Deep Learning para Classificação Supervisionada de Imagens CBERS-4A da Área Urbana de Rio Claro (SP)
Barra lateral de artigos
Conteúdo do artigo principal
Resumo
O presente artigo tem por objetivo avaliar a acurácia do mapeamento do uso e cobertura da terra, realizado em um trecho da área urbana de Rio Claro (SP), a partir de técnicas de Deep Learning e utilizando uma imagem CBERS-4A (WPM) com 2 m de resolução espacial. Foi estruturada uma rede neural convolucional U-Net a partir de script em Python, utilizando as bibliotecas Keras e Tensor Flow. A verdade terrestre, utilizada para treinamento e verificação da acurácia do modelo, foi elaborada por meio de classificação supervisionada da mesma imagem no software ArcGIS Pro, utilizando o algoritmo Support Vector Machine (SVM) e procedimentos de pós-classificação, incluindo aplicação de filtro majoritário e edição manual de pixels. O resultado obtido pela U-Net foi comparado ao resultado obtido pelo SVM (sem pós-classificação), visando compreender se há ganhos de acurácia, tendo em vista o maior esforço humano, para a criação do ground truth, e computacional, para processamento dos dados, inerente às técnicas de Deep Learning. Para isso, ambos os resultados foram submetidos a avaliação de acurácia utilizando as métricas Overall Accuracy, Precision, Recall, F1 Score e Kappa. Constatou-se que o modelo U-Net apresenta melhor acurácia em todas elas, destacando-se o aumento da Precision de 0,48 (SVM) para 0,78 (U-Net). Tais resultados indicam o potencial das técnicas de Deep Learning para o mapeamento do uso e cobertura da terra em áreas urbanas a partir de imagens de alta resolução, o que pode contribuir, de modo significativo, para ações de planejamento e gestão territorial nos municípios brasileiros
Downloads
Detalhes do artigo
Seção
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
Autores que publicam nesta revista concordam com os seguintes termos:
- Autores mantém os direitos autorais e concedem à revista o direito de primeira publicação, com o trabalho simultaneamente licenciado sob a Licença Creative Commons Atribuição que permite o compartilhamento do trabalho com reconhecimento da autoria e publicação inicial nesta revista.
- Autores têm autorização para assumir contratos adicionais separadamente, para distribuição não-exclusiva da versão do trabalho publicada nesta revista (ex.: publicar em repositório institucional ou como capítulo de livro), com reconhecimento de autoria e publicação inicial nesta revista.
- Autores têm permissão e são estimulados a publicar e distribuir seu trabalho online (ex.: em repositórios institucionais ou na sua página pessoal) a qualquer ponto antes ou durante o processo editorial, já que isso pode gerar alterações produtivas, bem como aumentar o impacto e a citação do trabalho publicado (veja "O Efeito do Acesso Aberto").
Como Citar
Referências
Abdollahi, A., Pradhan, B., Shukla, N., Chakraborty, S., & Alamri, A. (2021). Multi-object segmentation in complex urban scenes from high-resolution remote sensing data. Remote Sensing, 13(18), 3710. https://doi.org/10.3390/rs13183710
Amani, M., Ghorbanian, A., Ahmadi, S. A., Kakooei, M., Moghimi, A., Mirmazloumi, S. M., Alizadeh Moghaddam, S. H., Mahdavi, S., Ghahremanloo, M., Parsian, S., Wu, Q., & Brisco, B. (2020). Google Earth Engine cloud computing platform for remote sensing big data applications: A comprehensive review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 5326–5350. https://doi.org/10.1109/JSTARS.2020.3011956
Braga, J. R. G., Peripato, V., Dalagnol, R., Ferreira, M. P., Tarabalka, Y., Aragão, L. E. O. C., Campos Velho, H. F. de, Shiguemori, E. H., & Wagner, F. H. (2020). Tree crown delineation algorithm based on a convolutional neural network. Remote Sensing, 12(8), 1288. https://doi.org/10.3390/rs12081288
Brownlee, J. (2019). Deep learning for computer vision: Image classification, object detection and face recognition in Python. Machine Learning Mastery.
Carranza-García, M., García-Gutiérrez, J., & Riquelme, J. (2019). A framework for evaluating land use and land cover classification using convolutional neural networks. Remote Sensing, 11(3), 274. https://doi.org/10.3390/rs11030274
Chi, M., Plaza, A., Benediktsson, J. A., Sun, Z., Shen, J., & Zhu, Y. (2016). Big data for remote sensing: Challenges and opportunities. Proceedings of the IEEE, 104(11), 2207. https://doi.org/10.1109/JPROC.2016.2598228
Chollet, F. (2021). Deep learning with Python (2nd ed.). Manning Publications.
