Advertisement

International Journal of Computer Vision

, Volume 83, Issue 1, pp 12–29 | Cite as

Contour Grouping Based on Contour-Skeleton Duality

  • Nagesh Adluru
  • Longin Jan Latecki
Article

Abstract

In this paper we present a method for grouping relevant object contours in edge maps by taking advantage of contour-skeleton duality. Regularizing contours and skeletons simultaneously allows us to combine both low level perceptual constraints as well as higher level model constraints in a very effective way. The models are represented using paths in symmetry sets. Skeletons are treated as trajectories of an imaginary virtual robot in a discrete space of “symmetric points” obtained from pairs of edge segments. Boundaries are then defined as the maps obtained by grouping the associated pairs of edge segments along the trajectories. Casting the grouping problem in this manner makes it similar to the problem of Simultaneous Localization and Mapping (SLAM). Hence we adapt the state-of-the-art probabilistic framework namely Rao-Blackwellized particle filtering that has been successfully applied to SLAM. We use the framework to maximize the joint posterior over skeletons and contours.

Keywords

Contour grouping Skeletons Shape models Rao-Blackwellized particle filters SLAM 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Adluru, N., Latecki, L. J., Lakamper, R., Young, T., Bai, X., & Gross, A. (2007). Contour grouping based on local symmetry. In ICCV ’07: Proceedings of the eleventh IEEE international conference on computer vision. IEEE Computer Society. Google Scholar
  2. Adluru, N., Latecki, L. J., Sobel, M., & Lakaemper, R. (2008). Merging maps of multiple robots. In IAPR international conference on pattern recognition (ICPR). Google Scholar
  3. Bai, X., & Latecki, L. J. (2008). Path similarity skeleton graph matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(7), 1283–1292. Google Scholar
  4. Belongie, S., Malik, J., & Puzicha, J. (2002). Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 705–522. CrossRefGoogle Scholar
  5. Black, M. J., & Fleet, D. J. (2000). Probabilistic detection and tracking of motion boundaries. International Journal of Computer Vision, 38(3), 231–245. zbMATHCrossRefGoogle Scholar
  6. Blake, A., & Isard, M. (1997). Active contours. Berlin: Springer. Google Scholar
  7. Blum, H. (1967). A transformation for extracting new descriptors of shape. In W. Wathen-Dunn (Ed.), Models for the perception of speech and visual form. Cambridge: MIT. Google Scholar
  8. Blum, H. (1973). Biological shape and visual science. Journal of Theoretical Biology, 38, 205–287. CrossRefMathSciNetGoogle Scholar
  9. Borenstein, E., & Ullman, S. (2002). Class-specific, top-down segmentation. In ECCV ’02: Proceedings of the 7th European conference on computer vision—Part II (pp. 109–124). London: Springer. Google Scholar
  10. Borgefors, G. (1988). Hierarchical chamfer matching: A parametric edge matching algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence, 10(6), 849–865. doi: 10.1109/34.9107. CrossRefGoogle Scholar
  11. Bruce, J., Giblin, P., & Gibson, C. (1985). Symmetry sets. Proceedings Royal Society of Edinburgh, 101(A), 163–186. zbMATHMathSciNetGoogle Scholar
  12. Carpenter, J., Clifford, P., & Fearnhead, P. (1999). Building robust simulation-based filters for evolving data sets (Tech. Rep.). Dept. of Statistics, University of Oxford. Google Scholar
  13. Carpin, S., Birk, A., & Jucikas, V. (2005). On map merging. Robotics and Autonomous Systems, 53(1), 1–14. CrossRefGoogle Scholar
  14. Chang, H. J., Lee, C. S. G., Lu, Y. H., & Hu, Y. C. (2007). P-SLAM: Simultaneous localization and mapping with environmental-structure prediction. IEEE Transactions on Robotics, 23(2), 281–293. CrossRefGoogle Scholar
  15. Choi, H. I., Choi, S. W., & Moon, H. P. (1997). Mathematical theory of medial axis transform. Pacific Journal of Mathematics, 181(1), 57–88. MathSciNetCrossRefGoogle Scholar
  16. Cox, I., Rehg, J., & Hingorani, S. (1993). A Bayesian multiple-hypothesis approach to edge grouping and contour segmentation. International Journal of Computer Vision, 11(1), 5–24. CrossRefGoogle Scholar
  17. Doucet, A. (1998). On sequential simulation-based methods for Bayesian filtering (Tech. Rep.). Cambridge University Department of Engineering. Google Scholar
  18. Doucet, A., de Freitas, N., & Gordon, N. (2001). Sequential Monte Carlo methods in practice. Berlin: Springer. zbMATHGoogle Scholar
  19. Eliazar, A., & Parr, R. (2003). DP-SLAM: Fast, robust simulataneous localization and mapping without predetermined landmarks. In Int. joint conf. on artificial intelligence (IJCAI). Google Scholar
  20. Eliazar, A., & Parr, R. (2004). DP-SLAM 2.0. In IEEE int. conf. on robotics and automation (ICRA). Google Scholar
  21. Feldman, J. (1999). The role of objects in perceptual grouping. Acta Psychologica, 102(2–3), 137–163. CrossRefGoogle Scholar
  22. Feldman, J. (2001). Bayesian contour integration. Perception & Psychophysics, 63(7), 1171–1182. Google Scholar
  23. Feldman, J. (2003). Perceptual grouping by selection of a logically minimal model. International Journal of Computer Vision, 55(1), 5–25. CrossRefGoogle Scholar
  24. Feldman, J., & Singh, M. (2006). Bayesian estimation of the shape skeleton. Proceedings of the National Academy of Sciences, 103(47), 18,014–18,019. CrossRefMathSciNetGoogle Scholar
  25. Ferrari, V., Tuytelaars, T., & Gool, L. J. V. (2006). Object detection by contour segment networks. In ECCV (pp. 14–28). Google Scholar
  26. Ferrari, V., Fevrier, L., Jurie, F., & Schmid, C. (2008). Groups of adjacent contour segments for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(1), 36–51. CrossRefGoogle Scholar
  27. Fox, D. (2003). Adapting the sample size in particle filters through kld-sampling. International Journal of Robotics Research (IJRR), 22(12), 985–1003. CrossRefGoogle Scholar
  28. Fox, D., Burgard, W., Kruppa, H., & Thrun, S. (1999). Efficient multi-robot localization based on Monte Carlo approximation. citeseer.ist.psu.edu/article/fox99efficient.html.
  29. Galun, M., Basri, R., & Brandt, A. (2007). Multiscale edge detection and fiber enhancement using differences of oriented means. In ICCV ’07: Proceedings of the eleventh IEEE international conference on computer vision. IEEE Computer Society. Google Scholar
  30. Giblin, P. J. (2000). Symmetry sets and medial axes in two and three dimensions. In Proceedings of the 9th IMA conference on the mathematics of surfaces (pp. 306–321). London: Springer. Google Scholar
  31. Giblin, P. J., & Kimia, B. B. (2003a). On the intrinsic reconstruction of shape from its symmetries. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(7), 895–911. CrossRefGoogle Scholar
  32. Giblin, P. J., & Kimia, B. B. (2003b). On the local form and transitions of symmetry sets, medial axes, and shocks. International Journal of Computer Vision, 54(1–3), 143–156. zbMATHCrossRefGoogle Scholar
  33. Gordon, N., Salmond, D., & Smith, A. (1993). Novel approach to nonlinear/non-Gaussian Bayesian state estimation. In Radar and signal processing, IEE proceedings (Vol. 140, pp. 107–113). Google Scholar
  34. Grisetti, G., Stachniss, C., & Burgard, W. (2007). Improved techniques for grid mapping with rao-blackwellized particle filters. IEEE Transactions on Robotics, 23, 34–46. CrossRefGoogle Scholar
  35. Handschin, J. E. (1970). Monte Carlo techniques for prediction and filtering of non-linear stochastic processes. Automatica, 6, 555–563. zbMATHCrossRefMathSciNetGoogle Scholar
  36. Handschin, J. E., & Mayne, D. Q. (1969). Monte Carlo techniques to estimate the conditional expectation in multi-stage non-linear filtering. International Journal of Controls, 9(5), 353–358. MathSciNetGoogle Scholar
  37. Hoiem, D., Stein, A., Efros, A. A., & Hebert, M. (2007). Recovering occlusion boundaries from a single image. In International conference on computer vision (ICCV). Google Scholar
  38. Howard, A. (2005). Multi-robot simultaneous localization and mapping using particle filters. In Proceedings of robotics: science and systems. Cambridge, USA. Google Scholar
  39. Isard, M., & Blake, A. (1998). Condensation—conditional density propagation for visual tracking. International Journal of Computer Vision, 29(1), 5–28. CrossRefGoogle Scholar
  40. Kimia, B. B., & Tamrakar, A. (2002). The role of propagation and medial geometry in human vision. In BMCV ’02: Proceedings of the second international workshop on biologically motivated computer vision (pp. 219–229). London: Springer. CrossRefGoogle Scholar
  41. Kong, A., Liu, J., & Wong, W. (1994). Sequential imputations and Bayesian missing data problems. The American Statistical Association, 89, 278–288. zbMATHCrossRefGoogle Scholar
  42. Kovesi, P. D. (2008). MATLAB and Octave functions for computer vision and image processing. School of Computer Science & Software Engineering, The University of Western Australia, available from: http://www.csse.uwa.edu.au/~pk/research/matlabfns/.
  43. Kuijper, A., & Olsen, O. F. (2004). Transitions of the pre-symmetry set. In ICPR ’04: Proceedings of the pattern recognition, 17th international conference on (ICPR’04) (Vol. 3, pp. 190–193). Washington: IEEE Computer Society. CrossRefGoogle Scholar
  44. Kuijper, A., & Olsen, O. F. (2005). Geometric skeletonization using the symmetry set. In Image processing, 2005. ICIP 2005 (pp. 497–500). IEEE International Conference. Google Scholar
  45. Kuijper, A., & Olsen, O. (2006). Describing and matching 2d shapes by their points of mutual symmetry. In ECCV06 (pp. III: 213–225). Google Scholar
  46. Kuijper, A., Olsen, O. F., Bille, P., & Giblin, P. (2006a). Matching 2d shapes using their symmetry sets. In ICPR ’06: Proceedings of the 18th international conference on pattern recognition (pp. 179–182). Washington: IEEE Computer Society. Google Scholar
  47. Kuijper, A., Olsen, O. F., Giblin, P., & Nielsen, M. (2006b). Alternative 2d shape representations using the symmetry set. Journal of Mathematical Imaging and Vision, 26(1–2), 127–147. CrossRefMathSciNetGoogle Scholar
  48. Kumar, M. P., Torr, P. H. S., & Zisserman, A. (2005). OBJ CUT. In Proceedings of the IEEE conference on computer vision and pattern recognition (Vol. 1, pp. 18–25). San Diego. Google Scholar
  49. Latecki, L. J., Sobel, M., & Lakaemper, R. (2006). New EM derived from Kullback-Leibler divergence. In ACM SIGKDD int. conf. on knowledge discovery and data mining. Google Scholar
  50. Latecki, L. J., Lu, C., Sobel, M., & Bai, X. (2008). Multiscale random fields with application to contour grouping. In Neural information processing systems conf. (NIPS). Vancouver. Google Scholar
  51. Leibe, B., & Schiele, B. (2003). Interleaved object categorization and segmentation. In BMVC03. Google Scholar
  52. Leibe, B., Seemann, E., & Schiele, B. (2005). Pedestrian detection in crowded scenes. In Proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition (Vol. 1, pp. 878–885). Washington: IEEE Computer Society. Google Scholar
  53. Leyton, M. (1992). Symmetry, causality, mind. Cambridge: MIT. Google Scholar
  54. Ling, H., & Jacobs, D. W. (2007). Shape classification using inner-distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29, 286–299. CrossRefGoogle Scholar
  55. Liu, J. S. (1996). Metropolized independent sampling with comparisons to rejection sampling and importance sampling. Statistics and Computing, 6, 113–119. CrossRefGoogle Scholar
  56. Liu, J. S., Chen, R., & Wong, W. H. (1998a). Rejection control and sequential importance sampling. Journal of the American Statistical Association, 93(443), 1022–1031. zbMATHCrossRefMathSciNetGoogle Scholar
  57. Liu, T., Geiger, D., & Yuille, A. L. (1998b). Segmenting by seeking the symmetry axis. In Proc. CVPR (pp. 994–998). Google Scholar
  58. Lockwood, E. H. (2007). A book of curves. Cambridge: Cambridge University Press. zbMATHGoogle Scholar
  59. Lowe, D. G. (1985). Perceptual organization and visual recognition. Boston: Kluwer Academic. Google Scholar
  60. Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2001). A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. Proceedings of the 8th International Conference on Computer Vision, 2, 416–423. Google Scholar
  61. Meilǎ, M. (2005). Comparing clusterings: an axiomatic view. In ICML ’05: Proceedings of the 22nd international conference on machine learning (pp. 577–584). New York: ACM. CrossRefGoogle Scholar
  62. Mohan, R., & Nevatia, R. (1992). Perceptual organization for scene segmentation and description. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(6), 616–635. CrossRefGoogle Scholar
  63. Moravec, H. (1988). Sensor fusion in certainty grids for mobile robots. AI Magazine, 9(2), 61–74. Google Scholar
  64. Opelt, A., Pinz, A., & Zisserman, A. (2006). A boundary-fragment-model for object detection. In Proceedings of the European conference on computer vision. Google Scholar
  65. Perez, P., Blake, A., & Gangnet, M. (2001). Rjetstream: Probabilistic contour extraction with particles. In Proc. ICCV (pp. 524–531). Google Scholar
  66. Podolak, J., Shilane, P., Golovinskiy, A., Rusinkiewicz, S., & Funkhouser, T. (2006). A planar-reflective symmetry transform for 3D shapes. ACM Transactions on Graphics (Proceedings SIGGRAPH) 25(3). Google Scholar
  67. Raviv, D., Bronstein, A., Bronstein, M., & Kimmel, R. (2007). Symmetries of non-rigid shapes. In ICCV. Google Scholar
  68. Reid, D. B. (1979). An algorithm for tracking multiple targets. IEEE Transactions on Automatic Control 24(6), 843–854. CrossRefGoogle Scholar
  69. Ren, X., Berg, A., & Malik, J. (2005). Recovering human body configurations using pairwise constraints between parts. In Proc. ICCV. Google Scholar
  70. Ren, X., Fowlkes, C. C., & Malik, J. (2008). Learning probabilistic models for contour completion in natural images. International Journal of Computer Vision, 77(1–3), 47–63. doi: 10.1007/s11263-007-0092-6. CrossRefGoogle Scholar
  71. Sebastian, T. B., Klein, P. N., & Kimia, B. B. (2004). Recognition of shapes by editing their shock graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(5), 550–571. CrossRefGoogle Scholar
  72. Shotton, J., Blake, A., & Cipolla, R. (2005). Contour-based learning for object detection. In ICCV ’05: Proceedings of the tenth IEEE international conference on computer vision (ICCV’05) (Vol. 1, pp. 503–510). Washington: IEEE Computer Society. CrossRefGoogle Scholar
  73. Siddiqi, K., & Pizer, S. M. (2007). Medial representations: mathematics, algorithms and applications. Berlin: Springer. Google Scholar
  74. Siddiqi, K., Shokoufandeh, A., Dickinson, S. J., & Zucker, S. W. (1999). Shock graphs and shape matching. International Journal of Computer Vision, 35, 13–32. CrossRefGoogle Scholar
  75. Stachniss, C., Grisetti, G., & Burgard, W. (2005). Information gain-based exploration using rao-blackwellized particle filters. In Proc. of robotics: science and systems (RSS) (pp. 65–72). Cambridge, MA, USA. Google Scholar
  76. Stahl, J. S., & Wang, S. (2006). Globally optimal grouping for symmetric boundaries. In Proc. CVPR. Google Scholar
  77. Stein, A., Hoiem, D., & Hebert, M. (2007). Learning to find object boundaries using motion cues. In IEEE international conference on computer vision (ICCV). Google Scholar
  78. Tamrakar, A., & Kimia, B. B. (2007). No grouping left behind: From edges to curve fragments. In ICCV ’07: Proceedings of the eleventh IEEE international conference on computer vision. IEEE Computer Society. Google Scholar
  79. Tanizaki, H. (1997). Nonlinear and nonnormal filters using Monte Carlo methods. Computational Statistics and Data Analysis, 25(4), 417–439. zbMATHCrossRefGoogle Scholar
  80. Thrun, S., Burgard, W., & Fox, D. (2005). Probabilistic robotics. Cambridge: MIT. zbMATHGoogle Scholar
  81. Trinh, N., & Kimia, B. B. (2007). A symmetry-based generative model for shape. In ICCV ’07: Proceedings of the eleventh IEEE international conference on computer vision. IEEE Computer Society. Google Scholar
  82. Tu, Z., & Yuille, A. (2004). Shape matching and recognition: using generative models and informative features. In ECCV04 (Vol. 3, pp. 195–209). Google Scholar
  83. Tu, Z., Chen, X., Yuille, A., & Zhu, S. C. (2005). Image parsing: Unifying segmentation, detection, and recognition. International Journal of Computer Vision, 63, 113–140. CrossRefGoogle Scholar
  84. Veksler, O. (2008). Star shape prior for graph-cut image segmentation. In ECCV08. Google Scholar
  85. Wang, H., & Oliensis, J. (2006). A global contour measure for image segmentation. In POCV06. Google Scholar
  86. Wang, H., & Oliensis, J. (2008). Shape matching by segmentation expectation. In ECCV08. Google Scholar
  87. Wang, L., Shi, J., Song, G., & Shen, I. (2007). Object detection combining recognition and segmentation. In ACCV07 (pp. 189–199). Google Scholar
  88. Wertheimer, M. (1923). Untersuchungen zur lehre von der gestalt II. Psycologische Forschung, 4, 301–350. CrossRefGoogle Scholar
  89. Wertheimer, M. (1958). Principles of perceptual organization. In D. Beardslee & M. Wertheimer (Eds.), Readings in perception. Princeton: Princeton University Press. Google Scholar
  90. Witkin, A. P., & Tenenbaum, J. M. (1983). On the role of structure in vision. In J. Beck, B. Hope, & A. Rosenfeld (Eds.), Human and Machine Vision. New York: Academic Press. Google Scholar
  91. Yang, X., Bai, X., Latecki, L. J., & Tu, Z. (2008). Improving shape retrieval by learning graph transduction. In ECCV08. Google Scholar
  92. Zaritskii, V., Svetnik, V., & Shimelevich, L. (1975). Monte Carlo technique in problems of optimal data processing. Automation and Remote Control, 12, 95–103. MathSciNetGoogle Scholar
  93. Zhu, Q., Song, G., & Shi, J. (2007). Untangling cycles for contour grouping. In ICCV ’07: Proceedings of the eleventh IEEE international conference on computer vision. IEEE Computer Society. Google Scholar
  94. Zhu, Q., Wang, L., Wu, Y., & Shi, J. (2008). Contour context selection for object detection: A set-to-set contour matching approach. In ECCV08. Google Scholar
  95. Zhu, S. C., & Yuille, A. (1995). Forms: a flexible object recognition and modelling system. In Proc. ICCV (pp. 465–472). Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Temple UniversityPhiladelphiaUSA

Personalised recommendations