CVPR MultiEarth 2023 Deforestation Estimation Challenge:SpaceVision4Amazon
Sunita Arya, S Manthira Moorthi, Debajyoti Dhar

TL;DR
This paper introduces an attention-guided UNet model for deforestation estimation using EO and SAR satellite imagery, achieving high accuracy and F1-scores in the Amazon region.
Contribution
The study presents a novel multi-sensor deep learning approach with separate models for EO and SAR data for deforestation detection.
Findings
Landsat-8 model achieved 93.45% training accuracy
Sentinel-1 model achieved 83.87% validation accuracy
Test set pixel accuracy was 84.70% with F1-Score of 0.79
Abstract
In this paper, we present a deforestation estimation method based on attention guided UNet architecture using Electro-Optical (EO) and Synthetic Aperture Radar (SAR) satellite imagery. For optical images, Landsat-8 and for SAR imagery, Sentinel-1 data have been used to train and validate the proposed model. Due to the unavailability of temporally and spatially collocated data, individual model has been trained for each sensor. During training time Landsat-8 model achieved training and validation pixel accuracy of 93.45% and Sentinel-2 model achieved 83.87% pixel accuracy. During the test set evaluation, the model achieved pixel accuracy of 84.70% with F1-Score of 0.79 and IoU of 0.69.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRemote Sensing and LiDAR Applications · Advanced Image and Video Retrieval Techniques · Remote-Sensing Image Classification
