GndNet: Fast ground plane estimation and point cloud segmentation for autonomous vehicles

Paigwar A., Erkent Ö., Sierra-Gonzalez D., Laugier C.

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020, Nevada, United States Of America, 24 October 2020 - 24 January 2021, pp.2150-2156 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/iros45743.2020.9340979
  • City: Nevada
  • Country: United States Of America
  • Page Numbers: pp.2150-2156


© 2020 IEEE.Ground plane estimation and ground point segmentation is a crucial precursor for many applications in robotics and intelligent vehicles like navigable space detection and occupancy grid generation, 3D object detection, point cloud matching for localization and registration for mapping. In this paper, we present GndNet, a novel end-to-end approach that estimates the ground plane elevation information in a grid-based representation and segments the ground points simultaneously in real-time. GndNet uses PointNet and Pillar Feature Encoding network to extract features and regresses ground height for each cell of the grid. We augment the SemanticKITTI dataset to train our network. We demonstrate qualitative and quantitative evaluation of our results for ground elevation estimation and semantic segmentation of point cloud. GndNet establishes a new state-of-the-art, achieves a run-time of 55Hz for ground plane estimation and ground point segmentation.