Dynamic Object Removal for Point Cloud Map Creation in Autonomous Driving : Enhancing Map Accuracy via Two-Stage Offline Model

Abstract: Autonomous driving is an emerging area that has been receiving an increasing amount of interest from different companies and researchers. 3D point cloud map is a significant foundation of autonomous driving as it provides essential information for localization and environment perception. However, when trying to gather road information for map creation, the presence of dynamic objects like vehicles, pedestrians, and cyclists will add noise and unnecessary information to the final map. In order to solve the problem, this thesis presents a novel two-stage model that contains a scan-to-scan removal stage and a scan-to-map generation stage. By designing the new three-branch neural network and new attention-based fusion block, the scan-to-scan part achieves a higher mean Intersection-over-Union (mIoU) score. By improving the ground plane estimation, the scan-to-map part can preserve more static points while removing a large number of dynamic points. The test on SemanticKITTI dataset and Scania dataset shows our two-stage model outperforms other baselines.