International Journal of Computer Vision

, Volume 112, Issue 1, pp 43–70 | Cite as

Robust Temporally Coherent Laplacian Protrusion Segmentation of 3D Articulated Bodies

Article

Abstract

In motion analysis and understanding it is important to be able to fit a suitable model or structure to the temporal series of observed data, in order to describe motion patterns in a compact way, and to discriminate between them. In an unsupervised context, i.e., no prior model of the moving object(s) is available, such a structure has to be learned from the data in a bottom-up fashion. In recent times, volumetric approaches in which the motion is captured from a number of cameras and a voxel-set representation of the body is built from the camera views, have gained ground due to attractive features such as inherent view-invariance and robustness to occlusions. Automatic, unsupervised segmentation of moving bodies along entire sequences, in a temporally-coherent and robust way, has the potential to provide a means of constructing a bottom-up model of the moving body, and track motion cues that may be later exploited for motion classification. Spectral methods such as locally linear embedding can be useful in this context, as they preserve “protrusions”, i.e., high-curvature regions of the 3D volume, of articulated shapes, while improving their separation in a lower dimensional space, making them in this way easier to cluster. In this paper we therefore propose a spectral approach to unsupervised and temporally-coherent body-protrusion segmentation along time sequences. Volumetric shapes are clustered in an embedding space, clusters are propagated in time to ensure coherence, and merged or split to accommodate changes in the body’s topology. Experiments on both synthetic and real sequences of dense voxel-set data are shown. This supports the ability of the proposed method to cluster body-parts consistently over time in a totally unsupervised fashion, its robustness to sampling density and shape quality, and its potential for bottom-up model construction.

Keywords

Unsupervised segmentation 3D shape analysis 3D shape tracking Human motion analysis Spectral embedding 

