Details
| Original language | English |
|---|---|
| Pages (from-to) | 1497-1505 |
| Number of pages | 9 |
| Journal | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Volume | 43 |
| Issue number | B3 |
| Publication status | Published - 22 Aug 2020 |
| Event | 2020 24th ISPRS Congress - Technical Commission III - Nice, Virtual, France Duration: 31 Aug 2020 → 2 Sept 2020 |
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.
Keywords
- Amazon Forest, Change Detection, Deep Learning, DeepLabv3+, Deforestation, Semantic Segmentation
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Social Sciences(all)
- Geography, Planning and Development
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Vol. 43, No. B3, 22.08.2020, p. 1497-1505.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Evaluation of semantic segmentation methods for deforestation detection in the amazon
AU - Andrade, R. B.
AU - Costa, G. A. O. P.
AU - Mota, G. L. A.
AU - Ortega, M. X.
AU - Feitosa, R. Q.
AU - Soto, P. J.
AU - Heipke, C.
N1 - Funding Information: This work is supported by CNPq (Conselho Nacional de Desen-volvimento Científico e Tecnológico), CAPES (Coordenac¸ão de Aperfeic¸oamento de Pessoal de Nível Superior), and FAPERJ (Fundac¸ão de Amparo à Pesquisa do Estado do Rio de Janeiro).
PY - 2020/8/22
Y1 - 2020/8/22
N2 - 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.
AB - 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.
KW - Amazon Forest
KW - Change Detection
KW - Deep Learning
KW - DeepLabv3+
KW - Deforestation
KW - Semantic Segmentation
UR - http://www.scopus.com/inward/record.url?scp=85091163041&partnerID=8YFLogxK
U2 - 10.5194/isprs-archives-XLIII-B3-2020-1497-2020
DO - 10.5194/isprs-archives-XLIII-B3-2020-1497-2020
M3 - Conference article
AN - SCOPUS:85091163041
VL - 43
SP - 1497
EP - 1505
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
SN - 1682-1750
IS - B3
T2 - 2020 24th ISPRS Congress - Technical Commission III
Y2 - 31 August 2020 through 2 September 2020
ER -