Method and device for processing traffic sign symbols

Abstract

The invention relates to a method and a device for processing traffic sign symbols; the method comprises the steps: acquiring obtained streetscape images; generating candidate windows of non-blue traffic sign symbols of the images and the candidate windows of blue traffic sign symbols; classifying and identifying the generated candidate windows by adopting a preset classifier; and judging whether the candidate windows have traffic signs and traffic sign types in the generated candidate windows according to the classification and identification result. According to the method and the device for processing the traffic sign symbols, the traffic signs can be identified rapidly in the images corresponding to complex scenes, the time-consumed sliding of the windows is avoided, the traffic sign identification efficiency is improved and the manpower resource and time cost are also reduced.

Description

Technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for processing traffic sign images. Background technique [0002] At present, with the development of science and technology and the continuous improvement of people's living standards, the number of various vehicles on highways is increasing day by day, which has brought great convenience to people's lives, and the problem of traffic accidents has become more and more serious. The factors that cause traffic accidents are driver misoperation, bad road conditions, and weather influences. According to statistics, 80% of traffic accidents are attributed to driver misoperation. In order to reduce the rate of traffic accidents, the road traffic sign recognition system TSR (Traffic Signs Recognition) came into being. The road traffic sign recognition system recognizes the traffic signs and feeds them back to the driver, so that the driver can understan...

AI Technical Summary

Problems solved by technology

[0003] At present, in the detection and recognition of traffic signs based on street view panoramas, most of the traffic signs are recognized manually, which requires a lot of human resources and time costs.

Most of the existing methods for automatic recognition of traffic signs are based on color for area screening, and the sliding window method is used to identify and classify traffic signs in area images. For high-resolution images, the number of candidate windows will be very large, and it will take a long time

[0004] In addition, the uncertainty of the distance from the shooting point to the traffic sign leads to the uncertainty of the size of the traffic sign, which makes it necessary to try more windows of different sizes, and the huge number of windows makes it very time-consuming to identify traffic signs in an image. Time

Images