References

  1. Agarwal, S., Lim, J., Zelnik-Manor, L., Perona, P., Kriegman, D., Belongie, S. (2005). Beyond pairwise clustering. In Computer Vision and Pattern Recognition, pp. 838–845. Google Scholar
  2. Ali, S., Basharat, A., Shah, M. (2007). Chaotic invariants for human action recognition. In International Conference on Computer Vision.Google Scholar
  3. Alpert, A. B., Kahng, C. J., & Yao, S.-Z. (1999). Spectral partitioning with multiple eigenvectors. Discrete Applied Mathematics, 90(1–3), 3–26.CrossRefMATHMathSciNetGoogle Scholar
  4. Bronstein, A. M., Bronstein, M. M., & Kimmel, R. (2006). Generalized multidimensional scaling: A framework for isometry-invariant partial surface matching. Proceedings of the National Academy of Sciences, 103(5), 1168–1172.CrossRefMATHMathSciNetGoogle Scholar
  5. Bronstein, A. M., Bronstein, M. M., & Kimmel, R. (2009). Topology-invariant similarity of nonrigid shapes. International Journal of Computer Vision, 81(3), 281–301.CrossRefGoogle Scholar
  6. Belkin, M., & Niyogi, P. (2003). Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation, 15, 1373–1396.CrossRefMATHGoogle Scholar
  7. Bengio, Y., Delalleau, O., Le Roux, N., Paiement, J.-F., Vincent, P., & Ouimet, M. (2004). Learning eigenfunctions links spectral embedding and kernel PCA. Neural Computation, 16(10), 2197–2219.CrossRefMATHGoogle Scholar
  8. Bengio, Y., Paiement, J.-F., & Vincent, P. (2003). Out-of-sample extensions for LLE, Isomap, MDS, eigenmaps, and spectral clustering. Technical report: Université Montreal.Google Scholar
  9. Bissacco, A., Chiuso, A., & Soatto, S. (2007). Classification and recognition of dynamical models: The role of phase, independent components, kernels and optimal transport. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(11), 1958–1972.CrossRefGoogle Scholar
  10. Biyikoglu, J., Leydold, T., & Stadler, P. F. (2007). Laplacian eigenvectors of graphs. Berlin: Springer.CrossRefMATHGoogle Scholar
  11. Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R. (2005). Actions as space-time shapes. In International Conference on Computer Vision, pp. 1395–1402.Google Scholar
  12. Brand, M. (1999) Shadow puppetry. In International Conference on Computer Vision.Google Scholar
  13. Brostow, G.-J., Essa, I., Steedly, D., Kwatra, V. (2004). Novel skeletal representation for articulated creatures. In European Conference on Computer Vision.Google Scholar
  14. Carter, N., Young, D., Ferryman. J. (2006) Supplementing Markov chains with additional features for behavioural analysis. In Proceedings of AVSBS.Google Scholar
  15. Chang, W., Zwicker, M. (2008). Automatic registration for articulated shapes. In Eurographics Symposium on Geometry Processing.Google Scholar
  16. Chaudhry, R., Ravichandran, A., Hager, G., Vidal, R. (2009) Histograms of oriented optical flow and Binet–Cauchy kernels on nonlinear dynamical systems for the recognition of human actions. In Computer Vision and Pattern Recognition, pp. 1932–1939.Google Scholar
  17. Chu, C.-W., Jenkins, O. C., Mataric, M. J. (2003) Markerless kinematic model and motion capture from volume sequences. In Computer Vision and Pattern Recognition, pp. 475–482.Google Scholar
  18. Chung, F. (1997). Spectral Graph Theory. Providence: American Mathematical Society.MATHGoogle Scholar
  19. Cuzzolin, F., Sarti, A., & Tubaro, S. (2004). Action modeling with volumetric data. In Proceedings of ICIP, 2, 881–884.Google Scholar
  20. Cuzzolin, F., Sarti, A., Tubaro, S. (2004). Invariant action classification with volumetric data. In International Workshop on Multimedia Signal Processing, pp. 395–398.Google Scholar
  21. Cuzzolin, F., Mateus, D., Boyer, E., & Horaud, R. (2007). Robust spectral 3D-bodypart segmentation along time in Workshop on Human Motion—Understanding, Modeling. Capture and Animation, 196–211, 2007.Google Scholar
  22. Cuzzolin, F., Mateus, D., Knossow, D., Boyer, E., Horaud, R. (2008). Coherent Laplacian 3-D protrusion segmentation. In Computer Vision and Pattern Recognition.Google Scholar
  23. Cvetkovic, M., Doob, D. M., & Sachs, H. (1998). Spectra of graphs, theory and application. Berlin: Vch Verlagsgesellschaft Mbh.Google Scholar
  24. Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Pang, H., Davis, J. (2004). The correlated correspondence algorithm for unsupervised registration of non-rigid surfaces. In Neural Information Processing Systems.Google Scholar
  25. Anguelov, D., Koller, D., Pang, H.-C., Srinivasan, P., Thrun, S. (2004). Recovering articulated object models from 3D range data. In Proceedings of UAI.Google Scholar
  26. Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society, 39, 1–38.MATHMathSciNetGoogle Scholar
  27. Dhillon, Y., Guan, I. S., Kulis, B. (2004). Kernel kmeans: spectral clustering and normalized cuts. In Proceedings of KDD, pp. 551–556.Google Scholar
  28. Elgammal, A., Lee, C. (2004). Inferring 3D body pose from silhouettes using activity manifold learning. In Computer Vision and Pattern Recognition.Google Scholar
  29. Elliot, R., Aggoun, L., & Moore, J. (1995). Hidden Markov models: Estimation and control. New York: Springer.Google Scholar
  30. Fouss, A. R.-J. M., Pirotte, F., & Saerens, M. (2007). Random-walk computation of similarities between nodes of a graph, with application to collaborative recommendation. IEEE Transactions on Knowledge and Data Engineering, 19(3), 355–369.CrossRefGoogle Scholar
  31. Franco, J. S., & Boyer, E. (2009). Efficient polyhedral modeling from Silhouettes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(3), 414–427.CrossRefGoogle Scholar
  32. Franco, J. S., Boyer, E. (2011). Learning Temporally Consistent Rigidities. In Computer Vision and Pattern Recognition.Google Scholar
  33. Furukawa, Y., Ponce, J. (2005) Carved visual hulls for high accuracy image-based modeling. In Technical Sketch at SIGGRAPH.Google Scholar
  34. Golovinskiy, A., Funkhouser, T. (2009). Consistent segmentation of 3d models. In SIGGRAPH.Google Scholar
  35. Grauman, K., Shakhnarovich, G., Darrell, T. (2003). Inferring 3D structure with a statistical image-based shape model. In International Conference on Computer Vision, pp. 641–648.Google Scholar
  36. Gupta, A., Srinivasan, P., Shi, J., Davis, L. S. (2009). Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In Computer Vision and Pattern Recognition, pp. 2012–2019.Google Scholar
  37. Hayashi, C. (1972). Two dimensional quantification based on the measure of dissimilarity among three elements. Annals of the Institute of Statistical Mathematics, 24, 251–257.CrossRefMATHMathSciNetGoogle Scholar
  38. Heiser, W. J., & Bennani, M. (1997). Triadic distance models: Axiomatization and least squares representation. Journal of Mathematical Psychology, 41, 189–206.CrossRefMATHMathSciNetGoogle Scholar
  39. Hernandez, C., & Schmitt, F. (2004). Silhouette and stereo fusion for 3d object modeling. Computer Vision and Image Understanding, 96(3), 367–392.CrossRefGoogle Scholar
  40. Jain, V., Zhang, H. (2006). Robust 3d shape correspondence in the spectral domain. In Shape Modeling International.Google Scholar
  41. Jakobson, N., & Toth, J. (2001). Geometric properties of eigenfunctions. Russian Mathematical Surveys, 56(6), 1085–1106.CrossRefMATHMathSciNetGoogle Scholar
  42. Jenkins, O., Mataric, M. (2004). A spatio-temporal extension to isomap nonlinear dimension reduction. In International Conference on Machine Learning.Google Scholar
  43. Katz, S., Leifman, G., & Tal, A. (2005). Mesh segmentation using feature point and core extraction. The Visual Computer, 21, 649–658.CrossRefGoogle Scholar
  44. Kim, T., & Cipolla, R. (2009). Canonical correlation analysis of video volume tensors for action categorization and detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(8), 1415–1428.CrossRefGoogle Scholar
  45. Knossow, D., Ronfard, R., & Horaud, R. (2008). Human motion tracking with a kinematic parameterization of extremal contours. International Journal of Computer Vision, 79(3), 247–269.CrossRefGoogle Scholar
  46. Lafon, S., & Lee, A. B. (2006). Diffusion maps and coarse-graining: A unified framework for dimensionality reduction, graph partitioning, and data set parameterization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(9), 1393–1403.Google Scholar
  47. Levi, B. (2006) Laplace–Beltrami eigenfunctions: Towards and algorithm that understands geometry. In Shape Modeling International.Google Scholar
  48. Lien, J.-M., Amanto, N. (2007). Approximate convex decomposition of polyhedra. In Proceedings of the ACM Symposium on Solid and Physical Modeling, pp. 121–131.Google Scholar
