Method for improving traffic sign recognition precision in extreme weather and environment

Abstract

The invention discloses a method for improving the traffic sign recognition precision in extreme weather and environment, which is based on a YoV5 target detection model, integrates a focusing module, a cross-stage local fusion module and a spatial pyramid pooling structure, and can better extract feature map information from local features for traffic sign images with poor light, and the feature map more accurately expresses the image. For a small number of training data, the expressions of the traffic signs in different environments are simulated by using Gaussian noise, adding salt and pepper noise, reducing brightness, sharpening an image, reducing the size and the like in proportion, and the traffic signs are copied to a target-free picture by using a copying-pasting method, so that a data set is greatly enriched. By using the method provided by the invention, different image modes under different resolutions can be captured more easily, and the features of the target can be extracted and fused to the greatest extent; and meanwhile, convergence is quicker and more accurate, fewer positioning errors exist, and more accurate prediction is generated.

Description

technical field [0001] The invention relates to the technical fields of traffic and computer vision, in particular to a method for improving the recognition accuracy of traffic signs under extreme weather and environments. Background technique [0002] The traffic signs deployed along the road carry the specific management content and behavior rules of the road traffic. At present, autonomous vehicles mainly obtain such information through their own sensing equipment. Due to technical limitations, in some complex road conditions and environments, the image detection and recognition of traffic signs is affected by extreme weather such as snow, fog, dark clouds, dust, rain, etc., resulting in low visibility, as well as strong sunlight and street lighting at night, Under the influence of extreme conditions such as poor light at night, self-driving vehicles are easy to miss or difficult to recognize the traffic information carried by traffic signs and markings, and there are cer...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the detection accuracy of existing target detection technology for traffic signs under extreme weather is not high enough, the inadequacies of current target detection methods are analyzed in depth, combined with the problem of small sample data in the data set, the method of enhancing the data set is adopted, which greatly enriches the The amount of training sample data is reduced. At the same time, the present invention is improved based on the Yolo V5 model. Aiming at the problem to be solved by the present invention, a hybrid convolution and attention feature fusion are creatively added, and a focused high-efficiency IOU loss function is used to better Detect traffic signs under extreme adverse conditions such as rain, snow, fog, night, backlight, etc.

Images