Skip to Main content Skip to Navigation
Conference papers

Désoccultation de nuage de points LiDAR en topologie capteur

Abstract : This work proposes a novel approach for the disoccultation of mobile objects in 3D LIDAR scenes aquired via MMS. Although this work is often treated in the 3D space, our method offers to deal with it using a simplified representation of the point cloud known as range image. The range image is segmented using histograms. Then, it is inpainted using a variational method with an horizontal prior in the scene.
Document type :
Conference papers
Complete list of metadata

Cited literature [18 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01812057
Contributor : Pierre Biasutti <>
Submitted on : Monday, June 11, 2018 - 10:57:38 AM
Last modification on : Saturday, April 10, 2021 - 3:32:50 AM
Long-term archiving on: : Wednesday, September 12, 2018 - 6:26:14 PM

File

gretsi_2017.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01812057, version 1

Collections

Citation

Pierre Biasutti, Jean-François Aujol, Mathieu Brédif, Aurélie Bugeau. Désoccultation de nuage de points LiDAR en topologie capteur. Groupement de Recherche en Traitement du Signal et de l'Image (GRETSI), Sep 2017, Juan-Les-Pins, France. ⟨hal-01812057⟩

Share

Metrics

Record views

124

Files downloads

182