高光谱影像奇异谱分析特征提取方法:综述与评价

doi:10.11947/j.AGCS.2023.20220542

摘要/Abstract

摘要： 高光谱遥感影像（hyperspectral imagery，HSI）通常包含几十至数百个连续波段，具有图谱合一、光谱连续的特点，能够实现地物的精细分类，被广泛应用农业、林业、城市以及海洋等领域。HSI特征提取是高光谱应用的前提，也是遥感领域的研究热点和前沿课题之一。近年来，奇异谱分析（singular spectrum analysis，SSA）被应用于HSI领域，在光谱特征和空间特征提取方面取得了较好效果，逐渐成为特征提取的一种有效方法。本文首先分析了HSI特征提取的研究进展和存在的问题；其次对SSA方法进行了系统的梳理，分别介绍了光谱域1D-SSA、空间域2D-SSA和光谱-空间组合域SSA 3类方法的作用、效果及优缺点，并在两个公开的HSI数据集和一个高分五号HSI数据上进行了分类效果验证；最后，对SSA特征提取进行了总结，并讨论了未来的研究方向。

关键词: 高光谱影像, 特征提取, 奇异谱分析, 地物分类, 综述

Abstract: Hyperspectral remote sensing imagery (HSI) usually contains dozens to hundreds of continuous spectral bands, with the syncretism of spectrum and image, spectral continuity, which can realize fine classification of ground objects and has been widely used in agriculture, forestry, urban and marine areas. The feature extraction of HSI is the premise of hyperspectral applications and has become one of the research hotspots and frontier topics in remote sensing. In recent years, singular spectrum analysis (SSA) has been applied in HSI, achieving superior results in the extraction of spectral and spatial features, and gradually becoming an effective feature extraction method. In this paper, firstly, the research progress and existing problems of HSI feature extraction are analyzed. Secondly, the existing SSA methods are systematically summarized and reviewed. The functions, effects, advantages, and disadvantages of three types of methods, namely, spectral domain 1D-SSA, spatial domain 2D-SSA, and combined spectral-spatial domain SSA, are introduced respectively, and the classification results are verified on two publicly available HSI datasets and one China Gaofen-5 satellite HSI dataset. Finally, the SSA feature extraction is summarized and future research directions are discussed.

Key words: hyperspectral imagery, feature extraction, singular spectrum analysis, classification, review

中图分类号:

P237

孙根云, 付航, 张爱竹, 任金昌. 高光谱影像奇异谱分析特征提取方法:综述与评价[J]. 测绘学报, 2023, 52(7): 1148-1163.

SUN Genyun, FU Hang, ZHANG Aizhu, REN Jinchang. Singular spectrum analysis method for hyperspectral imagery feature extraction: a review and evaluation[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(7): 1148-1163.

参考文献

[1] 童庆禧,张兵, 张立福.中国高光谱遥感的前沿进展[J].遥感学报,2016,20(5):689-707. TONG Qingxi, ZHANG Bing, ZHANG Lifu. Current progress of hyperspectral remote sensing in China[J]. Journal of Remote Sensing, 2016, 20(5):689-707.
[2] ZHONG Y, HU X, LUO C, et al.WHU-Hi:UAV-borne hyperspectral with high spatial resolution (H²) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF[J]. Remote Sensing of Environment, 2020, 250:112012.
[3] LORENZ S, GHAMISI P, KIRSCH M, et al.Feature extraction for hyperspectral mineral domain mapping:a test of conventional and innovative methods[J]. Remote Sensing of Environment, 2021, 252:112129.
[4] TONG Fei, ZHANG Yun. Spectral-spatial and cascaded multilayer random forests for tree species classification in airborne hyperspectral images[J].IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-11.
[5] HUGHES G. On the mean accuracy of statistical pattern recognizers[J]. IEEE Transactions on Information Theory, 1968, 14(1):55-63.
[6] 张良培, 李家艺.高光谱图像稀疏信息处理综述与展望[J].遥感学报,2016,20(5):1091-1101. ZHANG Liangpei, LI Jiayi. Development and prospect of sparse representation-based hyperspectral image processing and analysis[J]. Journal of Remote Sensing, 2016, 20(5):1091-1101.
[7] RASTI B, HONG D, HANG R, et al. Feature extraction for hyperspectral imagery:the evolution from shallow to deep:overview and toolbox[J]. IEEE Geoscience and Remote Sensing Magazine, 2020, 8(4):60-88.
[8] 黄鸿, 石光耀, 段宇乐, 等. 加权空-谱联合保持嵌入的高光谱遥感影像降维方法[J]. 测绘学报,2019,48(8):1014-1024. HUANG Hong, SHI Guangyao, DUAN Yule, et al. Dimensionality reduction method for hyperspectral images based on weighted spatial-spectral combined preserving embedding[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(8):1014-1024.
[9] 罗甫林. 高光谱图像稀疏流形学习方法研究[J]. 测绘学报, 2017, 46(3):400.DOI:10.11947/j.AGCS.2017.20160621. LUO Fulin. Sparse manifold learning for hyperspectral imagery[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(3):400.DOI:10.11947/j.AGCS.2017.20160621.
[10] KUMAR B, DIKSHIT O, GUPTA A, et al.Feature extraction for hyperspectral image classification:a review[J].International Journal of Remote Sensing,2020, 41(16):6248-6287.
[11] 余岸竹, 刘冰, 邢志鹏, 等. 面向高光谱影像分类的显著性特征提取方法[J]. 测绘学报,2019,48(8):985-995. DOI:10.11947/j.AGCS.2019.20180499. YU Anzhu, LIU Bing, XING Zhipeng, et al.Salient feature extraction method for hyperspectral image classification[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(8):985-995. DOI:10.11947/j.AGCS.2019.20180499.
[12] LI Wan, ZHANG Liangpei, ZHANG Lefei, et al. GPU parallel implementation of isometric mapping for hyperspectral classification[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(9):1532-1536.
[13] ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science (New York, N Y), 2000, 290(5500):2323-2326.
[14] 杨秋兰, 万晓霞, 肖根生. 基于偏最小二乘法的多光谱降维算法[J]. 激光与光电子学进展, 2020, 57(1):013003. YANG Qiulan, WAN Xiaoxia, XIAO Gensheng. Multispectral dimension reduction algorithm based on partial least squares[J]. Laser & Optoelectronics Progress, 2020, 57(1):013003.
[15] ZABALZA J, REN J, YANG M, et al.Novel folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 93:112-122.
[16] ZABALZA J, REN Jinchang, REN Jie, et al. Structured covariance principal component analysis for real-time onsite feature extraction and dimensionality reduction in hyperspectral imaging[J]. Applied Optics, 2014, 53(20):4440.
[17] JIA Sen, TANG Guihua, ZHU Jiasong, et al. A novel ranking-based clustering approach for hyperspectral band selection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(1):88-102.
[18] 王密,何鲁晓,程宇峰,等。自适应高斯滤波与SFIM模型相结合的全色多光谱影像融合方法[J]. 测绘学报,2018,47(1):82-90. DOI:10.11947/j.AGCS.2018.20170421. WANG Mi, HE Luxiao, CHENG Yufeng, et al. Panchromatic and multi-spectral fusion method combined with adaptive Gaussian filter and SFIM model[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(1):82-90. DOI:10.11947/j.AGCS.2018.20170421.
[19] QIAO T, YANG Z, REN J, et al.Joint bilateral filtering and spectral similarity-based sparse representation:a generic framework for effective feature extraction and data classification in hyperspectral imaging[J]. Pattern Recognition, 2018, 77:316-328.
[20] GUO Xian, HUANG Xin, ZHANG Liangpei. Three-dimensional wavelet texture feature extraction and classification for multi/hyperspectral imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(12):2183-2187.
[21] GOLYANDINA N, ZHIGLIAVSKI A. Singular spectrum analysis for time series[M].New York:Plenum Press, 2010.
[22] ZABALZA J, REN J, WANG Z, et al. Singular spectrum analysis for effective feature extraction in hyperspectral imaging[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(11):1886-1890.
[23] PAOLETTI M E, HAUT J M, PLAZA J, et al. Deep learning classifiers for hyperspectral imaging:a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 158:279-317.
[24] 张良培, 何江, 杨倩倩, 等. 数据驱动的多源遥感信息融合研究进展[J]. 测绘学报,2022,51(7):1317-1337. DOI:10.11947/j.AGCS.2022.20220171. ZHANG Liangpei, HE Jiang, YANG Qianqian, et al. Data-driven multi-source remote sensing data fusion:progress and challenges[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7):1317-1337. DOI:10.11947/j.AGCS.2022.20220171.
[25] ZHOU Peicheng, HAN Junwei, CHENG Gong, et al. Learning compact and discriminative stacked autoencoder for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(7):4823-4833.
[26] XU Yonghao, ZHANG Liangpei, DU Bo, et al. Spectral-spatial unified networks for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(10):5893-5909.
[27] HONG Danfeng, GAO Lianru, YAO Jing, et al. Graph convolutional networks for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(7):5966-5978.
