Back to Search Start Over

A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distance

Authors :
Matteazzi, Andrea
Colling, Pascal
Arnold, Michael
Tutsch, Dietmar
Publication Year :
2024

Abstract

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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2405.10046
Document Type :
Working Paper