Bayesian Object Detection in Dynamic Scenes

Detecting moving objects using stationary cameras is an important precursor to many activity recognition, object recognition and tracking algorithms. In this paper, three innovations are presented over existing approaches. Firstly, the model of the intensities of image pixels as independently distributed random variables is challenged and it is asserted that useful correlation exists in the intensities of spatially proximal pixels. This correlation is exploited to sustain high levels of detection accuracy in the presence of nominal camera motion and dynamic textures. By using a nonparametric density estimation method over a joint domainrange representation of image pixels, multi-modal spatial uncertainties and complex dependencies between the domain (location) and range (color) are directly modeled. Secondly, temporal persistence is proposed as a detection criteria. Unlike previous approaches to object detection which detect objects by building adaptive models of the only background, ...

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Yaser Sheikh, Mubarak Shah
• Keywords: Computer Vision, CVPR 2005, Detection Accuracy, Detection Criteria, Image Pixels, Multi-modal Spatial Uncertainties, Proximal Pixels