No Access

A REAL-TIME DETECTION ALGORITHM FOR VISION-BASED PEDESTRIAN PROTECTION

GUANGLIN MA

Faculty of Electrical Information and Media Engineering, University of Wuppertal, D-42119 Wuppertal, Germany

Search for more papers by this author

SU-BIRM PARK

Advanced Engineering, Delphi Delco Electronics Europe, D-42119 Wuppertal, Germany

Search for more papers by this author

ALEXANDER IOFFE

Body & Security Electronics, Delphi Deutschland GmbH, D-51674 Wiehl, Germany

Search for more papers by this author

STEFAN MÜLLER-SCHNEIDERS

Advanced Engineering, Delphi Delco Electronics Europe, D-42119 Wuppertal, Germany

Search for more papers by this author

, and

ANTON KUMMERT

Faculty of Electrical Information and Media Engineering, University of Wuppertal, D-42119 Wuppertal, Germany

Search for more papers by this author

https://doi.org/10.1142/S0219878908001466Cited by:2 (Source: Crossref)

Abstract

This paper discusses the robust, real-time detection of stationary and moving pedestrians utilizing a single car-mounted monochrome camera. First, the system detects potential pedestrians above the ground plane by combining conventional Inverse Perspective Mapping (IPM)-based obstacle detection with the vertical 1D profile evaluation of the IPM detection result. Usage of the vertical profile increases the robustness of detection in low-contrast images as well as the detection of distant pedestrians significantly. A fast digital image stabilization algorithm is used to compensate for erroneous detections whenever the flat ground plane assumption is an inaccurate model of the road surface. Finally, a low-level pedestrian-oriented segmentation and fast symmetry search on the leg region of pedestrians is also presented. A novel approach termed Pedestrian Detection Strip (PDS) is used to improve the calculation time by a factor of six compared to conventional approaches.

Keywords:

References

D. Baehring et al. , Detection of close cut-in and overtaking vehicles for driver assistance based on planar parallax , Proc. IEEE Intelligent Vehicles Symposium ( 2005 ) . Google Scholar
S. Barnard and M. Fisher, ACM Comput. Surv. 14, 533 (1982), DOI: 10.1145/356893.356896. Web of Science, Google Scholar
M. Bertozzi and A. Broggi, IEEE Trans. Image Processing 7(1), 62 (1998), DOI: 10.1109/83.650851. Crossref, Web of Science, Google Scholar
M. Bertozzi, A. Broggi and A. Fascioli, Image and Vision Computing Journal (1998). Google Scholar
M. Bertozzi , A. Broggi and A. Fascioli , An extension to the inverse perspective mapping to handle not-flat roads , Proc. IEEE Int. Conf. Intelligent Vehicles ( 1998 ) . Google Scholar
M. Bertozziet al., Stereo vision based vehicle detection, Proc. of IEEE Intelligent Vehicles Symposium (2000) pp. 39–44. Google Scholar
M. Bertozzi et al. , Low-level pedestrian detection by means of visible and far infra-red tetra-vision , Proc. IEEE Intelligent Vehicles Symposium 2006 ( 2006 ) . Google Scholar
A. Broggi , M. Bertozzi and A. Fascioli , Self-calibration of a stereo vision system for automotive applications , Proc. 2001 IEEE Int. Conf. Robotics and Automation ( 2001 ) . Google Scholar
A. Broggi et al. , Pedestrian detection on a moving vehicle: An investigation about near infra-red images , Proc. IEEE Intelligent Vehicles Symposium 2006 ( 2006 ) . Google Scholar
M. Z. Brown, D. Burschka and G. D. Hager, IEEE Trans. Patt. Anal. Mach. Intell. 25, 993 (2003), DOI: 10.1109/TPAMI.2003.1217603. Crossref, Web of Science, Google Scholar
P. Cerri and P. Grisleri , Free space detection on highways using time correlation between stabilized sub-pixel precision IPM images , Proceedings of the 2005 IEEE International Conference on Robotics and Automation ( 2005 ) . Google Scholar
O. Faugeras , Three dimensional computer vision ( MIT Press , Cambridge, MA , 1993 ) . Google Scholar
U. Frankeet al., IEEE Intelligent Systems 13(6), 40 (1998), DOI: 10.1109/5254.736001. Crossref, Web of Science, Google Scholar
D. M. Gavrila, Computer Vision and Image Understanding 73(1), 82 (1999), DOI: 10.1006/cviu.1998.0716. Crossref, Web of Science, Google Scholar
D. M. Gavrila and V. Philomin, Real-time object detection for smart vehicles, Proceedings of IEEE International Conference on Computer Vision (1999) pp. 87–93. Google Scholar
D. M. Gavrila, Pedestrian detection from a moving vehicle, Proc. European Conference on Computer Vision (2000) pp. 37–49. Google Scholar
R. M. Haralick , Monocular vision using inverse perspective projection geometry: Analytic relations , IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) ( 1989 ) . Google Scholar
R. Hartley and A. Zisserman , Multiple view geometry in computer vision ( Cambridge University Press , UK , 2000 ) . Google Scholar
G. Y. Jiang et al. , Lane and obstacle detection based on fast inverse perspective mapping algorithm , IEEE International Conference on Systems, Man, and Cybernetics ( 2000 ) . Google Scholar
T. Kalinke, C. Tzomakas and W. von Seelen, A texture based object detection and an adaptive model-based classification, Proc. IEEE Intelligent Vehicles Symposium '98 (1998) pp. 341–346. Google Scholar
A. Kuehnle, Symmetry-based vehicle location for AHS, Proc. SPIE Transportation Sensors and Controls: Collision Avoidance, Traffic Management, and ITS2902 (1998) pp. 19–27. Google Scholar
G. Maet al., A real time object detection approach applied to reliable pedestrian detection, Proceedings of the IEEE Intelligent Vehicles Symposium, IV07 (2007) pp. 755–760. Google Scholar
G. Maet al., Vision-based pedestrian detection: Reliable pedestrian candidate detection by combining IPM and a ID profile, Proceedings of the 10th International IEEE Intelligent Transportation Systems Conference, ITSC07 (2007) pp. 137–142. Google Scholar
H. A. Mallotet al., Biomedical and Life Sciences, Computer Science and Engineering 64(3), (1991). Google Scholar
E. Morimoto, M. Suguri and M. Umeda, Agricultural Engineering International: The CIGR Journal of Scientific Research and Development IV, (2002). Google Scholar
A. M. Muad et al. , Implementation of inverse perspective mapping algorithm for the development of an automatic lane tracking system , IEEE TENCON 2004 ( 2004 ) . Google Scholar
H. Niemann, W. Kasprzka and P. Weierich, Integrated motion and geometry based obstacle detection in image sequence of traffic scenes, Proc. SPIE Enhanced and Synthetic Vision2736 (1996) pp. 228–239. Google Scholar
K. Onoguchi, Shadow elimination method for moving object detection, Proceedings of 14th International Conference on Pattern Recognition1 (1998) pp. 583–587. Google Scholar
A. Shashua , Y. Gdalyahu and G. Hayun , Pedestrian detection for driving assistance systems: Single-frame classification and system level performance , Proceedings of IEEE Intelligent Vehicles Symposium 2004 ( 2004 ) . Google Scholar
S. Schauland et al. , Vision-based pedestrian detection: Improvement and verification of feature extraction methods and SVM-based classification , Proceedings of the IEEE ITSC 2006 ( 2006 ) . Google Scholar
Williamson, T. A. [1998] "A high-performance stereo vision system for obstacle detection," CMU-RI-TR-98-24, Robotics Institute Carnegie Mellon University, Pittsburg, PA 15123 . Google Scholar
K. Wojciechowski et al. , Pedestrian detection using derived third-order symmetry of legs , Proceedings of International Conference on Computer Vision and Graphics (ICCVG) 2004 ( 2004 ) . Google Scholar
F. Xu, X. Liu and K. Fujimura, IEEE Transactions on Intelligent Transportation Systems (2005). Google Scholar
M. Yasuno et al. , Pedestrian detection and tracking in far infrared images , Proc. IEEE Intelligent Transportation Systems 2005 ( 2005 ) . Google Scholar
A. Yeni and S. Ertürk, IEEE Transactions on Consumer Electronics 51(3), 917 (2005), DOI: 10.1109/TCE.2005.1510503. Crossref, Web of Science, Google Scholar
Y. Zhang et al. , Robust moving object detection at distance in the visible spectrum and beyond using a moving camera , Proc. 2006 Conf. Computer Vision and Pattern Recognition Workshop ( 2006 ) . Google Scholar