Cliff Change detection using Siamese KPConv deep network on 3D point clouds - Archive ouverte HAL
Poster De Conférence Année : 2022

Cliff Change detection using Siamese KPConv deep network on 3D point clouds

Christophe Delacourt

Résumé

Context:• Cliffs cover 52% of the world’s coastline [1]• Cliff erosion likely to increase with sea level rise [2]• Endangering nearby populations and infrastructuresChallenges:• Working directly on raw 3D point clouds to avoid the loss of information when rasterizing the vertical cliffs• Randomness of natural cliffs (unlike buildings in urban areas)• Being able to study vertical or very steep cliffs
Fichier principal
Vignette du fichier
PosterISPRS22_a0__de_Gelis_Bessin.pdf (3.6 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03707448 , version 1 (29-06-2022)

Identifiants

  • HAL Id : hal-03707448 , version 1

Citer

Iris de Gélis, Zoé Bessin, Pauline Letortu, Marion Jaud, Christophe Delacourt, et al.. Cliff Change detection using Siamese KPConv deep network on 3D point clouds. ISPRS Congress, Jun 2022, Nice, France. , 55, pp.457 - 476, 2022. ⟨hal-03707448⟩
96 Consultations
67 Téléchargements

Partager

More