TY - GEN
T1 - A statistical field model for pedestrian detection
AU - Wu, Ying
AU - Yu, Ting
AU - Hua, Gang
PY - 2005
Y1 - 2005
N2 - 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 va national analysis of this model provides computationally efficient algorithms for computing the likeli-hood 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 by combining bottom-up and top-down methodologies. Extensive experiments demonstrate the effectiveness of the proposed model for deformable objects.
AB - 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 va national analysis of this model provides computationally efficient algorithms for computing the likeli-hood 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 by combining bottom-up and top-down methodologies. Extensive experiments demonstrate the effectiveness of the proposed model for deformable objects.
UR - http://www.scopus.com/inward/record.url?scp=33645136021&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33645136021&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2005.49
DO - 10.1109/CVPR.2005.49
M3 - Conference contribution
AN - SCOPUS:33645136021
SN - 0769523722
SN - 9780769523729
T3 - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
SP - 1023
EP - 1030
BT - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PB - IEEE Computer Society
T2 - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Y2 - 20 June 2005 through 25 June 2005
ER -