Fast human detection in crowded scenes by contour integration and local shape estimation

The complexity of human detection increases significantly with a growing density of humans populating a scene. This paper presents a Bayesian detection framework using shape and motion cues to obtain a maximum a posteriori (MAP) solution for human configurations consisting of many, possibly occluded pedestrians viewed by a stationary camera. The paper contains two novel contributions

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Csaba Beleznai, Horst Bischof
• Keywords: Bayesian Detection Framework, Computer Vision, CVPR 2009, Human Detection Increases, Motion Cues