The detection algorithm of existing traffic signs was improved, and the implementation of traffic sign detection and recognition was described in detail. This article mainly contains the following: Through targeted feature extraction, a trained cascaded classifier is used to obtain the location of traffic signs. Combined with the previous detection results, feature extraction is performed on the specified part of the target. The results are analyzed according to the location of detection or the results of the trained support vector machine are used to classify, and the classification results are obtained to realize the recognition of traffic signs. The total number of samples used for goal training in this article has reached thousands. The test results show that the detection rate of the traffic sign under the trained scene has been more than 90%. The algorithm has been optimized by the multi-thread method and combined with augmented reality to achieve real-time feedback.