Sustainable road anomaly detection method and system based on multi-source sensor fusion

The invention discloses a sustainable road anomaly detection method based on multi-source sensor fusion, and the method comprises the steps: collecting acceleration data, a GPS, a timestamp and video data in a vehicle driving process through a client in a road anomaly detection section, and uploading the acceleration data, the GPS, the timestamp and the video data to a server; and data preprocessing is carried out on the server. When the resolution of the video frame is larger than a preset resolution threshold value, the acceleration data and the video frame data are input into a first road anomaly detection network for prediction, and a first single vehicle abnormal road surface detection result is obtained; when the resolution of the video frame is smaller than a preset resolution threshold, inputting the acceleration data into a second road anomaly detection network for prediction to obtain a second single vehicle abnormal road surface detection result; and carrying out multi-vehicle sensing result fusion