A two-staged approach to vision-based pedestrian recognition using Haar and HOG features

This article presents a two-staged approach to recognize pedestrians in video sequences on board of a moving vehicle. The system combines the advantages of two feature families by splitting the recognition process into two stages: In the first stage, a fast search mechanism based on simple features is applied to detect interesting regions. The second stage uses a computationally more expensive, but also more accurate set of features on these regions to classify them into pedestrian and non-pedestrian. We compared various feature extraction configurations of different complexities regarding classification performance and speed. The complete system was evaluated on a number of labeled test videos taken from real-world drives and also compared against a publicly available pedestrian detector. This first system version analyzes only single image frames without using any temporal information like tracking. Still, it achieves good recognition performance at reasonable run time.

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

[2]  Silviu Bota,et al.  Multi-Feature Walking Pedestrian Detection Using Dense Stereo and Motion , 2007 .

[3]  David Gerónimo Gómez,et al.  Haar Wavelets and Edge Orientation Histograms for On-Board Pedestrian Detection , 2007, IbPRIA.

[4]  Mei-Chen Yeh,et al.  Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[5]  Ivan Laptev,et al.  Improvements of Object Detection Using Boosted Histograms , 2006, BMVC.

[6]  D. Fernandez,et al.  Bounding Box Accuracy in Pedestrian Detection for Intelligent Transportation Systems , 2006, IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics.

[7]  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).

[8]  P. Mahonen,et al.  Pedestrian Recognition Based on 3D Image Data , 2007, 2007 IEEE International Symposium on Industrial Electronics.

[9]  M. Szarvas,et al.  Real-time Pedestrian Detection Using LIDAR and Convolutional Neural Networks , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[10]  Fatih Murat Porikli,et al.  Integral histogram: a fast way to extract histograms in Cartesian spaces , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Massimo Bertozzi,et al.  Shape-based pedestrian detection , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[12]  Dariu Gavrila,et al.  Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle , 2007, International Journal of Computer Vision.

[13]  A. Shashua,et al.  Pedestrian detection for driving assistance systems: single-frame classification and system level performance , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[14]  G. Schneider,et al.  Radar-Vision Based Vehicle Recognition with Evolutionary Optimized and Boosted Features , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[15]  Klaus Dietmayer,et al.  Pedestrian recognition in urban traffic using a vehicle based multilayer laserscanner , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[16]  A. Zelinsky,et al.  3D vision sensing for improved pedestrian safety , 2004, IEEE Intelligent Vehicles Symposium, 2004.

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

[18]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[19]  Liang Zhao,et al.  Stereo- and neural network-based pedestrian detection , 2000, IEEE Trans. Intell. Transp. Syst..

[20]  Stefano Soatto,et al.  A semi-direct approach to structure from motion , 2003, The Visual Computer.