A single individual evolutionary strategy for endmember search in hyperspectral images

被引:12
作者
Graña, M [1 ]
Hernandez, C [1 ]
Gallego, J [1 ]
机构
[1] Univ Pais Vasco EHU, Fac Informat, Dept CCIA, San Sebastian 20080, Spain
关键词
D O I
10.1016/j.ins.2003.05.005
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We define an single individual evolutionary strategy (SIE) for the induction of a set of endmembers and we compare it with a conventional evolutionary strategy (ES), tailored to this task, over a couple of hyperspectral images. The SIE considers a set of endmembers as an evolving population. Individuals correspond to hypothetical endmember spectra, and they are selected as candidates for mutation on the basis of their partial abundance images. The population's global fitness when the mutated individual substitutes its parent is the measure of the goodness of the individual. Although the aim of defining the SIE was to reduce the computational cost of applying ES to the high volume data in hyperspectral images, we have found that SIE also improves the fitness performance of conventional ES. (C) 2003 Elsevier Inc. All rights reserved.
引用
收藏
页码:181 / 197
页数:17
相关论文
共 12 条
[1]   Evolutionary computation: An overview [J].
Back, T ;
Schwefel, HP .
1996 IEEE INTERNATIONAL CONFERENCE ON EVOLUTIONARY COMPUTATION (ICEC '96), PROCEEDINGS OF, 1996, :20-29
[2]  
Back T., 1996, EVOLUTIONARY ALGORIT
[3]   An Overview of Evolutionary Algorithms for Parameter Optimization [J].
Baeck, Thomas ;
Schwefel, Hans-Paul .
EVOLUTIONARY COMPUTATION, 1993, 1 (01) :1-23
[4]   MINIMUM-VOLUME TRANSFORMS FOR REMOTELY-SENSED DATA [J].
CRAIG, MD .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1994, 32 (03) :542-552
[5]  
Graña M, 2002, LECT NOTES ARTIF INT, V2527, P526
[6]   Multispectral and hyperspectral image analysis with convex cones [J].
Ifarraguerri, A ;
Chang, CI .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (02) :756-770
[7]   Resource limitations and strategies for the treatment of uremia - A dialysis unit in the Himalayan foothills [J].
Keshaviah, P .
BLOOD PURIFICATION, 2001, 19 (01) :44-52
[8]  
LANDGREBE DA, INDIAN PINES AVIRIS
[9]   A spectral mixture process conditioned by Gibbs-based partitioning [J].
Rand, RS ;
Keenan, DM .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (07) :1421-1434
[10]   Covariance estimation with limited training samples [J].
Tadjudin, S ;
Landgrebe, DA .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1999, 37 (04) :2113-2118