Road traffic sign detection and identification method

Abstract

An embodiment of the invention relates to a deep learning-based road traffic sign detection and identification method. The method comprises the steps of calculating convolutional features of a plurality of layers for training set data by utilizing a convolutional neural network; training a region-of-interest suggestion network by utilizing the convolutional features; and training a classification layer and a regression layer of an output layer by utilizing a random gradient descent method based on the convolutional features and candidate boxes obtained by the trained region-of-interest suggestion network.

Description

technical field [0001] The disclosure belongs to the fields of image processing and automatic driving, and in particular relates to a method for detecting and recognizing road traffic signs based on deep learning. Background technique [0002] In today's society, vehicles have become the preferred tool for people to travel, which greatly facilitates people's travel. However, frequent traffic accidents have become an important factor threatening people's lives. According to statistics, in all traffic accidents, accidents caused by people's subjective reasons account for a large proportion. Such as drunk driving, speeding, running a red light, changing lanes at will, and a series of non-compliance with traffic regulations. How to alleviate or even eliminate the problem of frequent traffic accidents, advanced driver assistance systems and unmanned driving came into being. Obtain the environmental information around the vehicle through on-board equipment such as cameras, lida...

AI Technical Summary

Problems solved by technology

This kind of independent module design accumulates errors, which reduces the detection accuracy of road traffic signs

Images