A traffic sign deep learning mode identification method

Abstract

The invention discloses a traffic sign deep learning mode identification method. The method includes the following steps: pretreatment is performed on a test sample and, a training sample of a trafficsign image, a residual deep learning network based on the multiscale characteristic weight operation fusion of a convolution nerve network is designed, the characteristic is automatically extracted by the network in order to eliminate the artificial trace mainly through training, and identification is performed on the traffic sign test sample by using a deep color characteristic trained classifier. The image characteristic weight operation combining with the multiscale convolution fusion network is applied to the traffic mode identification technology, the training efficiency of the network is substantially improved, and the problem that the accuracy and the real-time performance are not ideal, the network structure is complex, the training time is long, the stability and the robustness are bad encountered in the traffic sign identification method can be effectively solved. The image recognition accuracy of the trained network in 43 kinds of traffic signs reaches 97%.

Description

technical field [0001] The invention relates to the field of traffic sign recognition, in particular to a method for deep network model image pattern recognition. Background technique [0002] During the driving process of the car, the pattern recognition of the traffic sign image is an important part of the intelligent traffic control system. In this link, the recognition accuracy of different traffic command states plays a vital role in the subsequent driving control effect of the car. Different types of traffic data in the road scene environment are collected by camera for identification, and the type of current traffic instruction status is judged, which is fed back to the control mechanism of the car, and the safe driving of the car is guaranteed by controlling the operation of the executive body, and finally the smart car meets the requirements. The production standard of unmanned driving, so we should seek and study the pattern recognition method of high-precision tra...

AI Technical Summary

Problems solved by technology

[0007] To sum up, there is no effective solution to the problems of low accuracy, redundant parameters and overfitting of traffic sign recognition in the prior art.

Images