Skip to Main Content
This paper presents a large scale experimental study on pedestrian detection. The focus of the study is the Chamfer System, a generic system for shape-based object recognition. Matching involves a simultaneous coarse-to-fine approach over a template hierarchy and over the transformation parameters based on correlation with (chamfer) distance-transformed images. Candidate solutions are verified by a neural network with local receptive fields, using a richer set of texture features. Detection is supplemented by an alpha-beta tracker which integrates results over time; the tracker compensates for momentarily missing detections due to image noise or occlusions. For this study, an extensive database of 4762 pedestrian images was compiled with precise ground-truth data. System performance was analyzed by several ROC curves. Although not viable for real-world deployment yet, system performance is shown to be quite promising.