Automated Markerless Extraction of Walking People Using Deformable Contour Models

We develop a new automated markerless motion capture system for the analysis of walking people. We employ global evidence gathering techniques guided by biomechanical analysis to robustly extract articulated motion. This forms a basis for new deformable contour models, using local image cues to capture shape and motion at a more detailed level. We extend the greedy snake formulation to include temporal constraints and occlusion modelling, increasing the capability of this technique when dealing with cluttered and self-occluding extraction targets. This approach is evaluated on a large database of indoor and outdoor video data, demonstrating fast and autonomous motion capture for walking people