深圳大学学报理工版

为了提升高光谱图像的稀疏解混精度,提出一种基于改进鲸群优化算法的子空间匹配追踪(improved whale optimized subspace matching pursuit, IWOSMP)的稀疏解混算法.对鲸群优化算法进行改进,通过引入非线性种群控制参数和进化策略,提高鲸群优化算法的收敛速度和收敛精度,基于子空间匹配追踪算法,以约束稀疏回归为目标函数,利用改进的鲸群优化算法对已知端元集求解丰度系数.以重构误差最小为标准,通过最大程度地去除系数较小的冗余端元,提高子空间匹配追踪算法的端元提取的精确度,进一步提高了高光谱图像的解混精度.合成图像实验和真实遥感图像实验表明,IWOSMP能有效去除大量的冗余端元,且解混精度更高.

This paper proposes a whale optimized subspace matching pursuit algorithm to improve the precision of sparse unmixing of hyperspectral data. The proposed algorithm modifies the traditional whale group optimization algorithm by introducing the nonlinear population control parameters and evolution strategy and thus improves the convergence speed and convergence precision of the whale cluster optimization algorithm. Based on the improved subspace matching pursuit algorithm, the new algorithm uses the whale optimization algorithm to solve the abundance coefficients of the known end members, where the objective function is modeled as a constrained sparse regression. In order to improve the precision of the subspace matching pursuit algorithm, the minimum reconstruction error is taken as the criterion and the redundant end members with smaller coefficients are removed to the greatest extent. The simulation and real data experiments show that the proposed algorithm can effectively remove the redundant endmembers and has a higher precision of unmixing.

引言
1 高光谱图像稀疏解混模型
2 子空间匹配追踪算法
3 WOA及其改进
4 IWOSMP算法
5 结果与分析
6 结语

表1 用于测试改进算法的基准函数<br/>Table 1 Benchmark functions for testing improved algorithms

表1 用于测试改进算法的基准函数
Table 1 Benchmark functions for testing improved algorithms

图1 六种测试函数的进化曲线<br/>Fig.1 (Color online)Convergence of six algorithms

图1 六种测试函数的进化曲线
Fig.1 (Color online)Convergence of six algorithms

图2 不同高斯噪声下5个端元的合成图像的解混结果<br/>Fig.2 Unmixed results of composite images with five end elements under different Gaussian noises

图2 不同高斯噪声下5个端元的合成图像的解混结果
Fig.2 Unmixed results of composite images with five end elements under different Gaussian noises

图3 30 dB高斯噪声背景下不同端元个数的解混结果<br/>Fig.3 Unmixing results of different endmember numbers under the background of 30 dB Gaussian noises

图3 30 dB高斯噪声背景下不同端元个数的解混结果
Fig.3 Unmixing results of different endmember numbers under the background of 30 dB Gaussian noises

图4 不同贪婪算法在30 dB背景下的端元提取结果<br/>Fig.4 Endmember extraction results of different greedy algorithms under 30 dB background

图4 不同贪婪算法在30 dB背景下的端元提取结果
Fig.4 Endmember extraction results of different greedy algorithms under 30 dB background

图5 六种算法的3种端元丰度估计图<br/>Fig.5 Three endmembers abundance estimation diagrams for six algorithms

图5 六种算法的3种端元丰度估计图
Fig.5 Three endmembers abundance estimation diagrams for six algorithms

