KNN e Rede Neural Convolucional para o Reconhecimento de Plataformas de Petróleo em Imagens SAR do Sentinel-1
DOI:
https://doi.org/10.55972/spectrum.v24i1.395Palavras-chave:
Synthetic Aperture Radar (SAR), Reconhecimento automático de alvos (ATR), Machine learningResumo
O reconhecimento automático de alvos (plataformas petrolíferas) por meio de imagens SAR de média resolução auxilia a vigilância de áreas extensas como o Atlântico Sul. Por isso, esse trabalho aprofundou o estudo do emprego da VGG-16 como extratora de atributos para alimentar algoritmos de Machine Learning, especificamente, o kNN. Variou-se o número de vizinhos para um conjunto de amostras de imagens SAR do Sentinel-1 contendo plataformas marítimas e falsos-alarmes, usando um experimento com 50 blocos de treinamento e teste. Demonstrou-se que o ajuste de parâmetros do classificador apresenta melhorias significativas, com um incremento de 6,46% no indicador AUC.
Referências
Comando da Aeronáutica, Ministério da Defesa, and Brasil, “Dimensão 22,” 2018. [Online]. Available: http://www.fab.mil.br/dimensao22. [Accessed: 02-Apr-2018].
IEEE GRSS Beijing Chapter and RADI, “Proceedings of 2017 SAR in Big Data Era: Models, Methods and Applications, BIGSARDATA 2017,” Proc. 2017 SAR Big Data Era Model. Methods Appl. BIGSARDATA 2017, vol. 2017-Janua, p. 2017, 2017.
F. Palazzo et al., “RUS: A New Expert Service for Sentinel Users,” Proceedings, vol. 2, no. 7, p. 369, 2018.
A. G. Castriotta and R. Knowelden, “COPE-SERCO-RP-17-0186: Sentinel Data Access 2017 Annual Report,” Frascati, 2018.
J. Blumenfeld, “Getting Ready for NISAR — and for Managing Big Data using the Commercial Cloud,” ASF News, 2018. [Online]. Available: https://www.asf.alaska.edu/news-notes/winter-2017-1/getting-ready-for-nisar/.
A. Marino, D. Velotto, and F. Nunziata, “Offshore Metallic Platforms Observation Using Dual-Polarimetric TS-X/TD-X Satellite Imagery: A Case Study in the Gulf of Mexico,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 10, no. 10, pp. 4376–4386, Oct. 2017.
L. E. Falqueto, J. A. S. Sa, R. L. Paes, and A. Passaro, “Oil Rig Recognition Using Convolutional Neural Network on Sentinel-1 SAR Images,” IEEE Geosci. Remote Sens. Lett., pp. 1–5, 2019.
PETROBRAS, “Tipos de plataformas,” 2018. [Online]. Available: http://www.petrobras.com.br/infograficos/tipos-de-plataformas/desktop/index.html. [Accessed: 15-Jun-2018].
D. Zhang, J. Liu, W. Heng, K. Ren, and J. Song, “Transfer Learning with Convolutional Neural Networks for SAR Ship Recognition,” IOP Conf. Ser. Mater. Sci. Eng., vol. 322, no. 7, p. 072001, Mar. 2018.
S. Chen, H. Wang, F. Xu, and Y. Q. Jin, “Target Classification Using the Deep Convolutional Networks for SAR Images,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 8, pp. 4806–4817, 2016.
M. Wilmanski, C. Kreucher, and J. Lauer, “Modern approaches in deep learning for SAR ATR,” in Modern approaches in deep learning for SAR ATR, Proc. SPIE 9843, 2016, no. 98430N, p. 10.
J. Pei, Y. Huang, W. Huo, Y. Zhang, J. Yang, and T.-S. Yeo, “SAR Automatic Target Recognition Based on Multiview Deep Learning Framework,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 4, pp. 1–15, 2017.
H. Furukawa, “SAVERS: SAR ATR with Verification Support Based on Convolutional Neural Network,” pp. 23–28, 2018.
F. Gao, T. Huang, J. Sun, J. Wang, A. Hussain, and E. Yang, “A New Algorithm of SAR Image Target Recognition Based on Improved Deep Convolutional Neural Network,” Cognit. Comput., vol. 18, no. 1, pp. 25–30, Jun. 2018.
F. Gao, Y. Yang, J. Wang, J. Sun, E. Yang, and H. Zhou, “A Deep Convolutional Generative Adversarial Networks (DCGANs)-Based Semi-Supervised Method for Object Recognition in Synthetic Aperture Radar (SAR) Images,” Remote Sens., vol. 10, no. 6, p. 846, May 2018.
E. G. Zelnio, M. Levy, R. D. Friedlander, and E. Sudkamp, “Deep learning model-based algorithm for SAR ATR,” Algorithms Synth. Aperture Radar Imag. XXV, no. May, p. 10, 2018.
C. Wang, H. Zhang, F. Wu, B. Zhang, and S. Tian, “Ship classification with deep learning using COSMO-SkyMed SAR data,” in 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2017, pp. 558–561.
C. Bentes, D. Velotto, and B. Tings, “Ship Classification in TerraSAR-X Images With Convolutional Neural Networks,” IEEE J. Ocean. Eng., vol. 43, pp. 258–266, Jan. 2017.
D. C. Montgomery, Design and Analysis of Experiments, Eighth. Arizona: John Wiley & Sons, Inc., 2013.
K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Inf. Softw. Technol., vol. 51, no. 4, pp. 769–784, Sep. 2014.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
J. Demšar et al., “Orange: Data Mining Toolbox in Python,” J. Mach. Learn. Res., vol. 14, pp. 2349–2353, 2013.
O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,” Int. J. Comput. Vis., vol. 115, no. 3, pp. 211–252, Dec. 2015.
S. B. Kotsiantis, I. D. Zaharakis, and P. E. Pintelas, “Machine learning: a review of classification and combining techniques,” Artif. Intell. Rev., vol. 26, no. 3, pp. 159–190, Nov. 2006.
T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, 2006.
M. Ferguson, R. Ak, Y.-T. T. Lee, and K. H. Law, “Automatic localization of casting defects with convolutional neural networks,” no. December, pp. 1726–1735, 2018.
Downloads
Publicado
Como Citar
Edição
Seção
Categorias
Licença
Copyright (c) 2023 Falqueto, Rafael Paes, Angelo
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
