International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

Machine Learning-based Classification of Hyperspectral Imagery

  • Haq, Mohd Anul (Department of Computer Science, College of Computer and Information Sciences, Majmaah University) ;
  • Rehman, Ziaur (Department of Civil and Environmental Engineering, College of Engineering, Majmaah University) ;
  • Ahmed, Ahsan (Department of Information Technology, College of Computer and Information Sciences, Majmaah University) ;
  • Khan, Mohd Abdul Rahim (Department of Computer Science, College of Computer and Information Sciences, Majmaah University)
  • Received : 2022.04.05
  • Published : 2022.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The classification of hyperspectral imagery (HSI) is essential in the surface of earth observation. Due to the continuous large number of bands, HSI data provide rich information about the object of study; however, it suffers from the curse of dimensionality. Dimensionality reduction is an essential aspect of Machine learning classification. The algorithms based on feature extraction can overcome the data dimensionality issue, thereby allowing the classifiers to utilize comprehensive models to reduce computational costs. This paper assesses and compares two HSI classification techniques. The first is based on the Joint Spatial-Spectral Stacked Autoencoder (JSSSA) method, the second is based on a shallow Artificial Neural Network (SNN), and the third is used the SVM model. The performance of the JSSSA technique is better than the SNN classification technique based on the overall accuracy and Kappa coefficient values. We observed that the JSSSA based method surpasses the SNN technique with an overall accuracy of 96.13% and Kappa coefficient value of 0.95. SNN also achieved a good accuracy of 92.40% and a Kappa coefficient value of 0.90, and SVM achieved an accuracy of 82.87%. The current study suggests that both JSSSA and SNN based techniques prove to be efficient methods for hyperspectral classification of snow features. This work classified the labeled/ground-truth datasets of snow in multiple classes. The labeled/ground-truth data can be valuable for applying deep neural networks such as CNN, hybrid CNN, RNN for glaciology, and snow-related hazard applications.

Keywords

Acknowledgement

Ziaur Rehman would like to thank the Deanship of Scientific Research at Majmaah University for supporting this work under Project No. R-2022-10.

