Pavement disease detection model training method and device and computer equipment

Abstract

The invention relates to a pavement disease detection model training method and device and computer equipment. The method comprises the following steps: acquiring a plurality of pavement images; detecting a disease image in the plurality of pavement images, wherein the disease image is a pavement image with diseases, and a plurality of disease images are provided; marking the disease image according to the disease, and generating a mask image of the disease image according to the marked content; obtaining a training data set of the pavement disease detection model according to the disease image and the mask image of the disease image; training the pavement disease detection model based on the training data set to obtain a trained pavement disease detection model; and using the trained pavement disease detection model for performing pavement disease detection on a to-be-detected pavement image. By adopting the method, all pavement diseases in the to-be-detected pavement image can be accurately identified.

Description

technical field [0001] The present application relates to the technical field of road detection, in particular to a road surface disease detection model training method and device, a road surface disease detection method and device, a computer device and a storage medium. Background technique [0002] Pavement disease refers to various defects such as damage and deformation that appear on the cement or asphalt pavement after it has been used for a period of time. Timely detection of pavement disease can avoid cracks, potholes, subsidence, etc. on the road. [0003] At present, there are mainly two methods for road surface disease detection. One is to collect road surface data through road inspection vehicles and manually detect the collected road surface data. The other is to use computer vision technology to automatically detect road surface diseases. [0004] However, when using the method of road inspection vehicles to collect data, it is necessary to manually detect and ...

AI Technical Summary

Problems solved by technology

[0004] However, when using the method of road inspection vehicles to collect data, it is necessary for personnel familiar with road surface diseases to perform manual detection and classification. In the case of a large amount of data, there are problems of low detection efficiency and high detection cost; if computer vision is used for Automatic detection, because it needs to extract the features of the image through the artificially designed feature model, the robustness and generalization ability are poor. When the road surface disease is complicated and there is texture noise in the road surface image, it is impossible to accurately identify all road surface diseases.

[0005] Therefore, the current pavement disease detection technology has the problem of not being able to accurately identify all pavement diseases

Images