Pedestrian detection in crowded scenes

In this paper, we address the problem of detecting pedestrians in crowded real-world scenes with severe overlaps. Our basic premise is that this problem is too difficult for any type of model or feature alone. Instead, we present an algorithm that integrates evidence in multiple iterations and from different sources. The core part of our method is the combination of local and global cues via probabilistic top-down segmentation. Altogether, this approach allows examining and comparing object hypotheses with high precision down to the pixel level. Qualitative and quantitative results on a large data set confirm that our method is able to reliably detect pedestrians in crowded scenes, even when they overlap and partially occlude each other. In addition, the flexible nature of our approach allows it to operate on very small training sets.

[1]  A. Bhattacharyya.  On a measure of divergence between two statistical populations defined by their probability distributions , 1943 .

[2]  Robert C. Bolles,et al.  Parametric Correspondence and Chamfer Matching: Two New Techniques for Image Matching , 1977, IJCAI.

[3]  Gunilla Borgefors,et al.  Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Clark F. Olson,et al.  Automatic target recognition by matching oriented edge pixels , 1997, IEEE Trans. Image Process..

[5]  Dariu Gavrila,et al.  Multi-feature hierarchical template matching using distance transforms , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[6]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[7]  Dariu Gavrila,et al.  Pedestrian Detection from a Moving Vehicle , 2000, ECCV.

[8]  Pedro F. Felzenszwalb.  Learning models for object recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Tomaso A. Poggio,et al.  Example-Based Object Detection in Images by Components , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Dorin Comaniciu,et al.  The Variable Bandwidth Mean Shift and Data-Driven Scale Selection , 2001, ICCV.

[11]  Dan Roth,et al.  Learning a Sparse Representation for Object Detection , 2002, ECCV.

[12]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[13]  B. Schiele,et al.  Interleaved Object Categorization and Segmentation , 2003, BMVC.

[14]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[15]  Björn Stenger,et al.  Shape context and chamfer matching in cluttered scenes , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[16]  Jianbo Shi,et al.  Object-Specific Figure-Ground Segregation , 2003, CVPR.

[17]  B. Schiele,et al.  Combined Object Categorization and Segmentation With an Implicit Shape Model , 2004 .

[18]  Bernt Schiele,et al.  Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search , 2004, DAGM-Symposium.

[19]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[20]  Tomaso A. Poggio,et al.  A Trainable System for Object Detection , 2000, International Journal of Computer Vision.

[21]  Cordelia Schmid,et al.  Human Detection Based on a Probabilistic Assembly of Robust Part Detectors , 2004, ECCV.

[22]  Paul A. Viola,et al.  Detecting Pedestrians Using Patterns of Motion and Appearance , 2005, International Journal of Computer Vision.

[23]  Ruzena Bajcsy,et al.  Segmentation of range images as the search for geometric parametric models , 1995, International Journal of Computer Vision.