Abstract
J. Zhang
J. Luo
R. Collins
Y. Liu
Abstract |
|
| 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 cluttered images with varying poses including walking, dancing and various types of sports activities demonstrate the feasibility of the proposed approach. | |
|
| |
| Figure 1. Given a single image (left), we want to get a boundary estimate (middle) and its uncertainty (right; shown as error ellipses of selected landmarks) for each body part. | |
Publication |
|
The paper at CVPR'06:
| |
Results |
|||
| |||
|
Last update: Aug 12, 2006 |
