Improving LiDAR Point Cloud Classification using Intensities and Multiple Echoes

Christophe Reymann (1) , Simon Lacroix (1)

1 LAAS-RIS - Équipe Robotique et InteractionS

Besides precise and dense geometric information, some LiDARs also provide intensity information and multiple echoes, information that can advantageously be exploited to enhance the performance of the purely geometric classification approaches. This information indeed depends on the physical nature of the perceived surfaces, and is not strongly impacted by the scene illumination – contrary to visual information. This article investigates how such information can augment the precision of a point cloud classifier. It presents an empirical evaluation of a low cost LiDAR, introduces features related to the intensity and multiple echoes and their use in a hierarchical classification scheme. Results on varied outdoor scenes are depicted, and show that more precise class identification can be achieved using the intensity and multiple echoes than when using only geometric features.

Domaines: Robotique [cs.RO]

Christophe Reymann, Simon Lacroix. Improving LiDAR Point Cloud Classification using Intensities and Multiple Echoes. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015), Sep 2015, Hamburg, Germany. 7p. ⟨hal-01182604⟩