A Parts-based Person Detector

This work presents a parts-based person detection framework. The individual body segmentslegs, torsos, and heads are detected by Adaboost classifiers, which have proven useful other classification tasks [12] [6] [1] [13]. The body segment candidates are combined into kinematically plausible configurations and each is assigned a score. The body configurations are calculated using an efficient dynamic programming implementation for pictorial structures [3]. The tracker is run on several video sequences that exhibit camera motion and significant differences in lighting and environment. This method can be made to run in realtime and can be easily extended to incorporate more complex models of human kinematics.