References

  1. J. Dozier, G. Robert, A. Nolin and T. Painter,: Interpretation of snow properties from imaging spectrometry, Remote Sensing of Environment, vol. 113 (4), pp. 25-37, (2013)
  2. M. A. Haq,: Comparative analysis of hyperspectral and multispectral data for mapping snow cover and snow grain size, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 8 (499), pp 1-6, (2014)
  3. B. Hosseiny and R. Shah-Hosseini,: A hyperspectral anomaly detection framework based on segmentation and convolutional neural network algorithms, International Journal of Remote Sensing, vol. 41 (18), pp. 6946-6975, (2020) https://doi.org/10.1080/01431161.2020.1752413
  4. T. A. Moughal,: Hyperspectral image classification using support vector machine, Journal of Physics: Conference Series, vol. 439(42) , pp. 882-885, (2013) https://doi.org/10.1088/1742-6596/439/1/012042
  5. J. Yue, W. Zhao, S. Mao and H. Liu,: Spectral-spatial classification of hyperspectral images using deep convolutional neural networks, Remote Sensing Letters, vol. 6 (6), pp. 468-477, (2015) https://doi.org/10.1080/2150704X.2015.1047045
  6. L. Pan, H. C. Li, Y. J. Deng, F. Zhang, X. D. Chen and Q. Du,: Hyperspectral dimensionality reduction by tensor sparse and low-rank graph-based discriminant analysis, Remote Sensing, vol. 9 (452), pp. 1-20, (2017)
  7. S. Yu, S. Jia and C. Xu,: Convolutional neural networks for hyperspectral image classification, Neurocomputing, vol. 219, pp. 88-98, (2017) https://doi.org/10.1016/j.neucom.2016.09.010
  8. J. Xu, H. Li, P. Liu and L. Xiao,: A Novel Hyperspectral Image Clustering Method with Context-Aware Unsupervised Discriminative Extreme Learning Machine, IEEE Access, vol. 6, pp.16176-16188. (2018) https://doi.org/10.1109/access.2018.2813988
  9. R. Hang, Q. Liu, D. Hong and P. Ghamisi,: Cascaded Recurrent Neural Networks for Hyperspectral Image Classification, IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 8, pp. 5384-5394, (2019) https://doi.org/10.1109/tgrs.2019.2899129
  10. X. Zhao, Liang, A. J. X. Guo and F. Zhu,: Classification of smallscale hyperspectral images with multi-source deep transfer learning. Remote Sensing Letters, vol. 11 (4), pp. 303-312, (2020) https://doi.org/10.1080/2150704x.2020.1714772
  11. Q. Sun and S. Bourennane,: Hyperspectral image classification with unsupervised feature extraction," Remote Sensing Letters, vol. 11 (5), pp. 475-484, (2020) https://doi.org/10.1080/2150704x.2020.1731769
  12. J. Tang, S. Alelyani and S. Liu,: Feature Selection for Classification: A Review, Data Classification: Algorithms and Applications, CRC Press, pp. 1-29, (2014)
  13. A. Agarwal, T. El-Ghazawi, H. El-Askary and J. Le-Moigne,: Efficient hierarchical-PCA dimension reduction for hyperspectral imagery, in Proc. ISSPIT, Giza, Egypt, pp. 1077-1080, (2007)
  14. S. Kumar, J. Ghosh and M. M. Crawford,: Best-bases feature extraction algorithms for classification of hyperspectral data, IEEE Transactions on Geoscience and Remote Sensing, vol. 39 (7), pp. 1368-1379, (2001) https://doi.org/10.1109/36.934070
  15. G. Camps-Valls and L. Bruzzone,: Kernel-based methods for hyperspectral image classification, IEEE Transactions on Geoscience and Remote Sensing, vol. 43 (6), pp. 1351-1362, (2005) https://doi.org/10.1109/TGRS.2005.846154
  16. L. Zhang, L. Zhang, D. Tao and X. Huang,: On combining multiple features for hyperspectral remote sensing image classification, IEEE Transactions on Geoscience and Remote Sensing, vol. 50 (7), pp. 879-893, (2012) https://doi.org/10.1109/TGRS.2011.2162339
  17. Y. Chen, Z. Lin, X. Zhao, G. Wang and Y. Gu,: Deep Learning-Based Classification of Hyperspectral Data, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing vol. 7 (6), pp. 2094-2107, (2014) https://doi.org/10.1109/JSTARS.2014.2329330
  18. A E. Maxwell, T. A. Warner and F. Fang,: Implementation of machine-learning classification in remote sensing: an applied review, International Journal of Remote Sensing, vol. 39 (9), pp. 2784-2817, (2018) https://doi.org/10.1080/01431161.2018.1433343
  19. M. Coskun, O. Yildirim, A. Ucar and Y. Demir,: An Overview of Popular Deep Learning Methods, European Journal of Technology, vol. 7 (2), pp. 165-176, (2017) https://doi.org/10.23884/ejt.2017.7.2.11
  20. G. Ososkov and P. Goncharov,: Shallow and deep learning for image classification, Optical Memory and Neural Networks, vol. 26 (4), pp. 221-248, (2017) https://doi.org/10.3103/s1060992x1704004x
  21. A. Voulodimos, N. Doulamis, A. Doulamis and E. Protopapadakis,: Deep Learning for Computer Vision: A Brief Review, Computational Intelligence and Neuroscience, vol. 2018 (7068349), pp. 1-13, (2018)
  22. M. Peychev, P. Velickovic, and P. Lio,: Quantifying the Effects of Enforcing Disentanglement on Variational Autoencoders, in Proc. NIPS 2017, California, USA, (2017)
  23. Y. Chen, X. Zhao and X. Jia,: Spectral-spatial classification of hyperspectral data based on deep belief network, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing vol. 8 (6), pp. 2381-2392, (2015) https://doi.org/10.1109/JSTARS.2015.2388577
