基于空间预处理联合稀疏表示高光谱图像分类

doi:10.12305/j.issn.1001-506X.2021.09.07

摘要/Abstract

摘要：

针对高光谱图像分类时光谱信息和空间信息利用不充分、分类精度低的情况, 提出一种结合空间预处理的联合稀疏表示分类方法。一方面能够弥补联合稀疏表示固定窗口模式中空间信息利用不充分的问题, 另一方面也避免了像元多次参与联合稀疏模型的构建过程。考虑每个像元对联合稀疏模型的贡献不同, 通过赋予邻域像元相应权重以提高稀疏重构精度。最后, 充分利用训练样本的已知信息修正分类结果, 在Pavia University和AVIRIS Salinas两个数据集上进行实验验证。实验结果表明, 所提方法能够有效地提高高光谱图像分类精度。

关键词: 高光谱图像分类, 联合稀疏表示, 空间预处理, 权重

Abstract:

Aiming at the situation of insufficient utilization of spectral information or spatial information and low classification accuracy in hyperspectral image classification, a joint sparse representation classification method combined with spatial preprocessing is proposed. On the one hand, it can make up for the problem of insufficient utilization of spatial information in the fixed window mode of the joint sparse representation; on the other hand, it also avoids the pixels from participating in the construction process of the joint sparse model multiple times. Considering that each pixel contributes differently to the joint sparse model, the neighboring pixels are given corresponding weights to improve the accuracy of sparse reconstruction. Finally, make full use of the known information of the training samples to correct the classification results. Experiments were conducted on Pavia University and AVIRIS Salinas. The experimental results show that the method proposed in this paper can effectively improve the classification accuracy of hyperspectral images.

Key words: hyperspectral image classification, joint sparse representation, spatial preprocessing, weights

中图分类号:

TP751

陈善学, 王欣欣. 基于空间预处理联合稀疏表示高光谱图像分类[J]. 系统工程与电子技术, 2021, 43(9): 2422-2429.

Shanxue CHEN, Xinxin WANG. Joint sparse representation hyperspectral image classification based on spatial preprocessing[J]. Systems Engineering and Electronics, 2021, 43(9): 2422-2429.

