Compressed hyperspectral image sensing with joint sparsity reconstruction

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 研究生部

	Compressed hyperspectral image sensing with joint sparsity reconstruction
	LiuHaiying ; LiYunsong ; ZhangJing ; SongJuan ; LvPei
	2011
会议名称	conference on satellite data compression, communications, and processing vii
会议日期	aug 23-24, 2011
会议地点	san diego, ca
关键词	hyperspectral imagery compressive sensing (CS) linear prediction projections onto convex sets(POCS) steepest descent method
页码	815703
通讯作者	liu haiying
英文摘要	recent compressed sensing (cs) results show that it is possible to accurately reconstruct images from a small number of linear measurements via convex optimization techniques. in this paper, according to the correlation analysis of linear measurements for hyperspectral images, a joint sparsity reconstruction algorithm based on interband prediction and joint optimization is proposed. in the method, linear prediction is first applied to remove the correlations among successive spectral band measurement vectors. the obtained residual measurement vectors are then recovered using the proposed joint optimization based pocs (projections onto convex sets) algorithm with the steepest descent method. in addition, a pixel-guided stopping criterion is introduced to stop the iteration. experimental results show that the proposed algorithm exhibits its superiority over other known cs reconstruction algorithms in the literature at the same measurement rates, while with a faster convergence speed.
收录类别	EI ; CPCI
产权排序	2
会议录	proceedings of spie - the international society for optical engineering
会议录出版者	spie
会议录出版地	p.o. box 10, bellingham, wa 98227-0009, united states
语种	英语
ISSN号	0277-786x
内容类型	会议论文
源URL	[http://ir.opt.ac.cn/handle/181661/20156]
专题	西安光学精密机械研究所_研究生部
推荐引用方式 GB/T 7714	LiuHaiying,LiYunsong,ZhangJing,et al. Compressed hyperspectral image sensing with joint sparsity reconstruction[C]. 见:conference on satellite data compression, communications, and processing vii. san diego, ca. aug 23-24, 2011.