Traffic identification method based on color space fusion network and space transformation network

Abstract

The invention belongs to the technical field of advanced aided driving. On the basis of a deep convolutional neural network theory, the invention discloses a traffic identification method based on a color space fusion network and a space transformation network. Traffic sign images of an RGB color space, an HSV color space, a YIQ color space and a grayscale image space are fused by constructing thecolor space fusion network so as to enrich features extracted by a convolutional neural network; improving the spatial invariance of the convolutional neural network to the input image by using a spatial transformation network; the global maximum pooling is used to replace the full connection layer to reduce the parameter quantity of the convolutional neural network. Experiments show that the traffic sign recognition method based on the color space fusion network and the space transformation network designed by the invention can obtain a higher recognition rate under the condition of fewer parameters.

Description

technical field [0001] The invention belongs to the technical field of advanced automobile driving assistance, and in particular relates to a traffic sign recognition method, in particular to a traffic recognition method based on a color space fusion network and a space transformation network. Background technique [0002] Traffic sign recognition is one of the key technologies to realize the advanced assisted driving system of automobiles, and it is also an effective way to ensure the safety of the driver's life and property and reduce traffic accidents. [0003] At present, traffic sign recognition methods mainly include recognition methods based on template matching algorithms, recognition methods based on color and shape features, recognition methods based on traditional machine learning, and recognition methods based on convolutional neural networks. The traffic sign recognition based on the template matching algorithm has a high accuracy rate for the signs that are wel...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problems that the existing convolutional neural network cannot make full use of the color characteristics of traffic signs and the lack of spatial invariance when used for traffic sign recognition, the number of parameters is large and the recognition rate is not high, and a new method is invented. It is necessary to design a traffic sign recognition method based on color space fusion network and space transformation network with less parameters and high recognition rate

Images