Traffic signal lamp automatic detection and recognition method based on visual sense

Abstract

Provided is a traffic signal lamp automatic detection and recognition method based on the visual sense. A hierarchy framework combining color space linear filtering and gradient direction histogram features is adopted, and a detection and recognition model of typical traffic signal lamps in China is established through training. The method comprises a training stage and a testing stage, in the training stage, collection of a training dataset, determination of a target color spectrum and determination of classification model parameters are completed, in the testing stage, detection and recognition of the traffic signal lamps are achieved by utilizing the models obtained in the training stage, and the testing stage comprises screening of candidate areas of the traffic signal lamps, filtering of connected domains, determining of shapes of the traffic signal lamps and determining of indication directions of the traffic signal lamps. The traffic signal lamp automatic detection and recognition method based on the visual sense overcomes the defects that detection and recognition instantaneity of the traffic signal lamps is poor and the recognition precision is sensitive to illumination and templates in the prior art, achieves better detection and recognition effects, and has wide application prospects in the field of intelligent decision and driver assistant systems of unmanned vehicles.

Description

Technical field: [0001] The invention provides a vision-based automatic detection and recognition method for traffic lights, which relates to a hierarchical structure that uses color space linear filtering and gradient direction histogram features to construct an automatic detection and recognition method for typical traffic lights in my country through training. The invention belongs to the technical field of specific target detection and recognition. Background technique: [0002] Intelligent Transportation System (ITS for short), as the development direction of the future transportation system, is an effective integration of advanced information technology, data communication transmission technology, control technology, electronic sensor technology and computer technology, etc. It is a real-time, accurate and efficient comprehensive transportation and management system that plays a role in a wide range and in all directions. As an important branch of the intelligent tran...

AI Technical Summary

Problems solved by technology

In the candidate area screening stage, since the traffic signal light is an active light-emitting unit, the light-emitting unit of the traffic signal light in the video image obtained by the camera is often distorted in color. The robustness of illumination changes and color distortion is not good, and the morphological filtering method can only target circular light-emitting units, and the real-time performance is not good; in the shape confirmation stage, the template matching method is mainly used at present. This method has a great dependence on the selection of templates, and in order to achieve universality, the template space is large, so it is difficult to achieve high accuracy in terms of real-time and universality.

Images