Communication Dans Un Congrès Année : 2024

Detecting Forged Sentinel-2 Images Through Parallax-Based Cloud Analysis

Résumé

The availability and significance of satellite imagery in our world is continuously growing. Satellite images now play a crucial role in various applications such as weather forecasting, greenhouse gas monitor- ing, agricultural crop health assessment, and external security. However, this also exposes them to malicious attacks aimed at hiding or manip- ulating information. Forensic analysis is, therefore, a necessary shield against disinformation and disruption attempts in these areas. While forensic analysis of photographs has received considerable academic at- tention in recent years, the same cannot be said for satellite imagery. In this study, we present two methodologies to create realistic datasets of images forged with added clouds, that may inconspicuously hide infor- mation. We show results produced by state-of-the-art forensic methods are unable to detect the forged satellite images. To overcome this prob- lem, we propose a parallax-based method to detect inconsistent satellite images.

Fichier principal
Vignette du fichier
Detecting_Forged_Sentinel_2_Images_Through_Parallax_Based_Cloud_Analysis__1_-5.pdf (26.25 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04852176 , version 1 (20-12-2024)

Licence

Identifiants

Citer

Matthieu Serfaty, Quentin Bammey, Tina Nikoukhah, Rafael Grompone von Gioi, Carlo de Franchis. Detecting Forged Sentinel-2 Images Through Parallax-Based Cloud Analysis. European Conference on Computer Vision (ECCV) 2024, Sep 2024, Milan (Italie), Italy. ⟨10.1007/978-3-031-91838-4_8⟩. ⟨hal-04852176⟩
380 Consultations
197 Téléchargements

Altmetric

Partager

  • More