Traffic sign detection method in natural scene

Abstract

The invention provides a traffic sign detection method in a natural scene. The method comprises the steps that a detection image shot in the natural scene is acquired; luminance information of the detection image is subjected to statistical analysis, different luminance areas are divided according to grade luminance threshold values, pixel ratios of different luminance areas are calculated respectively, and the image is divided into a dark scene, a bright scene, a backlighting scene and a normal scene according to all the pixel ratios and scene classification threshold values; gamma parameter values are selected according to scene classification results, and an adaptive Gamma enhancement algorithm is adopted to perform image enhancement processing on a classification image; a partitioning algorithm is selected to perform image color partitioning according to different scenes in an RGB color space to obtain suspected target areas; a grayscale image obtained after color partitioning is subjected to binarization processing to obtain the suspected target areas after binarization; and the suspected target areas are screened through a feature screener to position traffic sign regions. Through the method, robustness and real-time performance of sign detection can be both considered.

Description

technical field [0001] The invention relates to the technical field of sign recognition and detection, in particular to a traffic sign detection method in a natural scene. Background technique [0002] Traffic signs play an important role in ensuring the orderly passage of road traffic. During driving, accurate identification of traffic signs is of great significance to improve road driving safety. Ignoring traffic signs may lead to traffic accidents. For unmanned vehicles, if the vehicle cannot automatically detect and accurately recognize traffic signs, it cannot be truly unmanned. At present, in the fields of computer vision, pattern recognition, intelligent robots and intelligent transportation systems, traffic sign detection and recognition technology has been widely studied, which has important academic significance and practical value. The application of traffic sign detection and recognition in real life still faces huge challenges, including: ADAS, automatic drivin...

AI Technical Summary

Problems solved by technology

However, the RGB color space is very sensitive to illumination changes, which can easily cause missed or wrong detections. Therefore, how to overcome this problem has always been the focus and difficulty of color segmentation in RGB space.

In addition, the Hough transform also has the disadvantage of slow calculation, which cannot meet the real-time requirements

(2) The radial symmetric fast detection algorithm uses the symmetry of triangles, squares, rhombuses, and circles to extract target areas. However, for deformed targets, it is exposed to insufficient robustness

But for the complex interference of urban traffic, the robustness cannot be guaranteed

(3) The neural network is to design a neural network feature extractor for color and shape features and then use fuzzy logic to fuse them, but this method has a large amount of calculation and cannot meet the real-time requirements

(4) Adaboost classifier effectively combines color and local feature information to realize traffic sign detection, but it takes a long time for online calculation in complex real scenes, which cannot meet the real-time requirements

(5) The combination of HOG and SVM classifier is the HOG feature of each color component of the component, which effectively fuses color information and edge information as the input feature of the SVM classifier, but this process takes a long time and cannot meet the real-time requirements

[0007] None of the above research methods can take into account the robustness and real-time performance of sign detection, and often cannot meet the real-time requirements under the premise of ensuring robustness and improving detection accuracy; or under the premise of ensuring real-time Insufficient robustness

Images