Advertisement

Hyperspectral Target Detection Based on Spectral Weighting

  • Di WuEmail author
  • Yulei Wang
  • Yao Shi
  • Qingyu Zhu
  • Anliang Liu
Conference paper
  • 5 Downloads
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 571)

Abstract

Target detection has become an important research direction in hyperspectral imagery (HSI) processing. In this paper, aiming at the phenomenon that different bands have different abilities to distinguish materials, a spectral weighting detection algorithm is proposed. Firstly, relative distance between different categories as the spectral separability criterion is used to estimate the distinction ability of each band. And then different bands are endowed with different weighting coefficients. Finally, the RX and LPD algorithms are used to test the efficiency of the proposed spectral weighting method. The experimental results show that the detection algorithms based on spectral weighting have better performances than the traditional RX and LPD algorithms.

Keywords

Hyperspectral imagery Target detection Spectral separability criterion Spectral weighting 

Notes

Acknowledgements

This work is supported by the National Nature Science Foundation of China (61801075), the Fundamental Research Funds for the Central Universities (3132019218).

References

  1. 1.
    Tong Q, Zhang B, Zheng L (2006) Hyperspectral remote sensing. High Education Press, pp 1–2, 129–135Google Scholar
  2. 2.
    Manolakis D, Shaw G (2002) Detection algorithms for hyperspectral imaging applications. Sig Process Mag IEEE 19:29–43Google Scholar
  3. 3.
    Reed IS, Yu X (1990) Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution. IEEE Trans Acoust Speech Signal Process 38(10):1760–1770Google Scholar
  4. 4.
    Harsanyi JC (1993) Detection and classification of subpixel spectral signatures in hyperspectral image sequences. Department of Electral Engineering, University of Maryland Baltimore Country, BaltimoreGoogle Scholar
  5. 5.
    Gao H, Wan J, Xu Z, Qian L (2011) Semisupervised classification of hyperspectral Image based on spectrally weighted TSVM. Sig Process 27(N0):1Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Di Wu
    • 1
    Email author
  • Yulei Wang
    • 1
    • 2
  • Yao Shi
    • 1
  • Qingyu Zhu
    • 1
  • Anliang Liu
    • 1
  1. 1.Information and Technology CollegeDalian Maritime UniversityDalianChina
  2. 2.State Key Laboratory of Integrated Services NetworksXidian UniversityXianChina

Personalised recommendations