A Statistical Field Model for Pedestrian Detection

This paper presents a new statistical model for detecting and tracking deformable objects such as pedestrians, where large shape variations induced by local shape deformation can not be well captured by global methods such as PCA. The proposed model employs a Boltzmann distribution to capture the prior of local deformation, and embeds it into a Markov network which can be learned from data. A mean field variational analysis of this model provides computationally efficient algorithms for computing the likelihood of image observations and facilitate fast model training. Based on that, effective detection and tracking algorithms for deformable objects are proposed and applied to pedestrian detection and tracking. The proposed method has several advantages. Firstly, it captures local deformation well and thus is robust to occlusions and clutter. In addition, it is computationally tractable. Moreover, it divides deformation into local deformation and global deformation, then conquers them ...

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Ying Wu, Ting Yu, Gang Hua
• Keywords: Computer Vision, CVPR 2005, Deformable Objects, Fast Model Training, Global Deformation, Local Deformation, Local Shape Deformation