Advertisement

Data Mining and Knowledge Discovery

, Volume 27, Issue 1, pp 117–145 | Cite as

Generic visual analysis for multi- and hyperspectral image data

  • Björn Labitzke
  • Serkan Bayraktar
  • Andreas Kolb
Article

Abstract

Multi- and hyperspectral imaging and data analysis has been investigated in the last decades in the context of various fields of application like remote sensing or microscopic spectroscopy. However, recent developments in sensor technology and a growing number of application areas require a more generic view on data analysis, that clearly expands the current, domain-specific approaches. In this context, we address the problem of interactive exploration of multi- and hyperspectral data, consisting of (semi-)automatic data analysis and scientific visualization in a comprehensive fashion. In this paper, we propose an approach that enables a generic interactive exploration and easy segmentation of multi- and hyperspectral data, based on characterizing spectra of an individual dataset, the so-called endmembers. Using the concepts of existing endmember extraction algorithms, we derive a visual analysis system, where the characteristic spectra initially identified serve as input to interactively tailor a problem-specific visual analysis by means of visual exploration. An optional outlier detection improves the robustness of the endmember detection and analysis. An adequate system feedback of the costly unmixing procedure for the spectral data with respect to the current set of endmembers is ensured by a novel technique for progressive unmixing and view update which is applied at user modification. The progressive unmixing is based on an efficient prediction scheme applied to previous unmixing results. We present a detailed evaluation of our system in terms of confocal Raman microscopy, common multispectral imaging and remote sensing.