  24. J. Feng, and J. Zhang,: Unsupervised Feature Extraction in Hyperspectral Image Based on Improved Neighborhood Preserving Embedding, In Proc. IGARSS, pp. 1291-1294, Jia Feng, Junping Zhang, Harbin Institute of Technology, China, (2020)
  25. A. Romero, C.Gatta, and G. Camps-Valls,: Unsupervised deep feature extraction for remote sensing image classification, IEEE Transactions on Geoscience and Remote Sensing, vol. 54 (3), pp.1349-1362, (2015) https://doi.org/10.1109/TGRS.2015.2478379
  26. J. Ji, S.Mei, J. Hou, X. Li, and Q. Du,: Learning sensorspecific features for hyperspectral images via 3- dimensional convolutional autoencoder, In Proc. IGARSS , pp. 1820-1823, United States, (2017)
  27. Zhang, J., Wei, W., Zhang, L. and Zhang, Y.: Improving hyperspectral image classification with unsupervised knowledge learning. In Proc. IGARSS , pp. 2722-2725, Yokohama, Japan, July, (2019)
  28. M. Liang, L.Jiao, S. Yang, F. Liu, B. Hou, and H. Chen,: Deep multiscale spectral-spatial feature fusion for hyperspectral images classification, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 11 (8), pp.2911-2924, (2018) https://doi.org/10.1109/jstars.2018.2836671
  29. J. Bai, R.Feng, L. Wang, H.Li, F. Li, Y.Zhong, and L. Zhang,: Semi-Supervised Hyperspectral Unmixing with Very Deep Convolutional Neural Networks, In Proc. IGARSS , pp. 2400-2403 , Waikoloa, HI, USA , (2020)
  30. S. Singh, R. Kumar and A. P. Dimri,: Mass Balance Status of Indian Himalayan Glaciers: A Brief Review, Frontiers in Environmental Science, Vol 6 (30), pp. 1-9, (2018) https://doi.org/10.3389/fenvs.2018.00001
  31. L. Hamlin, R. O. Green, P. Mouroulis, P. Eastwood, Michael, D. Wilson, M. Dudik and C. Paine,: Imaging Spectrometer Science Measurements for Terrestrial Ecology: AVIRIS and New Developments, In Proc. AERO'11, Washington DC, USA, pp. 1 - 7, (2011)
  32. A. K. Thorpe, C. Frankenberg, A. D. Aubrey, D. A. Roberts, A. A. Nottrott, T. A. Rahn, J. A. Sauer, M. K. Dubey, K. R. Costigan, C. Arata and A. M. Steffke,: Mapping methane concentrations from a controlled release experiment using the next generation airborne visible/infrared imaging spectrometer (AVIRIS-NG), Remote Sensing of Environment, vol. 179, pp. 104-115, (2016) https://doi.org/10.1016/j.rse.2016.03.032
  33. M. A. Haq, K. Jain and K. P. R. Menon,: Modelling of Gangotri glacier thickness and volume using an artificial neural network, International Journal of Remote Sensing, vol. 35 (16), pp. 6035-6042, (2014) https://doi.org/10.1080/01431161.2014.943322
  34. M. A. Haq and M. F. Azam: Application of Artificial Neural Networks for Glacier Thickness Estimation in the Western Himalayas, India, In Proc. NCHC-2017, Banglore, India, pp. 17-22, (2017)
  35. M. A. Haq, A. Ghosh, G. Rahaman and P. Baral,: Artificial neural network-based modeling of snow properties using field data and hyperspectral imagery, Natural Resource Modeling, vol. 32 (4), pp. 1-36, (2019)
  36. R. Srinet, S. Nandy, H. Padalia, S. Ghosh, T. Watham, N. R. Patel and P. Chauhan,: Mapping plant functional types in Northwest Himalayan foothills of India using random forest algorithm in Google Earth Engine, International Journal of Remote Sensing, vol. 41 (18), pp. 1-14, (2020) https://doi.org/10.1080/01431161.2019.1597294
  37. I. Good fellow, Y. Bengio and A. Courville,: Deep Learning (Adaptive Computation and Machine Learning series), The MIT Press, ISBN 0262035618, (2019)
  38. K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhutdinov, R. Zemel and Y Bengio,: Show, Attend and Tell: Neural Image Caption Generation with Visual Attention, In International conference on machine learning, pp. 2048-2057. PMLR, (2015)
  39. D. Thompson and S.D., Walter,: A reappraisal of the Kappa coefficient, Journal of Clinical Epidemiology, vol. 41, pp. 949-958, (1988) https://doi.org/10.1016/0895-4356(88)90031-5
  40. L. Boschetti, S. Flasse and P. Brivio,: Analysis of the conflict between omission and commission in low spatial resolution dichotomic thematic products: The Pareto Boundary, Remote Sensing of Environment, vol. 91, pp. 280-292, (2004) https://doi.org/10.1016/j.rse.2004.02.015
  41. J. Sim and C.C. Wright,: The Kappa Statistic in Reliability Studies: Use, Interpretation, and Sample Size Requirements, Physical Therapy, vol. 85 (3), pp. 257-268, (2005) https://doi.org/10.1093/ptj/85.3.257
  42. J. M. Cook, A. Hodson, A. J. Taggart, S. H. Mernild and M. Tranter,: A predictive model for the spectral bioalbedo of snow, Journal of Geophysical Research Earth Surface, vol. 122, pp. 434-454. (2017) https://doi.org/10.1002/2016JF003932
  43. Xi. Kan, Y. Zhang, L. Zhu, L. Xiao, J. Wang, W. Tian and H. Tan,: Snow cover mapping for mountainous areas by fusion of MODIS L1B and geographic data based on stacked denoising auto-encoders, Computer Materials and Continua, vol. 57 (1), pp. 49-68, (2018) https://doi.org/10.32604/cmc.2018.02376