The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B3-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2020, 1497–1505, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-1497-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2020, 1497–1505, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-1497-2020

  22 Aug 2020

22 Aug 2020

EVALUATION OF SEMANTIC SEGMENTATION METHODS FOR DEFORESTATION DETECTION IN THE AMAZON

R. B. Andrade1, G. A. O. P. Costa1, G. L. A. Mota1, M. X. Ortega2, R. Q. Feitosa2, P. J. Soto2, and C. Heipke3 R. B. Andrade et al.
  • 1Dept. of Informatics and Computer Science, Rio de Janeiro State University (UERJ), Brazil
  • 2Dept. of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Brazil
  • 3Institute of Photogrammetry and GeoInformation, Leibniz Universität Hannover (LUH), Germany

Keywords: Amazon Forest, Deforestation, Semantic Segmentation, Change Detection, Deep Learning, DeepLabv3+

Abstract. Deforestation is a wide-reaching problem, responsible for serious environmental issues, such as biodiversity loss and global climate change. Containing approximately ten percent of all biomass on the planet and home to one tenth of the known species, the Amazon biome has faced important deforestation pressure in the last decades. Devising efficient deforestation detection methods is, therefore, key to combat illegal deforestation and to aid in the conception of public policies directed to promote sustainable development in the Amazon. In this work, we implement and evaluate a deforestation detection approach which is based on a Fully Convolutional, Deep Learning (DL) model: the DeepLabv3+. We compare the results obtained with the devised approach to those obtained with previously proposed DL-based methods (Early Fusion and Siamese Convolutional Network) using Landsat OLI-8 images acquired at different dates, covering a region of the Amazon forest. In order to evaluate the sensitivity of the methods to the amount of training data, we also evaluate them using varying training sample set sizes. The results show that all tested variants of the proposed method significantly outperform the other DL-based methods in terms of overall accuracy and F1-score. The gains in performance were even more substantial when limited amounts of samples were used in training the evaluated methods.