Young-suk JI1, Hwan-ik CHUNG2, Hern-soo HAHN1
1. Dept. of Electronic Engineering, Soonsil University, Seoul 156743, Korea;2. Dept. of Internet Information, Kyungbok College, Kyeonggi-do 487717, Korea
Abstract-This paper proposes a method which uses the extended edge analysis to supplement the inaccurate edge information for better vehicle detection during vehicle detection. The extended edge analysis method detects t wo vertical edge items, which are the borderlines of both sides of the vehicle, by extending the horizontal edges obtained inaccurately due to the illumination or noise existing on the image. The proposed method extracts the horizontal edg es with the method of merging edges by using the horizontal edge information ins ide the Region of Interest (ROI), which is set up on the pre-processing step. T he bottom line is determined by detecting the shadow regions of the vehicle from the extracted horizontal edge one. The general width of the vehicle detecting and the extended edge analyzing methods are carried out side by side on the bott om line of the vehicle to determine width of the vehicle. Finally, the final veh icle is detected through the verification step. On the road image with complicat e background, the vehicle detecting method based on the extended edge analysis i s more efficient than the existing vehicle detecting method which uses the edge information. The excellence of the proposed vehicle detecting method is confirme d by carrying out the vehicle detecting experiment on the complicate road image.
Key words-vehicle detection; edge analysis; ROI
Manuscript Number: 1674-8042(2010)03-0250-06
dio: 10.3969/j.issn.1674-8042.2010.03.11
References
[1]G.Y.Song, K.Y.Lee, J.W.Lee, Paljoo Yoon, 2007. Vehicle Detection usi ng Edge Analysis and AdaBoost Algorithm. The Korean Society of Automotive Engine ers, p.27-34.
[2]R.Miller, Z.Sun, G.Bebis, 2004. On Road vehicleDetection. IEEE Transactions on Pattern Analysis andMachine Intelligence. 28: 694 -711.
[3]Zehang Sun, George Bebis, and Ronald Miller, 2005. On-road vehicle detection using evolutionary gabor filter optimization. IEEE Transacti ons on Intelligent Transportation Systems, 6(2): 125-137.
[full text view]
