Abstract A vehicle detection approach based on Gabor feature and multiresolution hypothesisverification structure is proposed. The proposed approach includes two basic phases. Firstly, the Regions of Interest (ROI) in an image are determined according to the lane vanishing points. Then a hypothesis list in each ROI is created according to the vertical edges and horizontal edges. Finally, a hypothesis list for the whole image is obtained by combining these three lists. In the hypothesis validation phase, a vehicle validation approach using Support Vector Machine (SVM) is proposed. The proposed algorithm decreases the computational cost by eliminating uninteresting area, and in the hypothesis verification phase, the positive false is low. The experimental results show that the average right detection rate reaches 90% and the execution speed is 20fps using a Pentium(R)4 CPU 2.4GHz.
[1] Zheng Nanning, Tang Shuming, Cheng Hong, et al. Toward Intelligent Driver-Assistance and Safety Warning System. IEEE Intelligent Systems, 2004, 19(2): 8-11 [2] Sun Zehang, Miller R, Bebis G, et al. A Real-Time Precrash Vehicle Detection System // Proc of the 6th IEEE Workshop on Applications of Computer Vision. Orland, USA, 2002: 171-176 [3] Broggi A, Cerri P, Antonello P C. Multi-Resolution Vehicle Detection Using Artificial Vision // Proc of the IEEE International Symposium on Intelligent Vehicle. Parma, Italy, 2004: 310-314 [4] Du Y, Papanikolopoulos N P. Real-Time Vehicle Following through a Novel Symmetry-Based Approach // Proc of the IEEE International Conference on Robotics and Automation. Albuquerque, USA, 1997, Ⅳ: 3160-3165 [5] Batavia P H, Pomerleau D E, Thorpe C E. Overtaking Vehicle Detection Using Implicit Optical Flow // Proc of the IEEE Conference on Intelligent Transportation System. Boston, USA, 1997: 729-734 [6] Kutsuma Y, Yaguchi H, Hamamoto T. Real-Time Lane Line and Forward Vehicle Detection by Smart Image Sensor // Proc of the IEEE International Symposium on Communications and Information Technology. Sapporo, Japan, 2004, Ⅱ: 957-962 [7] Rasmussen C. Grouping Dominant Orientations for Ill-Structured Road Following // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA, 2004, Ⅰ: 470-477 [8] Gabor D. Communication Theory and Physics. IEEE Trans on Information Theory, 1953, 1(1): 48-59 [9] Sun Zehang, Miller R, Bebis G. On-Road Vehicle Detection Using Evolutionary Gabor Filter Optimization. IEEE Trans on Intelligent Transportation Systems, 2005, 6(2): 125-137 [10] Li Li, Song Jingyan, Wang Feiyue, et al. IVS 05: New Developments and Research Trends for Intelligent Vehicles. IEEE Intelligent Systems, 2005, 20(4): 10-14 [11] Liu Tie, Zheng Nanning, Zhao Li, et al. Learning Based Symmetric Feature Selection for Vehicle Detection //Proc of the IEEE International Symposium on Intelligent Vehicle. Las Vegas, USA, 2005:124-129
2006, Vol. 19 
