cvpr cvpr2013 cvpr2013-226 cvpr2013-226-reference knowledge-graph by maker-knowledge-mining

226 cvpr-2013-Intrinsic Characterization of Dynamic Surfaces


Source: pdf

Author: Tony Tung, Takashi Matsuyama

Abstract: This paper presents a novel approach to characterize deformable surface using intrinsic property dynamics. 3D dynamic surfaces representing humans in motion can be obtained using multiple view stereo reconstruction methods or depth cameras. Nowadays these technologies have become capable to capture surface variations in real-time, and give details such as clothing wrinkles and deformations. Assuming repetitive patterns in the deformations, we propose to model complex surface variations using sets of linear dynamical systems (LDS) where observations across time are given by surface intrinsic properties such as local curvatures. We introduce an approach based on bags of dynamical systems, where each surface feature to be represented in the codebook is modeled by a set of LDS equipped with timing structure. Experiments are performed on datasets of real-world dynamical surfaces and show compelling results for description, classification and segmentation.


reference text

[1] B. Afsari, R. Chaudhry, A. Ravichandran, and R. Vidal. Group action induced distances for averaging and clustering 222333999

[2]

[3]

[4]

[5]

[6]

[7]

[8]

[9]

[10] linear dynamical systems with applications to the analysis of dynamic scenes. CVPR, 2012. 4 J. Allard, C. M ´enier, B. Raffin, E. Boyer, and F. Faure. Grimage: Markerless 3d interactions. SIGGRAPH - Emerging Technologies, 2007. 2, 5, 6 M. Bojsen-Hansen, H. Li, and C. Wojtan. Tracking surfaces with evolving topology. SIGGRAPH, 2012. 2 C. Cagniart, E. Boyer, and S. Ilic. Probabilistic deformable surface tracking from multiple videos. ECCV, 2010. 2, 3, 4, 6, 7 H. Cetingul and R. Vidal. Intrinsic mean shift for clustering on stiefel and grassmann manifolds. CVPR, 2009. 4 A. B. Chan, E. Coviello, and G. R. G. Lanckriet. Clustering dynamic textures with the hierarchical em algorithm. CVPR, 2010. 4 A. B. Chan and N. Vasconcelos. Mixtures of dynamic textures. ICCV, 2005. 1, 2, 4 A. B. Chan and N. Vasconcelos. Classifying video with kernel dynamic textures. CVPR, 2007. 6 R. Chaudhry, A. Ravichandran, G. Hager, and R. Vidal. Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions. CVPR, 2009. 2, 3 K. M. Cheung, S. Baker, and T. Kanade. Shape-from-

[11]

[12]

[13]

[14]

[15]

[16]

[17]

[18]

[19]

[20]

[21] silhouette across time: Part ii: Applications to human modeling and markerless motion tracking. IJCV, 63(3):225–245, 2005. 2 E. de Aguiar, C. Stoll, C. Theobalt, N. Ahmed, H.-P. Seidel, and S. Thrun. Performance capture from sparse multi-view video. ACM Trans. Graphics, 27(3), 2008. 1, 2, 4, 5, 6 E. de Aguiar, C. Theobalt, C. Stoll, and H.-P. Seidel. Markerless deformable mesh tracking for human shape and motion capture. CVPR, 2007. 2 G. Doretto, A. Chiuso, Y. Wu, and S. Soatto. Dynamic textures. IJCV, 51(2):91–109, 2003. 1, 2, 3, 4 G. Doretto, D. Cremers, P. Favaro, and S. Soatto. Dynamic texture segmentation. ICCV, 2003. 2 C. Fowlkes, S. Belongie, F. Chung, and J. Malik. Spectral grouping using the nystrom method. PAMI, 2009. 5 J. Franco and E. Boyer. Learning temporally consistent rigidities. CVPR, 2011. 2, 7 J. Franco, C. Menier, E. Boyer, and B. Raffin. A distributed approach for real-time 3d modeling. CVPR Workshop on Real-Time 3D Sensors and theirApplications, page 3 1, 2004. 1, 2 Y. Furukawa and J. Ponce. Dense 3d motion capture from synchronized video streams. CVPR, 2008. 2 P. Huang, A. Hilton, and J. Starck. Shape similarity for 3d video sequences of people. IJCV Special Issue on 3D Object Retrieval, 89(2-3):362–381, 2010. 2 H. Jiang, H. Liu, P. Tan, G. Zhang, and H. Bao. 3d reconstruction of dynamic scenes with multiple handheld cameras. ECCV, 2012. 1, 2 Y.-G. Jiang, C.-H. Ngo, and J. Yang. Towards optimal bagof-features for object categorization and semantic video re-

