Hyperspectral Images Target Recognition Using Projection Pursuit

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 238)

Abstract

In order to solve the recognition problem of the specific target, a hyperspectral target recognition method using minimum noise fraction (MNF) and projection pursuit was used. Firstly, MNF was used to calculate the intrinsic dimension as well as image denoising. Then, using spectral information divergence (SID) as the projection index, remove the background and extract the spectral curve via adaptive threshold of the value of the projection index. When calculating each projection index, we used a simplified approach to maximize the projection index, which does not require an optimization algorithm. It searches for a solution by obtaining a set of candidate projections from the data and choosing the one with the highest projection index. Finally, identify the target and its location using the spectral angle mapping method. Through a series of hyperspectral images experiments, the results show that the MNF image preprocessing can make the projections better and reduce the computational effectively. Remove the background using adaptive threshold of the projection index quickly and efficiently. The method can not only reduce the images noise more effectively but also extract endmember and identify the target quickly, reliably, and fastly.

Keywords

Entropy Covariance 

References

  1. 1.
    Chemical Technology. The spectroscopy in chemicals-technology. http://www.chemicals-technology.com/glossary/spectroscopy.html
  2. 2.
    The International Society for Optical Engineering, SPIE. In: The hyperspectral. http://www.spie.org/web/oer/November/image_spectro.html
  3. 3.
    Kruse FA. In: Imaging Spectrometer Data Analysis-A Tutorial. http://www.hgimaging.com/PDF/Kruse_isssr94tut.pdf
  4. 4.
    Breckinridge JB (1996) Evolution of imaging spectrometry: past, present, and future. In: Proceedings of SPIE conference on imaging spectrometry IIGoogle Scholar
  5. 5.
    Rinker JN (1990) Hyper-spectral imagery – a new technique for targeting and intelligence. AD reportGoogle Scholar
  6. 6.
    Chang CI, Chiang SS (2002) Anomaly detection and classification for hyperspectral imagery. IEEE Trans Geosci Remote Sens 40(6):1314–1325CrossRefGoogle Scholar
  7. 7.
    Donoho DL (2000) High-dimensional data analysis: the curses and blessings of dimensionality. International conference of mathematicians, Paris, Aug 2000Google Scholar
  8. 8.
    Hwang J, Lay S, Lippman A (1994) Nonparametric multivariate density estimation: a comparative study. IEEE Trans Signal Processing 42:2795–2810CrossRefGoogle Scholar
  9. 9.
    Tian Z, Xiao HY (1995) On a better approach for non-linear time series model building and forecasting in engineering. J Northwest Polytechnic Univ 13(3):478–480Google Scholar
  10. 10.
    Zhao Y, Atkeson CG (1996) Implementing projection pursuit learning. IEEE Trans Neural Netw 17(7):362–373CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.Academy of EquipmentBeijingChina

Personalised recommendations