Advertisement

Classification of Hyper Spectral Remote Sensing Imagery Using Intrinsic Parameter Estimation

  • L. N. P. Boggavarapu
  • Prabukumar ManoharanEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 941)

Abstract

A Hyperspectral remote sensing image (HSI) composed of various intrinsic components such as shading, albedo, noise and continuous narrow bands in different wavelengths. The classification of the HSI image is one of the challenging tasks in the area of Remote Sensing as it has numerous applications on environment, mineral exploration, target detection and anomaly detection. The present paper identifies a novel approach in classifying the image by incorporating the albedo intrinsic component retrieved from the image on principal components and factor analysis obtained through the dimensionality reduction. The obtained results are classified via Support Vector Machine classifier. The proposed algorithm tested on the benchmark datasets available worldwide such as Indian Pines, University of Pavia and Salinas. The extraction of albedo intrinsic components helps in effective classification of HSI image and outperforms the results with state of the art techniques, achieved the overall accuracy (OA) on these datasets.

Keywords

Classification Hyperspectral Dimensionality reduction Support vector machine 

References

  1. 1.
    State of the forest report 2013: Forest Survey of India, Ministry of Environment and Forests, Government of India, Dehradun (2013)Google Scholar
  2. 2.
    Olmanson, L.G., Brezonik, P.L., Bauer, M.E.: Airborne hyperspectral remote sensing to assess spatial distribution of water quality characteristics in large rivers: the Mississippi River and its tributaries in Minnesota. Remote Sens. Environ. 130, 254–265 (2013)CrossRefGoogle Scholar
  3. 3.
    Zarco-Tejada, P.J., Berjón, A., López-Lozano, R., Miller, J.R., Martín, P., Cachorro, V., González, M.R., de Frutos, A.: Assessing vineyard condition with hyperspectral indices: leaf and canopy reflectance simulation in a row-structured discontinuous canopy. Remote Sens. Environ. 99, 271–287 (2005)CrossRefGoogle Scholar
  4. 4.
    Pascucci, S., Belviso, C., Cavalli, R.M., Laneve, G., Misurovic, A., Perrino, C., Pignatti, S.: Red mud soil contamination near an urban settlement analyzed by airborne hyperspectral remote sensing. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2009), pp. IV-893, IV-896, 12–17 July 2009 (2009)Google Scholar
  5. 5.
    Vaddi, R., Prabukumar, M.: Comparative study of feature extraction techniques for hyper spectral remote sensing image classification: a survey. In: International Conference on Intelligent Computing and Control Systems, 15–16 June 2017. Vaigai College Engineering (VCE), Madurai, India (2017)Google Scholar
  6. 6.
    Barrow, H., Tenenbaum, J.: Computer Vision Systems: Recovering Intrinsic Scene Characteristics from Images. Academic Press, New York (1978)Google Scholar
  7. 7.
    Zhan, K., Wang, H., Xie, Y., Zhang, C., Min, Y.: Albedo recovery for hyperspectral image classification. J. Electron. Imaging 26(4), 043010 (2017).  https://doi.org/10.1117/1.JEI.26.4.043010CrossRefGoogle Scholar
  8. 8.
    Chutia, D., Bhattacharyya, D.K., Sarma, K.K., Kalita, R., Sudhakar, S.: Hyperspectral remote sensing Classifications: a perspective survey. Trans. GIS 20(4), 463–490 (2016)CrossRefGoogle Scholar
  9. 9.
    Hughes, G.F.: On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inf. Theory IT-14(1), 55–63 (1968)CrossRefGoogle Scholar
  10. 10.
    Raczko, E., Zagajewski, B.: Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images. Eur. J. Remote Sens. 50(1), 144–154 (2017)CrossRefGoogle Scholar
  11. 11.
    Nandhini, K., Porkodi, R.: Spatial classification and prediction in hyperspectral remote sensing data using random forest by tuning parameters. Int. J. Adv. Res. Comput. Sci. 8(3), 259–266 (2017)Google Scholar
  12. 12.
    Tagliabue, G., et al.: Forest species mapping using airborne hyperspectral APEX data. Misc. Geogr. – Reg. Stud. Dev. 20(1), 28–33 (2016)Google Scholar
  13. 13.
    Richter, R., et al.: The use of airborne hyperspectral data for tree species classification in a species-rich Central European forest area. Int. J. Appl. Earth Obs. Geoinf. 52, 464–474 (2016)CrossRefGoogle Scholar
  14. 14.
    Sheeren, D., et al.: Tree species classification in temperate forests using Formosat-2 satellite image time series. Remote Sens. 8, 1–29 (2016)CrossRefGoogle Scholar
  15. 15.
    Zhang, Z., et al.: Object-based tree species classification in urban ecosystems using LiDAR and hyperspectral data. Forests 7(6), 1–16 (2016)Google Scholar
  16. 16.
    Rummel, J.R.: Applied factor analysis. Library of congress catalog, card no, pp. 73–78327, United States of America (1988)Google Scholar
  17. 17.
    Gastal, E.S.L., Oliveira, M.M.: Domain transform for edge-aware image and video processing. ACM Trans. Graph. 30(4), 69:1–69:12 (2011)CrossRefGoogle Scholar
  18. 18.
    Abdi, H., Williams, L.J.: Principal component analysis. Wiley Interdiscip. Rev.: Comput. Stat. (2010).  https://doi.org/10.1002/wics.101
  19. 19.
    Melgani, F., Bruzzone, L.: Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans. Geosci. Remote Sens. 42(8), 1778–1790 (2004)CrossRefGoogle Scholar
  20. 20.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888–905 (2000)CrossRefGoogle Scholar
  21. 21.
    Kumar, C.A.: Analysis of unsupervised dimensionality reduction techniques. Comput. Sci. Inf. Syst. 6(2), 217–227 (2009)CrossRefGoogle Scholar
  22. 22.
    Prabukumar, M., Sawant, S., Samiappan, S., Agilandeeswari, L.: Three-dimensional discrete cosine transform-based feature extraction for hyperspectral image classification. J. Appl. Remote Sens. 12(4), 046010 (2018)Google Scholar
  23. 23.
    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. 12(4), 046015 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Information Technology Engineering (SITE)VIT UniversityVelloreIndia
  2. 2.Department of Information TechnologyV. R. Siddhartha Engineering CollegeVijayawadaIndia

Personalised recommendations