Detecting humans under occlusion using variational mean field method

This paper proposes a human detection method using variational mean field approximation for occlusion reasoning. In the method, parts of human objects are detected individually using template matching. Initial detection hypotheses with spatial layout information are represented in a graphical model and refined through a Bayesian estimation. In this paper, mean field method is employed for such an estimation. The proposed method was evaluated on the popular CAVIAR-INRIA dataset. Experimental results show that the proposed algorithm is able to detect humans in severe occlusion within reasonable processing time.

[1]  Tommi S. Jaakkola,et al.  Tutorial on variational approximation methods , 2000 .

[2]  Ramakant Nevatia,et al.  Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[3]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Wanqing Li,et al.  A part-based template matching method for multi-view human detection , 2009, 2009 24th International Conference Image and Vision Computing New Zealand.

[5]  Larry S. Davis,et al.  Hierarchical Part-Template Matching for Human Detection and Segmentation , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Shuicheng Yan,et al.  Discriminative local binary patterns for human detection in personal album , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Bernt Schiele,et al.  Pedestrian detection in crowded scenes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Wanqing Li,et al.  An Improved Template Matching Method for Object Detection , 2009, ACCV.

[9]  Ramakant Nevatia,et al.  Segmentation and Tracking of Multiple Humans in Crowded Environments , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Larry S. Davis,et al.  Bilattice-based Logical Reasoning for Human Detection , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  H. Bischof,et al.  Fast human detection in crowded scenes by contour integration and local shape estimation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Dariu Gavrila,et al.  A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.