Hyperspectral target detection by airborne and spaceborne image fusion based on 3D GMRF

Chen Shanjing; Kang Qing; Gu Zhongzheng; Wang Zhenggang; Shen Zhiqiang; Pu Huan; Xin Ying

doi:10.3788/IRLA201645.S223003

To solve the problem that traditional hyperspectral target detection is based on either airborne image or spaceborne image, and doesn't utilize the advantage of aerial and space imaging comprehensively, a target detection method for airborne and spaceborne image fusion, which combined 3D GMRF with D-S evidence theory, was proposed in this paper. The 3D GMRF detection results from airborne image and spaceborne image were fused by D-S evidence theory in decision level. The experimental results show that the proposed target detection method complements the advantage of aerial hyperspectral image and space hyperspectral image, and enhances accuracy on target detection. This technology is new target detection method by fusing the aerial and space hyperspectral image.

Hyperspectral target detection by airborne and spaceborne image fusion based on 3D GMRF

1. Department of National Defense Construction Planning and Environment Engineering,Logistical Engineering University,Chongqing 401311,China;

2. College of Science,Air Force Engineering University,Xi'an 710051,China

Received Date: 2016-08-08

Rev Recd Date: 2016-09-07

Publish Date: 2016-12-25

Key words:

hyperspectral image /
target detection /
GMRF /
detection model of airborne and spaceborne image fusion /
D-S evidence theory

Abstract: To solve the problem that traditional hyperspectral target detection is based on either airborne image or spaceborne image, and doesn't utilize the advantage of aerial and space imaging comprehensively, a target detection method for airborne and spaceborne image fusion, which combined 3D GMRF with D-S evidence theory, was proposed in this paper. The 3D GMRF detection results from airborne image and spaceborne image were fused by D-S evidence theory in decision level. The experimental results show that the proposed target detection method complements the advantage of aerial hyperspectral image and space hyperspectral image, and enhances accuracy on target detection. This technology is new target detection method by fusing the aerial and space hyperspectral image.

HTML

Reference (15)

[1]	Zhou J, Kwan C, Ayhan B, et al. A novel cluster kernel RX algorithm for anomaly and change detection using hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(11): 6497-6504.
[2]	Song M P, Chang C I. A theory of recursive orthogonal subspace projection for hyperspectral imaging[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(6): 3055-3072.
[3]	Wang Cailing, Wang hongwei, Hu Bingliang, et al. A new spectral-spatial algorithm method for hyperspectral image target detection[J]. Spectroscopy and Spectral Analysis, 2016, 36(4): 1163-1169. (in Chinese)
[4]	Kaufman J R, Eismann M T, C M. Assessment of spatial-spectral feature-level fusion for hyperspectral target detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(6): 2534-2544.
[5]	Schweizer S M, Maura J M F. Efficient detection in hyperspectral imagery[J]. IEEE Transactions on Image Processing, 2001, 10(4): 584-594.
[6]	Wang L J, Gao K, Cheng X M, et al. A hyperspectral imagery anomaly detection algorithm based on Gauss-Markov model[C]//International Conference on Computational and Information Sciences (ICCIS), 2012, 7: 135-138.
[7]	Schweizer S M, Maura J M F. hyperspectral imagery: clutter adaptation in anomaly detection[J]. IEEE Transactions on Information Theory, 2000, 46(5):1855-1871.
[8]	Li S S, Zhang B, Chen D, et al. Adaptive support vector machine and Markov random field model for classifying hyperspectral imagery[J]. Journal of Applied Remote Sensing, 2011, 5: 053538-1-12.
[9]	Jafari A, Heidarpour M. A decision fusion framework for high-resolution remote-sensing image classification[C]//20159th Iranian Conference on Machine Vision and Image Processing (MVIP), Tehran, Iran, 2015, 11: 219-222.
[10]	Chang Z, Liao X J, Liu Y, et al. Research of decision fusion for multi-source remote-sensing satellite information based on SVMs and DS evidence theory[C]//2011 Fourth International Workshop on Advanced Computational Intelligence (IWACI), 2011, 10: 416-420.
[11]	Moura J M F, Balram N. Recursive structure of noncausal Gauss-Markov Random Fields[J]. IEEE Transactions on Information Theory, 1992, 3(38): 334-354.
[12]	Chen Y, Nasrabadi N M, Tran T D. Effects of random measurements on the performance of target detection in hyperspectral imagery[C]//Proceedings of SPIE Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVII, 2011, 8048: D1-D13.
[13]	Sun Jixiang. Pattern Recognition[M]. Changsha: National University of Defense Technology Press, 2002. (in Chinese)
[14]	Truslow E, Manolakis D, Pieper M, et al. Performance prediction of matched filter and adaptive cosine estimator hyperspectral target detectors[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6): 2337-2350.
[15]	Chen Shanjing, Hu Yihua, Sun Dujuan. A simulation method by air and space integrated fusion based on hyper-/multi-spectral imagery[J]. Acta Physica Sinica, 2013, 62(20): 2042011-2042018. (in Chinese)

Hyperspectral target detection by airborne and spaceborne image fusion based on 3D GMRF

doi: 10.3788/IRLA201645.S223003

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views