[22]

[23]

[24]

[25]

[26]

[27]

[28]

[29]

[30] [3 1] trieval. CIVR, 2007. 4, 5 T. Kanade, A. Yoshida, K. Oda, H. Kano, and M. Tanaka. A stereo machine for video-rate dense depth mapping and its new applications. CVPR, 1996. 2 L. Kaufman and P. Rousseeuw. Clustering by means of medoids. Statistical Data Analysis Based on the L1-Norm and Related Methods, Y. Dodge Ed., North-Holland, 1987. 4, 5 H. Kawashima and T. Matsuyama. Interval-based modeling of human communication dynamics via hybrid dynamical systems. NIPS Workshop on Modeling Human Communication Dynamics, 2010. 2, 4 J. Koenderink and A. van Doorn. Surface shape and curvature scales. Image and Vision Computing, 1992. 2 Z. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. CVPR, 2006. 4 T. Matsuyama, X. Wu, T. Takai, and S. Nobuhara. Real-time 3d shape reconstruction, dynamic 3d mesh deformation, and high fidelity visualization for 3d video. CVIU, 96(3):393– 434, 2004. 1, 2 M. Ovsjanikov, Q. Merigot, F. Memoli, and L. J. Guibas. One point isometric matching with the heat kernel. Comput. Graph. Forum, 29(5): 1555–1564, 2010. 2 L. R. Rabiner. A tutorial on hidden markow models and selected applications in speech recognition. IEEE, 77(2):257– 286, 1989. 2 A. Ravichandran, R. Chaudhry, and R. Vidal. View-invariant dynamic texture recognition using a bag of dynamical systems. CVPR, 2009. 1, 2, 3, 4, 5, 6, 7 L. Saboret, P. Alliez, and B. L e´vy. Planar parameterization

[32]

[33]

[34]

[35]

[36]

[37]

[38]

[39]

[40]

[41] of triangulated surface meshes. In CGAL Reference Manual. CGAL Editorial Board, 4.0 edition, 2012. 3 P. Saisan, G. Doretto, Y. Wu, and S. Soatto. Dynamic texture recognition. CVPR, 2001 . 2, 3, 4, 6 J. Starck and A. Hilton. Spherical matching for temporal correspondence of non-rigid surfaces. ICCV, 2005. 2 J. Starck and A. Hilton. Surface capture for performancebased animation. IEEE Computer Graphics and Applications, 2007. 1, 2, 3, 5, 6, 7 T. Tung and T.Matsuyama. Dynamic surface matching by geodesic mapping for 3d animation transfer. CVPR, 2010. 2 T. Tung and T.Matsuyama. Invariant surface-based shape descriptor for dynamic surface encoding. ACCV, 2012. 3 T. Tung and T.Matsuyama. Topology dictionary for 3d video understanding. PAMI, 34(8): 1645–1657, 2012. 2, 5 K. Varanasi, A. Zaharescu, E. Boyer, and R. Horaud. Temporal surface tracking using mesh evolution. ECCV, 2008. 2 S. Vedula, S. Baker, P. Rander, R. Collins, and T. Kanade. Three-dimensional scene flow. PAMI, 27(1):475– 480, 2005. 2 R. Vidal and A. Ravichandran. Optical flow estimation and segmentation of multiple moving dynamical textures. CVPR, 2005. 2 A. Zaharescu, E. Boyer, K. Varanasi, and R. Horaud. Surface feature detection and description with applications to mesh matching. CVPR, 2009. 2 222444000