A TRAINABLE PEDESTRIAN DETECTION SYSTEM

In the near future, we can expect on-board automotive vision systems that inform or alert the driver about pedestrians, track surrounding vehicles, and read street signs. Object detection is fundamental to the success of this type of next-generation vision system. In this paper, w e present a trainable object detection system that automatically learns to detect objects of a certain class in unconstrained scenes. We apply our system to the task of pedestrian detection. Unlike previous approaches to pedestrian detection that rely heavily on hand-crafted models and motion information, our system learns the pedestrian model from examples and uses no motion cues. The system can easily be extended to include motion information. We review our previous system, describe a new system that exhibits significantly better performance, provide a comparison between using different combinations of feature sets with classifiers of varying complexity, and describe improvements that increase the system’s processing speed by two orders of magnitude.

[1]  David C. Hogg.  Model-based vision: a program to see a walking person , 1983, Image Vis. Comput..

[2]  Yoshiaki Shirai,et al.  Detection of the movements of persons from a sparse sequence of TV images , 1983, Pattern Recognit..

[3]  Yee-Hong Yang,et al.  Human body motion segmentation in a complex scene , 1987, Pattern Recognit..

[4]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[6]  Karl Rohr,et al.  Incremental recognition of pedestrians from image sequences , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Yoshiaki Shirai,et al.  Detecting multiple image motions by exploiting temporal coherence of apparent motion , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  David C. Hogg,et al.  An efficient method for contour tracking using active shape models , 1994, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

[9]  Christopher J. C. Burges,et al.  Simplified Support Vector Decision Rules , 1996, ICML.

[10]  Bernhard Schölkopf,et al.  Comparison of View-Based Object Recognition Algorithms Using Realistic 3D Models , 1996, ICANN.

[11]  Alex Pentland,et al.  Pfinder: real-time tracking of the human body , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[12]  Shaogang Gong,et al.  Non-intrusive Person Authentication for Access Control by Visual Tracking and Face Recognition , 1997, AVBPA.

[13]  Tomaso A. Poggio,et al.  Pedestrian detection using wavelet templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Ulrich Kressel,et al.  Tracking non-rigid, moving objects based on color cluster flow , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  C. Papageorgiou,et al.  Object and pattern detection in video sequences , 1997 .

[16]  J. C. BurgesChristopher.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998 .

[17]  Tomaso A. Poggio,et al.  A general framework for object detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[18]  Christian Wöhler,et al.  Motion-based recognition of pedestrians , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[19]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.