Shape-Based Pedestrian Segmentation in Still Images

Pedestrian segmentation is a problem of considerable practical interest. In this work we propose a shape-based model for pedestrian segmentation. Our model is initialized by a bounding-box of the person under analysis, which can be estimated by a person detector. The basic idea of the proposed model is to create a graph around the detected person, based on a scale invariant shape model and the estimated contour is given by a path in the graph that maximizes certain boundary energy. In practice, such energy should be large in the boundary between the foreground/background. To cope with pose/shape variations, the final estimate is given by a selection scheme, which takes into consideration the individual estimate given by different generated graphs. Experimental results indicated that the proposed technique works well in non trivial images, with comparable accuracy to the state-of-the-art.