Traffic Lights Recognition Based on Concatenated Filtering Method

Abstract

Abstract: A method for detection and recognition of traffic lights based on intelligent vehiclemounted camera was proposed. Applying the threshold acquired by image training, the candidate regions of traffic lights are extracted using the color segmentation method. Next the concatenated filters are proposed as a way to classify the extracted candidate regions. And then template matching using normalized cross correlation techniques is adopted to validate the classified traffic lights candidates. The experimental results show that the proposed algorithm works effectively and robustly for traffic lights recognition for intelligent vehicles in complex urban environments.

Key words: traffic lights recognition, color segmentation, concatenated filtering, normalized cross correlation

CLC Number:

TP 391

JIN Tao-a, WANG Chun-Xiang-a, WANG Bing-b, YANG Ming-b. Traffic Lights Recognition Based on Concatenated Filtering Method[J]. Journal of Shanghai Jiaotong University, 2012, 46(09): 1355-1360.

References

［1］Hwang T H, Joo I, Cho S L. Detection of traffic lights for visionbased car navigation systems［C］//First Pacific Rim Symposium on Image and Video Technology. Berlin: SpringerVerlag, 2006: 682691.
［2］Soetedjo A, Yamada K. Fast and robust traffic sign detection［C］ //IEEE International Conference on Systems, Man and Cybernetics. USA: IEEE, 2005: 13411346.
［3］Gao X W, Podladchikova L, Shaposhnikov D, et al. Recognition of traffic signs based on their colour and shape features extracted using human vision models［J］. Journal of Visual Communication and Image Representation, 2005, 17 (4): 675685.
［4］Gong J W, Jiang Y H, Xiong G M, et al. The recognition and tracking of traffic lights based on color segmentation and CAMSHIFT for intelligent vehicles［C］//IEEE Intelligent Vehicles Symposium. USA: IEEE, 2010: 431435.
［5］Omachi M, Omachi S. Traffic light detection with color and edge information［C］//2009 2nd IEEE International Conference on Computer Science and Information Technology. USA: IEEE, 2009: 284287.
［6］Shen Y H, Ozguner U, Redmill K, et al. A robust video based traffic light detection algorithm for intelligent vehicles［C］//IEEE Intelligent Vehicles Symposium. Piscataway NJ, USA: IEEE, 2009:521526.
［7］De Charette R, Nashashibi F. Real time visual traffic lights recognition based on spot light detection and adaptive traffic lights templates［C］// IEEE Intelligent Vehicles Symposium. Piscataway NJ, USA: IEEE, 2009: 358363.
［8］Chang Y L, Li X B. Adaptive image regiongrowing［J］. IEEE Transactions on Image Processing, 1994, 3 (6): 868872.
［9］Lewis J P. Fast normalized crosscorrelation ［DB/OL］. ［20111108］. http://www.cipprs.org/papers/VI/VI1995/pp120123Lewis1995.pdf.

[1]	JIANG Dong-Dong, HONG Fang-Jun, ZHENG Ping. Droplet Oscillations under AC Electrowetting [J]. Journal of Shanghai Jiaotong University, 2013, 47(04): 513-518.
[2]	HUANG Xiang-Long, ZHANG Xiao-Jing, BAI Guo-Juan, XU Wu, WANG Hai. Residual Strength Analysis of Thin-Walled Structures with Multiple Site Damage Based on Crack Tip Opening Angle Method [J]. Journal of Shanghai Jiaotong University, 2013, 47(04): 519-524.
[3]	LIU Yi-Peng, HU Xue-Yu, CHEN Jia-Luo, WANG Ping-Yang, DU Chao-Hui. Direct Image Correction Algorithm for PIV Measurement of Flowfield within Circular Tube [J]. Journal of Shanghai Jiaotong University, 2013, 47(04): 525-532.
[4]	ZHU Han-Hao, PU Sheng-Chun, ZHANG Hai-Gang, LIU Wei, AN Xu-Dong. Verification of the Calculation of Acoustic Field with Typical Bottom Based on Parabolic Equation in Scaled Tank Experiment [J]. Journal of Shanghai Jiaotong University, 2013, 47(04): 532-537.
[5]	YANG Jing-Jing-1, LIU Yong-Sheng-1, FANG Wen-Jian-1, FANG Jin-1, PENG Lin-1, YANG Zheng-Long-2, GAO Tian-1, GU Min-An-1. Design and Efficiency of Photovoltaic-Thermoelectric Power Generator with Negative Feedback Characteristic [J]. Journal of Shanghai Jiaotong University, 2013, 47(04): 550-554.
[6]	LIU Chen-Yan-1, 2 , PAN Li-1, 2 , ZI Xiao-Chao-2. A Binary-String-Set-Based Algebraic Framework for Policy Composition [J]. Journal of Shanghai Jiaotong University, 2013, 47(04): 579-583.
[7]	PENG Yan-Bin-1, ZHENG Zhi-Jun-1, YU Cheng-Bo-2, LI Ji-Ming-3. Automated Negotiation Decision Model Based on Classifier Fusion [J]. Journal of Shanghai Jiaotong University, 2013, 47(04): 644-649.
[8]	NING Xiao-Lin-1, ZHAO Yi-Fei-2, CHEN Fei-儿1. Index System and Prosperity Indices of Global Shipping Industry and Applied Research [J]. Journal of Shanghai Jiaotong University, 2013, 47(03): 417-422.
[9]	KONG Xiang-Qiang-1, LIN Lin-1, LI Ying-1, ZHANG Dong-2, YANG Qian-Ming-1. Effect of Refrigerant Charge on the Performance of a Direct Expansion Solar Assisted Heat Pump Water Heater Using R410A [J]. Journal of Shanghai Jiaotong University, 2013, 47(03): 370-375.
[10]	HUANG Kang, 欧Yang-Guang-Yao , AN Shi-Jie, CHANG Han-Bao. Design and Simulation Research on Double-Staggered Arranged Porous Nozzle [J]. Journal of Shanghai Jiaotong University, 2013, 47(03): 434-437.
[11]	WANG Lei, GU Meng-Di. Optimal Reinsurance-Investment Strategies in a Mean-Reverting Market [J]. Journal of Shanghai Jiaotong University, 2013, 47(03): 438-443.
[12]	XIONG Hao, YAN Hui-Li, ZHOU He-Ping, LIU Wu-Sheng. Real-Time Optimization Strategy of the Multi-Period Dynamic Vehicle Routing Problems [J]. Journal of Shanghai Jiaotong University, 2013, 47(03): 450-453.
[13]	HONG Jiang-Tao-1, YANG Xiao-Yan-1, CHEN Jun-Fang-2. An Empirical Research on the Relationship among Knowledge Management, Knowledge Competence and Core Competence [J]. Journal of Shanghai Jiaotong University, 2013, 47(03): 444-449.
[14]	LI Bin-a, JI Jian-Hua-a, b , LI Guo-Wei-a. Study on Supply Chain Robustness Index Mode Considering Profits and Risks [J]. Journal of Shanghai Jiaotong University, 2013, 47(03): 484-488.
[15]	XU Shi-Yin, HUANG Xiu-Chang, HUA Hong-Xing. Study on the Band Structure of Hexagonal Chiral Structures [J]. Journal of Shanghai Jiaotong University, 2013, 47(02): 167-172.