Road Damage may result in a reduction in the efficiency of traffic, and even endanger the safety of human and property. To realize automatic and timely detection of road damage, in this article, we design an edge-to-client road damage detection system based on the YOLO object detection algorithm, which includes roadside information collection platform, edge computing equipment, cloud transfer system, and client. We compared the effects of YOLOv5, YOLOv4, and YOLOv4-tiny on the RDD2020 data set and implemented model deployment and model optimization based on the NVIDIA Jetson NX platform. Experimental results show that the system can realize real-time display of road damage detection.