Detection and Utilization of Reflections in LiDAR Scans through Plane Optimization and Plane SLAM

Authors:
Open Access
Publisher website
Google Scholar
Abstract
In LiDAR sensing, glass, mirrors and other materials often cause inconsistent data readings from reflections. This causes problems in robotics and 3D reconstruction, especially with respect to localization, mapping and, thus, navigation. Extending our previous work, we construct a global, optimized map of reflective planes, in order to then classify all LiDAR readings at the end. For this, we optimize the reflective plane parameters of the plane detection of multiple scans. In a further method, we apply the reflective plane estimation in a plane SLAM algorithm, highlighting the applicability of our method for robotics. As our experiments will show, this approach provides superior classification accuracy compared to the single scan approach. The code and data for this work are available as open source online.
Funding Information
  • Science and Technology Commission of Shanghai Municipality (22JC1410700)
  • Shanghai Frontiers Science Center of Human-centered Artificial Intelligence (22JC1410700)

This publication has 30 references indexed in Scilit: