Tunnel lining crack detection method and system based on deep learning and electronic equipment

The invention relates to the technical field of image processing and recognition, and particularly discloses a tunnel lining crack detection method and system based on deep learning and electronic equipment, and the method comprises the steps: obtaining the image data of the surface of a tunnel lining, carrying out the marking, size adjustment, normalization and image brightness equalization processing of the image data, and obtaining the image data of the surface of the tunnel lining; and making a label according to the frame selected interference factor to obtain a marked image data set, obtaining diagonal bounding box data based on the marked image data set and the crack position identification model, and performing threshold segmentation on the image data sample based on the diagonal bounding box data to obtain a crack sample. A binary image is obtained based on a crack sample crack size identification model, the binary image is input into a contour processing algorithm model to obtain statistical data of