Multi-target crack defect detection method and device based on AI intelligent camera

The invention discloses a multi-target crack defect detection method and device based on an AI intelligent camera, and the method comprises the steps: shooting a first image covering a plurality of detection regions on a same detection station through a single AI intelligent camera, obtaining the segmentation images and workpiece types of a plurality of target workpieces from the first image through a deep learning segmentation model, according to the workpiece type, obtaining an opening contour area image from the segmented image of each target workpiece in parallel, then cutting a group of detection images along the opening contour by using a sliding window with a predetermined image size and step length, and sequentially inputting a deep learning defect classification model corresponding to the workpiece type of each target workpiece, and identifying whether crack defects exist in the group of detection images. According to the method, the cost of detecting the hole crack defects of the multiple types of t