Keywords

Multi-/hyperspectral data Feature extraction Interactive visual analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Biehl L, Landgrebe D (2002) Multispec: a tool for multispectral–hyperspectral image data analysis. Comput Geosci 28: 1153–1159. doi: 10.1016/S0098-3004(02)00033-X CrossRefGoogle Scholar
  2. Boardman JW, Kruse FA, Green RO (1995) Mapping target signatures via partial unmixing of aviris data. Summaries of the Fifth Annual JPL Airborne Geoscience Workshop 1, PasadenaGoogle Scholar
  3. Broersen A, van Liere R (2005) Transfer functions for imaging spectroscopy data using principal component analysis. In: Brodlie K, Duke D, Joy K (eds) Eurographics/IEEE VGTC symposium on visualization, eurographics association, Leeds, pp 117–123. doi: 10.2312/VisSym/EuroVis05/117-123
  4. Chang CI (2005) Orthogonal subspace projection (OSP) revisited: a comprehensive study and analysis. IEEE Trans Geosci Remote Sens 43(3): 502–518. doi: 10.1109/TGRS.2004.839543 CrossRefGoogle Scholar
  5. Chang CI, Du Q (2004) Estimation of number of spectrally distinct signal sources in hyperspectral imagery. IEEE Trans Geosci Remote Sens 42(3): 608–619. doi: 10.1109/TGRS.2003.819189 CrossRefGoogle Scholar
  6. Colantoni P, Pillay R, Lahanier C, Pitzalis D (2006) Analysis of multispectral images of paintings, EURASIP. Eusipco, http://www.eurasip.org/Proceedings/Eusipco/Eusipco2006/papers/1568987421.pdf
  7. Cui M, Razdan A, Hu J, Wonka P (2009) Interactive hyperspectral image visualization using convex optimization. IEEE Trans Geosci Remote Sens 47(6): 1673–1684. doi: 10.1109/TGRS.2008.2010129 CrossRefGoogle Scholar
  8. Dieing, T, Hollricher, O, Toporski, J (eds) (2010) Confocal Raman microscopy, Springer series in optical sciences, vol 158. Springer, Berlin. doi: 10.1007/978-3-642-12522-5
  9. Egan WJ, Morgan SL (1998) Outlier detection in multivariate analytical chemical data. Anal Chem 70(11):2372–2379. doi: 10.1021/ac970763d, http://pubs.acs.org/doi/abs/10.1021/ac970763d, http://pubs.acs.org/doi/pdf/10.1021/ac970763d Google Scholar
  10. Gray R (1984) Vector quantization. ASSP Mag, IEEE 1(2): 4–29. doi: 10.1109/MASSP.1984.1162229 CrossRefGoogle Scholar
  11. Harsanyi JC, Chang CI (1994) Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach. IEEE Trans Geosci Remote Sens 32(4): 779–785. doi: 10.1109/36.298007 CrossRefGoogle Scholar
  12. Inselberg A, Dimsdale B (1990) Parallel coordinates: a tool for visualizing multi-dimensional geometry. In: Proc. First IEEE Conf. Visualization Visualization ’90, pp 361–378. doi: 10.1109/VISUAL.1990.146402
  13. ITT (2011) Visual information solutions: ENVI. http://www.ittvis.com, August 2011
  14. Jacobson NP, Gupta MR (2005) Design goals and solutions for display of hyperspectral images. IEEE Trans Geosci Remote Sens 43(11): 2684–2692. doi: 10.1109/TGRS.2005.857623 CrossRefGoogle Scholar
  15. Jordan J, Angelopoulou E (2010) Gerbil: a novel software framework for visualization and analysis in the multispectral domain, vol 1. In: Koch R, Kolb A, Rezk-Salama C (eds) VMV 2010: Vision, modeling & Vvsualization, Goslar, pp 259–266Google Scholar
  16. Joye WA, Mandel E (2003) New features of saoimage ds9. In: Payne HE, Jedrzejewski RI, Hook N (eds) Astronomical data analysis software and systems XII, vol 295. Astronomical society of the Pacific, ASP conference series, pp 489–492Google Scholar
  17. Kästner M, Villmann T (2011) Functional relevance learning in learning vector quantization for hyperspectral data. In: 3rd Workshop on hyperspectral image and signal processing: evolution in remote sensing (WHISPERS), Lisboa, pp 1–4. doi: 10.1109/WHISPERS.2011.6080854
  18. Keim D, Andrienko G, Fekete JD, Görg C, Kohlhammer J, Melançon G (2008) Information visualization, Chap. In: Visual analytics: definition, process, and challenges, Springer, Berlin, pp 154–175. doi: 10.1007/978-3-540-70956-5_7
  19. Keshava N (2003) A survey of spectral unmixing algorithms. Lincoln Lab J 14(1):55–78Google Scholar
  20. Kim SJ, Zhuo S, Deng F, Fu CW, Brown M (2010) Interactive visualization of hyperspectral images of historical documents. IEEE Trans Visual Comput Graph 16(6): 1441–1448. doi: 10.1109/TVCG.2010.172 CrossRefGoogle Scholar
  21. Kruse F, Lefkoff A, Boardman J, Heidebrecht K, Shapiro A, Barloon P, Goetz A (1993) The spectral image processing system (SIPS): interactive visualization and analysis of imaging spectrometer data. Remote Sens Environ 44(2–3):145–163. doi: 10.1016/0034-4257(93)90013-N
