Deteção e delimitação de corpos de água em imagens de satélite de alta resolução com aprendizagem profunda
Um estudo preliminar com o Detectron2
DOI:
https://doi.org/10.59192/mapping.442Palabras clave:
Segmentação de Imagem, Imagens de Satélite, Detectron2, Corpos de Água, Aprendizagem profunda, Recursos Hídricos, Visão ComputacionalResumen
A delimitação de corpos de água com recurso a imagens de satélite desempenha umpapel crucial em diversas aplicações, como monitorização ambiental, planeamento derecursos hídricos, planeamento na defesa contra a incêndios e na análise dasalteraçõesclimáticas. Neste trabalho, pretendemos explorar a aplicação daaprendizagem profunda tendo por base oFramework Detectron2, nageraçãoautomática depolígonos que representamcorpos de águacomopequenasalbufeiras,lagos,charcos e reservatórios.A caracterização eficiente das disponibilidades hídricasdos reservatórios, albufeiras e barragenspermite uma melhor e maiseficientemonitorização dos Planos de Água (PA), bem como a boa gestão desses mesmosrecursos. A área geográfica de estudo e as metodologias desenvolvidas, encontra-seenquadrada nas áreas de jurisdição da Administração da Região Hidrográfica doAlentejo, Departamentos desconcentrados da Agência portuguesa do Ambiente, I.P..Foidesenvolvidoum conjunto de dados abrangente e personalizado composto porimagens de satélite de alta resolução e rótulos anotados manualmente, identificandoas áreas correspondentes aos corpos de água, para treinar o modelo.Foi utilizada aarquiteturaResNet-50 combinada com aMask R-CNN, presentesno Detectron2, pararealizar a tarefa de deteção de objetos em gerale segmentação respetivamente. Emseguida, treinamos o modelo de aprendizagem profunda utilizando o nosso conjuntode dados na plataforma Google Colab, aproveitando o poder computacional dasunidades de processamento gráfico (GPU).A vantagem de usara FrameworkDetectron2 é a sua capacidade rápida e eficiente dedelimitação de corpos de águaem grandes volumes de dados,comparativamente aométodo tradicional, oqual envolve um processo manual de análise e marcaçãodospolígonosnas imagens de satéliteatravés de pessoal especializado,apresentandoelevados custos em termos de recursos humanos, económicose com elevadamorosidade.Na(Figura-1)é possível observar dois corpos de água corretamente segmentadosutilizando o método proposto.Esta abordagem pode impulsionar o desenvolvimento detécnicas mais precisas e eficientes para a deteção e delimitação de característicashidrológicas em imagens de satéliteuma vez que conseguimos segmentar corpos deágua com dimensões de até 121 m2.A abordagem implementada neste trabalho podeser aplicada a outras áreas temáticas como por exemplo a deteção de incêndios,blooms de algas, identificação de estruturas urbanas, delimitação de florestas e cultivos agrícolas.
Descargas
Citas
H. Xia, J. Zhao, Y. Qin, J. Yang, Y. Cui, H. Song, L. Ma, N. Jin, Q. Meng, Changes in Water Surface Area during 1989–2017 in the Huai River Basin using Landsat Data and Google Earth Engine, Remote Sens. 2019, Vol. 11, Page 1824. 11 (2019) 1824. https://doi.org/10.3390/RS11151824. DOI: https://doi.org/10.3390/rs11151824
D. Yang, Y. Yang, J. Xia, Hydrological cycle and water resources in a changing world: A review, Geogr. Sustain. 2 (2021) 115–122. https://doi.org/10.1016/J.GEOSUS. 2021.05.003. DOI: https://doi.org/10.1016/j.geosus.2021.05.003
A. El Moll, Water resources and climate change: regional, national and international perspective, Sustain. Circ. Manag. Resour. Waste Towar. a Green Deal. (2023) 309–336. https://doi.org/10.1016/B978-0-323-95278-1.00010-3. DOI: https://doi.org/10.1016/B978-0-323-95278-1.00010-3
M. Yadav, H.G. Gosai, G. Singh, A. Singh, A.K. Singh, R.P. Singh, R.N. Jadeja, Major impact of global climate change in atmospheric, hydrospheric and lithospheric context, Glob. Clim. Chang. Environ. Refug. Nature, Framew. Leg. (2023) 35–55. https://doi.org/10.1007/978- DOI: https://doi.org/10.1007/978-3-031-24833-7_3
-031-24833-7_3/COVER.
