Body Localization in Still Images Using Hierarchical Models and Hybrid Search

We present a 3-level hierarchical model for localizing human bodies in still images from arbitrary viewpoints. We first fit a simple tree-structured model defined on a small landmark set along the body contours by Dynamic Programming (DP). The output is a series of proposal maps that encode the probabilities of partial body configurations. Next, we fit a mixture of view-dependent models by Sequential Monte Carlo (SMC), which handles self-occlusion, anthropometric constraints, and large viewpoint changes. DP and SMC are designed to search in opposite directions such that the DP proposals are utilized effectively to initialize and guide the SMC inference. This hybrid strategy of combining deterministic and stochastic search ensures both the robustness and efficiency of DP, and the accuracy of SMC. Finally, we fit an expanded mixture model with increased landmark density through local optimization. The model hierarchy is trained on a large number of gait images. Extensive tests on clutte...

• Type: Conference
• Year: 2006
• Where: CVPR
• Authors: Jiayong Zhang, Jiebo Luo, Robert T. Collins, Yanxi Liu
• Keywords: 3-level Hierarchical Model, Computer Vision, CVPR 2006, Dp Proposals, Mixture Model, Simple Tree-structured Model, Smc Inference