Pavement crack detection method fusing Gabor filter and convolutional neural network

Abstract

The invention discloses a pavement crack detection method fusing a Gabor filter and a convolutional neural network. The method comprises the following steps: acquiring a pavement image; preprocessingan acquired image; dividing a preprocessed image into image blocks and marking the image blocks, and dividing the marked image blocks into a training set and a test set; and inputting the pavement image blocks into a designed convolutional neural network to obtain a pavement crack detection result. Pavement crack detection is mainly based on the characteristics of texture information; a Gabor filter is fused into a convolutional neural network, road surface image texture features are extracted by using the Gabor filter, a texture feature graph is classified by using a residual network, and thesensitivity of the network to texture information can be improved by introducing the Gabor filter, so that the crack identification precision is improved.

Description

technical field [0001] The invention belongs to the technical field of traffic pavement image detection, and in particular relates to a method for detecting pavement cracks by combining a Gabor filter and a convolutional neural network. Background technique [0002] As one of the main forms of road surface diseases, pavement cracks not only pose a direct threat to road safety, but also may become the cause of other road diseases. Timely detection and repair of pavement cracks is an important part of road maintenance. The traditional crack detection method is mainly manual detection, which is greatly affected by subjective factors, and has high labor costs and low efficiency, so it is difficult to meet the needs of information timeliness. [0003] In recent years, image-based automatic pavement crack detection technology has become the main detection method. High-speed digital cameras are used to collect road surface information, and image processing technology is used to de...

AI Technical Summary

Problems solved by technology

Traditional crack detection methods, such as the threshold segmentation method, contain a large number of empirical parameters that need to be manually set. The fixed parameters make this type of method less robust, and it is difficult to effectively detect pavement images with complex noise, uneven illumination, and shadow occlusion. detection, unable to meet the needs of timely and efficient road maintenance

Images