طبقه‌بندی شورایی تطبیقی پوشش اراضی با استفاده از تصاویر پلاریمتریک راداری و قاعده ترکیب پیشنهادی

نوع مقاله: مقاله پژوهشی

نویسندگان

دانشگاه بیرجند

چکیده

با توجه به قابلیت‌های فراوان تصاویر پلاریمتریک راداری به‌عنوان یک منبع اطلاعات راهبردی، استفاده از آنها در کاربردهای نظامی و تجاری، رشد روزافزونی دارد. یکی از موضوع‌های مهم و مورد علاقه پژوهشگران، بحث طبقه‌بندی این تصاویر است. لذا در این مقاله، ساختار یک طبقه‌بند شورایی مبتنی بر روش نمایش تنک که به‌صورت تطبیقی برای دو دسته از پیکسل‌ها مرزی و غیرمرزی تصاویر پلاریمتریک اجرا می‌شود، ارائه گردیده است. در این طرح جنبه‌های مختلف (طبقه‌بندهای پایه و تنوع آنها، ساختار طبقه‌بند شورایی، قابلیت اطمینان، قاعده ترکیب، ویژگی‌های پلاریمتریک و بافت و اطلاعات زمینه‌ای) مد نظر قرار گرفته است. جهت طراحی قاعده ترکیب طبقه‌بندهای پایه، از یک روش پیشنهادی مبتنی بر پارامتر قابلیت اطمینان و برای کاهش گسستگی‌های ناخواسته در خروجی طبقه‌بند شورایی، از یک مرحله پس‌پردازش استفاده شده است. نتایج پیاده‌سازی الگوریتم‌های پیشنهادی بر روی نمونه تصویر پلاریمتریک، حاکی از برتری آنها نسبت به سایر روش‌های متداول است.

کلیدواژه‌ها


عنوان مقاله [English]

Adaptive Ensemble Classification for Land Cover Classification Using Polarimetric Radar Images and Proposed Combination Rule

نویسندگان [English]

  • Hasan farsi
  • reza saleh
University of Birjand
چکیده [English]

Due to numerous capabilities of polarimetric radar images as a source of strategic information, their use in military and commercial applications is rapidly growing. One of the important topics of interest to researchers is the classification of these images. So in this paper, the structure of an ensemble of classifiers based on sparse representation technique is presented which classifies adaptively two sets of border and non-border pixels in a polarimetric image. In this plan, various aspects such as base classifiers and their diversity, ensemble of classifier structure, reliability, combination rule, polarimetric and texture features and contextual information are considered. For designing the combination rule of base classifiers, a method based on reliability parameter is proposed. Also, a post-processing stage is used for reducing the unwanted discretion in the output of the ensemble of classifiers. Implementation of the proposed algorithms on a benchmark PolSAR image, demonstrates their superiority over that of traditional techniques.

کلیدواژه‌ها [English]

  • PolSAR Data
  • Ensemble Classification
  • Rule Combination
  • Sparse Representation-Based Classifiers
  • Reliability
  • Post-Processing

[1] S. Shitole, Y. Rao, B. K. Mohan, and A. Das, “Selection of Suitable Window Size for Speckle Reduction and Deblurring using SOFM in Polarimetric SAR Images,” Journal of the Indian Society of Remote Sensing, vol. 43, pp. 739-750, 2015.
[2] K. Ouchi, “Recent trend and advance of synthetic aperture radar with selected topics,” Remote Sensing, vol. 5, pp. 716-807, 2013.
[3] J. A. Richards, “Remote sensing with imaging radar,” Springer, 2009.
[4] J. Feng, Z. Cao, and Y. Pi, “Polarimetric Contextual Classification of PolSAR Images Using Sparse Representation and Superpixels,” Remote Sensing, vol. 6, pp. 7158-7181, 2014.
[5] L. Zhang, L. Sun, B. Zou, and W. M. Moon, “Fully polarimetric SAR image classification via sparse representation and polarimetric features,” Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of, vol. 8, pp. 3923-3932, 2015.
[6] M. Salehi, Y. Maghsoudi, M. R. Sahebi “Improving the Urban Area Classification Using Radar Polarimetric Data and multiobjective optimization methods,” Journal of Radar, vol. 1, no. 2, pp. 45-56, 2014.
[7] J. Yang, Y. Yamaguchi, L. Jong-Sen, R. Touzi, and W. M. Boerner, “Applications of polarimetric sar,” Journal of Sensors, vol. 2015, pp. 1-2, 2015.
[8] L. Shi, L. Zhang, J. Yang, L. Zhang, and P. Li, “Supervised graph embedding for polarimetric SAR image classification,” Geoscience and Remote Sensing Letters, IEEE, vol. 10, pp. 216-220, 2013.
[9] A. Masjedi, M. J. V. Zoej, and Y. Maghsoudi, “Classification of Polarimetric SAR Images Based on Modeling Contextual Information and Using Texture Features,” IEEE Transactions on Geoscience and Remote Sensing, vol. 54, pp. 932-943, 2016.
[10] T. Ince, S. Kiranyaz, and M. Gabbouj, “Evolutionary RBF classifier for polarimetric SAR images,” Expert Systems with Applications, vol. 39, pp. 4710-4717, 2012.
[11] Y. Maghsoudi, M. J. Collins, and D. G. Leckie, “Radarsat-2 polarimetric SAR data for boreal forest classification using SVM and a wrapper feature selector,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 6, pp. 1531-1538, 2013.
[12] Y. Chen, N. M. Nasrabadi, and T. D. Tran, “Hyperspectral image classification via kernel sparse representation,” IEEE Transactions on Geoscience and Remote sensing, vol. 51, pp. 217-231, 2013.
[13] L. Zhang, Y. Chen, D. Lu, and B. Zou, “Polarmetric SAR images classification based on sparse representation theory,” in Geoscience and Remote Sensing Symposium (IGARSS), 2013 IEEE International, pp. 3179-3182, 2013.

