Recurrent neural networks for automatic clustering of multispectral satellite images

被引:4
作者
Koprinkova-Hristova, P. [1 ]
Alexiev, K. [1 ]
Borisova, D. [2 ]
Jelev, G. [2 ]
Atanassov, V. [2 ]
机构
[1] Bulgarian Acad Sci, Inst Informat & Commun Technol, Acad G Bonchev Str Bl 25A, BU-1113 Sofia, Bulgaria
[2] Bulgarian Acad Sci, Space Res & Technol Inst, BU-1113 Sofia, Bulgaria
来源
IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XIX | 2013年 / 8892卷
关键词
multispectral satellite image; data clustering; recurrent neural network; Echo state network; fuzzy C-means;
D O I
10.1117/12.2029191
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In the present work we applied a recently developed procedure for multidimensional data clustering to multispectral satellite images. The core of our approach lays in projection of the multidimensional image to a two dimensional space. For this purpose we used extensively investigated family of recurrent artificial neural networks (RNN) called "Echo state network" (ESN). ESN incorporates a randomly generated recurrent reservoir with sigmoid nonlinearities of neurons outputs. The procedure called Intrinsic Plasticity (IP) that is aimed at reservoir output entropy maximization was applied for adapting of reservoir steady states to the multidimensional input data. Next we consider all possible combinations between steady states of each two neurons in the reservoir as two-dimensional projections of the original multidimensional data. These low dimensional projections were subjected to subtractive clustering in order to determine number and position of data clusters. Two approaches to choose a proper projection among the all possible combinations between neurons were investigated. The first one is based on the calculation of two-dimensional density distributions of each projection, determination of number of their local maxima and choice of the projections with biggest number of these maxima. The second one applies clustering to all projections and chooses those with maximum number of clusters. Multispectral data from Landsat 7 Enhanced Thematic Mapper Plus (ETM+) instrument are used in this work. The obtained number and position of clusters of a multi-spectral image of a mountain region in Bulgaria is compared with the regional landscape classification.
引用
收藏
页数:8
相关论文
共 17 条
[1]  
ACKLEY DH, 1985, COGNITIVE SCI, V9, P147
[2]  
[Anonymous], GLOB VIS VIEW
[3]  
[Anonymous], 2002, approach
[4]  
[Anonymous], 1994, Journal of Intelligent and Fuzzy Systems, DOI DOI 10.3233/IFS-1994-2301
[5]   KERNEL DENSITY ESTIMATION VIA DIFFUSION [J].
Botev, Z. I. ;
Grotowski, J. F. ;
Kroese, D. P. .
ANNALS OF STATISTICS, 2010, 38 (05) :2916-2957
[6]  
Hammouda K, 2000, SYDE 625 TOOLS INTEL
[7]   Reducing the dimensionality of data with neural networks [J].
Hinton, G. E. ;
Salakhutdinov, R. R. .
SCIENCE, 2006, 313 (5786) :504-507
[8]   NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES [J].
HOPFIELD, JJ .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08) :2554-2558
[9]   Data clustering: A review [J].
Jain, AK ;
Murty, MN ;
Flynn, PJ .
ACM COMPUTING SURVEYS, 1999, 31 (03) :264-323
[10]  
Koprinkova-Hristova Petia, 2012, Artificial Neural Networks and Machine Learning - ICANN 2012. Proceedings 22nd International Conference on Artificial Neural Networks, P571, DOI 10.1007/978-3-642-33269-2_72