access icon free Hyperspectral remote sensing image classification using combinatorial optimisation based un-supervised band selection and CNN

Hyperspectral image (HSI) consists of hundreds of contiguous spectral bands, which can be used in the classification of different objects on the earth. The inclusion of both spectral as well as spatial features stands essential in order that high classification accuracy is achieved. However, incorporation of the spectral and spatial information without preserving the intrinsic structure of the data leads on to downscaling the classification accuracy. To address the issue aforementioned, the proposed method which involves using unsupervised spectral band selection based on three major constrains: (i) low reconstruction error with neighbourhood bands, (ii) low noise, (iii) high information entropy, is put forward. In addition, the structure-preserving recursive filter is used to extract spatial features. Finally, the classification is performed using convolutional neural networks (CNNs) with different sets of convolutional, pooling, and fully connected layers. To test the performance of the proposed method, experiments have been carried out with three benchmark HSI datasets Indian pines, University of Pavia, and Salinas. These experiments reveal that the proposed method offers better classification accuracy over the purportedly state-of-the-art methods in terms of standard metrics like overall accuracy, average accuracy, and kappa coefficient (K). The proposed method has attained OAs of 99.9, 98.9, and 99.93% for the three datasets, respectively.

Inspec keywords: image classification; feature extraction; geophysical image processing; convolutional neural nets; entropy; hyperspectral imaging; unsupervised learning; remote sensing

Other keywords: hyperspectral remote sensing image classification; neighbourhood bands; spatial information; structure-preserving recursive filter; benchmark HSI datasets Indian pines; high information entropy; high classification accuracy; un-supervised band selection; hyperspectral image; low reconstruction error; spectral information; unsupervised spectral band selection; convolutional neural networks; contiguous spectral bands; spatial features; combinatorial optimisation; intrinsic structure

Subjects: Geography and cartography computing; Unsupervised learning; Data and information; acquisition, processing, storage and dissemination in geophysics; Neural nets; Geophysical techniques and equipment; Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research; Computer vision and image processing techniques; Image recognition

