Method and device for identifying traffic lights

Abstract

The present application provides a method for identifying traffic lights, the method comprising: acquiring a color photographed image containing traffic lights; converting the color photographed image into a grayscale image; position information of the traffic signal light, and obtain the position information of the traffic signal light in the color photographed image according to the position information of the traffic signal light in the grayscale image; according to the position information of the traffic signal light in the color photographed image Determine the current indication state information of the traffic signal light. By using the method provided in the present application, it is possible to realize accurate positioning of the traffic signal lights and to accurately identify the state of the traffic signal lights. The present application also provides an identification device for a traffic signal light.

Description

technical field [0001] The present application relates to the technical field of automatic driving, and in particular to a method and device for identifying traffic lights. Background technique [0002] The identification of traffic lights refers to the identification of the state of traffic lights on the basis of accurately locating the position of traffic lights. For example, red lights, green lights, yellow lights, etc.) to determine the indication status of the traffic signal lights (such as allowed to pass, prohibited to pass, etc.). The recognition of traffic lights can be used to judge the traffic status at traffic intersections, which is of great significance in automatic driving, navigation prompts, etc. [0003] At present, the identification of traffic lights mainly depends on the deep learning method. The road information in front of the vehicle is obtained through the camera installed on the vehicle, and then the color image captured by the camera is input into...

AI Technical Summary

Problems solved by technology

[0003] At present, the identification of traffic lights mainly depends on the deep learning method. The road information in front of the vehicle is obtained through the camera installed on the vehicle, and then the color image captured by the camera is input into the neural network model for deep learning to obtain the position of the traffic lights, and then Obtain the state of the traffic signal lights, but because the outline of the traffic signal lights in the color image captured by the camera is often blurred, this reduces the accuracy of the traffic signal light morphological feature extraction during the deep learning process, thus reducing the accuracy of the traffic signal lights. The accuracy of positioning, which leads to the inability to accurately identify the status of the traffic lights

Images