A Fast Traffic Light Detection Algorithm for Autonomous Vehicles

Abstract

The invention discloses a traffic light fast detection algorithm applied to unmanned vehicles, comprising the following steps: S1. Select red and green candidate areas according to the values ​​of each channel of each frame image collected, and the candidate areas include Several connected domains; S2. According to the position of the traffic light area in the previous frame image and the data of the sensor, combined with the height range of the traffic light, predict the position of the traffic light area in the current frame image to form a prediction area; S3. For the current frame image The shape and color of the connected domain are identified. When the connected domain of the same shape and color appears in the prediction area, the connected domain is a traffic light area. The present invention uses the image of the last moment (the last frame) and the image of the present moment (this frame) collected by the camera, and uses the sensor to collect the curve of the vehicle speed between the two moments, the steering angle of the car and the time change, and the two moments The angle between the camera and the horizontal plane, using the height of the traffic light in line with the characteristics of the national standard, achieves the purpose of narrowing the detection range and improving the detection accuracy of the traffic light color and shape detection.

Description

technical field [0001] The invention relates to the field of traffic information detection, in particular to a traffic light fast detection algorithm applied to unmanned vehicles. Background technique [0002] Most of the existing traffic light detection and recognition technologies use computer graphics image processing technology, machine learning and other technologies. The general idea is nothing more than: after the color space conversion, use a certain threshold to extract areas that may be traffic lights, and then use complex algorithms or machine learning methods to remove a certain degree of non-traffic light areas. The disadvantages of these methods are very obvious. Often, traffic cannot be detected, or the false scene rate is too high. For example, LED display signs on the side of the road and red objects under sunlight will be detected as traffic lights. Especially at night, it is powerless; at the same time, the high complexity of the algorithm leads to long p...

AI Technical Summary

Problems solved by technology

The disadvantages of these methods are very obvious. Often, traffic cannot be detected, or the false scene rate is too high. For example, LED display signs on the side of the road and red objects under sunlight will be detected as traffic lights. Especially at night, it is powerless; at the same time, the algorithm complexity is too high and the processing time is too long, which is also a fatal shortcoming. After all, in automatic driving equipment, very fast detection and recognition capabilities are required.

[0003] The methods mentioned above are applicable to a relatively general environment. The devices using the above algorithms are only "driving assistance devices", which only serve as reminders and warnings, and cannot replace humans, so they are not suitable for automatic driving. in the car system

Images