Road traffic sign automatic detection and identification method

Abstract

The invention relates to a road traffic sign automatic detection and identification method. The method is realized based on an automatic detection and identification system. The automatic detection and identification system comprises a traffic sign acquisition module, a traffic sign detection and processing module and a traffic sign identification module. The traffic sign acquisition module is used for collecting driving videos; the traffic sign detection and processing module is used for carrying out processing on the collected videos, detecting image frames containing traffic signs and carrying out extraction on regions of interest; and the traffic sign identification module is used for carrying out classification and recognition on images of the extracted regions of interest. The road traffic sign automatic detection and identification method can identify various types of traffic signs, is high in precision, high in identification accuracy and good in robustness, reduces influence of illumination, geometric deformation and rotation and the like, and has better anti-interference capability.

Description

technical field [0001] The invention relates to a method for automatic detection and recognition of road traffic signs, which belongs to the technical field of environment perception assisted driving. Background technique [0002] With the continuous progress of society and economy, the construction of my country's road traffic network has been continuously and rapidly developed, the number of cars has increased, and the road traffic situation has become more and more complicated. Today, there are many types and quantities of traffic signs on or on both sides of the road. While the driver is concentrating on driving the car, he must also pay attention to various traffic signs set on the road, which puts forward higher requirements for the driver. For novices with unskilled driving skills, ignoring traffic signs often occurs, causing illegal driving and so on. Therefore, designing an automatic detection and recognition system for road traffic signs is of great significance ...

AI Technical Summary

Problems solved by technology

[0022] The above-mentioned methods to achieve multi-classification have their advantages and disadvantages. The problem of the direct method is mainly to solve the optimal solution of multiple planes at one time, which leads to a large amount of calculation and can only be used in small projects.

However, the "one-class-to-remainder method" will inevitably produce a data set skew problem (positive and negative samples are seriously unbalanced) during the training process, which is the situation that most affects the performance of the trained classifier.

Images