计算机系统应用 ISSN 1003-3254, CODEN CSAOBN E-mail: ******@ ComputerFinally, the detection of exposed distress of cement pavements is realized by the improved RetinaNet. The results show that the improved RetinaNet model enhances the detection accuracy of exposed distress by % compared with the original model, which reaches %. In comparison with Faster R-CNN, SSD and YOLOv3 methods, the model significantly improved the detection effect for the same test data. Key words: road detection; cement exposed distress; deep learning; binarization; improved RetinaNet