Spatial -Spectral Feature Extraction using Three-Dimensional Singular Spectrum Analysis for Hyperspectral Image Classification

Subject Areas : Remote Sensing

Ehsan Dashtifard ¹ , Azar Mahmoodzadeh ² , Ahmad Keshavarz ³ , Hamed Agahi ⁴

1 - Department of Electrical Engineering, Shiraz Branch, Islamic Azad University, Shiraz,, Iran
2 - Department of Electrical Engineering, Shiraz Branch, Islamic Azad University, Shiraz, Iran
3 - IoT and Signal Processing Research Group, ICT Research Institute, Faculty of Intelligent Systems Engineering and Data Science, Persian Gulf University, 7516913817 Bushehr, Iran
4 - Department of Electrical Engineering, Shiraz Branch, Islamic Azad University, Shiraz, Iran

Received: 2022-11-04 Accepted : 2023-01-21 Published : 2023-03-21

Keywords: Feature extraction, spatial-spectral, hyperspectral image (HSI), Classification, 3D-singular spectrum analysis (3D-SSA),

Abstract :

Feature extraction has a valuable role in hyperspectral images processing. In recent years, various methods have been presented to extract efficient features of hyperspectral images. Recent studies have successfully used conventional singular spectrum analysis in the spectral domain and two-dimensional singular spectrum analysis in the spatial domain for feature extraction in hyperspectral images. However, a lack of success in joint spectral-spatial feature extraction is a problem with both algorithms. This study uses a three-dimensional singular spectrum analysis extension to overcome this problem. The implementation of proposal model on hyperspectral images removes the noise components during spectral-spatial feature extraction process and significantly improves features identification capability. This study conducts experiments using two publically available datasets. Experimental results show that our proposed method has a promising performance so that it has obtained a classification accuracy of at least 1.93% and 1.27% respectively on the hyperspectral dataset of Indian Pines and Pavia University compared to other recent methods.

References:

[1]        L. He, J. Li, C. Liu, and S. Li, “Recent advances on spectral–spatial hyperspectral image classification: An overview and new guidelines,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 3, pp. 1579–1597, Mar. 2018, doi: 10.1109/TGRS.2017.2765364.

[2]        S. D. Fabiyi et al., “Varietal classification of rice seeds using RGB and hyperspectral images,” IEEE Access, vol. 8, pp 22493–22505, Jan. 2020, doi: 10.1109/ACCESS.2020.2969847.

[3]        F. Luo, B. Du, L. Zhang, L. Zhang and D. Tao, “Feature learning using spatial-spectral hypergraph discriminant analysis for hyperspectral image,” IEEE Trans. Cybern, vol. 49, no. 7, pp. 2406–2419, July. 2019, doi: 10.1109/TCYB.2018.2810806.

[4]        B. Kumar, O. Dikshit, A. Gupta and M.K. Singh, “Feature extraction for hyperspectral image  classification: A review,” Int. J. Remote Sens, vol. 41, no. 16, pp. 6248–6287, Jun. 2020, doi: 10.1080/01431161.2020.1736732.

[5]        C. Zhao, X. Li, J. Ren, and S. Marshall, “Improved sparse representation using adaptive spatial support for effective target detection in hyperspectral imagery,” Int. J. Remote Sens., vol. 34, no. 24, pp. 8669–8684, 2013, doi: 10.1080/01431161.2013.845924.

[6]        T. Qiao et al., “Effective denoising and classification of hyperspectral images using curvelet transform and singular spectrum analysis,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 1, pp. 119–133, Jan. 2017, doi: 10.1109/TGRS.2016.2598065.

[7]        G. Chen and S.-E. Qian, “Denoising of hyperspectral imagery using principal component analysis andwavelet shrinkage,” IEEE Trans.Geosci. Remote Sens., vol. 49, no. 3, pp. 973–980, Mar. 2011, doi: 10.1109/TGRS.2010.2075937.

[8]        T. Qiao et al., “Joint bilateral filtering and spectral similarity-based sparse representation: A generic framework for effective feature extraction and data classification in hyperspectral imaging,” Pattern Recognit., vol. 77, pp. 316–328, 2018, doi: 10.1016/j.patcog.2017.10.008.

[9]        X. Kang, X. Xiang, S. Li, and J. A. Benediktsson, “PCA-based edgepreserving features for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 12, pp. 7140–7151, Dec. 2017, doi: 10.1109/TGRS.2017.2743102.

