A Multi-Feature Fusion Method for Forward Vehicle Detection with Single Camera

Abstract:

Vehicle detection is very important for Advanced Driver Assistance System. This paper focused on improving the performance of vehicle detection system with single camera and proposed a multi-feature fusion method for forward vehicle detection. The shadow and edges of the vehicle are the most important features, so they can be utilized to detect vehicle at daytime. The shadow and edge features were segmented accurately by using histogram analysis method and adaptive dual-threshold method respectively. The initial candidates were generated by combining edge and shadow features, and these initial candidates were further verified using an integrated feature based on the fusion of symmetry, texture and shape matching degree features. The weight of each feature was determined by the Fisher criterion, and the non-vehicle initial candidates were rejected by a threshold. The experimental results show that the proposed method could be adapt to different illumination circumstances robustly and improve the accuracy of forward vehicle detection.

• Periodical: Applied Mechanics and Materials (Volumes 321-324)
• Pages: 998-1004
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.321-324.998
• Online since: June 2013
• Authors: Xing Li*, Xiao Song Guo, Jun Bin Guo
• Keywords: Advanced Driver Assistance System, Fisher Criterion, Forward Vehicle Detection, Multi-Feature Fusion

References

[1] WHO, World Report on Road Traffic Injury Prevention, http://www.who.int/violence injury revention.

[2] The Road Accident Statistics Report of China[M], Traffic Management Bureau of Public Security Ministry, Beijing, 2011, In Chinese.

[3] Z. Sun, G. Bebis, and R. Miller, On-road Vehicle Detection: A Review, IEEE Trans. Pattern Anal. Mach. Intell, vol. 28, no. 5, 2006, pp.694-711.

DOI: 10.1109/tpami.2006.104

[4] X. Liu, B Dai, H He. Real-time On-Road Vehicle Detection Combining Specific Segmentation and SVM Classification, Proc. Int'l Conf. Digital Manufacturing and Automation, 2010, pp.885-888.

DOI: 10.1109/icdma.2011.219

[5] CT Chen, CY Su, WC Kao. An Enhanced Segmentation on Vision-Based Shadow Removal for Vehicle Detection, Green Circuits and Systems. 2010, pp.679-682.

DOI: 10.1109/icgcs.2010.5542975

[6] GY Song, KY Lee, JW Lee. Vehicle Detection by Edge-Based Candidate Generation and Appearance-Based Classification. IEEE Intelligent Vehicles Symposium, 2008, pp.428-433.

DOI: 10.1109/ivs.2008.4621139

[7] N. Srinivasa, A Vision-Based Vehicle Detection and Tracking Method for Forward Collision Warning, Proc. IEEE Intelligent Vehicle Symposium, 2002, pp.626-631.

DOI: 10.1109/ivs.2002.1188021

[8] M. Bertozzi et al., Vision-Based Intelligent Vehicles: State of the Art and Perspectives, Robotics and Autonomous Systems, vol. 32, 2000, pp.1-16.

DOI: 10.1016/s0921-8890(99)00125-6

[9] W. von Seelen et al., Scene Analysis and Organization of Behavior in Driver Assistance Systems, Proc. IEEE Int'l Conf. Image Processing, 2000, pp.524-527.

[10] T. Kate et al., Mid-range and Distant Vehicle Detection With a Mobile Camera, Intelligent Vehicles Symposium, 2004, pp.72-77.

DOI: 10.1109/ivs.2004.1336358

[11] Z. Sun, et al., On-Road Vehicle Detection Using Gabor Filters and Support Vector Machines, Proc. IEEE Int'l Conf. Digital Signal Processing, 2002, pp.1019-1022.

DOI: 10.1109/icdsp.2002.1028263

[12] Sun. Li, et al., Multi-View Vehicle Detection in Traffic Surveillance Combining HOG-HCT and Deformable Part Models, Proc. Int'l Conf. Wavelet Analysis and Pattern Recognition, 2012, pp.202-207.

DOI: 10.1109/icwapr.2012.6294779

[13] H. Foley D et al., An optimal set of discriminant vectors. IEEE Trans. on Computers, 24(3): 281-289, 1975.

DOI: 10.1109/t-c.1975.224208