Bolt step-by-step detection method based on deep learning

The invention discloses a bolt step-by-step detection method based on deep learning. The method comprises the following steps: S1, selecting a YOLO v5 network as a deep learning network for identifying and segmenting a bolt in an image; s2, establishing a bridge bolt identification data set, and evaluating a bolt image to be detected; after the bolts are marked manually, the expanded data set is adopted to train the selected different YOLO v5 network models, and according to training results of the YOLO v5 network models, an optimal model is selected as a bolt detection model; s3, identifying the bolt by the bolt detection model, recording the position of the bolt, and segmenting the bolt from the image according to an identification result; and carrying out classification and discrimination on the segmented single bolt image through an efficientNet network. According to the invention, the health condition of the bridge bolt can be accurately and automatically detected, and the detection speed is high. 本发明公开了