Method for identifying traffic sign

Abstract

The invention discloses a method for identifying a traffic sign and belongs to the field of image processing. The method comprises the following steps of: extracting key points from an acquired image to be matched, establishing local feature descriptors, color feature descriptors and position feature descriptors respectively, extracting key points from the image to be matched and a template image in a template image library respectively to form feature point pairs to be matched, and finding a template image with most feature point pairs to be matched by judging whether position feature descriptors, color feature descriptors and local feature descriptors of the feature point pairs to be matched meet certain conditions, wherein the template image with most feature point pairs to be matched is taken as a finally identified traffic sign image for the image to be matched. By the method, the advantage that scale invariant feature transform (SIFT) features are invariant for the scale change and rotation of images is retained, and color and spatial position features of extracted feature quantities can be conveniently distinguished; and the method is extremely effective to the identification of traffic signs with rich colors and different spatial position distribution changes.

Description

technical field [0001] The invention relates to a traffic sign recognition method, which belongs to the fields of image processing, pattern recognition and computer vision. Background technique [0002] At present, the intelligent transportation system is developing rapidly in our country, and the problems of driving safety, urban traffic congestion, and transportation efficiency are all expected to be improved through the transformation of vehicle informatization and intelligence. As an important subsystem of the intelligent transportation system, the traffic sign recognition system based on image detection and processing technology has gradually become a hot spot in the research of intelligent transportation systems at home and abroad. [0003] The traffic sign recognition system is generally completed by capturing the traffic sign image in the outdoor natural scene through the camera installed on the vehicle, and inputting it into the computer for processing. Due to the i...

AI Technical Summary

Problems solved by technology

However, the SIFT feature matching of the entire image will increase the amount of calculation and cannot guarantee the real-time performance of the system

In complex environments, it will lead to more false detection rates

[0005] Defects in the existing technology: due to environmental lighting changes, fading of signal boards, etc., in complex environments, color-based traffic sign recognition systems often cannot detect and recognize correctly. For example, traffic signs with a blue background cannot pass through blue. filter detects

Therefore, it is difficult to deal with environmental lighting changes, occlusion and geometric deformation by classification methods based on color or outline shape.

In addition, the traffic sign recognition method based only on local edge information (SIFT, etc.) is powerless for the recognition of traffic signs with the same geometric pattern but different colors.

Images