آمار

تعداد نشریات36
تعداد شماره‌ها1,192
تعداد مقالات8,579
تعداد مشاهده مقاله6,988,711
تعداد دریافت فایل اصل مقاله4,032,562
درویش نژاد, محسن, سبط, محمدعلی. (1401). انتخاب ویژگیهای پلارمیتری استخراج شده از تصاویر PolSAR برمبنای اطلاعات متقابل ویژگیها به منظور طبقه بندی پوششی سطح زمین در تصاویر استخراج شده از رادار دهانه مصنوعی. پدافند الکترونیکی و سایبری, 10(1), 35-55.
محسن درویش نژاد; محمدعلی سبط. "انتخاب ویژگیهای پلارمیتری استخراج شده از تصاویر PolSAR برمبنای اطلاعات متقابل ویژگیها به منظور طبقه بندی پوششی سطح زمین در تصاویر استخراج شده از رادار دهانه مصنوعی". پدافند الکترونیکی و سایبری, 10, 1, 1401, 35-55.
درویش نژاد, محسن, سبط, محمدعلی. (1401). 'انتخاب ویژگیهای پلارمیتری استخراج شده از تصاویر PolSAR برمبنای اطلاعات متقابل ویژگیها به منظور طبقه بندی پوششی سطح زمین در تصاویر استخراج شده از رادار دهانه مصنوعی', پدافند الکترونیکی و سایبری, 10(1), pp. 35-55.
درویش نژاد, محسن, سبط, محمدعلی. انتخاب ویژگیهای پلارمیتری استخراج شده از تصاویر PolSAR برمبنای اطلاعات متقابل ویژگیها به منظور طبقه بندی پوششی سطح زمین در تصاویر استخراج شده از رادار دهانه مصنوعی. پدافند الکترونیکی و سایبری, 1401; 10(1): 35-55.

انتخاب ویژگیهای پلارمیتری استخراج شده از تصاویر PolSAR برمبنای اطلاعات متقابل ویژگیها به منظور طبقه بندی پوششی سطح زمین در تصاویر استخراج شده از رادار دهانه مصنوعی

رادار
مقاله 5، دوره 10، شماره 1 - شماره پیاپی 27، تیر 1401، صفحه 35-55    اصل مقاله (1.74 M)
نوع مقاله: مقاله پژوهشی
نویسندگان
محسن درویش نژاد* 1؛ محمدعلی سبط2
1دانشجوی دکترا، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران
2دانشیار، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران
تاریخ دریافت: 24 آبان 1400،  تاریخ بازنگری: 16 آذر 1401،  تاریخ پذیرش: 02 اسفند 1401 
چکیده
درسالیان اخیر، طبقه‌بندی پوششی سطح زمین به عنوان یکی از مهمترین کاربردهای تصاویر پلاریمتری استخراج شده از رادار دهانه مجازی عنوان شده است. داده‌های پلاریمتری راداری ذاتا دارای ویژگی‌های مناسبی برای طبقه‌بندی اهداف مختلف سطح زمین می‌باشند. لذا به منظور استفاده بالا و مناسب از پتانسیل بالای اطلاعاتی از این دادگان می‌توانیم ویژگی‌های متعددی از آنها استخراج نماییم. لذا استخراج ویژگی از این دادگان گام مهمی در طبقه‌بندی اهداف سطح زمین می‌باشد. در این مقاله، هدف استخراج و انتخاب ویژگی از تصاویر پلاریمتری رادار دهانه مصنوعی به شکلی است که نرخ طبقه‌بندی اهداف موجود در سطح زمین بهبود پیدا کند. در این مقاله، چهار گام اساسی برای بهبود دقت طبقه‌بندی اتخاذ شده است:1-استخراج ویژگی پلاریمتری راداری در قالب سه گروه ویژگی بنام‌های: ویژگی‌های اصلی، ویژگی‌های تجزیه هدف و تفکیک کننده‌های رادار دهانه مصنوعی.2-طبقه‌بندی اولیه دادگان با استفاده از ویژگی‌های استخراج شده.3-رتبه-بندی ویژگی‌ها بر اساس اطلاعات متقابل بین ویژگی‌ها و نقشه طبقه‌بندی اولیه بدست آمده در مرحله دوم.4-بدست آوردن ویژگی‌های بهینه با استفاده از روش‌های پیشنهادی و طبقه‌بندی نهایی. در روش‌ پیشنهادی از طبقه‌بند ماشین بردار پشتیبان به منظور طبقه‌بندی دادگان استفاده خواهد شد و ویژگی‌های بهینه به نحوی که نرخ طبقه‌بندی افزایش پیدا کند، انتخاب خواهند شد. نتایج حاصله بر روی تصویر راداری منطقه Flevoland حاکی از افزایش دقت طبقه‌بندی روش پیشنهادی نسبت به سایر روش‌های مورد استفاده در این تحقیق است.
