Articulation-Invariant Representation of Non-planar Shapes

Given a set of points corresponding to a 2D projection of a non-planar shape, we would like to obtain a representation invariant to articulations (under no self-occlusions). It is a challenging problem since we need to account for the changes in 2D shape due to 3D articulations, viewpoint variations, as well as the varying effects of imaging process on different regions of the shape due to its non-planarity. By modeling an articulating shape as a combination of approximate convex parts connected by non-convex junctions, we propose to preserve distances between a pair of points by (i) estimating the parts of the shape through approximate convex decomposition, by introducing a robust measure of convexity and (ii) performing part-wise affine normalization by assuming a weak perspective camera model, and then relating the points using the inner distance which is insensitive to planar articulations. We demonstrate the effectiveness of our representation on a dataset with non-planar articulations, and on standard shape retrieval datasets like MPEG-7.

[1]  Philip N. Klein,et al.  Recognition of shapes by editing their shock graphs , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Radu Horaud,et al.  Articulated shape matching using Laplacian eigenfunctions and unsupervised point registration , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  R. Collins,et al.  Representation and matching of articulated shapes , 2004, CVPR 2004.

[4]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[5]  Zhuowen Tu,et al.  Improving Shape Retrieval by Learning Graph Transduction , 2008, ECCV.

[6]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[7]  Ulrich Eckhardt,et al.  Shape descriptors for non-rigid shapes with a single closed contour , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[8]  Longin Jan Latecki,et al.  Locally constrained diffusion process on locally densified distance spaces with applications to shape retrieval , 2009, CVPR.

[9]  Paul L. Rosin,et al.  A new convexity measure for polygons , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Robert M. Haralick,et al.  Decomposition of Two-Dimensional Shapes by Graph-Theoretic Clustering , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Jitendra Malik,et al.  Can convexity explain how humans segment objects into parts , 2010 .

[12]  Joshua D. Schwartz,et al.  Hierarchical Matching of Deformable Shapes , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[14]  Jiří Matas,et al.  Computer Vision - ECCV 2004 , 2004, Lecture Notes in Computer Science.

[15]  Andrzej Lingas,et al.  The Power of Non-Rectilinear Holes , 1982, ICALP.

[16]  Paul L. Rosin.  Shape Partitioning by Convexity , 1999, BMVC.

[17]  Zhuowen Tu,et al.  Shape Matching and Recognition - Using Generative Models and Informative Features , 2004, ECCV.

[18]  Raif M. Rustamov,et al.  Laplace-Beltrami eigenfunctions for deformation invariant shape representation , 2007 .

[19]  Esa Rahtu,et al.  A new convexity measure based on a probabilistic interpretation of images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Remco C. Veltkamp,et al.  State of the Art in Shape Matching , 2001, Principles of Visual Information Retrieval.

[21]  Nancy M. Amato,et al.  Approximate convex decomposition of polygons , 2004, SCG '04.

[22]  Ron Kimmel,et al.  On Bending Invariant Signatures for Surfaces , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Jürgen Teich,et al.  Minimal enclosing parallelogram with application , 1995, SCG '95.

[24]  Haibin Ling,et al.  Shape Classification Using the Inner-Distance , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Alfred M. Bruckstein,et al.  Matching Two-Dimensional Articulated Shapes Using Generalized Multidimensional Scaling , 2006, AMDO.

[26]  Alfred M. Bruckstein,et al.  Partial Similarity of Objects, or How to Compare a Centaur to a Horse , 2009, International Journal of Computer Vision.

[27]  Daniel Cremers,et al.  Matching non-rigidly deformable shapes across images: A globally optimal solution , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[29]  Kap Luk Chan,et al.  Shape evolution for rigid and nonrigid shape registration and recovery , 2009, CVPR.