A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distance
This addresses challenges like varying density and occlusions in LiDAR data for applications requiring offline processing, but it is incremental as it builds on existing state-of-the-art models.
The paper tackles the problem of LiDAR semantic segmentation in long-distance outdoor scenarios by proposing a preprocessing and postprocessing voxel-based method, achieving improvements of over 5 percentage points in mIoU for medium range and over 10 percentage points for far range.
In recent years considerable research in LiDAR semantic segmentation was conducted, introducing several new state of the art models. However, most research focuses on single-scan point clouds, limiting performance especially in long distance outdoor scenarios, by omitting time-sequential information. Moreover, varying-density and occlusions constitute significant challenges in single-scan approaches. In this paper we propose a LiDAR point cloud preprocessing and postprocessing method. This multi-stage approach, in conjunction with state of the art models in a multi-scan setting, aims to solve those challenges. We demonstrate the benefits of our method through quantitative evaluation with the given models in single-scan settings. In particular, we achieve significant improvements in mIoU performance of over 5 percentage point in medium range and over 10 percentage point in far range. This is essential for 3D semantic scene understanding in long distance as well as for applications where offline processing is permissible.