The recognition of traffic signs plays an important role in the safe driving of vehicles, especially in the presence of light changes and occlusions, the automatic recognition of traffic signs with high accuracy and good real-time performance needs to be solved urgently. Among the deep learning algorithms, YOLOV3 and Faster-RCNN have achieved excellent target detection performance. Compared with traditional feature detection and recognition methods, the use of YOLOV3 algorithm helps to solve the problem of small target detection, traffic sign recognition under the conditions of light changes, partial occlusion, etc. It is the main way to improve the performance of automatic driving and unmanned driving in the future.