基于光谱相似度量的高光谱图像多任务联合稀疏光谱解混方法

许宁; 尤红建; 耿修瑞; 曹银贵

doi:10.11999/JEIT160011

基于光谱相似度量的高光谱图像多任务联合稀疏光谱解混方法

doi: 10.11999/JEIT160011

基金项目:

中国地质调查局地质调查项目(1212011120226)，国家863计划(2012AA12A308)，中国科学院科技服务网络计划项目(KFJ- EW-STS-046)

计量
- 文章访问数: 2127
- HTML全文浏览量: 158
- PDF下载量: 1095
- 被引次数: 0
出版历程
- 收稿日期: 2016-01-04
- 修回日期: 2016-06-06
- 刊出日期: 2016-11-19

Multi-task Jointly Sparse Spectral Unmixing Method Based on Spectral Similarity Measure of Hyperspectral Imagery

Funds:

The Geological Survey Program of China Geological Survey (1212011120226), The National 863 Program of China (2012AA12A308), The Science and Technology Services Network Program of Chinese Academy of Sciences (KFJ-EW- STS-046)

摘要

摘要: 基于图像中存在的邻域以及非局部相似等图像空间特征和联合稀疏解混思想，该文提出一种基于高光谱图像光谱相似性度量的多任务联合稀疏解混方法。通过高光谱图像的光谱特性统计值设定光谱度量阈值，对高光谱图像中相似的像元光谱进行光谱相似性度量分组，再对分组像元光谱数据进行多任务联合稀疏光谱解混模型的构建和求解，得到最终的丰度系数。模拟数据实验结果表明，该方法一定程度上提升了现有联合稀疏光谱解混方法的丰度估计精度，真实数据结果也验证了方法的有效性。
- 高光谱图像 /
- 光谱解混 /
- 联合稀疏表示 /
- 光谱相似性度量
Abstract: In this paper, a multi-task jointly sparse spectral unmixing method based on spectral similarity measure of hyperspectral imagery is proposed, which is a refinement of collaborative sparse spectral unmixing method. First, a threshold value is obtained through the statistical characters of some random selected neighboring pixels in hypersepctral image. Second, all pixels of hyperspectral image are grouped by a spectral similarity measure and the threshold value. Then, a multi-task jointly sparse optimization problem is constructed and solved for the grouped pixels, and the abundance coefficients are obtained finally. Experimentals results on synthetic and real hyperspectral image demonstrate the effectiveness of the proposed approach.
- Hyperspectral imagery /
- Spectral unmixing /
- Joint sparse representation /
- Spectral similarity measure

HTML全文

参考文献(33)

KESHAVE N and MUSTARD J F. Spectral unmixing[J]. IEEE Signal Processing Magazine, 2002, 19(1): 44-57. doi: 10.1109/79.974727.

童庆禧, 张兵, 郑兰芬. 高光谱遥感原理、技术与应用[M]. 北京: 高等教育出版社, 2006: 246-248.

TONG Qingxi, ZHANG Bing, and ZHENG Lanfen. Hypersepctral Remote SensinuPrinciples, Techniques and Applications[M]. Beijing: Higher Education Press, 2006: 246-248.

浦瑞良, 宫鹏. 高光谱遥感及其应用[M]. 北京: 高等教育出版社, 2000: 1-5.

PU Ruiliang and GONG Peng. Hyperspectral Remote Sening and Its Application[M]. Beijing: Higher Education Press, 2000: 1-5.

HEINZ D C and CHANG C I. Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(3): 529-545. doi: 10.1109/36.911111.

耿修瑞, 张兵, 张霞, 等. 一种基于高维空间凸面单形体体积的高光谱图像解混算法[J]. 自然科学进展, 2004, 14(7): 810-814.

GENG Xiurui, ZHANG Bing, ZHANG Xia, et al. An unmixing method of hyperspectral imagery based on convex volume in high dimensional space[J]. Progress in Natureal Science, 2004, 14(7): 810-814

HONEINE P and RICHARD C. Geometric unmixing of large hyperspectral images: A barycentric coordinate approach[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(6): 2185-2195. doi: 10.1109/TGRS.2011.2170999.

YUAN Yuan, FU Min, and LU Xiaoqing. Substance dependence constrained sparse NMF for hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(6): 2975-2986. doi: 10.1109/TGRS.2014. 2365953.

NASCIMENTO J M P and BIOUCAS-DIAS J M. Does independent component analysis play a role in unmixing hyperspectral data?[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(1): 175-187. doi: 10.1109/ TGRS.2004.839806.

SHI Chen and WANG Le. Incorporating spatial information in spectral unmixing: A review[J]. Remote Sensing of Environment, 2014, 149: 70-87. doi: 10.1016/j.rse.2014.03. 034.

BIOUCAS-DIAS J M. A variable splitting augmented Lagragian approach to linear spectral unmixing[C]. First Workshop on Hyperspectral Image Signal Processing: Evolution in Remote Sensing, Grenoble, 2009: 1-4. doi: 10.1109/WHISPERS.2009. 5289072.

IORDACHE M D, BIOUCAS-DIAS J M, and PLAZA A. Total variation spatial regularization for sparse hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(11): 4484-4502. doi: 10.1109/TGRS.2012. 2191590.

ZHONG Yanfei, FENG Ruyi, and ZHANG Liangpei. Non-local sparse unmixing for hyperspectral remote sensing imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6): 1889-1909. doi: 10.1109/JSTARS.2013.2280063.

CHEN Fen and ZHANG Yan. Sparse hyperspectral unmixing based on constrained lp-l2 optimization[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(5): 1142-1146. doi: 10.1109/LGRS.2012.2232901.

IORDACHE M D, BIOUCAS-DIAS J M, and PLAZA A. Collaborative sparse regression for hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1): 341354. doi: 10.1109/TGRS.2013.2240001.

BIENIARZ J, AGUILERA E, ZHU X X, et al. Joint sparsity model for multilook hyperspectral image unmixing[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(4): 696-700. doi: 10.1109/LGRS.2014.2358623.

王蕊, 李恒超, 尹忠科. 考虑端元差异性的协同稀疏高光谱解混算法[J]. 电子科技大学学报, 2014, 43(6): 813-817. doi: 10. 3969/j.issn.1001-0548.2014.06.003.

WANG Rui, LI Hengchao, and YIN Zhongke. Collaborative sparse unmixing of hyperspectral data considering the difference of endmembers[J]. Journal of University of Electronic Science and Technology of China, 2014, 43(6): 813-817. doi: 10.3969/j.issn.1001-0548.2014.06.003.

KIM S J, KOH K, LUSTIG M, et al. An interior-point method for large-scale l1-regularized least squares[J]. IEEE Journal of Selected Topics in Signal Processig, 2007, 1(4): 606-617. doi: 10.1109/JSTSP.2007.910971.

刘建军, 吴泽彬, 韦志辉, 等. 基于空间相关性约束稀疏表示的高光谱图像分类[J]. 电子与信息学报, 2012, 34(11): 2666-2671. doi: 10.3724/SP.J.1146.2012.00577.

LIU Jianjun, WU Zebin, WEI Zhihui, et al. Spatial correlation constrained sparse representation for hyperspectral image classification[J]. Journal of Electronics Information Technology, 2012, 34(11): 2666-2671. doi: 10.3724/SP.J.1146. 2012.00577.

ZHANG Hongyan, LI Jiayi, HUANG Yuancheng, et al. A nonlocal weighted joint sparse representation classification method for hyperspectral imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6): 2057-2066. doi: 10.1109/JSTARS.2013. 2264720.

WAKIN N M, DUARTE M, SARVOTHAM S, et al. Recovery of jointly sparse signals from few random projections[C]. Processing Workshop on Neural Information Processing System, Vancouver, 2005: 1435-1442.

YUAN Xiaotong, LIU Xiaobai, and YAN Shuicheng. Visual classification with multi-task joint sparse representation[J]. IEEE Transactions on Image Processing, 2012, 21(10): 4349-4360. doi: 10.1109/TIP.2012.2205006.

LI Jiayi, ZHANG Hongyan, and ZHANG Liangpei. Efficient superpixel-level multitask joint sparse representation for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(10): 5923-5936. doi: 10.1109/TGRS.2015.2421638.

耿修瑞. 高光谱遥感图像信息提取的若干数学原理[R]. 北京师范大学博士后研究工作报告, 北京, 2007.

GENG Xiurui. Several mathmatical principles on information extraction for hyperspectral imagery[R]. Research Report for Post-Ph.D. in Beijing Normal University, Beijing, 2007.

IORDACHE M D, BIOUCAS J M, and PLAZA A. Dictionary pruning in sparse unmixing of hyperspectral data[C]. 4th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Shanghai, 2012: 1-4. doi: 10.1109/WHISPERS.2012.6874329.

CLARK R, SWAYZE G, LIVO K, et al. Imaging spectroscopy: Earth and planetary remote sensing with the USGS tetracorder and expert systems[J]. Journal of Geophysical Research, 2003, 108(E12): 5131. doi: 10.1029/ 2002JE001847.

普晗晔, 王斌, 夏威. 约束最小二乘的高光谱图像非线性解混[J]. 红外与毫米波学报, 2014, 33(5): 552-559. doi: 10.3724/SP.J. 1010.2014.00552.

PU Hanye, WANG Bin, and XIA Wei. Nonlinear unmixing of hyperspectral imagery based on constrained least squares[J]. Journal of Infrared and Millimeter Waves, 2014, 33(5): 552-559. doi: 10.3724/SP.J.1010.2014.00552.

施引文献

资源附件(0)

访问统计