Spectral Mixture Analysis: Linear and Semi-parametric Full and Iterated Partial Unmixing in Multi- and Hyperspectral Image Data

  • Allan Aasbjerg Nielsen


As a supplement or an alternative to classification of hyperspectral image data linear and semi-parametric mixture models are considered in order to obtain estimates of abundance of each class or end-member in pixels with mixed membership. Full unmixing based on both ordinary least squares (OLS) and non-negative least squares (NNLS), and the partial unmixing methods orthogonal subspace projection (OSP), constrained energy minimization (CEM) and an eigenvalue formulation alternative are dealt with. The solution to the eigenvalue formulation alternative proves to be identical to the CEM solution. The matrix inversion involved in CEM can be avoided by working on (a subset of) orthogonally transformed data such as signal maximum autocorrelation factors, MAFs, or signal minimum noise fractions, MNFs. This will also cause the partial unmixing result to be independent of the noise isolated in the MAF/MNFs not included in the analysis. CEM and the eigenvalue formulation alternative enable us to perform partial unmixing when we know one desired end-member spectrum only and not the full set of end-member spectra. This is an advantage over full unmixing and OSP. The eigenvalue formulation of CEM inspires us to suggest an iterated CEM scheme. Also the target constrained interference minimized filter (TCIMF) is described. Spectral angle mapping (SAM) is briefly described. Finally, semi-parametric unmixing (SPU) based on a combined linear and additive model with a non-linear, smooth function to represent end-member spectra unaccounted for is introduced. An example with two generated bands shows that both full unmixing, the CEM, the iterated CEM and TCIMF methods perform well. A case study with a 30 bands subset of AVIRIS data shows the utility of full unmixing, SAM, CEM and iterated CEM to more realistic data. Iterated CEM seems to suppress noise better than CEM. A study with AVIRIS spectra generated from real spectra shows (1) that ordinary least squares in this case with one unknown spectrum performs better than non-negative least squares, and (2) that although not fully satisfactory the semi-parametric model gives better estimates of end-member abundances than the linear model.

least squares regression spectral angle mapping (SAM) orthogonal subspace projection (OSP) matched filtering iterated constrained energy minimization (CEM) generalized eigenvalue problem target constrained interference minimized filter (TCIMF) non-linear semi-parametric unmixing (SPU) 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Anderson, E., Bai, Z., Bischof, C., Demmel, J., Dongarra, J., Croz, J.D., Greenbaum, A., Hammarling, S., McKenney, A., Ostrouchov, S., and Sorenson, D. 1995. LAPACK Users' Guide 2nd ed. Society for Industrial and Applied Mathematics Philadelphia.Google Scholar
  2. Anderson, T.W. 1984. An Introduction to Multivariate Statistical Analysis, 2nd ed. John Wiley: New York.Google Scholar
  3. AVIRIS, Jet Propulsion Laboratory, National Aeronautics and Space Administration, Pasadena, CA.Google Scholar
  4. Bernard, A., Kanellopoulos, I., and Wilkinson, G.G. 1997. Training strategies for neural network soft classification of remotely sensed imagery. International Journal of Remote Sensing, 18(8):1851–1856.Google Scholar
  5. Chambers, J.M. and Hastie T.J. (Eds.) 1992. Statistical Models in S. Wadsworth and Brooks/Cole: Pacific Grove, CA.Google Scholar
  6. Conradsen, K., Ersbøll, B.K.,* and Nielsen, A.A. 1991. Noise removal in multichannel image data by a parametric maximum noise fractions estimator. In Proceedings of the 24th International Symposium on Remote Sensing of Environment, ERIM (Ed.), Rio de Janeiro, Brazil, pp. 403–416.Google Scholar
  7. Conradsen, K., Nielsen, B.K., and Thyrsted, T. 1985. A comparison of min/max autocorrelation factor analysis and ordinary factor analysis. In Proceedings from Symposium in Applied Statistics, Lyngby, Denmark, pp. 47–56.Google Scholar
  8. Crippen, R.E. and Bloom, R.G. 1999. Unveiling the lithology of vegetated terrains in remotely sensed imagery via forced decorrelation. In Proceedings of the Thirteenth International Conference on Applied Geologic Remote Sensing, Vol. I, Vancouver, British Columbia, Canada, ERIM (Ed.), p. 150.Google Scholar
  9. Dempster, A., Laird N., and Rubin, D. 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39:1–38.Google Scholar
  10. Dixon, W.J. (Ed.) 1985. BMDP Statistical Software. University of California Press, p. 734.Google Scholar
  11. Dongarra, J.J., Bunch, J.R., Moler, C.B., and Stewart, G.W. 1979. LINPACK Users' Guide. Society for Industrial and Applied Mathematics, Philadelphia.Google Scholar
  12. Ersbøll, B.K. 1989. Transformations and classifications of remotely sensed data: Theory and geological cases. Ph.D. thesis, Institute of Mathematical Statistics and Operations Research, Technical University of Denmark, Lyngby, p. 297.Google Scholar
  13. Flesche, H., Nielsen, A.A., and Larsen, R. 2000. Supervised mineral classification with semi-automatic training and validation set generation in scanning electron microscope energy dispersive spectroscopy images of thin sections. Mathematical Geology, 32(3): 337–366.Google Scholar
  14. Gill, P.E., Hammarling, S.J., Murray, W., Saunders, M.A., and Wright, M.H. 1986. User's guide for LSSOL (Version 1.0): A FORTRAN package for constrained linear least-squares and convex quadratic programming, Technical Report 86–1, Department of Operations Research, Stanford University, CA.Google Scholar
  15. Green, A.A., Berman, M., Switzer, P., and Craig, M.D. 1988. Transformation for ordering multispectral data in terms of image quality with implications for noise removal. IEEE Transactions on Geoscience and Remote Sensing, 26(1):65–74.Google Scholar
  16. Harsanyi, J.C. and Chang, C.-I. 1994. Hyperspectral image classifi-cation and dimensionality reduction: An orthogonal subspace projection approach. IEEE Transactions on Geoscience and Remote Sensing, 32(4):779–785.Google Scholar
  17. Hastie, T.J. and Tibshirani, R.J. 1990. Generalized Additive Models. Chapman and Hall: London.Google Scholar
  18. Jacobsen, A., Heidebrecht, K.B., and Nielsen, A.A. 1998. Monitoring grasslands using convex geometry and partial unmixing— A case study. In Proceedings of the First EARSeL Workshop on Imaging Spectroscopy, M. Schaepman, D. Schläpfer, and K. Itten (Eds.), Zürich, Switzerland, pp. 309–316.Google Scholar
  19. Jacobson, A.S., Berkin, A.L., and Orton, M.N. 1994. LinkWinds: Interactive scientific data analysis and visualization. Communications of the ACM, 37(4):42–52. Scholar
  20. Kent, J.T. and Mardia, K.V. 1988. Spatial classification using fuzzy membership models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 10(5):659–671.Google Scholar
  21. Kruse, F.A., Lefkoff, A.B., Boardman, J.B., Heidebrecht, K.B., Shapiro, A.T., Barloon, P.J., and Goetz, A.F.H. 1993. The spectral image processing system (SIPS)-Interactive visualization and analysis of imaging spectrometer data. Remote Sensing of Environment, 44:145–163.Google Scholar
  22. Landy, M.S. 1993. HIPS-2 software for image processing: Goals and directions. In Proceedings of the SPIE 1964 Applications of Artificial Intelligence 1993: Machine Vision and Robotics, K.L. Boyer and L. Stark (Eds.), pp. 382–391. Scholar
  23. Landy, M.S., Cohen, Y., and Sperling, G. 1984a. HIPS: A UNIX based image processing system. Computer Vision, Graphics and Image Processing, 25(3):331–347. Scholar
  24. Landy, M.S., Cohen, Y., and Sperling, G. 1984b. HIPS: Image processing under UNIX. Software and applications. Behavior Research Methods, Instrumentation, and Computers, 16(2):199–216. Scholar
  25. Larsen, R., Nielsen, A.A., and Conradsen, K. 1997. Restoration of hyperspectral push-broom scanner data. In Proceedings of the 17th EARSeL Symposium on Future Trends in Remote Sensing, P. Gudmandsen (Ed.), Lyngby, Denmark, pp. 157–162.Google Scholar
  26. Larsen, R., Nielsen, A.A., and Flesche, H. 1999. Sensitivity study of a semi-automatic supervised classifier applied to minerals from X-ray mapping images. In Proceedings of the Scandinavian Image Analysis Conference (SCIA'99), Vol. 2, B.E. Ersbøll and P. J ohansen (Eds.), Kangerlussuaq, Greenland, pp. 785–792.Google Scholar
  27. Larsen, R., Nielsen, A.A., and Flesche, H. 2000. Sensitivity study of a semi-automatic training set generator. Pattern Recognition Letters, 21(13/14):1175–1182.Google Scholar
  28. Lee, J.B., Woodyatt, A.S., and Berman, M. 1990. Enhancement of high spectral resolution remote-sensing data by a noise-adjusted principal components transform. IEEE Transactions on Geoscience and Remote Sensing, 28(3):295–304.Google Scholar
  29. Marsh, S.E., Switzer, P., Kovalik, W.S., and Lyon, R.J.P. 1980. Resolving the percentage of component terrains within single resolution elements. Photogrammetric Engineering and Remote Sensing, 46:1079–1086.Google Scholar
