A real time traffic sign recognition method in complex environment
1.College of Energy and Power, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu 210016, China; 2.Hefei General Machinery Research Institute, Hefei, Anhui 230031, China
Abstract：A traffic sign recognition method was proposed to solve the nonuniform exposure in complex traffic environments. The improved Log Gabor wavelet was used to extract feature of traffic signs at multi scales. The phase consistency was calculated to overcome the influence of environmental illumination. Support vector machine (SVM) was used as multiple targets classifier to be tested in the authoritative traffic sign database of German traffic sign recognition benchmark (GTSRB). The results show that the average recognition rate of the proposed method for 6 main category is 98%, which is better than those of the traditional algorithms. The computational efficiency with Intel dual core CPU 2.4 GHz is 28 frames·s-1, which satisfies the requirement in realtime. The proposed method overcomes the problem of uneven exposure in complex traffic environment, which can achieve good robustness.
2013, Vol. 34 
