The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B3-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2022, 713–719, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-713-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2022, 713–719, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-713-2022
 
30 May 2022
30 May 2022

DEFORESTATION DETECTION WITH WEAK SUPERVISED CONVOLUTIONAL NEURAL NETWORKS IN TROPICAL BIOMES

P. J. Soto1, G. A. O. P. Costa2, M. X. Ortega3, J. D. Bermudez3, and R. Q. Feitosa3 P. J. Soto et al.
  • 1Institut Français de Recherche pour l'Exploitation de la Mer (Ifremer), PDG-REM-EEP-LEP, F-29280 Plouzané, France
  • 2Dept. of Informatics and Computer Science, Rio de Janeiro State University (UERJ), Brazil
  • 3Dept. of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Brazil

Keywords: change detection, deep learning, domain adaptation, deforestation, weak supervision

Abstract. Deep learning methods are known to demand large amounts of labeled samples for training. For remote sensing applications such as change detection, coping with that demand is expensive and time-consuming. This work aims at investigating a noisy-label-based weak supervised method in the context of a deforestation mapping application, characterized by a high class imbalance between the classes of interest, i.e., deforestation and no-deforestation. The study sites correspond to different regions in the Amazon and Brazilian Cerrado biomes. To mitigate the lack of ground-truth labeled training samples, we devised an unsupervised pseudo-labeling scheme based on the Change Vector Analysis technique. The experimental results indicate that the proposed approach can improve the accuracy of deforestation detection applications.