Quick traffic signal lamp detection method based on depth characteristic learning

Abstract

The invention provides a quick traffic signal lamp detection method based on depth characteristic learning, and relates to the fields of image processing, deep learning and intelligent traffic. The method comprises the steps: extracting a traffic signal lamp candidate region from a detected image; and carrying out the classification of the traffic signal lamp candidate region through a convolutionneural network. The adding of the training data can enable a network to apply to various types of complex scenes, thereby improving the recall rate of traffic signal lamps and the detection accuracy.Because a traffic signal lamp candidate region extraction algorithm and a classification network can achieve the higher recall rate and the classification accuracy, the classification network is enabled to adapt to various types of complex scenes. The method is high in detection rate, and meets the real-time requirements of an unmanned vehicle. The number of candidate regions is reduced, the subsequent calculation burden of the classification network is reduced, and the whole detection rate of a system is reduced. The method can be suitable for the traffic signal lamps in various complex scenes, and improves the detection accuracy.

Description

technical field [0001] The invention relates to the fields of image processing, deep learning and intelligent transportation, in particular to a traffic signal light detection method. Background technique [0002] Most of the current traffic signal recognition methods first extract features from images, and then use classifiers or template matching methods for recognition. The most obvious feature of a traffic light is its brightness, color, and shape. Use these features to describe it, set an appropriate threshold to segment the traffic light area from the image, and then use SVM, Adaboost and other classifiers for the extracted target area Classify the target area. [0003] Lu Yayun and others performed RGB normalization processing and clustering operations on the image to extract color features, then processed the image morphologically, and finally compared it with the sample data in the traffic signal database, and those that met the conditions were judged For traffic ...

AI Technical Summary

Problems solved by technology

[0010] In order to overcome the deficiencies of the prior art and solve the problems of small applicable range of artificially designed features, unsatisfactory recall rate and accuracy rate, and slow processing speed in the prior art, the present invention uses a convolutional neural network to automatically learn image depth feature information. characteristics, a fast traffic light detection algorithm based on deep feature learning is proposed

Images