基于二级字典的联合稀疏表示高光谱图像分类

doi:10.3969/j.issn.1001-506X.2020.03.007

摘要/Abstract

摘要：

针对多数传统分类算法应用于高光谱分类存在的分类精度较低、光谱信息利用不充分的问题,在基于核函数的联合稀疏表示分类方法的基础上提出了一种基于二级字典的联合稀疏表示的高光谱分类算法。在字典原子前加入待测像元与该原子的引力,以达到更快捷地找到与待测像元相匹配的原子的目的。加入的引力值由万有引力公式改进的适应于高光谱图像的公式计算而来。为了使得稀疏重构后的残差波段中包含的具有一定意义的分类鉴别信息被充分挖掘,本文采用指数平滑公式对残差信息进行再利用。通过在Indian Pine数据集和Salina-A数据集上进行实验,验证了所提算法可以提升分类精度。

关键词: 高光谱图像分类, 联合稀疏表示, 引力公式, 二级字典, 自适应

Abstract:

In view of the problems of low classification accuracy and insufficient utilization of spectral information in most traditional classification algorithms when applied in hyperspectral classification, based on the joint sparse representation of hyperspectral image classification based on kernel function, the joint sparse representation of hyperspectral image classification based on secondary dictionary is proposed. The gravitation between the pixel to be measured and the atom is added in front of the dictionary atom, so as to find the atom matching with the pixel to be measured more quickly. The added gravitational value is calculated by the formula adapted to the hyperspectral image modified by the gravitational formula. In order to explore the meaningful classification and identification information contained in the residual band after sparse reconstruction fully, this paper reuses the residual information is reused by using exponential smoothing formula. Experimental results in Indian Pines and Salina-A data sets show that the proposed algorithm achieves the purpose of improving the classification accuracy of hyperspectral images.

Key words: hyperspectral image classification, joint sparse representation, gravitation formula, secondary dictionary, adaptive

中图分类号:

TP751

陈善学, 陈雯雯. 基于二级字典的联合稀疏表示高光谱图像分类[J]. 系统工程与电子技术, 2020, 42(3): 550-556.

Shanxue CHEN, Wenwen CHEN. Joint sparse representation of hyperspectral image classification based on secondary dictionary[J]. Systems Engineering and Electronics, 2020, 42(3): 550-556.