کلیدواژه‌ها
طبقه‌بندی؛ رادار دهانه مصنوعی؛ تصاویر پلارمتری؛ انتخاب ویژگی
عنوان مقاله [English]
Feature Selection Method Based on Mutual Information for Polarimetric Synthetic Aperture Radar (PolSAR) Image Classification
نویسندگان [English]
Mohsen Darvishnezhad1؛ ُMohammad Ali Sebt2
1PhD student, K.N.Toosi University of Tech., Tehran, Iran
2Associate Professor, K.N.Toosi University of Tech., Tehran, Iran
چکیده [English]
In recent years, Polarimetric Synthetic Aperture Radar (PolSAR) image classification has been cited as one of the most important applications of images classification. Therefore, in order to achieve the best result of PolSAR image classification in this article, a new feature selection method will be proposed based on mutual information theory. In the proposed method, the features that are extracted from PolSAR images will be used to obtain an initial class map. Then, each feature will be ranked based on mutual information. In the next step, the best features will be selected by using the proposed method accurately. The results that are obtained on the real PolSAR image of the Flevoland area prove an increase in the classification accuracy of the proposed method compared with other methods that are used in this research.
کلیدواژه‌ها [English]
Classification, PolSAR, Feature Selection, Synthetic Aperture Radar
مراجع
  1. Yang, Chen, Biao Hou, Jocelyn Chanussot, Yue Hu, Bo Ren, Shuang Wang, and Licheng Jiao, "N-Cluster Loss and Hard Sample Generative Deep Metric Learning for PolSAR Image Classification," In IEEE Transactions on Geoscience and Remote Sensing,2, pp.205-207 , 2021.
  2. Okwuashi, Onuwa, Christopher E. Ndehedehe, Dupe Nihinlola Olayinka, Aniekan Eyoh, and Hosanna Attai, "Deep support vector machine for PolSAR image classification," In International Journal of Remote Sensing, 42, pp. 6502-6540, 2021.
  3. Liu, Guangyuan, Yangyang Li, Licheng Jiao, Yanqiao Chen, and Ronghua Shang, "Multiobjective evolutionary algorithm assisted stacked autoencoder for PolSAR image classification," In  Swarm and Evolutionary Computation, vol.60, no.25, pp.100794, 2021.
  4. Wang, Xiao, Lamei Zhang, Ning Wang, and Bin Zou, "Joint Polarimetric-Adjacent Features Based on LCSR for PolSAR Image Classification," In IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing vol.14, pp. 6230-6243, 2021.
  5. Dong, Hongwei, Lamei Zhang, and Bin Zou, "Exploring vision transformers for polarimetric SAR image classification," In IEEE Transactions on Geoscience and Remote Sensing, vol.4, pp. 1-15, 2021.
  6. Tsunoda, Stanley I., Frank Pace, Jesse Stence, Marv Woodring, William H. Hensley, Armin W. Doerry, and Bruce C. Walker, "Lynx: A high-resolution synthetic aperture radar," In IEEE Aerospace Conference, vol. 5, pp. 51-58, 2000.
  7. Cui, Yuanhao, Fang Liu, Licheng Jiao, Yuwei Guo, Xuefeng Liang, Lingling Li, Shuyuan Yang, and Xiaoxue Qian, "Polarimetric multipath convolutional neural network for PolSAR image classification," In IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-18, 2021.
  8. Ban, Yifang, and Hongtao Hu, "RADARSAT fine-beam SAR data for land-cover mapping and change detection in the rural-urban fringe of the greater Toronto area," In 2007 Urban Remote Sensing Joint Event, vol. 4, pp. 1-7, 2007.
  9. McNairn, H., J. Ellis, J. J. Van Der Sanden, T. Hirose, and R. J. Brown, "Providing crop information using RADARSAT-1 and satellite optical imagery," In International Journal of Remote Sensing, vol. 5, pp. 851-870, 2002.
  10. Morena, L. C., K. V. James, and J. Beck, "An introduction to the RADARSAT-2 mission," In Canadian Journal of Remote Sensing, vol. 3, pp. 221-234, 2004.
  11. Zhang, Yachao, Xuan Lai, Yuan Xie, Yanyun Qu, and Cuihua Li, "Geometry-Aware Discriminative Dictionary Learning for PolSAR Image Classification," In Remote Sensing, vol. 6, pp.12-18. 2021.
  12. Chen, Yanqiao, Lingling Li, Licheng Jiao, Yangyang Li, Xu Liu, and Xinghua Chai, "Nonlinear Projective Dictionary Pair Learning for PolSAR Image Classification." In IEEE Access, vol. 9, pp. 70650-70661, 2021.
  13. Kuo, Frances Y, and Ian H. Sloan, "Lifting the curse of dimensionality," In Notices of the AMS, vol. 11, pp. 1320-1328, 2005.
  14. Salehi M., Y. Maghsoudi, and M. R. Sahebi, "Improving the Urban Area Classification Using Radar Polarimetric Data and multiobjective optimization methods," In Journal of Radar, vol. 1, pp. 45-56, 2014 (in Persian).
  15. Maghsoudi, Yasser, Michael Collins, and Donald G. Leckie, "Polarimetric classification of Boreal forest using nonparametric feature selection and multiple classifiers," In International journal of applied earth observation and geoinformation, vol. 19, pp. 139-150, 2012.
  16. Dabbiru, Lalitha, Sathishkumar Samiappan, Rodrigo AA Nobrega, James A. Aanstoos, Nicolas H. Younan, and Robert J. Moorhead, "Fusion of synthetic aperture radar and hyperspectral imagery to detect impacts of oil spill in Gulf of Mexico," In 2015 IEEE international geoscience and remote sensing symposium (IGARSS), vol. 2, pp. 1901-1904, 2015.
  17. Cao, Yice, Yan Wu, Ming Li, Wenkai Liang, and Peng Zhang, "PolSAR image classification using a superpixel-based composite kernel and elastic net," In Remote Sensing, vol. 3, pp.380-381, 2021.
  18. Wang, Jianlong, Biao Hou, Licheng Jiao, and Shuang Wang, "Representative learning via span-based mutual information for PolSAR image classification," In Remote Sensing, vol. 9, pp.1609-1616, 2021.
  19. Liu, Hongying, Derong Xu, Tianwen Zhu, Fanhua Shang, Yuanyuan Liu, Jianhua Lu, and Ri Yang, "Graph convolutional networks by architecture search for PolSAR image classification," In Remote Sensing, vol. 7, pp. 1404-1405, 2021.
  20. Gui, Rong, Xin Xu, Rui Yang, Zhaozhuo Xu, Lei Wang, and Fangling Pu, "A general feature paradigm for unsupervised cross-domain PolSAR image classification," In IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2021.