[1] 童庆禧,张兵,郑兰芬.高光谱遥感[M].北京:高等教育出版社,2006.
[2] BIOUCAS-DIAS J M, PLAZA A. An overview on hyperspectral unmixing: geometrical, statistical, and sparse regression based approaches[C]// IEEE Intemational Geoscience and Remote Sensing Symposium. Vancouver, Canada: IEEE, 2011:1135-1138.
[3] 李殊瑶.基于结构稀疏表示的高光谱图像解混[D].西安:西安电子科技大学,2015.
[4] IORDACHE M D, BIOUCAS-DIAS J M, PLAZA A. Sparse unmixing of hyperspectral data[J]. IEEE Transaction on Geoscience and Remote Sensing, 2011, 49(6): 2014-2039.
[5] ZHANG Shaoquan, LI Jun, LI Hengchao, et al. Spectral-spatial weighted sparse regression for hyperspectral image unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(6): 3265-3276.
[6] FAN Wenyi, HU Baoxin, MILLER J, et al. Comparative study between a new nonlinear model and common linear model for analyzing laboratory simulated forest hyperspectral data[J]. International Journal of Remote Sensing, 2009, 30(11): 2951-2962.
[7] MALLAT S G, ZHANG Zzhifeng. Matching pursuits with time-frequency dictionaries[J]. IEEE Transaction on Signal Processing, 1993, 41(12):3397-3415.
[8] BRUCKSTEIN A M, ELAD M, ZIBULEVSKY M. On the uniqueness of nonnegative sparse solutions to underdetermined systems of equations[J]. IEEE Transaction on Information Theory, 2008, 54(11): 4813- 4820.
[9] TROPP J A, GILBERT A C. Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007, 53(12): 4655- 4666.
[10] TROPP J A, GILBERT A C, STRAUSS M J. Algorithms for simultaneous sparse approximation. part I: greedy pursuit[J]. Signal Processing, 2006, 86(3): 572-588.
[11] SHI Zhenwei, TANG Wei, DUREN Zhana, et al. Subspace matching pursuit for sparse unmixing of hyperspectral data[J]. IEEE Transaction on Geoscience and Remote Sensing, 2014, 52(6): 3256-3274.
[12] KONG Fanqiang, GUO Wenjun, LI Yunsong, et al. Backtracking-based simultaneous orthogonal matching pursuit for sparse unmixing of hyperspectral data[J]. Mathematical Problems in Engineering, 2015, 2015: 842017.
[13] 肖健钰.基于稀疏表示的高光谱图像解混算法研究[D].哈尔滨:哈尔滨工程大学,2015.
[14] LI Dan, ZHANG Chunmei, ZHOU Qianqi, et al. Subspace matching pursuit with Dice coefficient for sparse unmixing of hyperspectral data[C]// IEEE International Geoscience and Remote Sensing Symposium. Beijing: IEEE, 2016: 6585- 6588.
[15] ZHONG Yanfei, ZHAO Lin, ZHANG Liangpei. An adaptive differential evolution endmember extraction algorithm for hyperspectral remote sensing imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(6): 1061-1065.
[16] ZHONG Liang, LUO Wenfei, GAO Lianru. A particle swarm optimization algorithm for unmixing the polynomial post-nonlinear mixing model[C]// The 9th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics. Datong, China: IEEE, 2017: 596- 600.
[17] 陈雷, 郭艳菊, 葛宝臻.基于微分搜索的高光谱图像非线性解混算法[J].电子学报,2017,45(2):337-345.
[18] 陈雷,甘士忠,孙茜.基于回溯优化的非线性高光谱图像解混[J].红外与激光工程,2017,46(6):225-232.
[19] QUAN Jianing, KANG Zhilong, CHEN Lei, et al. Abundance estimation of crossover double particle swarms optimization for hyperspectral remote sensing imagery[J]. International Journal of Remote Sensing, 2018, 38(23): 1-25.
[20] MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51- 67.
[21] KENNEDY J, EBERHART R. Particle swarm optimization[C]// Proceedings of ICNN'95 IEEE International Conference on Neural Networks. Perth, Australia: IEEE, 2011: 1942-1948.
[22] RASHEDI E, NEZAMABADI-POUR H, SARYAZDI S. GSA: a gravitational search algorithm[J]. Information Sciences, 2009, 179(13): 2232-2248.
[23] KAVEH A, FARHOUDI N. A new optimization method: Dolphin echolocation[J]. Advances in Engineering Software, 2013, 59(5): 53-70.
[24] 高卫峰.人工蜂群算法及其应用的研究[D].西安:西安电子科技大学,2013.
[25] SAREMI S, MIRJALILI S, LEWIS A. Grasshopper optimisation algorithm: theory and application[J]. Advances in Engineering Software, 2017, 105: 30- 47.
[26] 张梅凤,邵诚.多峰函数优化的生境人工鱼群算法[J].控制理论与应用,2008,25(4):773-776.
[27] BIOUCAS-DIAS J M, FIGUEIREDO M A T. Alternating direction algorithms for constrained sparse regression: application to hyperspectral unmixing[C]// The 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing. Reykjavik, Iceland: IEEE, 2010: 1- 4.
[28] IORDACHE M D, BIOUCAS-DIAS J M, PLAZA A. Total variation spatial regularization for sparse hyperspectral unmixing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(11): 4484- 4502.
[29] IORDACHE M D, BIOUCAS-DIAS J M, PLAZA A. Collaborative sparse regression for hyperspectral unmixing[J]. IEEE Trans on Geoscience and Remote Sensing, 2013, 52(1): 341-354.

备注

引言

1 高光谱图像稀疏解混模型

2 子空间匹配追踪算法

3 WOA及其改进

4 IWOSMP算法

5 结果与分析

6 结语

补充材料文件请点击下载

期刊信息

备注

引言