Road Surface Defect Detection Method Based on Texture Feature Extraction

Abstract

A method for detecting road surface defects based on texture feature extraction provided by the present invention includes the following steps: acquiring an image with road surface defects and performing grayscale processing to form a grayscale image of road surface defects; performing texture feature extraction on the grayscale image of road surface defects, The feature values ​​are extracted to form the texture feature vector, and the gray-scale images of road defects represented by the texture feature vector of the same defect category are divided equally to form a training set and a test set; Extraction; the softmax layer logic classification layer is stacked on the stacked self-encoder to form a deep neural network, and the high-dimensional abstract features are trained through the deep neural network, and the classification and recognition of the road grayscale images in the test set are completed; it can detect road surface defects Accurate detection improves the accuracy of results.

Description

technical field [0001] The invention relates to a road surface defect detection method, in particular to a road surface defect detection method based on texture feature extraction. Background technique [0002] The detection of road surface defects is an important guarantee to ensure the normal operation of traffic. In the prior art, the detection of road surface defects includes the following methods: ultrasonic wave, detection radar, laser triangulation, manual detection, machine vision, etc.; the detection methods in the above , there are the following defects: First, there are many manual interventions, which waste manpower, low efficiency, high work intensity, and it is difficult to achieve traffic isolation during the detection process, which brings serious safety hazards to the staff; secondly, the existing detection methods It is difficult to guarantee the accuracy of the detection results: due to the influence of the road conditions by the environment, there are ser...

AI Technical Summary

Problems solved by technology

[0002] The detection of road surface defects is an important guarantee to ensure the normal operation of traffic. In the prior art, the detection of road surface defects includes the following methods: ultrasonic wave, detection radar, laser triangulation, manual detection, machine vision, etc.; the detection methods in the above , there are the following defects: First, there are many manual interventions, which waste manpower, low efficiency, high work intensity, and it is difficult to achieve traffic isolation during the detection process, which brings serious safety hazards to the staff; secondly, the existing detection methods It is difficult to guarantee the accuracy of the detection results: due to the influence of the road conditions by the environment, there is serious interference in the parameters in the detection in the natural environment. In order to propose interference, the calculation process is complicated and difficult

Images