基于色彩恒常性算法的交通标志检测

Traffic Signs Detection Based on Color Segmentation Algorithm

文章对由于颜色退化、光线减弱所导致的交通标志漏检问题提出一种算法。该算法首先用色彩恒常性对交通标志的图像增强色彩,然后将其转换到HSV(hue-saturation-value)彩色空间进行颜色分割。标志检测实验结果表明,该算法能够有效地克服光照减弱、颜色退化对交通标志颜色的影响,从而有效提高交通标志的检测率。

An algorithm is presented with respect to the variations of the paint on the signs and the weakening light conditions which are the important factors resulting false detection of traffic signs. The algorithm used color con- stancy traffic sign image for enhanced color, then convert it to HSV color space for color segmentation. Experimental results of traffic sign detection show that the algorithm can effectively overcome the weakening light, and the paint on the signs on the impact of traffic signs, which effectively improves the detection rate of traffic signs.