图/表 10

图1

图2

图3

表1

图4

图5

表2

图6

图7

表3

参考文献 31

1	SERPICO S B , BRUZZONE L . A new search algorithm for feature selection in hyperspectral remote sensing images[J]. IEEE Trans.on Geoscience and Remote Sensing, 2002, 39 (7): 1360- 1367.
2	KARAKAYA A, SENIHA E Y, ANKARA, et al. Target detection in hyperspectral images[C]//Proc. of the Signal Processing and Communication Application Conference, 2016.
3	徐栋, 杨敏, 苗宇宏, 等. 基于无人机高光谱遥感的海岛岸线精准提取方法研究与应用[J]. 海洋科学, 2020, 44 (12): 54- 60.
	XU D , YANG M , MIAO Y H , et al. Research and application of accurate extraction method of island shoreline based on hyperspectral remote sensing of unmanned aerial vehicle[J]. Marine Sciences, 2020, 44 (12): 54- 60.
4	EISMANN M T , STOCKER A D , NASRABADI N M . Automated hyperspectral cueing for civilian search and rescue[J]. Proceedings of the IEEE, 2009, 97 (6): 1031- 1055. doi: 10.1109/JPROC.2009.2013561
5	WANG X X , JIA K , LIANG S L , et al. Fractional vegetation cover estimation method through dynamic bayesian network combining radiative transfer model and crop growth model[J]. IEEE Trans.on Geoscience & Remote Sensing, 2016, 54 (12): 7442- 7450.
6	顾泽鑫, 王白娟, 苏文苹, 等. 高光谱无人机遥感影像识别技术在茶园病虫害防治中的应用研究[J]. 经济师, 2020, 12, 61- 62.
	GU Z X , WANG B J , SU W P , et al. Application of hyperspectral UAV remote sensing image recognition technology in pest control of tea garden[J]. China Economist, 2020, 12, 61- 62.
7	NOTESCO G, DOR E B, BROOK A, et al. Mineral mapping of makhtesh ramon in israel using hyperspectral remote sensing day and night LWIR images[C]//Proc. of the 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2014.
8	FENG J , CHEN J T , LIU L G , et al. CNN-based multilayer spatial-spectral feature fusion and sample augmentation with local and nonlocal constraints for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12 (4): 1299- 1313. doi: 10.1109/JSTARS.2019.2900705
9	CHEN Y S , ZHU K Q , ZHU L , et al. Automatic design of convolutional neural network for hyperspectral image classification[J]. IEEE Trans.on Geoscience and Remote Sensing, 2019, 57 (9): 7048- 7066. doi: 10.1109/TGRS.2019.2910603
10	XIE J , HE N J , FANG L Y , et al. Scale-free convolutional neural network for remote sensing scene classification[J]. IEEE Trans.on Geoscience & Remote Sensing, 2019, 57 (9): 6916- 6928.
11	WANG Z J , CHEN B , LU R Y , et al. FusionNet: an unsupervised convolutional variational network for hyperspectral and multispectral image fusion[J]. IEEE Trans.on Image Processing, 2020, 29, 7565- 7577. doi: 10.1109/TIP.2020.3004261
12	KULKARNI S, SENTHILNATH J, BENEDIKTSSON J A. Classification of multi-spectral satellite image using hierarchical clustering algorithms[C]//Proc. of the IEEE Symposium Series on Computational Intelligence, 2018.
13	ZHAO C J , ZHAO H D , WANG G Z , et al. Improvement SVM classification performance of hyperspectral image using chaotic sequences in artificial bee colony[J]. IEEE Access, 2020, 8, 73947- 73956. doi: 10.1109/ACCESS.2020.2987865
14	KAYABOL K . Approximate sparse multinomial logistic regression for classification[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2020, 42 (2): 490- 493. doi: 10.1109/TPAMI.2019.2904062
15	HAUT J M , PAOLETTI M E . Cloud implementation of multinomial logistic regression for UAV hyperspectral images[J]. IEEE Journal on Miniaturization for Air and Space Systems, 2020, 3 (1): 163- 171.
16	何同弟, 李见为. 基于自适应稀疏表示的高光谱遥感图像分类[J]. 系统工程与电子技术, 2013, 35 (9): 1994- 1998. doi: 10.3969/j.issn.1001-506X.2013.09.32
	HE T D , LI J W . Hyperspectral remote sensing image classification based on adaptive sparse representation[J]. Systems Engineering and Electronics, 2013, 35 (9): 1994- 1998. doi: 10.3969/j.issn.1001-506X.2013.09.32
17	YU H Y , GAO L . Global spatial and local spectral similarity-based manifold learning group sparse representation for hyperspectral imagery classification[J]. IEEE Trans.on Geoscience and Remote Sensing, 2020, 58 (5): 3043- 3056. doi: 10.1109/TGRS.2019.2947032
18	ZHANG Y Q, CAO G, WANG B S, et al. Dual sparse representation graph-based copropagation for semisupervised hyperspectral image classification[J/OL]. IEEE Trans. on Geoscience and Remote Sensing. DOI: 10.1109/TGRS.2020.3046780.
19	LIANG M M , JIAO L C , XU C D . Deep feature-based multitask joint sparse representation for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17 (9): 1578- 1582. doi: 10.1109/LGRS.2019.2950095
20	CHEN Y, NARSABADI N M, TRAN T D. Classification for hyperspectral imagery based on sparse representation[C]//Proc. of the Workshop on Hyperspectral Image & Signal: Evolution in Remote Sensing, 2010.
21	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
22	TANG Y Y , YUAN H , LI L . Manifold-based sparse representation for hyperspectral image classification[J]. IEEE Trans.on Geoscience & Remote Sensing, 2014, 52 (12): 7606- 7618.
23	JIA S , HU J , XIE Y , et al. Gabor cube selection based multitask joint sparse representation for hyperspectral image classification[J]. IEEE Trans.on Geoscience & Remote Sensing, 2016, 54 (6): 3174- 3187.
24	FANG L Y , WANG C , LI S T , et al. Hyperspectral image classification via multiple-feature-based adaptive sparse representation[J]. IEEE Trans.on Instrumentation & Measurement, 2017, 66 (7): 1645- 1657.
25	GAN L , XIA J S , DU P J , et al. Multiple feature kernel sparse representation classifier for hyperspectral imagery[J]. IEEE Trans.on Geoscience & Remote Sensing, 2018, 56 (9): 5343- 5356.
26	CHEN Y , NASRABAD N M , TRAN T D . Hyperspectral image classification using dictionary-based sparse representation[J]. IEEE Trans.on Geoence and Remote Sensing, 2011, 49 (10): 3973- 3985. doi: 10.1109/TGRS.2011.2129595
27	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 & Remote Sensing, 2014, 7 (6): 2056- 2065.
28	FU W , LI S , FANG L , et al. Hyperspectral image classification via shape-adaptive joint sparse representation[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2016, 9 (2): 556- 567.
29	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 hyperspectral image classification based on kernel function[J]. System Engineering and Electronic Technology, 2018, 40 (3): 692- 698.
30	ZHENG C Y , WANG N N , CUI J . Hyperspectral image classification with small training sample size using superpixel-guided training sample enlargement[J]. IEEE Trans.on Geoence and Remote Sensing, 2019, 57 (10): 7307- 7316. doi: 10.1109/TGRS.2019.2912330
31	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