图/表 12

图1

图2

表1

图3

图4

表2

图5

图6

表3

图7

表4

图8

参考文献 21

1	PAL M , FOODY G M . Feature selection for classification of hyperspectral data by SVM[J]. IEEE Trans.on Geoscience and Remote Sensing, 2010, 48 (5): 2297- 2307. doi: 10.1109/TGRS.2009.2039484
2	CHEN Y , NASRABADI N M , TRAN T D . Hyperspectral image classification via kernel sparse representation[J]. IEEE Trans.on Geoscience and Remote Sensing, 2013, 51 (1): 217- 231. doi: 10.1109/TGRS.2012.2201730
3	CAMPS-VALLS G , BANDOS M T , ZHOU D . Semi-supervised graph-based hyperspectral image classification[J]. IEEE Trans.on Geoscience and Remote Sensing, 2007, 45 (10): 3044- 3054. doi: 10.1109/TGRS.2007.895416
4	MELGANI F , BRUZZONE L . Classification of hyperspectral remote sensing images with support vector machines[J]. IEEE Trans.on Geoscience and Remote Sensing, 2004, 42 (8): 1778- 1790. doi: 10.1109/TGRS.2004.831865
5	XIE H , ZHAO A , HUANG S , et al. Unsupervised hyperspectral remote sensing image clustering based on adaptive density[J]. IEEE Geoscience & Remote Sensing Letters, 2018, 15 (4): 632- 636.
6	WINDRIM L , RAMAKRISHAN R , MELKUMYAN A , et al. A physics-based deep learning approach to shadow invariant representations of hyperspectral images[J]. IEEE Trans.on Image Processing, 2018, PP (99): 1.
7	LI J , ZHAO X , LI Y , et al. Classification of hyperspectral imagery using a new fully convolutional neural network[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (2): 292- 296. doi: 10.1109/LGRS.2017.2786272
8	LEE H, KWON H. Contextual deep CNN based hyperspectral classification[C]//Proc.of the Geoscience & Remote Sensing Symposium, 2016: 1-1.
9	CHEN Y , JIANG H , LI C , et al. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks[J]. IEEE Trans.on Geoscience and Remote Sensing, 2016, 54 (10): 6232- 6251. doi: 10.1109/TGRS.2016.2584107
10	LEE H , KWON H . Going deeper with contextual CNN for hyperspectral image classification[J]. IEEE Trans.on Image Process, 2017, 26 (10): 4843- 4855. doi: 10.1109/TIP.2017.2725580
11	CHEN Y , NARSRABADI N M , TRAN T D . Hyperspectral image classification using dictionary-based sparse representation[J]. IEEE Trans.on Geoscience and Remote Sensing, 2011, 49 (10): 3973- 3985. doi: 10.1109/TGRS.2011.2129595
12	BIOUCAS-DIAS J M , PLAZA A , CAMPS-VALLS G , et al. Hyperspectral remote sensing data analysis and future challenges[J]. IEEE Geoscience and Remote Sensing Magazine, 2013, 1 (2): 6- 36. doi: 10.1109/MGRS.2013.2244672
13	TU B , HUANG S Y , FANG L , et al. Hyperspectral image classification via weighted joint nearest neighbor and sparse representation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 1- 13.
14	ZHANG H , LI J , HUANG Y , 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): 2056- 2065. doi: 10.1109/JSTARS.2013.2264720
15	陈善学, 周艳发, 漆若兰. 基于核函数的联合稀疏表示高光谱图像分类[J]. 系统工程与电子技术, 2018, 40 (3): 692- 698.
	CHEN S X , ZHOU Y F , QI R L . Joint sparse representation of hyperspectral image classification based on Kernel function[J]. Systems Engineering and Electronices, 2018, 40 (3): 692- 698.
16	AHARON M , ELAD M , BRUCKSTEIN A . K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Trans.on Signal Processing, 2006, 54, 4311- 4322. doi: 10.1109/TSP.2006.881199
17	TROPP J A , GILBERT A C . Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Trans.on Information Theory, 2007, 53 (12): 4655- 4666. doi: 10.1109/TIT.2007.909108
18	TIBSHIRANI R J . Regression shrinkage and selection via the LASSO[J]. Journal of the Royal Statistical Society (Series B: Methodological), 1996, 73 (1): 273- 282.
19	WRIGHT S J , NOWAK R D , FIGUEIREDO M A T . Sparse reconstruction by separable approximation[J]. IEEE Trans.on Signal Processing, 2009, 57 (7): 2479- 2493. doi: 10.1109/TSP.2009.2016892
20	CUI M , PRASAD S . Class-dependent sparse representation classifier for robust hyperspectral image classification[J]. IEEE Trans.on Geoscience and Remote Sensing, 2015, 53 (5): 2683- 2695. doi: 10.1109/TGRS.2014.2363582
21	陈善学, 桂成名, 王一宁, 等. 基于紧耦合像元的自适应增强类内稀疏表示高光谱图像分类[J]. 系统工程与电子技术, 2017, 39 (3): 655- 661.
	CHEN S X , GUI C M , WANG Y N , et al. Close coupled set of pixels-based adaptive boosting class-wise sparse representation classifier for robust hyperspectral image classification[J]. and Electronices, 2017, 39 (3): 655- 661.

算法	字典原子个数/个
算法	5	30	50	70	100
SD-JSRC(本文)	67.81	83.24	87.96	91.37	95.98
K-JSRC(CEK)	65.03	77.93	83.85	86.89	89.46
KNN	56.26	73.31	76.15	77.97	82.59
cdSRC	59.80	76.18	80.80	83.86	86.71
OMP	58.97	74.43	77.52	80.44	83.77

算法	时间/s
SD-JSRC	816.47
K-JSRC	788.63
KNN	25.38
cdSRC	517.18
OMP	6.51

算法	字典原子个数/个
算法	10	30	100	150	200
SD-JSRC(本文)	85.07	93.62	97.05	98.50	99.18
K-JSRC(CEK)	84.39	92.83	95.95	96.37	97.20
KNN	77.85	83.57	85.60	87.10	88.14
cdSRC	81.38	89.05	93.42	94.13	94.72
OMP	76.92	82.75	85.95	87.73	88.92