References

    1. 1)
      • 4. Licciardi, G., Marpu, P.R., Chanussot, J., et al: ‘Linear versus nonlinear PCA for the classification of hyperspectral data based on the extended morphological profiles’, IEEE Geosci. Remote Sens. Lett., 2011, 9, (3), pp. 447451.
    2. 2)
    3. 3)
      • 18. Zhang, M., Gong, M., Chan, Y.: ‘Hyperspectral band selection based on multi-objective optimization with high information and low redundancy’, Appl. Soft Comput., 2018, 70, pp. 604621, ISSN 1568-4946, https://doi.org/10.1016/j.asoc.2018.06.009.
    4. 4)
    5. 5)
      • 50. Sawant, S.S., Prabukumar, M.: ‘Band fusion based hyper spectral image classification’, Int. J. Pure. Appl. Math., 2017, 117, (17), pp. 7176.
    6. 6)
      • 55. Prabukumar, M., Shrutika, S.: ‘Band clustering using expectation–maximization algorithm and weighted average fusion-based feature extraction for hyperspectral image classification’, J. Appl. Remote Sens., 2018, 12, (4), pp. 124.
    7. 7)
      • 11. Sawant, S.S., Prabukumar, M., Samiappan, S.: ‘A band selection method for hyperspectral image classification based on cuckoo search algorithm with corre-lation based initialization’. 10th IEEE GRSS WHISPERS is workshop on Hy-perspectral image and signal processing: Evolution in Remote Sensing (WHISPERS), Am-sterdam, Netherlands, 2019.
    8. 8)
    9. 9)
      • 2. Lowe, A., Harrison, N., French, A.P.: ‘Hyperspectral image analysis techniques for the detection and classification of the early onset of plant disease and stress’, Plant Methods, 2017, 13, p. 80.
    10. 10)
    11. 11)
      • 36. Li, C., Yang, S.X., Yang, Y., et al: ‘Hyperspectral remote sensing image classification based on maximum overlap pooling convolutional neural network’, Sensors (Basel), 2018, 18, (10), p. 3587, https://doi.org/10.3390/s18103587, Published 2018 October 22.
    12. 12)
      • 57. Vaddi, R., Prabukumar, M.: ‘CNN based hyperspectral image classification using unsupervised band selection and structure-preserving spatial features’, Infrared Phys. Technol., 2020, 110, p. 103457, ISSN 1350-4495.
    13. 13)
    14. 14)
      • 3. Khan, M.J., Khan, H.S., Yousaf, A., et al: ‘Modern trends in hyperspectral image analysis: a review’, IEEE Access, 2018, 6, pp. 1411814129.
    15. 15)
    16. 16)
      • 24. Vaddi, R., Manoharan, P.: ‘Probabilistic PCA based hyperspectral image classifica-tion for remote sensing applications’, in: Abraham, A., Cherukuri, A., Melin, P., Gandhi, N. (eds.): ‘Intelligent systems design and applications’. ISDA 2018 2018. Advances in Intelli-gent Systems and Computing (Springer, Cham, 2020), vol. 941, pp. 863869.
    17. 17)
      • 12. Feng, J., Jiao, L.C., Zhang, X., et al: ‘Hyperspectral band selection based on trivariate mutual information and clonal selection’, IEEE Trans. Geosci. Remote Sens., 2014, 52, (7), pp. 40924105.
    18. 18)
      • 47. Boggavarapu, L.N.P., Prabukumar, M.: ‘Hyper spectral image classification using fuzzy embedded hyperbolic sigmoid nonlinear principal component and weighted least square approach’, J. Appl. Remote Sens., 2020, 14, (2), pp. 118, https://doi.org/10.1117/1.JRS.14.024501.
    19. 19)
      • 6. Bandos, T.V., Bruzzone, L., Camps-Valls, G.: ‘Classification of hyperspectral images with regularized linear discriminant analysis’, IEEE Trans. Geosci. Remote Sens., 2009, 47, (3), pp. 862873.
    20. 20)
      • 44. Hyperspectral Remote Sensing Scenes. Available at http://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes, accessed on 19 April 2020.
    21. 21)
    22. 22)
    23. 23)
      • 54. Vaddi, R., Prabukumar, M.: ‘Stratified sampling method based training pixels selection for hyper spectral remote sensing image classification’, Int. J. Pure. Appl. Math., 2017, 117, (17), pp. 121126, ISSN: 1314-3395.
    24. 24)
      • 13. Sawant, S.S., Prabukumar, M.: ‘Semi-supervised techniques based hyperspectral image classification: a survey’. Int. Conf. on Innovations in Power and Advanced Computing Technologies [i-PACT2017], VIT Vellore, 2017.
    25. 25)
      • 14. Sawant, S.S., Prabukumar, M.: ‘Unsupervised band selection based on weighted information entropy and 3d discrete cosine transform for hyperspectral image classification’, Int. J. Remote Sens., 2020, 41, (10), pp. 39483969.
    26. 26)
      • 43. Melganiand, F., Bruzzone, L.: ‘Classification of hyperspectral remotesensing images with support vector machines’, IEEE Trans. Geosci. Remote Sens., 2004, 42, (8), pp. 17781790.
    27. 27)
      • 15. Sawant, S., Prabukumar, M.: ‘Hyperspectral band selection based on meta heuristic optimization approach’, Infrared Phys. Technol., 2020, 107, p. 103295, ISSN1350-4495, https://doi.org/10.1016/j.infrared.2020.103295.
    28. 28)
      • 52. Boggavarapu, L.N.P., Prabukumar, M.: ‘Robust classification of hyper spectral remote sensing images combined with multi hypothesis prediction and 3 dimensional discrete wavelet transform’, Int. J. Pure. Appl. Math., 2017, 117, (17), pp. 115120, ISSN: 1314-3395.
    29. 29)
      • 42. Gao, Q., Lim, S., Jia, X.: ‘Hyperspectral image classification using convolutional neural networks and multiple feature learning’, Remote Sens., 2018, 10, p. 299.
    30. 30)
    31. 31)
      • 51. Sawant, S.S., Prabukumar, M., Samiappan, S.: ‘Ranking and grouping based feature selection for hyperspectral image classification’. 39th Asian Conf. on Remote Sensing (ACRS 2018) Kuala Lumpur, Malaysia, 2018.