算法	类字典原子个数
算法	10	30	50	70	90	110	130	150
SP-JSRC	80.68	91.27	93.46	94.84	96.08	96.37	96.38	97.30
KJSRC	79.66	88.05	90.97	91.45	92.06	92.75	93.20	93.32
cdSRC	75.16	84.97	88.81	89.07	89.45	89.85	90.12	90.29
SVM	71.46	80.58	84.19	85.41	86.69	88.10	88.44	88.82
KNN	69.89	76.19	79.58	80.72	81.56	82.27	82.94	83.66

算法	类字典原子个数
算法	10	30	50	100	150
SP-JSRC	88.64	93.37	95.62	97.39	98.06
K-JSRC	84.27	92.82	93.84	95.93	96.31
cdSRC	81.45	89.21	91.67	93.42	94.27
SVM	79.53	83.79	85.69	87.33	89.43
KNN	79.31	82.52	83.96	85.88	87.27

算法	时间
SP-JSRC	1 199.291
K-JSRC	8 334.834
SVM	8.779
cdSRC	2 732.973
KNN	201.592

[1]	李翰, 张洪海, 张连东, 刘皞. 城市区域多物流无人机协同任务分配[J]. 系统工程与电子技术, 2021, 43(12): 3594-3602.
[2]	冯建鑫, 王雅雷, 王强, 胥彪. 基于改进粒子群算法的快速反射镜自抗扰控制[J]. 系统工程与电子技术, 2021, 43(12): 3675-3682.
[3]	霍超颖, 闫华, 冯雪健, 殷红成, 邢笑宇, 陆金文. HRRP稀疏自编码器深层特征与散射中心特征的关联性研究[J]. 系统工程与电子技术, 2021, 43(11): 3040-3053.
[4]	周璇, 何锋, 谷晓燕, 贾子睿, 熊华钢. 航电系统体系贡献率权重演化动态综合评估[J]. 系统工程与电子技术, 2020, 42(8): 1740-1750.
[5]	李彪, 王立文, 邢志伟, 罗谦. 过站航班地面保障流程效能评估[J]. 系统工程与电子技术, 2020, 42(7): 1543-1549.
[6]	田勇, 孙梦圆, 万莉莉. 终端区空域规划运行评价指标体系[J]. 系统工程与电子技术, 2020, 42(4): 851-862.
[7]	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.
[8]	姚靖宇, 靳鹏, 朱外明, 胡笑旋. 面向收益不均等区域目标的多星调度问题[J]. 系统工程与电子技术, 2020, 42(3): 638-645.
[9]	周亮, 孟进, 李毅, 刘伟. 考虑关键性的多约束下辐射干扰对消装备随舰备件配置优化方法[J]. 系统工程与电子技术, 2020, 42(2): 365-373.
[10]	雷杰, 徐晓滨, 徐晓健, 常雷雷. 基于置信规则库的并发故障诊断方法[J]. 系统工程与电子技术, 2020, 42(2): 497-505.
[11]	丁达理, 魏政磊, 唐上钦, 黄长强. 自适应预测权重的空战鲁棒机动决策方法[J]. 系统工程与电子技术, 2020, 42(10): 2275-2284.
[12]	江登英, 张徐军. 基于TFNCD算子的三角模糊数多属性群决策[J]. 系统工程与电子技术, 2019, 41(9): 2065-2071.
[13]	韦可佳, 耿俊豹, 徐孙庆. 基于模糊理论与D-S证据理论的FMEA方法[J]. 系统工程与电子技术, 2019, 41(11): 2662-2668.
[14]	刘久富, 丁晓彬, 郑锐, 王彪, 刘海阳, 王志胜. 混沌量子粒子群的权重类条件贝叶斯网络分类器参数学习[J]. 系统工程与电子技术, 2019, 41(10): 2304-2309.
[15]	王尔申, 王玉伟, 曲萍萍, 蓝晓宇, 陈佳美. 基于代价的复杂网络边攻击策略有效性分析[J]. 系统工程与电子技术, 2018, 40(4): 919-926.