  22. Landgrebe D (2002) Hyperspectral image data analysis. IEEE Signal Process Mag 19(1): 17–28. doi: 10.1109/79.974718 CrossRefGoogle Scholar
  23. Li H, Fu CW, Hanson A (2008) Visualizing multiwavelength astrophysical data. IEEE Trans Visual Comput Graph 14(6): 1555–1562. doi: 10.1109/TVCG.2008.182 CrossRefGoogle Scholar
  24. Mignotte M (2010) A multiresolution markovian fusion model for the color visualization of hyperspectral images. IEEE Trans Geosci Remote Sens 48(12): 4236–4247. doi: 10.1109/TGRS.2010.2051553 CrossRefGoogle Scholar
  25. Nascimento JMP, Dias JMB (2004) Vertex component analysis: a fast algorithm to unmix hyperspectral data. IEEE Trans Geosci Remote Sens 43: 898–910CrossRefGoogle Scholar
  26. Plaza A, Martínez P, Perez R, Plaza J (2002) Spatial/spectral endmember extraction by multidimensional morphological operations. IEEE Trans Geosci Remote Sens 40(9): 2025–2041. doi: 10.1109/TGRS.2002.802494 CrossRefGoogle Scholar
  27. Plaza A, Martín G, Zortea M (2009) On the incorporation of spatial information to endmember extraction: survey and algorithm comparison. In: Proceedings of first workshop hyperspectral image and signal processing: evolution in Remote Sensing WHISPERS ’09, pp 1–4. doi: 10.1109/WHISPERS.2009.5289024
  28. Plaza A, Zortea M, Plaza J, Martín G (2010) Recent developments in spectral unmixing and endmember extraction, vol 3. In: S Prasad LB, Chanussot J (eds) Optical remote sensing: advances in signal processing and exploitation techniques, Augmented vision and reality, Springer, Berlin, p 300Google Scholar
  29. Polder G, van der Heijden GW (2001) DieVisualization of spectral images. In: Censor Y, Ding M (eds) Visualization and optimization techniques, Proceedings of SPIE, vol 4553Google Scholar
  30. Roberto V, Hofer M (2008) Theia: open environment for multispectral image analysis. In: Proceedings of the working conference on Advanced visual interfaces, AVI ’08. ACM, New York, pp 462–465. http://doi.acm.org/10.1145/1385569.1385659
  31. Robila SA, Gershman A (2005) Spectral matching accuracy in processing hyperspectral data. In: IEEE Proceedings, international symposium on signals, circuits and systems, ISSCS 2005, vol 1, pp 163–166, doi: 10.1109/ISSCS.2005.1509878
  32. Sánchez S, Plaza A (2010) GPU implementation of the pixel purity index algorithm for hyperspectral image analysis. In: Proceedings of IEEE International Conference on Cluster Computing Workshops Posters (CLUSTER WORKSHOPS), pp 1–7. doi: 10.1109/CLUSTERWKSP.2010.5613110
  33. Sánchez S, Martín G, Plaza A (2010a) Parallel implementation of the N-FINDR endmember extraction algorithm on commodity graphics processing units. In: Proc. IEEE Int. Geosci Remote Sens Symp. (IGARSS), pp 955–958, doi: 10.1109/IGARSS.2010.5650231
  34. Sánchez S, Martín G, Plaza A, Chang CI (2010b) GPU implementation of fully constrained linear spectral unmixing for remotely sensed hyperspectral data exploitation. SPIE, vol 7810, p 78100G, doi: 10.1117/12.860775
  35. Setoain J, Prieto M, Tenllado C, Plaza A, Tirado F (2007) Parallel morphological endmember extraction using commodity graphics hardware. IEEE Geosci Remote Sens Lett 4(3): 441–445. doi: 10.1109/LGRS.2007.897398 CrossRefGoogle Scholar
  36. Setoain J, Prieto M, Tenllado C, Tirado F (2008) GPU for parallel on-board hyperspectral image processing. IJHPCA 22(4): 424–437. doi: 10.1177/1094342007088379 Google Scholar
  37. Tax DMJ, Duin RPW (2004) Support vector data description. Mach Learn 54:45–66, doi: 10.1023/B:MACH.0000008084.60811.49, http://dl.acm.org/citation.cfm?id=960091.960109 Google Scholar
  38. Veganzones MA, Graña M (2008) Endmember extraction methods: a short review, Chap. Knowledge-Based Intelligent Information and Engineering Systems, No. Part 3 in Lecture Notes in Computer Science, Springer, Berlin, pp 400–407. doi: 10.1007/978-3-540-85567-5_50
  39. Winter ME (1999) N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data. In: Storage and retrieval for image and video databases. doi: 10.1117/12.366289

Copyright information

© The Author(s) 2012

Authors and Affiliations

  • Björn Labitzke
    • 1
  • Serkan Bayraktar
    • 1
  • Andreas Kolb
    • 1
  1. 1.Computer Graphics Group, Institute for Vision and Graphics, Faculty IV: Science and TechnologyUniversity of SiegenSiegenGermany

Personalised recommendations