Rapid and accurate traffic signal lamp identification method based on prior information

The invention aims to provide a traffic signal lamp rapid and accurate identification method based on prior information, and belongs to the technical field of intelligent traffic information detection. In order to solve the problem that an existing HSV color space recognition method is difficult to select a verification component range to make a recognition result accurate, the method adds a step of detecting a main body area of a traffic signal lamp, and then sums the gray value of the main body area to judge the type of the traffic signal lamp so as to complete recognition. According to the method, high recognition accuracy can still be kept under the condition that serious color distortion occurs in the image, and the adaptive capacity in different environments and weather is improved; meanwhile, a machine learning or deep learning method is not adopted, so that the requirement on equipment is greatly reduced, long-time model selection and training are avoided, and meanwhile, the method has the advantages