[28] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all You need[EB/OL].[2017-06-12].https://arxiv.org/abs/1706.03762.
[29] LI Xian, DING Mingli, PIŽURICA A. Deep feature fusion via two-stream convolutional neural network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(4):2615-2629.
[30] AHMAD M, KHAN A M, MAZZARA M, et al. A fast and compact 3D CNN for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19:1-5.
[31] ZHONG Zilong, LI J, LUO Zhiming, et al. Spectral-spatial residual network for hyperspectral image classification:a 3D deep learning framework[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(2):847-858.
[32] SUN Yifan, LIU Bing, YU Xuchu, et al. Resolution reconstruction classification:fully octave convolution network with pyramid attention mechanism for hyperspectral image classification[J]. International Journal of Remote Sensing, 2022, 43(6):2076-2105.
[33] HE J, YUAN Q, LI J, et al.DsTer:a dense spectral transformer for remote sensing spectral super-resolution[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 109:102773.
[34] XUE Zhixiang, TAN Xiong, YU Xuchu, et al. Deep hierarchical vision transformer for hyperspectral and LiDAR data classification[J]. IEEE Transactions on Image Processing, 2022, 31:3095-3110.
[35] HONG Danfeng, HAN Zhu, YAO Jing, et al. SpectralFormer:rethinking hyperspectral image classification with transformers[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-15.
[36] YU Haoyang, XU Zhen, ZHENG Ke, et al. MSTNet:amultilevel spectral-spatial transformer network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-13.
[37] 刘冰, 左溪冰, 谭熊, 等. 高光谱影像分类的深度少样例学习方法[J]. 测绘学报,2020,49(10):1331-1342. DOI:10.11947/j.AGCS.2020.20190486. LIU Bing, ZUO Xibing, TAN Xiong, et al. A deep few-shot learning algorithm for hyperspectral image classification[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(10):1331-1342. DOI:10.11947/j.AGCS.2020.20190486.
[38] 孙一帆, 余旭初, 谭熊, 等. 面向小样本高光谱影像分类的轻量化关系网络[J]. 武汉大学学报(信息科学版), 2022, 47(8):1336-1348. SUN Yifan, YU Xuchu, TAN Xiong, et al. Lightweight relational network for small sample hyperspectral image classification[J]. Geomatics and Information Science of Wuhan University, 2022, 47(8):1336-1348.
[39] CHEN Yushi, ZHU Kaiqiang, ZHU Lin, et al. Automatic design of convolutional neural network for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(9):7048-7066.
[40] ZABALZA J, REN Jinchang, ZHENG Jiangbin, et al. Novel two-dimensional singular spectrum analysis for effective feature extraction and data classification in hyperspectral imaging[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(8):4418-4433.
[41] FU Hang, ZHANG Aizhu, SUN Genyun, et al. A novel band selection and spatial noise reduction method for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-13.
[42] FU Hang, SUN Genyun, REN Jinchang, et al. Fusion of PCA and segmented-PCA domain multiscale 2-D-SSA for effective spectral-spatial feature extraction and data classification in hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-14.
[43] YAN Yijun, REN Jinchang, LIU Qiaoyuan, et al. PCA-domain fused singular spectral analysis for fast and noise-robust spectral-spatial feature mining in hyperspectral classification[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20:1-5.
[44] GOLYANDINA N, KOROBEYNIKOV A, ZHIGLJAVSKY A. SSA for multivariate time series[M] Berlin:Springer, 2018:189-229.
[45] ZABALZA J, REN Jinchang, WANG Zheng, et al. Fast implementation of singular spectrum analysis for effective feature extraction in hyperspectral imaging[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(6):2845-2853.
[46] QIAO Tong, REN Jinchang, WANG Zheng, et al. Effective denoising and classification of hyperspectral images using curvelet transform and singular spectrum analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(1):119-133.
[47] ZABALZA J, QING C, YUEN P, et al.Fast implementation of two-dimensional singular spectrum analysis for effective data classification in hyperspectral imaging[J]. Journal of the Franklin Institute, 2018, 355(4):1733-1751.
[48] LIN Yuxin, LING B W K, HU Lingyue, et al. Hyperspectral image enhancement by two dimensional quaternion valued singular spectrum analysis for object recognition[J]. Remote Sensing, 2021, 13(3):405.
[49] FU Hang, SUN Genyun, ZABALZA J, et al. A novel spectral-spatial singular spectrum analysis technique for near real-time in situ feature extraction in hyperspectral imaging[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13:2214-2225.
[50] MA Ping, REN Jinchang, ZHAO Huimin, et al. Multiscale 2-D singular spectrum analysis and principal component analysis for spatial-spectral noise-robust feature extraction and classification of hyperspectral images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 14:1233-1245.
[51] 付航, 孙根云, 赵云华, 等. 多尺度超像素分割和奇异谱分析的高光谱影像分类[J]. 中国图象图形学报, 2021, 26(8):1978-1993. FU Hang, SUN Genyun, ZHAO Yunhua, et al. Combining multiscale superpixel segmentation and singular spectral analysis for hyperspectral image classification[J]. Journal of Image and Graphics, 2021, 26(8):1978-1993.
[52] SUBUDHI S, PATRO R, BISWAL P K, et al. Superpixel-based singular spectrum analysis for effective spatial-spectral feature extraction[J]. Applied Sciences, 2021, 11(22):10876.
[53] SUN Genyun, FU Hang, REN Jinchang, et al. SpaSSA:superpixelwise adaptive SSA for unsupervised spatial-spectral feature extraction in hyperspectral image[J]. IEEE Transactions on Cybernetics, 2022, 52(7):6158-6169.