Hierarchical traffic sign identification method based on quick dichotomous convolutional neural network

Abstract

The invention belongs to the technical fields of computer application and computer vision and provides a hierarchical traffic sign identification method based on a quick dichotomous convolutional neural network. According to the method, a quick dichotomous convolutional neural network structure is designed to relieve the problems of a large calculated quantity and time consumption in the convolution process, and a hierarchical classification algorithm based on the quick convolutional neural network is proposed. According to specific application, at a rough classification stage, a traffic signimage is preprocessed to obtain a region of interest first, and then the region of interest is input into the quick dichotomous convolutional neural network and roughly divided into a plurality of large categories; and at a fine classification stage, traffic signs are preprocessed again according to characteristics of all the categories, the quick dichotomous convolutional network is further utilized to perform fine classification on the processed signs, and a final result is obtained. The result shows that the proposed algorithm has a high classification correct rate, meanwhile has a high processing speed and is more suitable for a traffic sign identification system with a high instantaneity requirement.

Description

technical field [0001] The invention belongs to the technical field of computer application and computing vision, and relates to an improved structure of a convolutional neural network and its application in traffic sign recognition. The invention proposes a hierarchical traffic sign recognition method based on a fast bipartite convolutional neural network. The main innovation lies in the design of a fast bipartite convolutional neural network structure to alleviate the computationally intensive and time-consuming problems of the convolution process. Then based on the network structure, a hierarchical traffic sign recognition method is proposed. This method not only has a higher classification accuracy rate, but also has a faster processing speed, and is more suitable for traffic sign recognition systems that require high real-time performance. Background technique [0002] Traffic sign is a kind of public sign with remarkable color and shape characteristics, which plays th...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved in the present invention is how to use the convolutional neural network to solve the problem of traffic sign recognition. The key point is to improve the convolutional neural network to overcome the large amount of calculation and time-consuming problems of the convolution process, thereby improving real-time performance. The difficulty lies in how to improve the real-time performance while still ensuring high recognition accuracy

Images