Data Science Academy (DSA). (2022). Deep learning book. https://www.deeplearningbook.com.br/
Deng, T., Liu, X. & Mao, G. (2022). Improved YOLOv5 Based on Hybrid Domain Attention for Small Object Detection in Optical Remote Sensing Images. Eletronics, 11(17), 2657. https://doi.org/10.3390/electronics11172657
Foody, G. M. (2009). Sample size determination for image classification accuracy assessment and comparison. International Journal of Remote Sensing, 30(20), 5273-5291. https://doi.org/10.1080/01431160802582899
Ge, P., He, J., Zhang, S., Zhang, L., & She, J. F. (2019). An integrated framework combining multiple human activity features for land use classification. ISPRS International Journal of Geo-Information, 8(2), 90. https://doi.org/10.3390/ijgi8020090
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Hao, X., Liu, L., Yang, R., Yin, L., Zhang, L. & Li, X. (2023). A Review of Data Augmentation Methods of Remote Sensing Image Target Recognition. Remote Sensing, 15(3), 827. https://doi.org/10.3390/rs15030827
Johnson, J. M., & Khoshgoftaaar, T. M. (2019). Survey on deep learning with class imbalance. Journal of Big Data, 6(1), 27. https://doi.org/10.1186/s40537-019-0192-0
Jozdani, S. E., Johnson, B. A., & Chen, D. (2019). Comparing deep neural networks, ensemble classifiers, and support vector machine algorithms for object-based urban land use/land cover classification. Remote Sensing, 11(14), 1713. https://doi.org/10.3390/rs11141713
Karimian, R., Rangzan, K., Karimi, D. & Einali, G. (2024). Spatiotemporal Monitoring of Land Use-Land Cover and Its Relationship with Land Surface Temperature Changes Based on Remote Sensing, GIS, and Deep Learning. J Indian Soc Remote Sens, 52, 2461. https://doi.org/10.1007/s12524-024-01958-3
Klippel, S. (2022). CBERS4A downloader QGIS plugin. https://github.com/sandroklippel/cbers4a
Kuras, A., et al. (2021). Hyperspectral and Lidar data applied to the urban land cover machine learning and neural-network-based classification: A review. Remote Sensing, 13(17), 3393. https://doi.org/10.3390/rs13173393
Li, Z., Wang, Y., Zhang, N., Zhang, Y., Zhao, Z., Xu, D., Ben, G., & Gao, Y. (2022). Deep Learning-Based Object Detection Techniques for Remote Sensing Images: A Survey. Remote sensing, 14(10), 2385. https://doi.org/10.3390/rs14102385
Lv, Z., Huang, H., Sun, W., Lei, T., Benediktsson, J. A. & Li, J. (2023). Novel Enhanced UNet for Change Detection Using Multimodal Remote Sensing Image. IEEE Geoscience and Remote Sensing Letters, 20, 1. 10.1109/LGRS.2023.3325439
Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., & Johnson, B. A. (2019). Deep learning in remote sensing applications: A meta-analysis and review. ISPRS Journal of Photogrammetry and Remote Sensing, 152, 166–177. https://doi.org/10.1016/j.isprsjprs.2019.05.019
Magalhães, D. M. (2024). Avaliação da acurácia da classificação supervisionada de imagens de sensoriamento remoto utilizando o software ArcGIS Pro. In N. I. Ladwig, T. Sutil, C. H. R. da Silva, & B. Giaccom (Eds.), Planejamento e gestão territorial (1st ed., pp. 141-164). Pedro e João. http://dx.doi.org/10.51795/9786526514276
Malik, K., Robertson, C., Braun, D., & Greig, C. (2021). U-Net convolutional neural network models for detecting and quantifying placer mining disturbances at watershed scales. International Journal of Applied Earth Observation and Geoinformation, 104, 102510. https://doi.org/10.1016/j.jag.2021.102510
Maxwell, A. E., Warner, T. A. & Guillén, L. A. (2021a). Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 1: Literature Review. Remote Sensing, 13(13), 2450. https://doi.org/10.3390/rs13132450
Maxwell, A. E., Warner, T. A. & Guillén, L. A. (2021b). Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 2: Recommendations and Best Practices. Remote Sensing, 13(13), 2591. https://doi.org/10.3390/rs13132591
Morales-Barquero, L., Lyons, M. B., Phinn, S. R., & Roelfsema, C. M. (2019). Trends in Remote Sensing Accuracy Assessment Approaches in the Context of Natural Resources. Remote Sensing, 11(19), 2305. https://doi.org/10.3390/rs11192305
Nigar, A., Li, Y., Jat Baloch, M. Y., Alrefaei, A. F. & Almutairi, M. H. (2024). Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications. Frontiers in Environmental Science, 12, 01. 10.3389/fenvs.2024.1378443
Odenyo, V. A. O., & Pettry, D. E. (1977). Land-use mapping by machine processing of LANDSAT-1 data. Photogrammetric Engineering and Remote Sensing, 43(4), 515–523.
