An Anti-disturbance Target Detection and Tracking Algorithm in Unstructured Environment

In order to solve the problem of target loss in target detection and tracking in the case of sharp turns or sudden changes in vehicle posture in unstructured environments, this paper proposes an anti-disturbance target detection and tracking algorithm combining LiDAR and millimeter wave radar. First, the LiDAR tracking module is built based on Kalman filter and Minimum cut, and then the millimeter wave radar tracking module is optimized through lifecycle monitoring and near target matching. Finally, ensuring effective tracking of targets through target correlation matching. In order to verify the performance of the algorithm, we chose a road with a total length of about 30 km in an unstructured environment for real vehicle experiments. Experiments have shown that the algorithm proposed in this paper has good anti-interference ability and can effectively deal with sharp turns or sudden changes in vehicle posture in unstructured environments.