[14] R. Saleh, H. Farsi, and S. H. Zahiri, “Ensemble classification of PolSAR data using a classifier based on sparse representation and multi-objective heuristic combination rule (in Persian),” Journal of Electronics Industries, vol. 7, pp. 5-19, 2016.
[15] M. Woźniak, M. Graña, and E. Corchado, “A survey of multiple classifier systems as hybrid systems,” Information Fusion, vol. 16, pp. 3-17, 2014.
[16] H. Su and P. Du, “Multiple classifier ensembles with band clustering for hyperspectral image classification,” European Journal of Remote Sensing, vol. 47, pp. 217-227, 2014.
[17] C. Han, L. Zhang, and X. Wang, “Polarimetric SAR image classification based on selective ensemble learning of sparse representation,” in Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International, pp. 4964-4967, 2016.
[18] L. Zhang, X. Wang, and W. M. Moon, “PolSAR images classification through GA-based selective ensemble learning,” in Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International, pp. 3770-3773, 2015.
[19] X. Ma, H. Shen, J. Yang, L. Zhang, and P. Li, “Polarimetricspatial classification of SAR images based on the fusion of multiple classifiers,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, pp. 961-971, 2014.
[20] Y. Maghsoudi, M. Collins, and D. G. Leckie, “Polarimetric classification of Boreal forest using nonparametric feature selection and multiple classifiers,” International Journal of Applied Earth Observation and Geoinformation, vol. 19, pp. 139-150, 2012.
[21] S. Kiranyaz, T. Ince, S. Uhlmann, and M. Gabbouj, “Collective network of binary classifier framework for polarimetric SAR image classification: an evolutionary approach,” Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, vol. 42, pp. 1169-1186, 2012.
[22] C. He, M. Liu, Z. X. Liao, B. Shi, X. N. Liu, and X. Xu, “A learning-based target decomposition method using Kernel KSVD for polarimetric SAR image classification,” EURASIP Journal on Advances in Signal Processing, vol. 159, pp. 1-9, 2012.
[23] J. S. Lee and E. Pottier, “Polarimetric radar imaging: from basics to applications: CRC press, 2009.
[24] Y. Wang, H. Liu, and B. Jiu, “PolSAR coherency matrix decomposition based on constrained sparse representation,” IEEE Transactions on Geoscience and Remote Sensing, vol. 52, pp. 5906-5922, 2014.
[25] M. A. Bagheri, Gh. A. Montazer, and E. A. Kabir, “Multiple classifier systems, Design methods and combination rules,” Quarterly Journal of Signal and Data Processing, vol. 2, pp. 29-56, 2011. (in Persian)

[26] S. H. Nabavi and E. A. Kabir, “combination of classifiers: Diversity Creation and combination rules (in Persian),” Journal on Computer Science and Engineering, vol. 3, pp. 95-108, 2005.
[27] R. Polikar, “Ensemble based systems in decision making,” Circuits and systems magazine, IEEE, vol. 6, pp. 21-45, 2006.
[28] L. Rokach, “Pattern classification using ensemble methods,” vol. 75: World Scientific, 2010.
[29] S. Sheikh-Pour and S. H. Zahiri, “designing of multi-objective classifier using CFO (in Persian),” Journal of Intelligent Systems in Electrical Engineering, vol. 1, pp. 43-56, 2013.
[30] J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma, “Robust face recognition via sparse representation,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 31, pp. 210-227, 2009.
[31] H. Mohimani, M. Babaie-Zadeh, and C. Jutten, “A fast approach for overcomplete sparse decomposition based on smoothed norm,” IEEE Transactions on Signal Processing, vol. 57, pp. 289-301, 2009.
[32] J. S. Lee, M. R. Grunes, and G. De Grandi, “Polarimetric SAR speckle filtering and its implication for classification,” Geoscience and Remote Sensing, IEEE Transactions on, vol. 37, pp. 2363-2373, 1999.
[33] S. Foucher and C. López-Martínez, “An evaluation of PolSAR speckle filters,” in Geoscience and Remote Sensing Symposium, 2009 IEEE International, IGARSS 2009, pp. 845-848, 2009.
[34] H. Aghababaee, J. Amini, and Y. C. Tzeng, “Contextual PolSAR image classification using fractal dimension and support vector machines,” European Journal of Remote Sensing, vol. 46, pp. 317-332, 2013.
[35] A. Haddadi, G. M. R. Sahebi, and A. Mansourian, “Polarimetric SAR feature selection using a genetic algorithm,” Canadian Journal of Remote Sensing, vol. 37, pp. 27-36, 2011.
[36] S. Uhlmann and S. Kiranyaz, “Integrating color features in polarimetric SAR image classification,” Geoscience and Remote Sensing, IEEE Transactions on, vol. 52, pp. 2197-2216, 2014.
[37] R. Saleh, H. Farsi, and S. H. Zahiri, “Optimum Ensemble Classification for Fully Polarimetric SAR Data Using Global-Local Classification Approach,” IJE Transactions B: Applications, vol. 31, pp. 331-338, 2018.