A Real Time Object Detection Approach Applied to Reliable Pedestrian Detection

This paper presents a robust real time obstacle and pedestrian detection algorithm, which is capable of handling the challenges of stationary as well as moving objects, utilizing a single car mounted monochrome camera. First, the system detects obstacles above the ground plane by obtaining a "virtual stereo system" through the usage of inverse perspective mapping. A fast digital image stabilization algorithm is used to compensate erroneous detections whenever the flat ground plane assumption is an inaccurate model of the road surface. Finally, a low level pedestrian segmentation algorithm is developed to extract bounding boxes of potential pedestrians. Furthermore a novel approach called the pedestrian detection strip is used to improve the calculation time by a factor of six compared to previous attempts. Experiments have been carried out by applying the proposed algorithm on prerecorded sequences as well as within a test vehicle and thus in a closed loop environment. The experimental results indicate a promising detection performance. Obstacles and pedestrians up to 50 meters away from the vehicle have been detected reliably at 64 frames per second on a 3 GHz PC.

[1]  T. Williamson.  A high-performance stereo vision system for obstacle detection , 1998 .

[2]  J. Little,et al.  Inverse perspective mapping simplifies optical flow computation and obstacle detection , 2004, Biological Cybernetics.

[3]  Kazunori Onoguchi,et al.  Shadow elimination method for moving object detection , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

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

[5]  D. Baehring,et al.  Detection of close cut-in and overtaking vehicles for driver assistance based on planar parallax , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[6]  Heinrich Niemann,et al.  Integrated motion and geometry-based obstacle detection in image sequences of traffic scenes , 1996, Defense, Security, and Sensing.

[7]  Massimo Bertozzi,et al.  Self-calibration of a stereo vision system for automotive applications , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[8]  Massimo Bertozzi,et al.  Short Communication Stereo inverse perspective mapping: theory and applications , 1998 .

[9]  Sarp Ertürk,et al.  Sast digital image stabilization using one bit transform based sub-image motion estimation , 2005, IEEE Transactions on Consumer Electronics.

[10]  Anton Kummert,et al.  Vision-Based Pedestrian Detection -- Improvement and Verification of Feature Extraction Methods and SVM-Based Classification , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[11]  Massimo Bertozzi,et al.  AN EXTENSION TO THE INVERSE PERSPECTIVE MAPPING TO HANDLE NON-FLAT ROADS , 1998 .

[12]  Andreas Kuehnle.  Symmetry-based vehicle location for AHS , 1997, Other Conferences.

[13]  Massimo Bertozzi,et al.  GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection , 1998, IEEE Trans. Image Process..

[14]  Thomas Kalinke,et al.  A Texture-based Object Detection and an adaptive Model-based Classification , 1998 .

[15]  Yan Zhang,et al.  Robust Moving Object Detection at Distance in the Visible Spectrum and Beyond Using A Moving Camera , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[16]  Darius Burschka,et al.  Advances in Computational Stereo , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Frank Lindner,et al.  Autonomous Driving approaches Downtown , 1999 .

[18]  Olivier Faugeras,et al.  Three-Dimensional Computer Vision , 1993 .

[19]  Dariu Gavrila,et al.  The Visual Analysis of Human Movement: A Survey , 1999, Comput. Vis. Image Underst..

[20]  Martin A. Fischler,et al.  Computational Stereo , 1982, CSUR.

[21]  Dariu Gavrila,et al.  The Issues , 2011 .

[22]  R.M. Haralick.  Monocular vision using inverse perspective projection geometry: analytic relations , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[23]  Massimo Bertozzi,et al.  Stereo vision-based vehicle detection , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[24]  Mikio Umeda,et al.  Obstacle Avoidance System for Autonomous Transportation Vehicle Based on Image Processing , 2002 .

[25]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[26]  Massimo Bertozzi,et al.  Stereo inverse perspective mapping: theory and applications , 1998, Image Vis. Comput..