Um arcabouço de Seleção de Bandas Landsat-8 baseado em UMDA para Detecção de Desmatamento
Resumo
A conservação das florestas tropicais é um assunto atual de relevância social e ecológica, devido ao importante papel que elas desempenham no ecossistema global. Infelizmente, milhões de hectares são desmatados e degradados todo ano, sendo necessários programas (governamentais ou de iniciativas privadas) para monitoramento das florestas tropicais. Neste sentido, este trabalho propõe um novo arcabouço que utiliza de algoritmo de estimação de distribuição estocástico (UMDA) para selecionar bandas espectrais do satélite Landsat-8 que melhor representam as áreas de desmatamento que guiará a criação de novas composições de imagens para alimentar uma arquitetura de segmentação semântica chamada DeepLabv3+. Nos experimentos realizados foi possível encontrar diversas composições que conseguem acurácia balanceada maior que 90% na tarefa de classificação de segmentos. Além disso, a melhor composição de bandas (651) encontrada pelo algoritmo UMDA alimentou uma arquitetura DeepLabv3+ e resultou em melhor eficiência e eficácia contra todas as composições comparadas neste trabalho.Referências
C. Martin, On the Edge: The State and Fate of the World’s Tropical Rainforests. Greystone Books Ltd, 2015.
G. Urquhart, W. Chomentowski, D. Skole, and C. Barber, “Tropical deforestation,” 1998.
M. Hansen et al., “High-resolution global maps of 21st-century forest cover change,” science, vol. 342, no. 6160, pp. 850–853, 2013.
INPE, “Estimativa de desmatamento na Amazônia Legal para 2022 é de 11.568 km2,” https://encurtador.com.br/aBDP2, 2022, accessed: 2023-08-01.
M. Ortega, J. Bermudez, P. Happ, A. Gomes, and R. Feitosa, “Evaluation of deep learning techniques for deforestation detection in the amazon forest,” ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 4, pp. 121–128, 2019.
R. B. Andrade et al., “Evaluation of semantic segmentation methods for deforestation detection in the amazon,” ISPRS Archives; 43, B3, vol. 43, no. B3, pp. 1497–1505, 2020.
R. V. Maretto, L. M. Fonseca, N. Jacobs, T. S. Körting, H. N. Bendini, and L. L. Parente, “Spatio-temporal deep learning approach to map deforestation in amazon rainforest,” IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 5, pp. 771–775, 2020.
Z. Yu, L. Di, R. Yang, J. Tang, L. Lin, C. Zhang, M. S. Rahman, H. Zhao, J. Gaigalas, E. G. Yu et al., “Selection of landsat 8 oli band combinations for land use and land cover classification,” in 2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics). IEEE, 2019, pp. 1–5.
F. Dallaqua, A. Fazenda, and F. Faria, “ForestEyes Project: Can Citizen Scientists Help Rainforests?” in IEEE 15th International Conference on eScience. IEEE, 9 2019, pp. 18–27.
J.-P. Ma, Z.-B. Zheng, Q.-X. Tong, and L.-F. Zheng, “An application of genetic algorithms on band selection for hyperspectral image classification,” in Proceedings of the 2003 international conference on machine learning and cybernetics (IEEE Cat. No. 03EX693), vol. 5. IEEE, 2003, pp. 2810–2813.
K. Nagasubramanian, S. Jones, S. Sarkar, A. K. Singh, A. Singh, and B. Ganapathysubramanian, “Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean stems,” Plant methods, vol. 14, pp. 1–13, 2018.
I. Jolliffe, Principal component analysis. Springer, 2011.
R. Achanta et al., “SLIC superpixels compared to state-of-the-art superpixel methods,” IEEE transactions on pattern analysis and machine intelligence, vol. 34, no. 11, pp. 2274–2282, 2012.
R. M. Haralick et al., “Textural features for image classification,” IEEE Transactions on systems, man, and cybernetics, no. 6, pp. 610–621, 1973.
B. E. Boser et al., “A training algorithm for optimal margin classifiers,” in Workshop on Computational Learning Theory, ser. COLT ’92, 1992, pp. 144–152.
H. Mühlenbein and G. Paass, “From recombination of genes to the estimation of distributions i. binary parameters,” in International conference on parallel problem solving from nature. Springer, 1996, pp. 178–187.
