A modified Algorithm for Multi-Target Detection in Hyperspectral Image

被引:4
作者
Yin, Jihao [1 ]
Wang, Yan [1 ]
Wang, Yisong [1 ]
Zhao, Zhanjie [2 ]
机构
[1] Beijing Univ Aeronaut & Astronaut, Beijing, Peoples R China
[2] Chinese Acad Surveying & Mapping, Beijing, Peoples R China
来源
2010 2ND INTERNATIONAL ASIA CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS (CAR 2010), VOL 3 | 2010年
关键词
modified correlation matrix; multi-target detection; winner-take-all CEM; ORTHOGONAL SUBSPACE PROJECTION;
D O I
10.1109/CAR.2010.5456639
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In the area of hyperspectral image detection, Constrained Energy Minimization (CEM) algorithm has received considerable interest recently. However, it is very sensitive to noise and can only detect one target at one time. In order to solve this problem, Winner-Take-All Constrained Energy Minimization (WTACEM) was proposed. Based on it, we propose a modified multi-target detection approach. We study the sample correlation matrix and find if we exclude the desired target pixel vectors from the correlation matrix, we can achieve better results. The simulation results indicate that the errors caused by the modified WTACEM have decreased obviously and the output is more close to the true abundance fraction. The experiment also shows that when the abundance fraction of target increases, the detection performance improves.
引用
收藏
页码:105 / 108
页数:4
相关论文
共 10 条
[1]  
Ashton EA, 1998, PHOTOGRAMM ENG REM S, V64, P723
[2]  
Chang C.I., 2003, Hyperspectral Imaging: Techniques for Spectral Detection and Classification, V1
[3]   Orthogonal subspace projection (OSP) revisited: A comprehensive study and analysis [J].
Chang, CI .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (03) :502-518
[4]   On relationship among orthogonal subspace projection, constrained energy minimization and RX-algorithm [J].
Chang, CI .
ALGORITHMS AND TECHNOLOGIES FOR MULTISPECTRAL, HYPERSPECTRAL, AND ULTRASPECTRAL IMAGERY VIII, 2002, 4725 :490-500
[5]   A comparative study for orthogonal subspace projection and constrained energy minimization [J].
Du, Q ;
Ren, H ;
Chang, CI .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (06) :1525-1529
[6]   Performance analysis for CEM and OSP [J].
Du, Q ;
Ren, H .
ALGORITHMS AND TECHNOLOGIES FOR MULTISPECTRAL, HYPERSPECTRAL, AND ULTRASPECTRAL IMAGERY VIII, 2002, 4725 :501-508
[7]  
Harsanyi J. C., 1993, Detection and Classification of Subpixel Spectral Signatures in Hyperspectral Image Sequences
[8]   ADAPTIVE MULTIPLE-BAND CFAR DETECTION OF AN OPTICAL-PATTERN WITH UNKNOWN SPECTRAL DISTRIBUTION [J].
REED, IS ;
YU, XL .
IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1990, 38 (10) :1760-1770
[9]  
Ren Hsuan., 2003, Comparison between constrained energy minimization based approaches for hyperspectral imagery. pages, P244, DOI DOI 10.1109/WARSD.2003.1295199
[10]   Detection of spectral signatures in multispectral MR images for classification [J].
Wang, CM ;
Chen, CCC ;
Chung, YN ;
Yang, SC ;
Chung, PC ;
Yang, CW ;
Chang, CI .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2003, 22 (01) :50-61