Pavement crack segmentation method based on dense connection strategy and image gradient

The invention provides a pavement crack segmentation method based on a dense connection strategy and an image gradient, and belongs to the technical field of pavement crack detection, and the method comprises the steps: constructing a pavement crack segmentation model which comprises a feature encoder module used for outputting a feature map; the feature enhancement module is used for receiving the feature map and outputting an enhanced feature map; the feature decoder module is used for converting the enhanced feature map into a target image; the edge refinement device module is used for converting the pavement image into a real edge gradient image by using a Sobel operator; the image splicing module is used for splicing the real edge gradient image and the crack image to obtain a pavement crack segmentation image; and respectively inputting the original pavement image into the edge refinement device and the feature encoder module, and outputting a crack segmentation image. The method can segment the pavemen