    32. 32)
      • 33. Chen, Y., Jiang, H., Li, C., et al: ‘Deep feature extraction and classification of hyperspectral images based on convolutional neural networks’, IEEE Trans. Geosci. Remote Sens., 2016, 54, (10), pp. 62326251, https://doi.org/10.1109/TGRS.2016.2584107.
    33. 33)
    34. 34)
      • 7. Yang, J.-M., Yu, P.-T., Kuo, B.-C., et al: ‘Nonparametric fuzzy feature extraction for hyperspectral image classification’, Int. J. Fuzzy Syst., 2010, 12, (3), pp. 208217.
    35. 35)
      • 58. Phaneendra, L.N., Boggavarapu, K., Prabukumar, M.: ‘A new framework for hyperspectral image classification using gabor embedded patch based convolution neural network’, Infrared Phys. Technol., 2020, 110, p. 103455, ISSN 1350-4495.
    36. 36)
    37. 37)
    38. 38)
    39. 39)
      • 48. Deep Learning for hyperspectral image processing. Available at https://github.com/mtalebizadeh/hyperspectral-image-processing, accessed on 02 May 2020.
    40. 40)
      • 28. Zenzo, S.D., Bernstein, R., Degloria, S.D., et al: ‘Gaussian maximum likelihood and contextual classification algorithms for multicrop classification’, IEEE Trans. Geosci. Remote Sens., 1987, GE-25, (6), pp. 805814.
    41. 41)
      • 16. Sawant, S.S., Prabukumar, M.: ‘New framework for hyperspectral band selection using modified wind-driven optimization algorithm’, Int. J. Remote Sens., 2019, 40, (20), pp. 78527873.
    42. 42)
    43. 43)
      • 37. Wang, A., Wang, Y., Chen, Y.: ‘Hyperspectral image classification based on convolutional neural network and random forest’, Remote Sens. Lett., 2019, 10, (11), pp. 10861094, https://doi.org/10.1080/2150704X.2019.1649736.
    44. 44)
      • 5. Villa, A., Benediktsson, J.A., Chanussot, J., et al: ‘Hyperspectral image classification with independent component discriminant analysis’, IEEE Trans. Geosci. Remote Sens., 2011, 49, (12), pp. 48654876.
    45. 45)
    46. 46)
      • 39. Vaddi, R., Prabukumar, M.: ‘Hyperspectral image classification using CNN with spectral and spatial features integration’, Infrared Phys. Technol., 2020, 107, p. 103296, ISSN 1350-4495, https://doi.org/10.1016/j.infrared.2020.103296.
    47. 47)
      • 34. Chen, Y., Zhu, L., Ghamisi, P., et al: ‘Hyperspectral images classification with gabor filtering and convolutional neural network’, IEEE Geosci. Remote Sens. Lett., 2017, 14, (12), pp. 23552359, https://doi.org/10.1109/LGRS.2017.2764915.
    48. 48)
      • 27. Ma, L., Crawford, M.M., Tian, J.: ‘Local manifold learning-based k -nearest-neighbor for hyperspectral image classification’, IEEE Trans. Geosci. Remote Sens., 2010, 48, (11), pp. 40994109.
    49. 49)
      • 17. Zhang, F., Wang, Q., Li, X.: ‘Optimal neighboring reconstruction for hyperspectral band selection’. IGARSS 2018–2018 IEEE Int. Geoscience and Remote Sensing Symp., Valencia, 2018, pp. 47094712.
    50. 50)
      • 25. Boggavarapu, L.N.P., Prabukumar, M.: ‘Classification of hyper spectral remote sensing imagery using intrinsic parameter estimation’, in: AG 2020, ISDA 2018, AISC 941 (Springer Nature, Switzerland, 2020), pp. 111, https://doi.org/10.1007/978-3-030-16660-1_83.
    51. 51)
      • 49. Sawant, S.S., Prabukumar, M.: ‘A review on graph-based semi-supervised learning methods for hyperspectral image classification’, Egyptian J. Remote Sens. Space Sci., 2018, 23, (2), pp. 243248.
    52. 52)
    53. 53)
    54. 54)
      • 59. Sawant, S., Manoharan, P.: ‘A hybrid optimization approach for hyperspectral band selection based on wind driven optimization and modified cuckoo search optimization’, Multimed. Tools. Appl., 2020, 79, pp. 124, https://doi.org/10.1007/s11042-020-09705-9.
    55. 55)
      • 35. Aptoula, E., Ozdemir, M.C., Yanikoglu, B.: ‘Deep learning with attribute profiles for hyperspectral image classification’, IEEE Geosci. Remote Sens. Lett., 2016, 13, (12), pp. 19701974.
    56. 56)
      • 19. Qian, Y., Ye, M., Zhou, J.: ‘Hyperspectral image classification based on structured sparse logistic regression and three-dimensional wavelet texture features’, IEEE Trans. Geosci. Remote Sens., 2013, 51, (4), pp. 22762291.
    57. 57)
      • 20. Prabukumar, M., Sawant, S., Samiappan, S., et al: ‘Three-dimensional discrete cosine transform-based feature extraction for hyperspectral image classification’, J. Appl. Remote Sens., 2018, 12, (4), pp. 119.
    58. 58)
      • 8. Vaddi, R., Prabukumar, M.: ‘Comparative study of feature extraction techniques for hyper spectral remote sensing image classification: a survey’. 2017 Int. Conf. on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 2017.
    59. 59)
      • 23. Gastal, E.S.L., Oliveira, M.M.: ‘Domain transform for edge-aware image and video processing’, ACM Trans. Graph., 2011, 30, (4), pp. 112. Proceedings of SIGGRAPH 2011, Article 69.
    60. 60)
      • 38. Yu, C., Zhao, M., Song, M., et al: ‘Hyperspectral image classification method based on CNN architecture embedding with hashing semantic feature’, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2019, 12, (6), pp. 18661881, https://doi.org/10.1109/JSTARS.2019.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2020.0728
Loading

Related content

content/journals/10.1049/iet-ipr.2020.0728
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading