Deep Unsupervised Learning for 3D ALS Point Clouds Change Detection - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue ISPRS Journal of Photogrammetry and Remote Sensing Année : 2023

Deep Unsupervised Learning for 3D ALS Point Clouds Change Detection

Résumé

Change detection from traditional optical images has limited capability to model the changes in the height or shape of objects. Change detection using 3D point cloud aerial LiDAR survey data can fill this gap by providing critical depth information. While most existing machine learning based 3D point cloud change detection methods are supervised, they severely depend on the availability of annotated training data, which is in practice a critical point. To circumnavigate this dependence, we propose an unsupervised 3D point cloud change detection method mainly based on self-supervised learning using deep clustering and contrastive learning. The proposed method also relies on an adaptation of deep change vector analysis to 3D point cloud via nearest point comparison. Experiments conducted on a publicly available real dataset show that the proposed method obtains higher performance in comparison to the traditional unsupervised methods, with a gain of about 9% in mean accuracy (to reach more than 85%). Thus, it appears to be a relevant choice in scenario where prior knowledge (labels) is not ensured.
Fichier principal
Vignette du fichier
2305.03529b.pdf (10.73 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04310690 , version 1 (27-11-2023)

Identifiants

Citer

Iris de Gélis, Sudipan Saha, Muhammad Shahzad, Thomas Corpetti, Sébastien Lefèvre, et al.. Deep Unsupervised Learning for 3D ALS Point Clouds Change Detection. ISPRS Journal of Photogrammetry and Remote Sensing, In press, ⟨10.48550/arXiv.2305.03529⟩. ⟨hal-04310690⟩
45 Consultations
22 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More