J.J. Bogardi, B.M. Fekete, Water: A unique phenomenon and resource, Handb. Water Resour. Manag. Discourses, Concepts Examples. (2021) 9–40. https://doi. org/10.1007/978-3-030-60147-8_2/COVER. DOI: https://doi.org/10.1007/978-3-030-60147-8_2
F. Papa, F. Frappart, Surface Water Storage in Rivers and Wetlands Derived from Satellite Observations: A Review of Current Advances and Future Opportunities for Hydrological Sciences, Remote Sens. 2021, Vol. 13, Page 4162. 13 (2021) 4162. https://doi.org/10.3390/RS13204162. DOI: https://doi.org/10.3390/rs13204162
W. Dorigo, S. Dietrich, F. Aires, L. Brocca, S. Carter, J.F. Cretaux, D. Dunkerley, H. Enomoto, R. Forsberg, A. Guntner, M.I. Hegglin, R. Hollmann, D.F. Hurst, J.A. Johannessen, C. Kummerow, T. Lee, K. Luojus, U. Looser, D.G. Miralles, V. Pellet, T. Recknagel, C.R. Vargas, U. Schneider, P. Schoeneich, M. Schroder, N. Tapper, V. Vuglinsky, W. Wagner, L. Yu, L. Zappa, M. Zemp, V. Aich, Closing the Water Cycle from Observations across Scales: Where Do We Stand?, Bull. Am. Meteorol. Soc. 102 (2021) E1897–E1935. https://doi.org/10.1175/BAMS-D-19-0316.1. DOI: https://doi.org/10.1175/BAMS-D-19-0316.1
G.L. Kyriakopoulos, Circular economy and sustainable strategies: Theoretical framework, policies and regulation challenges, barriers, and enablers for water management, Water Manag. Circ. Econ. (2023) 197–230. https://doi.org/10.1016/B978-0-323-95280-4.00014-X. DOI: https://doi.org/10.1016/B978-0-323-95280-4.00014-X
C. Faye, A.A. Sow, S. Dieye, Water management policy for freshwater security in the context of climate change in Senegal, Clim. Chang. Water Resour. Africa Perspect. Solut. Towar. an Imminent Water Cris. (2021) 255–276. https://doi.org/10.1007/978-3-030-61225-2_12/COVER. DOI: https://doi.org/10.1007/978-3-030-61225-2_12
P.H. Gleick, H. Cooley, Freshwater Scarcity, Https://Doi. Org/10.1146/Annurev-Environ-012220-101319. 46 (2021) 319–348. https://doi.org/10.1146/ANNUREV-ENVIRON-012220-101319. DOI: https://doi.org/10.1146/annurev-environ-012220-101319
J. Rocha, C. Carvalho-Santos, P. Diogo, P. Beca, J.J. Keizer, J.P. Nunes, Impacts of climate change on reservoir water availability, quality and irrigation needs in a water scarce Mediterranean region (southern Portugal), Sci. Total Environ. 736 (2020) 139477. https://doi. org/10.1016/J.SCITOTENV.2020.139477. DOI: https://doi.org/10.1016/j.scitotenv.2020.139477
P.M.M. Soares, D.C.A. Lima, Water scarcity down to earth Surface in a Mediterranean climate: The extreme future of soil moisture in Portugal, J. Hydrol. 615 (2022) 128731. https://doi.org/10.1016/J.JHYDROL.2022.128731. [13] S. Lu, B. Wu, N. Yan, H. Wang, Water body mapping method with HJ-1A/B satellite imagery, Int. J. Appl. Earth Obs. Geoinf. 13 (2011) 428–434. https://doi.org/10.1016/J.JAG.2010.09.006. DOI: https://doi.org/10.1016/j.jhydrol.2022.128731
W. Jiang, Y. Ni, Z. Pang, X. Li, H. Ju, G. He, J. Lv, K. Yang, J. Fu, X. Qin, An Effective Water Body Extraction Method with New Water Index for Sentinel-2 Imagery, Water 2021, Vol. 13, Page 1647. 13 (2021) 1647. https://doi. org/10.3390/W13121647. DOI: https://doi.org/10.3390/w13121647
X. Yang, Q. Qin, P. Grussenmeyer, M. Koehl, Urban Surface water body detection with suppressed built-up noise based on water indices from Sentinel-2 MSI imagery, Remote Sens. Environ. 219 (2018) 259–270. https://doi. org/10.1016/J.RSE.2018.09.016. DOI: https://doi.org/10.1016/j.rse.2018.09.016
S. Ghosh, A. Pal, S. Jaiswal, K.C. Santosh, N. Das, M. Nasipuri, SegFast-V2: Semantic image segmentation with les parameters in deep learning for autonomous driving, Int. J. Mach. Learn. Cybern. 10 (2019) 3145–3154. https://doi.org/10.1007/s13042-019-01005-5. DOI: https://doi.org/10.1007/s13042-019-01005-5
