CROCO: CROSS-MODAL CONTRASTIVE LEARNING FOR LOCALIZATION OF EARTH OBSERVATION DATA - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Article Dans Une Revue ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences Année : 2022

CROCO: CROSS-MODAL CONTRASTIVE LEARNING FOR LOCALIZATION OF EARTH OBSERVATION DATA

Résumé

Abstract. It is of interest to localize a ground-based LiDAR point cloud on remote sensing imagery. In this work, we tackle a subtask of this problem, i.e. to map a digital elevation model (DEM) rasterized from aerial LiDAR point cloud on the aerial imagery. We proposed a contrastive learning-based method that trains on DEM and high-resolution optical imagery and experiment the framework on different data sampling strategies and hyperparameters. In the best scenario, the Top-1 score of 0.71 and Top-5 score of 0.81 are obtained. The proposed method is promising for feature learning from RGB and DEM for localization and is potentially applicable to other data sources too. Source code is released at https://github.com/wtseng530/AVLocalization.

Dates et versions

hal-03991207 , version 1 (15-02-2023)

Identifiants

Citer

W.-H. Tseng, H.-A. Lê, A. Boulch, Sébastien Lefèvre, D. Tiede. CROCO: CROSS-MODAL CONTRASTIVE LEARNING FOR LOCALIZATION OF EARTH OBSERVATION DATA. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022, V-2-2022, pp.415-421. ⟨10.5194/isprs-annals-V-2-2022-415-2022⟩. ⟨hal-03991207⟩
20 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More