[10]      J. Zabalza, R. Jinchang, W. Zheng, S. Marshall, and W. Jun, “Singular spectrum analysis for effective feature extraction in hyperspectral imaging,” IEEE Geosci. Remote Sens. Lett., vol. 11, no. 11, pp. 1886–1890, Nov. 2014, doi: 10.1109/LGRS.2014.2312754.

[11]      J. Zabalza, J. Ren, Z. Wang, H. Zhao, J. Wang, and S. Marshall, “Fast implementation of singular spectrum analysis for effective feature extraction in hyperspectral imaging,” IEEE J. Sel. Topics Appl. Earth Observation Remote Sens., vol. 8, no. 6, pp. 2845–2853, Jun. 2015, doi: 10.1109/JSTARS.2014.2375932.

[12]      Genyun Sun, et al., “SpaSSA: Superpixelwise Adaptive SSA for Unsupervised Spatial–Spectral Feature Extraction in Hyperspectral Image,” IEEE Trans. Geosci. Remote Sens., vol. 48, no. 11, pp. 4071–4084, Nov. 2021, doi: 10.1109/TCYB.2021.3104100.

[13]      P. R. Marpu, M. Pedergnana, M. D. Mura, J. A. Benediktsson, and L. Bruzzone, “Automatic generation of standard deviation attribute profiles for spectral–spatial classification of remote sensing data,” IEEE Geosci. Remote Sens. Lett., vol. 10, no. 2, pp. 293–297, Mar. 2013, doi: 10.1109/LGRS.2012.2203784.

[14]      S. Jia, L. Shen, and Q. Li, “Gabor feature-based collaborative representation for hyperspectral imagery classification,” IEEE Trans.Geosci. Remote Sens., vol. 53, no. 2, pp. 1118–1129, Feb. 2015, doi: 10.1109/TGRS.2014.2334608.

[15]      J. Zabalza et al., “Novel two-dimensional singular spectrum analysis for effective feature extraction and data classification in hyperspectral imaging,” IEEE Trans. Geosci. Remote Sens., vol. 53, no. 8, pp. 4418–4433, Aug. 2015, doi: 10.1109/TGRS.2015.2398468.

[16]      J. Zabalza, C. Qing, P. Yuen, G. Sun, H. Zhao, and J. Ren, “Fast implementation of two-dimensional singular spectrum analysis for effective data classification in hyperspectral imaging,” J. Franklin Inst., vol. 355, no. 4, pp. 1733–1751, 2018, doi: 10.1016/j.jfranklin.2017.05.020.

[17]      J. Xia, L. Bombrun, T. Adalı, Y. Berthoumieu, and C. Germain, “Spectral– spatial classification of hyperspectral images using ICA and edge-preserving filter via an ensemble strategy,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 8, pp. 4971–4982, Aug. 2016, doi: 10.1109/TGRS.2016.2553842.

[18]      X. Kang, S. Li, L. Fang, and J. A. Benediktsson, “Intrinsic image decomposition for feature extraction of hyperspectral images,” IEEE Trans. Geosci. Remote Sens., vol. 53, no. 4, pp. 2241–2253, Apr. 2015, doi: 10.1109/TGRS.2014.2358615.

[19]      B. Sun, X. Kang, S. Li, and J. A. Benediktsson, “Random-walker-based collaborative learning for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 1, pp. 212–222, Jan. 2017, doi: 10.1109/TGRS.2016.2604290.

[20]      F. Samadi, G. Akbarizadeh, and H. Kaabi, “Change detection in SAR images using deep belief network: A new training approach based on morphological images,” IET Image Process., vol. 13, no. 12, pp. 2255– 2264, 2019,  doi: 10.1049/iet-ipr.2018.6248.

[21]      F. Sharifzadeh, G. Akbarizadeh, and Y. Seifi Kavian, “Ship classification in SAR images using a new hybrid CNN–MLP classifier,” J. Indian Soc. Remote Sens., vol. 47, no. 4, pp. 551–562, 2018, doi: 10.1007/s12524-018-0891-y.

[22]      Y. Chen, Y. Wang, Y. Gu, X. He, P. Ghamisi, and X. Jia, “Deep learning ensemble for hyperspectral image classification,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 12, no. 6, pp. 1882–1897, Jun. 2019, doi: 10.1109/JSTARS.2019.2915259.