  49. Lin, R., Liu, C.-B., Yang, M.-H., Ahuja, N., Levinson, S. (2006) Learning nonlinear manifolds from time series. In European Conference on Computer Vision.Google Scholar
  50. Liu, R., Zhang, H. (2004). Segmentation of 3D meshes through spectral clustering. In Proceedings of Computer Graphics and Applications, pp. 298–305.Google Scholar
  51. Luxburg, U. (2007). A tutorial on spectral clustering. Statistics and Computing, 17(4), 395–416.CrossRefMathSciNetGoogle Scholar
  52. MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, 1, 281–297.MathSciNetGoogle Scholar
  53. Mateus, D., Horaud, R., Knossow, D., Cuzzolin, F., Boyer, E. (2008). Articulated shape matching using laplacian eigenfunctions and unsupervised point registration. In Computer Vision and Pattern Recognition.Google Scholar
  54. Meila, M., Shi, J. (2001). A random walks view of spectral segmentation. In Artificial Intelligence and Statistics.Google Scholar
  55. Ng, A., Jordan, M., Weiss, Y. (2002). On spectral clustering: Analysis and an algorithm. In Neural Information Processing Systems.Google Scholar
  56. Huang, Q.-X., Wicke, M., Adams, B., Guibas, L. (2009). Shape decomposition using modal analysis. In EUROGRAPHICS, volume 28.Google Scholar
  57. Pons, J.-P., Keriven, R., & Faugeras, O. (2007). Multi-view stereo reconstruction and scene flow estimation with a global image-based matching score. International Journal of Computer Vision, 72(2), 179–193.CrossRefGoogle Scholar
  58. Ralaivola, L., & d’Alche Buc, F. (2004). Dynamical modeling with kernels for nonlinear time series prediction. Information Processing Systems, 16, 129–136.Google Scholar
  59. Roweis, S., & Saul, L. (2000). Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500), 2323–2326.CrossRefGoogle Scholar
  60. Saerens, M., Fouss, F., Yen, L., Dupont, P. (2004). The principal components analysis of a graph, and its relationships to spectral clustering. In European Conference on Machine Learning, pp. 371–383. Google Scholar
  61. Shamir, A. (2008). A survey on mesh segmentation techniques. Computer Graphics Forum, 26, 1539–1556.Google Scholar
  62. Shapira, L., Shamir, A., & Cohen-Or, D. (2008). Consistent mesh partitioning and skeletonisation using the shape diameter function. The Visual Computer, 24, 249–259.CrossRefGoogle Scholar
  63. Sharma, A., Horaud, R., Knossow, D., von Lavante, E. (2009). Mesh segmentation using Laplacian eigenvectors and Gaussian mixtures. In Proceedings of the AAAI Fall Symposium on Manifold Learning and its Applications.Google Scholar
  64. Shi, J., & Malik, J. (2000). Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888–905.CrossRefGoogle Scholar
  65. Shi, Q., Wang, L., Cheng, L., Smola, A. (2008). Discriminative human action segmentation and recognition using semi-Markov model. In Computer Vision and Pattern Recognition.Google Scholar
  66. Starck, J., Hilton, A. (2007). Correspondence labeling for widetimeframe free-form surface matching. In International Conference on Computer Vision.Google Scholar
  67. Sundaresan, A., Chellappa, R. (2006). Segmentation and probalistic registration of articulated body models. In International Conference on Pattern Recognition.Google Scholar
  68. Tenenbaum, J. B., de Silva, V., & Langford, J. C. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500), 2319–2323.CrossRefGoogle Scholar
  69. Varanasi, K., Boyer, E. (2010). Temporally coherent segmentation of 3D reconstructions. In Proceedings of 3DPTV.Google Scholar
  70. Zaharescu, A., Boyer, E., & Horaud, R. (2011). Topology-adaptive mesh deformation for surface evolution, morphing, and multi-view reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(4), 823–837.CrossRefGoogle Scholar
  71. Zhou, K., Huang, J., Snyder, J., Liu, X., Bao, H., Guo, B., et al. (2005). Large mesh deformation using the volumetric graph Laplacian. ACM Transactions on Graphics, 24(3), 496–503.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.Department of Computing and Communication TechnologiesOxford Brookes UniversityOxfordUK
  2. 2.Institut für InformatikTechnische Universität MünchenGarching b. MünchenGermany
  3. 3.INRIA Grenoble Rhône-AlpesMontbonnot Saint-MartinFrance

Personalised recommendations