  21. Zhang, Peng, Xiaofeng Tan, Beibei Li, Yinyin Jiang, Wanying Song, Ming Li, and Yan Wu, "PolSAR image classification using hybrid conditional random fields model based on complex-valued 3-D CNN," In IEEE Transactions on Aerospace and Electronic Systems, vol. 3, pp. 1713-1730, 2021.
  22. Pottier, Eric, and J-S. Lee, "Application of the «H/A/alpha» polarimetric decomposition theorem for unsupervised classification of fully polarimetric SAR data based on the wishart distribution," In SAR workshop: CEOS Committee on Earth Observation Satellites, vol. 1, pp. 335, 2000.
  23. Krogager, E, "Absolute phase of the radar target scattering matrix," In Electronics Letters, vol. 26, pp. 1834-1835, 1990.
  24. Pottier, Eric, and Laurent Ferro-Famil, "PolSARPro V5. 0: An ESA educatonal toolbox used for self-education in the field of POLSAR and POL-INSAR data analysis," In IEEE International Geoscience and Remote Sensing Symposium, vol. 1, pp.5-11, 2012.
  25. Jiang, Yinyin, Ming Li, Peng Zhang, Xiaofeng Tan, and Wanying Song, "Unsupervised Complex-Valued Sparse Feature Learning for PolSAR Image Classification," In IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp.1-16, 2022.
  26. Xie, Wen, Licheng Jiao, and Wenqiang Hua, "Complex-Valued Multi-Scale Fully Convolutional Network with Stacked-Dilated Convolution for PolSAR Image Classification," In Remote Sensing, vol. 15, pp. 3737-3739, 2022.
  27. Liu, Guangyuan, Yangyang Li, Yanqiao Chen, Ronghua Shang, and Licheng Jiao, "Pol-NAS: A Neural Architecture Search Method With Feature Selection for PolSAR Image Classification," In IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp.9339-9354, 2022.
  28. Breyer, Marcel, Alexander Van Craen, and Dirk Pflüger, "A Comparison of SYCL, OpenCL, CUDA, and OpenMP for Massively Parallel Support Vector Machine Classification on Multi-Vendor Hardware," In International Workshop on OpenCL, vol.3, pp. 1-12. 2022.
  29. Jamali, Ali, Masoud Mahdianpari, Fariba Mohammadimanesh, Avik Bhattacharya, and Saeid Homayouni, "PolSAR image classification based on deep convolutional neural networks using wavelet transformation," In IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022.
  30. Khandelwal, Monika, Nazir Shabbir, and Saiyed Umer, "Extraction of Sequence-Based Features for Prediction of Methylation Sites in Protein Sequences." In Artificial Intelligence Technologies for Computational Biology, vol. 1, pp. 29-46, 2022.
  31. Sun, Jili, Lingdong Geng, and Yize Wang, "A Hybrid Model Based on Superpixel Entropy Discrimination for PolSAR Image Classification." In Remote Sensing, vol. 14, pp. 4116-4129, 2022.
  32. Ramírez-Rojas, A., P. R. Cárdenas-Moreno, and C. A. Vargas, "Mutual information analysis between NO2 and O3 pollutants measured in Mexico City before and during 2020 Covid-19 pandemic year," In Journal of Physics: Conference Series, vol. 2307, pp. 12053-12059. 2022.
  33. Dong, Wei, Junsheng Wu, Yi Luo, Zongyuan Ge, and Peng Wang, "Node Representation Learning in Graph via Node-to-Neighbourhood Mutual Information Maximization," In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, vol.1, pp. 16620-16629. 2022.
  34. Yu, Peter, A. Kai Qin, and David A. Clausi, "Unsupervised polarimetric SAR image segmentation and classification using region growing with edge penalty," In IEEE Transactions on Geoscience and Remote Sensing. vol. 4, pp. 1302-1317, 2011.