Liang-Chieh Chen et al., “Encoder-decoder with atrous separable convolution for semantic image segmentation,” 2018.
J. Deng et al., “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009, pp. 248–255.
D. Torres et al., “Deforestation detection with fully convolutional networks in the amazon forest from landsat-8 and sentinel-2 images,” Remote Sensing, vol. 13, no. 24, 2021.
G. Urquhart, W. Chomentowski, D. Skole, and C. Barber, “Tropical deforestation,” 1998.
M. Hansen et al., “High-resolution global maps of 21st-century forest cover change,” science, vol. 342, no. 6160, pp. 850–853, 2013.
INPE, “Estimativa de desmatamento na Amazônia Legal para 2022 é de 11.568 km2,” https://encurtador.com.br/aBDP2, 2022, accessed: 2023-08-01.
M. Ortega, J. Bermudez, P. Happ, A. Gomes, and R. Feitosa, “Evaluation of deep learning techniques for deforestation detection in the amazon forest,” ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 4, pp. 121–128, 2019.
R. B. Andrade et al., “Evaluation of semantic segmentation methods for deforestation detection in the amazon,” ISPRS Archives; 43, B3, vol. 43, no. B3, pp. 1497–1505, 2020.
R. V. Maretto, L. M. Fonseca, N. Jacobs, T. S. Körting, H. N. Bendini, and L. L. Parente, “Spatio-temporal deep learning approach to map deforestation in amazon rainforest,” IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 5, pp. 771–775, 2020.
Z. Yu, L. Di, R. Yang, J. Tang, L. Lin, C. Zhang, M. S. Rahman, H. Zhao, J. Gaigalas, E. G. Yu et al., “Selection of landsat 8 oli band combinations for land use and land cover classification,” in 2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics). IEEE, 2019, pp. 1–5.
F. Dallaqua, A. Fazenda, and F. Faria, “ForestEyes Project: Can Citizen Scientists Help Rainforests?” in IEEE 15th International Conference on eScience. IEEE, 9 2019, pp. 18–27.
J.-P. Ma, Z.-B. Zheng, Q.-X. Tong, and L.-F. Zheng, “An application of genetic algorithms on band selection for hyperspectral image classification,” in Proceedings of the 2003 international conference on machine learning and cybernetics (IEEE Cat. No. 03EX693), vol. 5. IEEE, 2003, pp. 2810–2813.
K. Nagasubramanian, S. Jones, S. Sarkar, A. K. Singh, A. Singh, and B. Ganapathysubramanian, “Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean stems,” Plant methods, vol. 14, pp. 1–13, 2018.
I. Jolliffe, Principal component analysis. Springer, 2011.
R. Achanta et al., “SLIC superpixels compared to state-of-the-art superpixel methods,” IEEE transactions on pattern analysis and machine intelligence, vol. 34, no. 11, pp. 2274–2282, 2012.
R. M. Haralick et al., “Textural features for image classification,” IEEE Transactions on systems, man, and cybernetics, no. 6, pp. 610–621, 1973.
B. E. Boser et al., “A training algorithm for optimal margin classifiers,” in Workshop on Computational Learning Theory, ser. COLT ’92, 1992, pp. 144–152.
H. Mühlenbein and G. Paass, “From recombination of genes to the estimation of distributions i. binary parameters,” in International conference on parallel problem solving from nature. Springer, 1996, pp. 178–187.
Liang-Chieh Chen et al., “Encoder-decoder with atrous separable convolution for semantic image segmentation,” 2018.
J. Deng et al., “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009, pp. 248–255.
D. Torres et al., “Deforestation detection with fully convolutional networks in the amazon forest from landsat-8 and sentinel-2 images,” Remote Sensing, vol. 13, no. 24, 2021.
Publicado
06/11/2023
Como Citar
B. NETO, Eduardo; PEDRO, Paulo R. C.; FAZENDA, Álvaro; FARIA, Fabio A..
Um arcabouço de Seleção de Bandas Landsat-8 baseado em UMDA para Detecção de Desmatamento. In: WORKSHOP DE TRABALHOS DA GRADUAÇÃO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 36. , 2023, Rio Grande/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 140-143.
DOI: https://doi.org/10.5753/sibgrapi.est.2023.27467.
