Traffic light recognition method

Abstract

The invention discloses a traffic light recognition method. The method comprises steps as follows: performing binarization on the brightness component of the HSV color space of a traffic light target area in advance, acquiring a binarization result and extracting connected domains representing a traffic light bright area from the result through switching between an RGB space gray binarization method and an HSV color space binarization method on the basis of the area characteristic of the maximum connected domain, meanwhile, calibrating horizontal coordinates of a traffic light target by using difference between bright components of traffic light images in front and back frames, then designing a classifier, acquiring a classification recognition result of the traffic light target according to the number, colors and position characteristics of the extracted connected domains, and finally, when the traffic light is a yellow light, calibrating the vertical position of the traffic light target by using the vertical coordinate of the yellow light. The method has the advantages that the method is simple to implement, high in recognition accuracy, high in adaptability to different crossroad environments and low in computational complexity, fewer resources are occupied, and positions of the traffic lights can be calibrated.

Description

technical field [0001] The invention relates to computer vision recognition technology, in particular to a traffic light recognition method. Background technique [0002] With the progress of society and the development of economy, the intelligent transportation system formed by introducing pattern recognition and electronic information technology has attracted the general attention of governments and transportation departments of various countries. The recognition of traffic signs is an important part of the intelligent transportation system and an important academic branch of machine learning research, which involves many technical fields such as pattern recognition, image processing, digital signal processing, artificial intelligence, communication technology and information theory. At present, the identification of the status of traffic lights mainly relies on the video surveillance system installed at traffic intersections to obtain information such as whether the vehic...

AI Technical Summary

Problems solved by technology

The traffic light recognition algorithm based on SVM support vector machine needs to train a large number of samples of representative environmental conditions such as day, night, shaking, reflection, color cast, etc. according to the different expressions of traffic light image information in different environments. In the case of strong reflection and color shift, still collecting information on the traffic light target will lead to a large amount of error information and the calibration of the traffic light target position cannot be achieved; the traffic light recognition algorithm based on template matching also requires various representative environments. The image is used as a template, and for different intersections, a new set of templates has to be regenerated. If the environment of the current intersection changes drastically, a large amount of wrong identification information will be generated if the template update lags behind, and the target position calibration of traffic lights cannot be achieved.

Images