improved LeNet-5 fusion network traffic sign recognition method for assisting driving

Abstract

improved LeNet-5 fusion network traffic sign recognition method for assisting driving is disclosed. The method comprises the following steps of constructing a traffic sign image data set and constructing a training set and a test set according to the traffic sign data set, .secondly, constructing a convolutional neural network CNN; substituting the training set image data into a convolutional neural network CNN for training, and storing the trained model; And finally, substituting the test set image data into the trained model for prediction to obtain a prediction result.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to an improved LeNet-5 fusion network traffic sign recognition method for driving assistance. Background technique [0002] In the current information age, with the development of urban modernization, the number of cars has increased sharply, traffic congestion, and frequent traffic accidents. Therefore, improving the safety of vehicles has become the primary issue of modern urban intelligent transportation systems. In recent years, traffic sign recognition technology in assisted driving has gradually attracted extensive attention from researchers at home and abroad. At present, the main algorithms of traffic sign classification and recognition include statistical classification method, template matching method, sparse coding method, neural network method and genetic algorithm, etc. Among them, the traffic sign recognition algorithm based on convolutional neural network has been hi...

AI Technical Summary

Problems solved by technology

However, when the LeNet-5 network structure classifies and recognizes multi-category targets such as traffic sign images, the accuracy rate is not high.

Images