Pabi, O. (2007). Understanding land-use/cover change process for land and environmental resources use management policy in Ghana. GeoJournal, 68(4), 369–383. https://doi.org/10.1007/s10708-007-9120-7
Parente, L., Taquary, E., Silva, A. P., Souza, C., & Ferreira, L. (2019). Next generation mapping: Combining deep learning, cloud computing, and big remote sensing data. Remote Sensing, 11(23), 2881. https://doi.org/10.3390/rs11232881
Picoli, M. C. A., Simoes, R., Chaves, M., Santos, L. A., Sanchez, A., Soares, A., Sanches, I. D., Ferreira, K. R., & Queiroz, G. R. (2020). CBERS data cube: A powerful technology for mapping and monitoring Brazilian biomes. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-3–2020, 533–539. https://doi.org/10.5194/isprs-annals-V-3-2020-533-2020
Ponti, M. A., & Costa, G. B. P. (2017). Como funciona o deep learning. In: Tópicos em gerenciamento de dados e informações (1st ed., p. 31). SBC.
Prakash, D. P., & Rao, A. S. K. R. (2017). Deep learning cookbook: Solve complex neural net problems with TensorFlow, H2O, and MXNET. Packt.
Sheykhmousa, M., Mahdianpari, M., Ghanbari, H., Mohammadimanesh, F., Ghamisi, P. & Homayouni, S. (2020). Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 6308. 10.1109/JSTARS.2020.3026724.
Solórzano, J. V., Mas, J. F., Gao, Y., & Gallardo-Cruz, J. A. (2021). Land use land cover classification with U-Net: Advantages of combining Sentinel-1 and Sentinel-2 imagery. Remote Sensing, 13(18), 3600. https://doi.org/10.3390/rs13183600
Vali, A., Comai, S., & Matteucci, M. (2020). Deep learning for land use and land cover classification based on hyperspectral and multispectral earth observation data: A review. Remote Sensing, 12(15), 2495. https://doi.org/10.3390/rs12152495
Vázquez, F. (2017, December 21). Deep learning made easy with deep cognition. Becoming Human: Artificial Intelligence Magazine. https://becominghuman.ai/deep-learning-made-easy-with-deep-cognition-403fbe445351
Wagner, F. H., Dalagnol, R., Tarabalka, Y., Segantine, T. Y. F., Thomé, R., & Hirye, M. C. M. (2020a). U-Net-Id, an instance segmentation model for building extraction from satellite images — Case study in the Joanópolis City, Brazil. Remote Sensing, 12(10), 1544. https://doi.org/10.3390/rs12101544
Wagner, F. H., Dalagnol, R., Tagle Casapia, X., Streher, A. S., Phillips, O. L., Gloor, E., & Aragão, L. E. O. C. (2020b). Regional mapping and spatial distribution analysis of canopy palms in an Amazon forest using deep learning and VHR images. Remote Sensing, 12(14), 2225. https://doi.org/10.3390/rs12142225
Wang, L., Zhang, M., Gao, X., & Shi, W. (2024). Advances and challenges in deep learning-based change detection for remote sensing images: A review through various learning paradigms. Remote Sensing, 16, 804. https://doi.org/10.3390/rs16050804
Yan, C., Fan, X., Fan, J., & Wang, N. (2022). Improved U-Net remote sensing classification algorithm based on multi-feature fusion perception. Remote Sensing, 14(5), 1118. https://doi.org/10.3390/rs14051118
Yang, Y., Wan, W., Huang, S., Lin, P., & Que, Y. (2017). A novel pan-sharpening framework based on matting model and multiscale transform. Remote Sensing, 9(4), 391. https://doi.org/10.3390/rs9040391
Yu, J., Zeng, P., Yu, Y., Yu, H., Huang, L., & Zhou, D. (2022). A combined convolutional neural network for urban land-use classification with GIS data. Remote Sensing, 14(5), 1128. https://doi.org/10.3390/rs14051128
Zhang, X., Du, L., Tan, S., Wu, F., Zhu, L., Zeng, Y., & Wu, B. (2021). Land use and land cover mapping using RapidEye imagery based on a novel band attention deep learning method in the Three Gorges Reservoir area. Remote Sensing, 13(6), 1225. https://doi.org/10.3390/rs13061225
Zhang, P., Wu, Y., Li, C., Li, R., Yao, H., Zhang, Y., Zhang, G. & Li, D. (2023). National-Standards- and Deep-Learning-Oriented Raster and Vector Benchmark Dataset (RVBD) for Land-Use/Land-Cover Mapping in the Yangtze River Basin. Remote Sensing, 14(15), 3907. https://doi.org/10.3390/rs15153907
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019). Object detection with deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems. https://doi.org/10.1109/TNNLS.2019.2897602
Zhao, S., Tu, K., Ye, S., Tang, H., Hu, Y. & Xie, C. (2023). Land Use and Land Cover Classification Meets Deep Learning: A Review. Remote Sensing, 23(21), 8966. https://doi.org/10.3390/s23218966