I. Papadeas, L. Tsochatzidis, A. Amanatiadis, I. Pratikakis, Real-Time Semantic Image Segmentation with Deep Learning for Autonomous Driving: A Survey, Appl. Sci. 2021, Vol. 11, Page 8802. 11 (2021) 8802. https://doi.org/10.3390/APP11198802. DOI: https://doi.org/10.3390/app11198802
X. Liu, L. Song, S. Liu, Y. Zhang, A Review of Deep-Learning-Based Medical Image Segmentation Methods, Sustain. 2021, Vol. 13, Page 1224. 13 (2021) 1224. https://doi.org/10.3390/SU13031224. DOI: https://doi.org/10.3390/su13031224
M.R. Ibrahim, J. Haworth, T. Cheng, Understanding cities with machine eyes: A review of deep computer visión in urban analytics, Cities. 96 (2020) 102481. https://doi.org/10.1016/J.CITIES.2019.102481. DOI: https://doi.org/10.1016/j.cities.2019.102481
Y. Lu, D. Chen, E. Olaniyi, Y. Huang, Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review, Comput. Electron. Agric.200 (2022) 107208. https://doi.org/10.1016/J.COMPAG. 2022.107208. DOI: https://doi.org/10.1016/j.compag.2022.107208
X. Sang, L. Xue, X. Ran, X. Li, J. Liu, Z. Liu, Intelligent High-Resolution Geological Mapping Based on SLICCNN, ISPRS Int. J. Geo-Information 2020, Vol. 9, Page 99. 9 (2020) 99. https://doi.org/10.3390/IJGI9020099. DOI: https://doi.org/10.3390/ijgi9020099
M.E. El-sayed, A.W. Youssef, O.M. Shehata, L.A. Shihata, E. Azab, Computer vision for package tracking on omnidirectional wheeled conveyor: Case study, Eng. Appl. Artif. Intell. 116 (2022) 105438. https://doi.org/10.1016/J.ENGAPPAI.2022.105438. DOI: https://doi.org/10.1016/j.engappai.2022.105438
A. Vembadi, A. Menachery, M.A. Qasaimeh, Cell Cytometry: Review and Perspective on Biotechnological Advances, Front. Bioeng. Biotechnol. 7 (2019) 462391.https://doi.org/10.3389/FBIOE.2019.00147/BIBTEX. DOI: https://doi.org/10.3389/fbioe.2019.00147
H. Farias, D. Ortiz, G. Damke, M. Jaque Arancibia, M. Solar, Mask galaxy: Morphological segmentation of galaxies, Astron. Comput. 33 (2020) 100420. https://doi.org/10.1016/J.ASCOM.2020.100420. DOI: https://doi.org/10.1016/j.ascom.2020.100420
I.J. Kadhim, P. Premaratne, A Novel Deep Learning Framework for Water Body Segmentation from Satellite Images, Arab. J. Sci. Eng. 48 (2023) 10429–10440. https://doi.org/10.1007/S13369-023-07680-5/FIGURES/4. DOI: https://doi.org/10.1007/s13369-023-07680-5
Z. Ma, M. Xia, L. Weng, H. Lin, Local Feature Search Network for Building and Water Segmentation of Remote Sensing Image, Sustain. 2023, Vol. 15, Page 3034. 15 (2023) 3034. https://doi.org/10.3390/SU15043034. DOI: https://doi.org/10.3390/su15043034
K. Yuan, X. Zhuang, G. Schaefer, J. Feng, L. Guan, H. Fang, Deep-Learning-Based Multispectral Satellite Image Segmentation for Water Body Detection, IEEE J. Sel.
Top. Appl. Earth Obs. Remote Sens. 14 (2021) 7422–7434. https://doi.org/10.1109/JSTARS.2021.3098678. DOI: https://doi.org/10.1109/JSTARS.2021.3098678
M. Wieland, S. Martinis, R. Kiefl, V. Gstaiger, Semantic segmentation of water bodies in very high-resolution satellite and aerial images, Remote Sens. Envi-ron. 287 (2023) 113452. https://doi.org/10.1016/J.RSE.2023.113452. DOI: https://doi.org/10.1016/j.rse.2023.113452
R.G. Tambe, S.N. Talbar, S.S. Chavan, Deep multi-feature learning architecture for water body segmentation from satellite images, J. Vis. Commun. Image Represent. 77 (2021) 103141. https://doi.org/10.1016/J.JVCIR.2021.103141. DOI: https://doi.org/10.1016/j.jvcir.2021.103141
GitHub - facebookresearch/detectron2: Detectron2 is a platform for object detection, segmentation and other visual recognition tasks., (n.d.). https://github.com/facebookresearch/detectron2 (accessed August31, 2023).
