Abstract




 
   

IJE TRANSACTIONS B: Applications Vol. 31, No. 2 (February 2018) 331-338   

PDF URL: http://www.ije.ir/Vol31/No2/B/18-2697.pdf  
downloaded Downloaded: 20   viewed Viewed: 318

  OPTIMUM ENSEMBLE CLASSIFICATION FOR FULLY POLARIMETRIC SAR DATA USING GLOBAL-LOCAL CLASSIFICATION APPROACH
 
R. Saleh and H. Farsi
 
( Received: August 25, 2017 – Accepted in Revised Form: October 12, 2017 )
 
 

Abstract    In this paper, a proposed ensemble classification for fully polarimetric synthetic aperture radar (PolSAR) data using a global-local classification approach is presented. In the first step, to perform the global classification, the training feature space is divided into a specified number of clusters. In the next step to carry out the local classification over each of these clusters, which contains elements of several classes, a base classifier is trained. Thus, an ensemble of classifiers has been formed which each of them acts professionally in a part of the feature space. To achieve more diversity, the data set is independently partitioned into variable number of clusters by classifier and K-means algorithm. To combine outputs of different arrangements, majority voting, Naïve Bayes and a heuristic combination rule with taking into account the classification accuracy and reliability (which in PolSAR classification less attention has been paid to it) as objective functions, are used. The experimental results over two PolSAR images prove effectiveness of the proposed algorithms in comparison to the baseline methods.

 

Keywords    PolSAR data; Ensemble classification; Global-local classification; H/α classifier; Clustering; Multi objective optimization; Reliability.

 

چکیده    در این مقاله، ساختار یک طبقه­بند شورایی با استفاده از رویکرد طبقه­بندی عمومی-محلی برای داده­های پلاریمتریک رادار با روزنه مصنوعی پیشنهاد می­شود. در گام نخست برای اجرای طبقه­بندی عمومی، فضای ویژگی داده­های آموزش به چندین خوشه تقسیم­بندی می­شود. در گام بعدی برای انجام طبقه­بندی محلی بر روی هر یک از خوشه­ها که شامل عناصر چند کلاس است، یک طبقه­بند پایه آموزش داده می­شود. به این ترتیب شورایی از طبقه­بندهای پایه که هر یک بر روی ناحیه­ای از فضای ویژگی به صورت تخصصی عمل می­کنند، تشکیل می­شود. جهت دستیابی به گوناگونی بیشتر، مجموعه داده به صورت مستقل توسط طبقه­بند H/α و الگوریتم K-means به تعداد متغییری خوشه تقسیم می­شود. جهت تلفیق خروجی آرایش­های مختلف از رای­گیری اکثریت، روش Naïve Bayes و یک قاعده ترکیب ابتکاری با در نظر گرفتن دقت طبقه­بندی و قابلیت اطمینان( که در مباحث طبقه­بندی تصاویر پلاریمتریک کمتر به آن توجه شده است) استفاده گردیده است. نتایج تجربی بیانگر برتری الگوریتم­های پیشنهادی در مقایسه با روش­های پایه است.

References   

1.       Shitole, S., De, S., Rao, Y., Mohan, B. K. and Das, A., 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, (2015), 739-750.

2.      Zhang, L., Sun, L., Zou, B. and Moon, W. M., Fully polarimetric SAR image classification via sparse representation and polarimetric features“, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 8, ( 2015), 3923-3932.

3.      Heidari, M., Fault detection of  bearings using a rule-based classifier ensemble and genetic algorithm“, International Journal of Engineering, Transaction A: Basics, Vol. 30,    ( 2017), 604-609.

4.      Chi, M., Kun, Q., Benediktsson, J. A. and Feng, R., Ensemble classification algorithm for hyperspectral remote sensing data“, IEEE Transaction on Geoscience and Remote  Sensing, Vol. 6, (2009), 762-766.

5.      Ma, X., Shen, H., Yang, J., Zhang, L. and Li P., Polarimetric-spatial 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, (2014), 961-971.

6.      Sadeghpour Haji, M., Mirbagheri, S., Javid, A., Khezri, M. and Najafpour, G., Awavelet support vector machine combination model for daily suspended sediment forecasting“, International Journal of Engineering, Transaction C: Aspects, Vol. 27,( 2014), 855-864.

7.      Kiranyaz, S., Ince, T., Uhlmann, S. and Gabbouj, M., Collective network of binary classifier framework for polarimetric SAR image classification: an evolutionary approach“, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 42, (2012), 1169-1186.

8.      Maghsoudi, Y., Collins, M. and Leckie, D. G., Polarimetric classification of Boreal forest using nonparametric feature selection and multiple classifiers," International Journal of Applied Earth Observation and Geoinformation, Vol. 19, (2012), 139-150.

9.      Aghababaee, H. and Sahebi, M. R., Game theoretic classification of polarimetric SAR images“, European Journal of Remote Sensing, Vol. 48, (2015), 33-48.

10.    Lee, J.-S. and Pottier, E., Polarimetric radar imaging: from basics to applications , CRC press, (2009).

11.    Zhang, C. and Ma, Y., Ensemble Machine Learning”, Springer, (2012).

12.    Polikar, R., Ensemble based systems in decision making“, IEEE Circuits and Systems Magazine, Vol. 6, (2006), 21-45.

13.    Rokach, L., Pattern Classification Using Ensemble Methods“, World Scientific, (2009).

14.    Kuncheva , L. I., Combining Pattern Classifiers: Methods and Algorithms,  John Wiley & Sons, (2004).

15.    Cloude, S. R. and Pottier, E., An entropy based classification scheme for land applications of polarimetric SAR“,  IEEE Transaction on Geoscience and Remote  Sensing, Vol. 35, (1997), 68-78.

16.    Pourzeynali, S., Malekzadeh, M. and Esmaeilian, F., Multi-objective optimization of semi-active control of seismically exited buildings using variable damper and genetic algorithms“, International Journal of Engineering Transaction A: Basics, Vol. 25, (2012), 265-276.

17.    Akbarpour , H., Karimi , G. and Sadeghzadeh , A., Discrete multi objective particle swarm optimization algorithm for FPGA placement“, International Journal of Engineering, Transaction C: Aspects, Vol. 28, (2015), 410-418.

18.    Lee, J.-S., Grunes, M. R. and Kwok, R., Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution“, International Journal of Remote Sensing, Vol. 15, (1994), 2299-2311.

19.    Rahman, A. and Verma, B., “Cluster based ensemble of classifiers “, Expert Systems, Vol.30, (2013), 270-282.

20.    Sharifi, A., Amini, J., Sumantyo, J. T. S. and Tateishi, R., “Speckle reduction of PolSAR images in forest regions using Fast ICA algorithm“,  Journal of the Indian Society of Remote Sensing, Vol. 43, (2015), 339-346.

21.    Lee, J.-S., Grunes, M. R. and De Grandi, G., “Polarimetric SAR speckle filtering and its implication for classification “, IEEE Transaction on Geoscience and Remote  Sensing, Vol. 37, (1999), 2363-2373.

22.    Ma, X., Shen, H., Yang, J., Zhang L. and Li, P., “Polarimetric-spatial 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, (2014), 961-971.

23.    Saleh, R., Farsi, H. and Zahiri, S. H., “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,( 2016), 5-19.

Uhlmann, S. and Kiranyaz, S., “Integrating color features in polarimetric SAR image classification “, IEEE Transaction on Geoscience and Remote  Sensing, Vol. 52, (2014), 2197-2216.


Download PDF 



International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir