Pavement　disease　identification　based　on　target　detection　and　image　segmentation　is　a　common　method　in　the　maintenance　of　pavement　diseases,　which　has　great　study　value　for　the　repair　of　road　disease　and　road　health　status　assessment.　The　study　use　pavement　disease　as　the　target,　building　segmention　data　set　and　detection　data　set　which　contains　pothole,　lateral　crack,　longitudinal　crack　and　mesh　crack.　For　the　detection　task,　the　pavement　disease　detection　model　is　based　on　the　improved　YOLOv5,　and　the　model＇s　mAP　is　94.2%.　For　the　segmentation　task,　pavement　disease　segmentation　model　is　based　on　the　improved　U-Net,　and　the　model＇s　mIOU　is　94.4%.　©　2023　ACM.