类别	字典原子个数/个	测试样本个数/个	OMP	cdSRC	KNN	K-JSRC	改进算法
1	150	2 009	98.66	100.00	98.01	100.00	100.00
2	150	3 726	98.63	99.92	98.95	99.70	99.92
3	150	1 976	96.46	100.00	98.94	100.00	100.00
4	150	1 394	98.92	99.86	99.28	98.92	99.57
5	150	2 678	95.37	99.03	95.59	98.84	98.95
6	150	3 959	99.75	99.80	99.22	99.72	99.75
7	150	3 579	99.72	99.80	99.16	99.80	99.92
8	150	11 271	69.05	90.87	63.22	92.17	99.65
9	150	6 023	98.61	98.68	96.66	100.00	100.00
10	150	3 278	91.85	99.60	90.51	97.44	98.72
11	150	1 068	98.78	99.72	94.57	99.16	99.63
12	150	1 927	96.32	100.00	99.90	99.95	100.00
13	150	916	95.74	98.91	97.05	99.02	98.80
14	150	1 070	96.54	95.79	93.55	96.54	96.54
15	150	7 268	62.16	74.61	69.36	88.43	92.45
16	150	1 807	99.06	99.00	98.62	99.67	99.89
总体分类精度			86.93	94.29	86.40	96.41	98.64

[1]	常浩伟, 庞春雷, 郭泽辉, 张良, 吕敏敏, 张闯. 基于自适应免疫算法的欺骗信号检测方法[J]. 系统工程与电子技术, 2022, 44(8): 2419-2426.
[2]	熊元燚, 谢文冲. 基于空时约束的自适应迭代单脉冲估计方法[J]. 系统工程与电子技术, 2022, 44(8): 2506-2514.
[3]	方志耕, 夏悦馨, 张靖如, 熊仪, 陈静邑. 基于Agent的体系过程A-GERT网络“刺激-反应”学习模型[J]. 系统工程与电子技术, 2022, 44(8): 2540-2553.
[4]	王帅, 向建军, 彭芳, 唐书娟, 李志军. 基于新最速下降算法的自适应波束形成[J]. 系统工程与电子技术, 2022, 44(7): 2104-2111.
[5]	闫世瑛, 颜克斐, 方伟, 陆恒杨. 基于差分进化邻域自适应的大规模多目标算法[J]. 系统工程与电子技术, 2022, 44(7): 2112-2124.
[6]	王冠, 茹海忠, 张大力, 马广程, 夏红伟. 弹性高超声速飞行器智能控制系统设计[J]. 系统工程与电子技术, 2022, 44(7): 2276-2285.
[7]	高升, 马广富, 郭延宁. 基于自适应未知输入观测器的多故障快速重构[J]. 系统工程与电子技术, 2022, 44(7): 2364-2373.
[8]	魏法, 杨明磊, 何小静, 周鼎森, 陈伯孝. 基于改进粒子群算法的平面阵同时多波束赋形方法[J]. 系统工程与电子技术, 2022, 44(6): 1789-1797.
[9]	陈江美, 张文德. 基于灰关联分析和时空偏好特征的兴趣点推荐算法[J]. 系统工程与电子技术, 2022, 44(6): 1934-1941.
[10]	董一平, 刘宁, 苏中, 王靖骁, 白宏阳. 基于AEKF的高速自旋飞行体组合导航方法[J]. 系统工程与电子技术, 2022, 44(6): 1977-1983.
[11]	王帅, 向建军, 彭芳, 唐书娟. 基于新最速下降法的目标跟踪算法[J]. 系统工程与电子技术, 2022, 44(5): 1512-1519.
[12]	罗世彬, 李晓栋, 王忠森, 徐骋. 并联式运载器上升段广义超螺旋有限时间控制[J]. 系统工程与电子技术, 2022, 44(5): 1626-1635.
[13]	李海, 程伟杰, 谢瑞杰. 基于同伦稀疏STAP的低空风切变风速估计[J]. 系统工程与电子技术, 2022, 44(4): 1174-1181.
[14]	李园, 史宪铭, 李亚娟, 赵美. 基于Adaboost的作战目标属性判定方法[J]. 系统工程与电子技术, 2022, 44(4): 1256-1262.
[15]	安通, 王鹏, 王建华, 汤国建, 潘玉龙, 陈海山. 弹性高超声速飞行器动态面制导控制一体化设计方法[J]. 系统工程与电子技术, 2022, 44(3): 956-966.