A.B. Abdusalomov, B.M.S. Islam, R. Nasimov, M. Mukhiddinov, T.K. Whangbo, An Improved Forest Fire Detection Method Based on the Detectron2 Model and a Deep Learning Approach, Sensors 2023, Vol. 23, Page 1512.23 (2023) 1512. https://doi.org/10.3390/S23031512. DOI: https://doi.org/10.3390/s23031512
V. Pham, C. Pham, T. Dang, Road Damage Detection and Classification with Detectron2 and Faster R-CNN, Proc. - 2020 IEEE Int. Conf. Big Data, Big Data 2020. (2020) 5592–5601. https://doi.org/10.1109/BIGDATA50022.2020.9378027. DOI: https://doi.org/10.1109/BigData50022.2020.9378027
R. Divya, J.D. Peter, Smart healthcare system-a brain-like computing approach for analyzing the performance of detectron2 and PoseNet models for anomalous action detection in aged people with movement impairments, Complex Intell. Syst. 8 (2022) 3021–3040. https://doi.org/10.1007/S40747-021-00319-8/FIGURES/21. DOI: https://doi.org/10.1007/s40747-021-00319-8
B. Rai, S.A.S. Kumar, F. Chincholi, H. Koestler, Detectron2 for Lesion Detection in Diabetic Retinopathy, Algorithms 2023, Vol. 16, Page 147. 16 (2023) 147. https://doi.org/10.3390/A16030147. DOI: https://doi.org/10.3390/a16030147
G. Merz, Y. Liu, C.J. Burke, P.D. Aleo, X. Liu, M. Carrasco, V. Kindratenko, Y. Liu, Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and Demonstration with Hyper Suprime-Cam Data, MNRAS. 000 (2023) 1–16. https://arxiv.org/abs/2307.05826v1 (accessed September 1, 2023). DOI: https://doi.org/10.1093/mnras/stad2785
.F. Restrepo-Arias, P. Arregoces-Guerra, J.W. Branch-Bedoya Crops Classification in Small Areas Using Unmanned Aerial Vehicles (UAV) and Deep Learning Pre-trained Models from Detectron2, Intell. Syst. Ref. Libr. 226 (2023) 273–291. https://doi.org/10.1007/978-3-031-08246-7_12/COVER. DOI: https://doi.org/10.1007/978-3-031-08246-7_12
Tian, Z. Chu, Q. Hu, L. Ma, Class-Wise Fully Convolutional Network for Semantic Segmentation of Remote Sensing Images, Remote Sens. 2021, Vol. 13, Page 3211. 13 (2021) 3211. https://doi.org/10.3390/RS13163211. DOI: https://doi.org/10.3390/rs13163211
O. Povoa, V. Lopes, A.M. Barata, N. Farinha, Monitoring Genetic Erosion of Aromatic and Medicinal Plant Species in Alentejo (South Portugal), Plants. 12 (2023) 2588. https://doi.org/10.3390/PLANTS12142588/S1. DOI: https://doi.org/10.3390/plants12142588
C. Santos-Silva, R. Louro, Assessment of the diversity of epigeous Basidiomycota under different soil-management systems in a montado ecosystem: a case study conducted in Alentejo, Agrofor. Syst. 90 (2016) 117–126. https://doi.org/10.1007/S10457-015-9800-3/FIGURES/2. DOI: https://doi.org/10.1007/s10457-015-9800-3
I. Pulido-Calvo, J.C. Gutierrez-Estrada, V. Sanz-Fernandez, Drought and Ecological Flows in the Lower Guadiana River Basin (Southwest Iberian Peninsula), Water 2020, Vol. 12, Page 677. 12 (2020) 677. https://doi.org/10.3390/W12030677. DOI: https://doi.org/10.3390/w12030677
A.A. Rodriguez Sousa, C. Tribaldos-Anda, S.A. Prats, C. Brigido, J. Munoz-Rojas, A.J. Rescia, Impacts of Fertilization on Environmental Quality across a Gradient of Olive Grove Management Systems in Alentejo (Portugal), Land. 11 (2022) 2194. ttps://doi.org/10.3390/LAND11122194/S1. DOI: https://doi.org/10.3390/land11122194
SNIRH :: Sistema Nacional de Informacao de Recursos Hidricos, (n.d.). https://snirh.apambiente.pt/ (accessed September 29, 2023).
C. Andrade, J. Contente, J.A. Santos, Climate change projections of dry and wet events in iberia based on the wasp-index, Climate. 9 (2021). https://doi.org/10.3390/cli9060094. DOI: https://doi.org/10.20944/preprints202104.0577.v1
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2023 Revista MAPPING
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.