Context-aware part-based people detection for video monitoring

Abstract

A novel approach for part-based people detection in images that uses contextual information is proposed. Two sources of context are distinguished regarding the local (neighbour) information and the relative importance of the parts in the model. Local context determines part visibility which is derived from the spatial location of static objects in the scene and from the relation between scales of analysis and detection window sizes. Experimental results over various datasets show that the proposed use of context outperforms the related state-of-the-art.