Traffic sign recognition method, device and equipment and storage medium

Abstract

The invention discloses a traffic sign identification method. The identification method comprises the steps of obtaining a to-be-identified image; preprocessing the to-be-identified image and generating an image pyramid; respectively extracting edge features and texture features of each layer of image in the image pyramid; performing feature association fusion on the edge features and the texturefeatures to obtain traffic sign information in the to-be-identified image; and performing identification processing based on the traffic sign information and a traffic sign classifier to obtain a traffic sign category corresponding to the traffic sign information. The invention further discloses a traffic sign recognition device and equipment and a storage medium. According to the invention, the position and size of the traffic sign can be better detected, and the detection capability of the traffic sign area is improved; and the recognition speed and the recognition rate can be improved.

Description

technical field [0001] The invention relates to image recognition technology, in particular to a traffic sign recognition method, device, equipment and storage medium. Background technique [0002] At present, traffic sign detection algorithms are mostly based on two types of algorithms: traditional algorithms and deep learning algorithms. Traditional algorithms are based on artificially designed feature operators such as image edges, shapes, or textures to extract and classify objects. This method is vulnerable to light. , deformation, occlusion and other factors, usually by a higher misrecognition rate. The deep learning algorithm is based on a deep neural network. Through layer-by-layer feature extraction and sampling processing, the classification performance is powerful, but it requires massive data and strong hardware processing capabilities, high power consumption, and high cost. Contents of the invention [0003] In order to solve the above technical problems, in ...

AI Technical Summary

Problems solved by technology

[0002] At present, traffic sign detection algorithms are mostly based on two algorithms: traditional algorithms and deep learning algorithms. Traditional algorithms are based on artificially designed feature operators such as image edges, shapes, or textures, and feature extraction and classification of targets. This method is vulnerable to light. , deformation, occlusion and other factors, usually caused by a higher misrecognition rate

The deep learning algorithm is based on a deep neural network. Through layer-by-layer feature extraction and sampling processing, the classification performance is powerful, but it requires massive data and strong hardware processing capabilities, high power consumption, and high cost.

Images