Road sign automatic classification method and system based on convolutional neural network

The invention discloses a road sign automatic classification method and system based on a convolutional neural network, and the method comprises the steps: constructing a road sign automatic classification detection model based on the convolutional neural network, and collecting a video of a to-be-recognized road sign, taking the video of the to-be-identified road signboard as the input of the road signboard automatic classification detection model, and outputting a classification result corresponding to the video of the road signboard by the road signboard automatic classification detection model; the road sign automatic classification detection model is constructed based on the convolutional neural network, extraction of features of different types of road signs can be automatically completed, the problems that much manual intervention is needed in the earlier stage, the accuracy is low, and the speed is low due to the fact that a traditional image processing method is used are solved, and in addition, by c