Current Optics and Photonics

Optical Society of Korea (한국광학회)
권호 표지
DOI QR코드

DOI QR Code

Research on the Applicability of Target-detection Methods for Land-based Hyperspectral Imaging

  • Qianghui Wang (Army Engineering University of PLA (Shijiazhuang Campus)) ;
  • Bing Zhou (Army Engineering University of PLA (Shijiazhuang Campus)) ;
  • Wenshen Hua (Army Engineering University of PLA (Shijiazhuang Campus)) ;
  • Jiaju Ying (Army Engineering University of PLA (Shijiazhuang Campus)) ;
  • Xun Liu (Army Engineering University of PLA (Nanjing Campus)) ;
  • Lei Deng (Army Engineering University of PLA (Shijiazhuang Campus))
  • Received : 2023.11.16
  • Accepted : 2024.04.18
  • Published : 2024.06.25
Download PDF
⟨ Previous Next ⟩

Abstract

Target detection (TD) is a research hotspot in the field of hyperspectral imaging (HSI). Traditional TD methods often mine targets from HSIs under a single imaging condition, without considering the influence of imaging conditions. In fact, the spectra of ground objects in HSIs are uncertain and affected by the imaging conditions (weather, atmospheric, light, time, and other angle conditions including zenith angle). Hyperspectral data changes under different imaging conditions. Therefore, the detection result for a single imaging condition cannot accurately reflect the effectiveness of the detection method used. It is necessary to analyze the performance of various detection methods under different imaging conditions, to find a more applicable detection method. In this paper, we study the performance of TD methods under various land-based imaging conditions. We first summarize classical TD methods and evaluation methods. Then, the detection effects under various imaging conditions are analyzed. Finally, the concepts of the stability coefficient (SC) and effective area under the curve (EAUC) are proposed to comprehensively evaluate the applicability of detection methods under land-based imaging conditions, in terms of both detection accuracy and stability. This is conducive to our selection of detection methods with better applicability in land-based contexts, to improve detection accuracy and stability.

Keywords

Acknowledgement

We would like to thank the Army Engineering University of PLA, Electronic and Optical Engineering Department for financial and equipment support in developing this work. We would also like to thank the anonymous reviewer for their helpful and insightful comments, which significantly improved the quality of the manuscript.

References

  1. C.-I. Chang and S.-S. Chiang, "Anomaly detection and classification for hyperspectral imagery," IEEE. Trans. Geosci. Remote. Sens. 40, 1314-1325 (2002).
  2. P. Bajorski, "Target detection under misspecified models in hyperspectral images," IEEE. J. Sel. Top. Appl. Earth. Obs. Remote. Sens. 5, 470-477 (2012).
  3. A. Sedaghat, M. Mokhtarzade, and H. Ebadi, "Uniform robust scale-invariant feature matching for optical remote sensing images," IEEE. Trans. Geosci. Remote. Sens. 49, 4516-4527 (2011).
  4. S. E. Qian, "Hyperspectral satellites, evolution, and development history," IEEE. J. Sel. Top. Appl. Earth. Obs. Remote. Sens. 14, 7032-7056 (2021).
  5. M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza,"Sparse un-mixing of hyperspectral data," IEEE. Trans. Geosci. Remote. Sens. 49, 2014-2039 (2011).
  6. C. Wang, M. Gong, M. Zhang, and Y. Chan, "Unsupervised hyperspectral image band selection via column subset selection," IEEE. Geosci. Remote. Sens. Lett. 12, 1411-1415 (2015).
  7. B. R. Foy, J. Theiler, and A. M. Fraser, "Decision boundaries in two dimensions for target detection in hyperspectral imagery," Opt. Express 17, 17391-17411 (2009).
  8. S. Matteoli, M. Diani, and G. Corsini, "Improved estimation of local background covariance matrix for anomaly detection in hyperspectral images," Opt. Eng. 49, 046201 (2010).
  9. S. Collings, P. Caccetta, N. Campbell, and X. Wu, "Techniques for BRDF correction of hyperspectral mosaics," IEEE. Trans. Geosci. Remote. Sens. 48, 3733-3746 (2010).
  10. J. Settle, "On constrained energy minimization and the partial unmixing of multispectral images," IEEE. Trans. Geosci. Remote. Sens. 40, 718-721 (2002).
  11. C.-I. Chang and D. C. Heinz, "Constrained subpixel target detection for remotely sensed imagery," IEEE. Trans. Geosci. Remote. Sens. 38, 1144-1159 (2000).
  12. G. Camps-Valls, "Kernel spectral angle mapper," Electron. Lett. 52, 1218-1220 (2016).
  13. H. Su, P. Du, and Q. Du, "Semi-supervised dimensionality reduction using orthogonal projection divergence-based clustering for hyperspectral imagery," Opt. Eng. 51, 111715 (2012).
  14. E. Angelopoulou, S. W. Lee, and R. Bajcsy, "Spectral gradient: A material descriptor invariant to geometry and incident illumination," in Proc. Seventh IEEE International Conference on Computer Vision (Kerkyra, Greece, Sep. 20-27, 1999), pp. 861-867.
  15. S. A. Robila, "Using spectral distances for speedup in hyperspectral image processing," Int. J. Remote. Sens. 26, 5629-5650 (2005).
  16. Y. Zhong, X. Lin, and L. Zhang, "A support vector conditional random fields classifier with a Mahalanobis distance boundary constraint for high spatial resolution remote sensing imagery," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 7, 1314-1330 (2014).
  17. M.-Z. Shieh and S.-C. Tsai, "Decoding frequency permutation arrays under Chebyshev distance," IEEE Trans. Inf. Theory. 56, 5730-5737 (2010).
  18. Y. Zha, Z. Qiu, P. Zhang, and W. Huang, "Unsupervised ensemble hashing: Boosting minimum hamming distance," IEEE Access. 8, 42937-42947 (2020).
  19. F. van der Meero and W. Bakker, "Cross correlogram spectral matching: Application to surface mineralogical mapping by using AVIRIS data from Cuprite, Nevada," Remote. Sens. Environ. 61, 371-382 (1997).
  20. J. Kerekes, "Receiver operating characteristic curve confidence intervals and regions," IEEE. Geosci. Remote. Sens. Lett. 5, 251-255 (2008).
  21. C. Chang, "Multiparameter receiver operating characteristic analysis for signal detection and classification," IEEE. Sens. J. 10, 423-442 (2010).