Pavement disease detection method and device based on edge detection neural network

Abstract

The invention discloses a pavement disease detection method and device based on an edge detection neural network, and the method comprises the steps: carrying out the pavement disease recognition of an inputted pavement image through employing a first edge detection neural network, and outputting a first disease probability matrix of the pavement image; performing pavement disease identification on the pavement image by using a second edge detection neural network, and outputting a second disease probability matrix of the pavement image; calculating a final disease probability matrix of the pavement image according to the first and second disease probability matrixes; recognizing pavement diseases from the pavement image according to the final disease probability matrix, wherein the firstedge detection neural network and the second edge detection neural network are obtained by pre-training pavement images with common pavement diseases and complex pavement diseases respectively. By applying the method and device, the pavement disease identification accuracy in the actual pavement acquisition image can be improved, the calculated amount in the identification process is reduced, andthe identification efficiency is improved.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method and device for detecting road surface defects based on an edge detection neural network. Background technique [0002] At present, the pavement disease recognition method based on pavement images is mainly realized by extracting image gray features for analysis and local deep learning recognition. [0003] At present, among the analysis methods based on the grayscale image frequency, the detection method based on the dynamic threshold mainly divides the image according to the grayscale value of the image. Since most of the pixels belonging to the cracks are in the range of low gray values, this rule is used to count the gray values ​​of the image, and the threshold is dynamically selected according to the statistical results, and finally the image is binarized to segment the cracks in the picture. [0004] Under ideal lighting conditions, the grayscale difference betwee...

AI Technical Summary

Problems solved by technology

However, in the case of uneven illumination, the gray information and clarity of cracks are not uniform, so it is difficult to find an algorithm that can fit crack characteristics under various environmental conditions using digital image processing methods

Generally speaking, digital image processing methods are used in actual road surface collection images with low recognition accuracy

[0009] 2. The amount of calculation in the identi

Images