ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-3-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2022, 657–664, 2022
https://doi.org/10.5194/isprs-annals-V-3-2022-657-2022
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2022, 657–664, 2022
https://doi.org/10.5194/isprs-annals-V-3-2022-657-2022
 
17 May 2022
17 May 2022

MULTI-ATTENTION GHOSTNET FOR DEFORESTATION DETECTION IN THE AMAZON RAINFOREST

M. X. Ortega Adarme1, G. A. O. P. Costa2, and R. Q. Feitosa1 M. X. Ortega Adarme et al.
  • 1Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Brazil
  • 2State University of Rio de Janeiro (UERJ), Rio de Janeiro, Brazil

Keywords: Deforestation Detection, Amazon Rainforest, GhostNet, Spatial Attention Mechanims, Fully Convolutional Networks

Abstract. Efficient deforestation detection techniques are essential to monitor and control illegal logging, thus reducing forest loss and carbon emissions in the Amazon rainforest. Recent works based on Deep Learning (DL) models have been proposed for that purpose. DL-based methods, however, are known to require large amounts of training data to be properly trained. Moreover, the deforestation detection application is characterized by a high class imbalance, as recent deforestation areas usually represent a small fraction of the geographic extents being monitored. In order to produce a lightweight architecture in terms of the number of learnable parameters and address the high class imbalance of the deforestation detection application, we propose a DL model based on the GhostNet architecture, which combines Ghost modules in a fully convolutional architecture. The proposed architecture also includes Spatial Attention Mechanisms attached to the skip connections of the GhostNet in order to better capture the spatial relationships among class features. Experiments were carried out using Sentinel-2 images of a region in the Para´ state, Brazil, in the Amazon rainforest. The results obtained show that the proposed model achieves accuracy levels that are superior to those delivered by state-of-the-art DL architectures, with a lower computational cost due to the smaller number of learnable parameters.