Recovering Human Body Configurations using Pairwise Constraints between Parts.pptVIP

Recovering Human Body Configurations using Pairwise Constraints between Parts Xiaofeng Ren, Alex Berg, Jitendra Malik Related Domains Tracking People Detecting Pedestrians ... … Localizing Human Figures Exemplar-based: [Toyama Blake 01], [Mori Malik 02], [Sullivan Carlsson 02], [Shakhnarovich, Viola Darrell 03], … Part-based: [Felzenswalb Huttenlocher 00], [Ioffe Forsyth 01], [Song, Goncalves Perona 03], [Mori, Ren, Efros Malik 04], … … … Preprocessing with Constrained Delaunay Triangulation Detecting Candidate Parts from Bottom-up Learning Pairwise Constraints between Parts Assembling Parts by Integer Quadratic Programming (IQP) Detect edges with Pb (Probability of Boundary) Trace contours with Canny’s hysteresis Recursively split contours into piecewise straight lines Complete the partial graph with Constrained Delaunay Triangulation Scale (width) consistency Use anthropometric data as groundtruth Symmetry of appearance (color) Orientation consistency Connectivity Short distance between adjacent parts “Smooth” connection between non-adjacent parts short “gaps” on shortest path (on CDT graph) small maximum angle on the shortest path few T-junctions/turns on the shortest path Suppose there are m parts and n candidates, the optimal assignment ? minimizes a quadratic function To find people under general conditions, we need to go beyond the traditional tree-based model; Most important constraints for the human body are between pairs of body parts; Pairwise constraints may be learned from a small set of training examples; Integer Quadratic Programming (IQP) efficiently finds optimal configurations under pairwise constraints. ** MSRI University of California Berkeley Finding People Challenges: Pose, Clothing, Lighting, Clutter, … Previous Work Beyond “Trees” A hard problem! More information is needed. Important cues that are NOT in the tree model: Symmetry of clothing/color “V-shape” formed by the upper legs Distance/smooth connection between arms and l