  35. Köppen, Mario, "The curse of dimensionality," In 5th Online World Conference on Soft Computing in Industrial Applications (WSC5), vol. 1, pp. 12-17, 2000.
  36. Kikukawa, Atsushi, Kiwamu Tanahashi, Yukio Honda, Yoshiyuki Hirayama, and Masaaki Futamoto, "Distributions and characteristics of spike noise," In Journal of magnetism and magnetic materials, vol. 1, 68-72, 2001.
  37. Imani, Maryam, "Polarimetric SAR Classification Using Ridge Regression-Based Polarimetric-Spatial Feature Extraction," In 26th International Computer Conference, Computer Society of Iran (CSICC), pp.1-5 2021.
  38. Lee, Jong-Sen, Mitchell R. Grunes, and Gianfranco De Grandi, "Polarimetric SAR speckle filtering and its implication for classification," In IEEE Transactions on Geoscience and remote sensing, vol.1 , pp. 2363-2373, 1999.
  39. Park, Jooyoung, and Irwin W. Sandberg, "Approximation and radial-basis-function networks," In Neural computation, vol. 2, pp. 305-316, 1993.
  40. Thielicke, William, and René Sonntag, "Particle Image Velocimetry for MATLAB: Accuracy and enhanced algorithms in PIVlab," In Journal of Open Research Softwar, vol. 1, pp.1-9, 2021.
  41. Rigby, Alan S, "Statistical methods in epidemiology. v. Towards an understanding of the kappa coefficient," In Disability and rehabilitation, vol. 8, pp. 339-344, 2000.
  42. Estévez, Pablo A., Michel Tesmer, Claudio A. Perez, and Jacek M. Zurada, "Normalized mutual information feature selection," In IEEE Transactions on neural networks, vol. 2, pp. 189-201, 2009.
  43. Cheng, Jianda, Fan Zhang, Deliang Xiang, Qiang Yin, and Yongsheng Zhou, "PolSAR image classification with multiscale superpixel-based graph convolutional network." In IEEE Transactions on Geoscience and Remote Sensing, vol. 1, pp. 1-14, 2021.
  44. Liu, Xu, Licheng Jiao, Xu Tang, Qigong Sun, and Dan Zhang, "Polarimetric convolutional network for PolSAR image classification," In IEEE Transactions on Geoscience and Remote Sensing, vol. 5, pp. 3040-3054, 2018.
  45. Chen, Si-Wei, and Chen-Song Tao, "PolSAR image classification using polarimetric-feature-driven deep convolutional neural network," In IEEE Geoscience and Remote Sensing Letters, vol.1, pp.627-631, 2018.
  46. Bi, Haixia, Feng Xu, Zhiqiang Wei, Yong Xue, and Zongben Xu, "An active deep learning approach for minimally supervised PolSAR image classification," In IEEE Transactions on Geoscience and Remote Sensing, vol. 11, pp. 9378-9395, 2019.
  47. Li, Yangyang, Yanqiao Chen, Guangyuan Liu, and Licheng Jiao, "A novel deep fully convolutional network for PolSAR image classification," In Remote Sensing , vol.12, pp. 1984-1991, 2018.
  48. Liao, Wenzhi, Mauro Dalla Mura, Jocelyn Chanussot, and Aleksandra Pižurica, "Fusion of spectral and spatial information for classification of remote-sensed imagery by local graph," In IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 2, pp. 583-594, 2015.
  49. Mou, Lichao, Pedram Ghamisi, and Xiao Xiang Zhu, "Deep recurrent neural networks for image classification," In IEEE Transactions on Geoscience and Remote Sensing, vol. 7, pp. 3639-3655, 2017.
  50. Dang, Bo, and Yansheng Li, "MSResNet: Multiscale residual network via self-supervised learning for water-body detection in remote sensing imagery," In Remote Sensing, vol. 16, pp. 3122-3129, 2021.
آمار
تعداد مشاهده مقاله: 313
تعداد دریافت فایل اصل مقاله: 46