Change Detection and Classification of Land Cover in Multispectral Satellite Imagery using Clustering of Sparse Approximations (CoSA) over Learned Feature Dictionaries

被引:0
作者
Moody, Daniela I. [1 ]
Brumby, Steven P. [1 ]
Rowland, Joel C. [1 ]
Altmann, Garrett L. [1 ]
Larson, Amy E. [1 ]
机构
[1] Los Alamos Natl Lab, MS D436, Los Alamos, NM 87545 USA
来源
2014 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR) | 2014年
关键词
learned dictionaries; feature dictionaries; Hebbian learning; sparse approximation; unsupervised classification; undercomplete dictionaries;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Neuromimetic machine vision and pattern recognition algorithms are of great interest for landscape characterization and change detection in satellite imagery in support of global climate change science and modeling. We present results from an ongoing effort to extend machine vision methods to the environmental sciences, using adaptive sparse signal processing combined with machine learning. A Hebbian learning rule is used to build multispectral, multiresolution dictionaries from regional satellite normalized band difference index data. Land cover labels are automatically generated via our CoSA algorithm: Clustering of Sparse Approximations, using a clustering distance metric that combines spectral and spatial textural characteristics to help separate geologic, vegetative, and hydrologic features. We demonstrate our method on example Worldview-2 satellite images of an Arctic region, and use CoSA labels to detect seasonal surface changes. Our results suggest that neuroscience-based models are a promising approach to practical pattern recognition and change detection problems in remote sensing.
引用
收藏
页数:10
相关论文
共 24 条
[1]  
ACIA, 2005, 2005 ARC CLIM IMP AS
[2]   K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation [J].
Aharon, Michal ;
Elad, Michael ;
Bruckstein, Alfred .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2006, 54 (11) :4311-4322
[3]  
[Anonymous], 2010, BENEFITS 8 SPECTRAL
[4]  
Coates A., 2011, P 28 INT C MACHINE L, P921
[5]  
Engan K, 1999, INT CONF ACOUST SPEE, P2443, DOI 10.1109/ICASSP.1999.760624
[6]   Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction [J].
Harvey, NR ;
Theiler, J ;
Brumby, SP ;
Perkins, S ;
Szymanski, JJ ;
Bloch, JJ ;
Porter, RB ;
Galassi, M ;
Young, AC .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (02) :393-404
[7]  
Hinkel KM, 2003, ARCT ANTARCT ALP RES, V35, P291, DOI 10.1657/1523-0430(2003)035[0291:SEAACS]2.0.CO
[8]  
2
[9]   High-resolution mapping of ecosystem carbon storage and potential effects of permafrost thaw in periglacial terrain, European Russian Arctic [J].
Hugelius, Gustaf ;
Virtanen, Tarmo ;
Kaverin, Dmitry ;
Pastukhov, Alexander ;
Rivkin, Felix ;
Marchenko, Sergey ;
Romanovsky, Vladimir ;
Kuhry, Peter .
JOURNAL OF GEOPHYSICAL RESEARCH-BIOGEOSCIENCES, 2011, 116
[10]  
Mairal J, 2008, PROC CVPR IEEE, P2415