichael, and M. Hebert, “3-D map reconstruction from range data,” in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '00) (IEEE, 2000), pp. 891-897.

http://marathon.csee.usf.edu/range/seg-comp/SegComp.html.

X. Jiang, K. Bowyer, Y. Morioka, S. Hiura, K. Sato, S. Inokuchi, M. Bock, C. Guerra, R. E. Loke, and J. M. H. du Buf., “Some further results of experimental comparison of range image segmentation algorithms,” in Proceedings of International Conference on Pattern Recognition, Vol. 4 (IEEE, 2000), pp. 877-881.
[CrossRef]

Y. Chen and G. Medioni, “Object modeling by registration of multiple range images,” in IEEE Conference on Robotics and Automations (IEEE, 1991), pp. 2724-2729.

Stan Z. Li, Markov Random Field Modeling in Image Analysis (Springer, 2001).

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 (12)

Fig. 1
Fig. 1

(a) Intensity image and (b) range image of the same scene.

Fig. 2
Fig. 2

Three kinds of border: (a) step, (b) roof, (c) combination.

Fig. 3
Fig. 3

Zoom of a range image (roof edge).

Fig. 4
Fig. 4

(a) Synthetic plane and (b) its quantization.

Fig. 5
Fig. 5

Corner points in one dimension

Fig. 6
Fig. 6

(a) Corner points of the plane in Fig. 4 and (b) the fitted plane (fitted with a small error).

Fig. 7
Fig. 7

Interface between regions (see text).

Fig. 8
Fig. 8

Example of the regions evaluated as oversegmentation; the regions produced by noise are inside the white ellipses: (a) range image and (b) segmentation produced by the CIMAT method.

Fig. 9
Fig. 9

Number of correctly detected regions versus tolerance of the evaluation tool for different segmentation methods (see text).

Fig. 10
Fig. 10

Number of missed regions versus tolerance of the evaluation tool for different segmentation methods (see text).

Fig. 11
Fig. 11

(a) Range image, (b) ground truth segmentation, (c) CIMAT segmentation, (d) UE segmentation.

Fig. 12
Fig. 12

(a) CIMAT segmentation, (b) ground truth, and (c) UE segmentation.

Tables (3)

Tables Icon

Table 1 Performance Comparison of the CIMAT and UE Methods

Tables Icon

Table 2 Area Under Performance (AUC) Value Comparison

Equations (22)

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

x ( r ) = ( 255 r 2 ) [ I ( r ) scal + offset ] f , y ( r ) = ( 255 r 1 ) c [ I ( r ) scal + offset ] f , z ( r ) = [ 255 I ( r ) ] scal ,
U ( ϕ 1 , ϕ 2 , ϕ 3 ) = r [ ϕ 1 ( r ) x ( r ) + ϕ 2 ( r ) y ( r ) + ϕ 3 ( r ) z ( r ) ] 2 + λ r s N r g ( w a [ ϕ 1 ( r ) ϕ 1 ( s ) ] 2 + w b [ ϕ 2 ( r ) ϕ 2 ( s ) ] 2 + w c [ ϕ 3 ( r ) ϕ 3 ( s ) ] 2 ) ,
z ( r ) = m k ( r ) + n ( r )
k = 1 K b k ( r ) = 1 , b k ( r ) 0     k , r ,
P b ( b ) = 1 Z b exp [ U b ( b ) ] ,
U b ( b ) = λ r , s k = 1 K [ b k ( r ) b k ( s ) ] 2 B ( r , s ) μ r L k = 1 K b k 2 ( r ) ,
U ( b | θ ) = k = 1 K r I ( log [ v k ( r , θ ) ] b k ( r ) 2 + μ b k ( r ) 2 ) + λ k = 1 K r , s [ b k ( r ) b k ( s ) ] 2 B ( r , s )
log [ v k ( r , θ ) ] = δ r [ z ( r ) m k ( r ) ] 2 ,
U ( b | θ ) = k = 1 K r L ( [ z ( r ) m k ( r ) ] 2 δ r μ ) b k ( r ) 2 + λ k = 1 K r , s [ b k ( r ) b k ( s ) ] 2 B ( r , s )
D ( I , r 1 ) = I ( r 1 ) I ( r 1 1 ) , D + ( I , r 1 ) = I ( r 1 ) I ( r 1 + 1 ) ,
D + ( I , r 1 ) · D ( I , r 1 ) = 0 , D + ( I , r 1 ) + D ( I , r 1 ) > 0.
D 1 + ( I , r ) = I ( r 1 , r 2 ) I ( r 1 + 1 , r 2 ) ; D 1 ( I , r ) = I ( r 1 , r 2 ) I ( r 1 1 , r 2 ) , D 2 + ( I , r ) = I ( r 1 , r 2 ) I ( r 1 , r 2 + 1 ) ; D 2 ( I , r ) = I ( r 1 , r 2 ) I ( r 1 , r 2 1 ) .
D 1 + ( I , r ) · D 1 ( I , r ) = D 2 + ( I , r ) · D 2 ( I , r ) = 0 , D 1 + ( I , r ) + D 1 ( I , r ) > 0 , D 2 + ( I , r ) + D 2 ( I , r ) > 0.
( r W δ r = 1 x ( r ) 2 r W δ r = 1 x ( r ) y ( r ) r W δ r = 1 x ( r ) r W δ r = 1 x ( r ) y ( r ) r W δ r = 1 y ( r ) 2 r W δ r = 1 y ( r ) r W δ r = 1 x ( r ) r W δ r = 1 y ( r ) r W δ r = 1 1 ) ( θ k 1 θ k 2 θ k 3 ) = ( r W δ r = 1 x ( r ) z ( r ) r W δ r = 1 y ( r ) z ( r ) r W δ r = 1 z ( r ) ) .
b k ( r ) = 1 K         r , k = 1 , K .
y int ( r ) = ( θ k 1 θ l 1 ) x ( r ) + ( θ k 3 θ l 3 ) ( θ k 2 θ l 2 ) .
B [ ( r 1 , r 2 ) , ( r 1 + 1 , r 2 ) ] = 0 [ y int ( r 1 , r 2 ) y ( r 1 , r 2 ) ] [ y int ( r 1 + 1 , r 2 ) y ( r 1 + 1 , r 2 ) ] 0 , B [ ( r 1 , r 2 ) , ( r 1 , r 2 + 1 ) ] = 0 [ y int ( r 1 , r 2 ) y ( r 1 , r 2 ) ] [ y int ( r 1 , r 2 + 1 ) y ( r 1 , r 2 + 1 ) ] 0.
L ( b , γ ) = k = 1 K r I [ ( [ z ( r ) m k ( r ) ] 2 δ r μ ) b k ( r ) 2 + λ s N r B ( r , s ) [ b k ( r ) b k ( s ) ] 2 ] r I γ r ( 1 k b k ( r ) ) ,
b k ( r ) = ( 1 i = 1 K M i ( r ) A i ( r ) ) A k ( r ) i = 1 k 1 A i ( r ) + M k ( r ) A k ( r ) ,
M k ( r ) = λ s N r B ( r , s ) b k ( s ) , A k ( r ) = [ z ( r ) m k ( r ) ] 2 δ r + λ s N r B ( r , s ) μ .
r W δ r = 1 x ( r ) 2
r : b k ( r ) > 0.5 δ r = 1 x ( r ) 2

Metrics