[23]      O. Oktay et al., “Anatomically constrained neural networks (ACNNs): Application to cardiac image enhancement and segmentation,” IEEE Trans. Med. Imag., vol. 37, no. 2, pp. 384–395, Feb. 2018, doi: 10.1109/TMI.2017.2743464.

[24]      M. Zalpour, G. Akbarizadeh, and N. Alaei-Sheini, “A new approach for oil tank detection using deep learning features with control false alarm rate in high-resolution satellite imagery,” Int. J. Remote Sens., vol. 41, no. 6, pp. 2239–2262, 2019, doi: 10.1080/01431161.2019.1685720.

[25]      X. Kang, C. Li, S. Li, and H. Lin, “Classification of hyperspectral images by gabor filtering based deep network,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 11, no. 4, pp. 1166–1178, Apr. 2018, doi: 10.1109/JSTARS.2017.2767185.

[26]      Y. Guo, H. Cao, J. Bai, and Y. Bai, “High efficient deep feature extraction and classification of spectral-spatial hyperspectral image using cross domain convolutional neural networks,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 12, no. 1, pp. 345–356, Jun. 2019, doi: 10.1109/JSTARS.2018.2888808.

[27]      Y. Kong, X. Wang, and Y. Cheng, “Spectral–spatial feature extraction for HSI classification based on supervised hypergraph and sample expanded CNN,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 11, no. 11, pp. 4128–4140, Nov. 2018, doi: 10.1109/JSTARS.2018.2869210.

[28]      E. Aptoula, M. C. Ozdemir, and B. Yanikoglu, “Deep learning with attribute profiles for hyperspectral image classification,” IEEE Geosci. Remote Sens. Lett., vol. 13, no. 12, pp. 1970–1974, Dec. 2016, doi: 10.1109/LGRS.2016.2619354.

[29]      L. Heming and Q. Li, “Hyperspectral imagery classification using sparse representations of convolutional neural network features,” Remote Sens., vol. 8, no. 99, 2016,  doi: 10.3390/rs8020099.

[30]      N. Golyandina and A. Zhigljavsky, “Singular Spectrum Analysis for Time Series,” Heidelberg, Germany: Springer, 2013.

[31]      A. Shlemov, N. Golyandina, D. Holloway, and A. Spirov, “Shaped 3D Singular Spectrum Analysis for Quantifying Gene Expression with Application to the Early Zebrafish Embryo,” Hindawi Publishing Corporation. BioMed Research International, pp. 1-15, 2015, doi: 10.1155/2015/986436.

[32]      H. Fu, G. Sun, J. Zabalza, A. Zhang, J. Ren, and X. Jia, “A novel spectral-spatial singular spectrum analysis technique for near realtime in situ feature extraction in hyperspectral imaging,” IEEE J. Sel. Topics Appl. Earth Observation Remote Sens., vol. 13, pp. 2214–2225, May 2020, doi: 10.1109/JSTARS.2020.2992230.

[33]      N. C. Shirazi, R. Hamzehyan, and A. Masoomi, “The Comparison of Classification Algorithms for Remote Sensing Images,” Journal of Communication Engineering., vol. 5,no.17, pp. 31-38, 2015(in persian).

[34]      F. Hajiani, N. Parhizgar, and A. Keshavarz, “Hyperspectral Image Classification Using Low Rank Representation and Spectral-Spatial Information,” Journal of Communication Engineering., vol. 11,no.43, pp. 27-38, 2022(in persian).

[35]      C. Chih-Chung and L. Chih-Jen, “LIBSVM: A library for support vector machines,” ACM Trans. Intell. Syst. Technol., vol. 2, no. 3, pp. 1–27, 2011, doi: 10.1145/1961189.1961199.

[36]      B. Liu, X.Yu, P. Zhang, A.Yu,Q. Fu, andX.Wei, “Supervised deep feature extraction for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 4, pp. 1909–1921, Apr. 2018, doi: 10.1109/TGRS.2017.2769673.

[37]      P . Ma, J. Ren, H. Zhao, G. Sun, P. Murray, and J. Zheng, “Multiscale 2-D Singular Spectrum Analysis and Principal Component Analysis for Spatial-Spectral Noise-Robust Feature Extraction and Classification of Hyperspectral Images,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 14, pp. 1233–1245, 2021, doi: 10.1109/JSTARS.2020.3040699.