  30. Maselli, F. 1998. Multiclass spectral decomposition of remotely sensed scenes by selective pixel unmixing. IEEE Transactions on Geoscience and Remote Sensing, 36(5):1809–1820.Google Scholar
  31. Miller, J.W.V., Farison, J.B., and Shin, Y. 1992. Spatially invariant image sequences. IEEE Transactions on Image Processing, 1(2): 148–161.Google Scholar
  32. Nielsen, A.A. 1994. Analysis of regularly and irregularly sampled spatial, multivariate, and multi-temporal data. Ph.D. Thesis, Department of Mathematical Modelling, Technical University of Denmark, Lyngby.∼aa/phd/.Google Scholar
  33. Nielsen, A.A. 1998. Linear mixture models and partial unmixing in multi-and hyperspectral image data. In Proceedings from the 1st EARSeL Workshop on Imaging Spectroscopy, M. Schaepman, D. Schläpfer, and K. Itten (Eds.), Zürich, Switzerland, pp. 165–172.Google Scholar
  34. Nielsen, A.A. 1999a. Linear mixture models, full and partial unmixing in multi-and hyperspectral image data. In Proceedings of the Scandinavian Image Analysis Conference (SCIA'99), Vol. 2, B.E. Ersbøll and P. Johansen (Eds.), Kangerlussuaq, Greenland, pp. 898–902.Google Scholar
  35. Nielsen, A.A. 1999b. Multi-channel remote sensing data and orthogonal transformations for change detection. In Machine Vision and Advanced Image Processing in Remote Sensing, I. Kanellopoulos, G.G. Wilkinson, and T. Moons (Eds.), Springer.Google Scholar
  36. Nielsen, A.A. 1999c. Partial unmixing in hyperspectral image data. In Proceedings from the Fourth International Airborne Remote Sensing Conference and Exhibition, Vol. II, ERIM (Ed.), Ottawa, Ontario, Canada, pp. 535–542.Google Scholar
  37. Nielsen, A.A., Conradsen, K., Pedersen, J.L., and Steenfelt, A. 1997. Spatial factor analysis of stream sediment geochemistry data from South Greenland. In Proceedings of the Third Annual Conference of the International Association for Mathematical Geology (IAMG'97), V. Pawlowsky-Glahn (Eds.), Barcelona, Spain, pp. 955–960.Google Scholar
  38. Nielsen, A.A., Conradsen, K., Pedersen, J.L., and Steenfelt, A. 2000. Maximum autocorrelation factorial kriging. In Proceedings of the Sixth International Geostatistics Congress (Geostats 2000), W.J. Kleingeld and D.K. Krige (Eds.). Cape Town, South Africa, paper no. E13 on CD Rom.Google Scholar
  39. Nielsen, A.A., Conradsen, K., and Simpson, J.J. 1998a. Multivariate alteration detection (MAD) and MAF post-processing in multispectral, bi-temporal image data: New approaches to change detection studies. Remote Sensing of Environment, 64:1–19.Google Scholar
  40. Nielsen, A.A., Ersbøll, B., Pälchen, W., and Rank, G. 1996. Spatial analysis of multivariate, (Ir-) regularly sampled data: Geochemistry from the eastern Erzgebirge. In Geostatistics Wollongong '96, E.Y. Baafi and N.A. Schofield (Eds), Wollongong, Australia, pp. 1173–1184.Google Scholar
  41. Nielsen, A.A., Flesche, H., Larsen, R., Rykkje, J.M., and Ramm, M. 1998b. Semi-automatic supervised classification of minerals from X-ray mapping images. In Proceedings of the Fourth Annual Conference of the International Association of Mathematical Geology (IAMG'98), A. Buccianti, G. Nardi, and R. Potenza (Eds.), Ischia, Italy, pp. 473–478.Google Scholar
  42. Nielsen, A.A. and Larsen, R. 1994. Restoration of GERIS data using the maximum noise fractions transform. In Proceedings from the First International Airborne Remote Sensing Conference and Exhibition, Vol. II, ERIM (Ed.), Strasbourg, France, pp. 557–568.Google Scholar
  43. Pendock, N. and Nielsen, A.A. 1993. Multispectral image enhancement neural networks and the maximum noise fraction transform. In Proceedings of the Fourth South African Workshop on Pattern Recognition, P. Cilliers (Ed.), Simon's Town, South Africa, pp. 2–13.Google Scholar
  44. Ren, H. and Chang, C.-I. 2000. A target-constrained interferenceminimized filter for subpixel detection in hyperspectral imagery. In Proceedings of the IEEE 2000 IGARSS, Honolulu, HI.Google Scholar
  45. Resmini, R.G., Kappus, M.E., Aldrich, W.S., Harsanyi, J.C., and Anderson, M. 1997. Mineral mapping with hyperspectral digital imagery collection experiment (HYDICE) sensor data at cuprite, Nevada, U.S.A. International Journal of Remote Sensing, 18(7): 1553–1570.Google Scholar
  46. Sadegh, P., Nielsen, H.A., and Madsen, H. 1999. A semi-parametric approach for decomposition of absorption spectra in the presence of unknown components. Technical Report 1999–17, Department of Mathematical Modelling, Technical University of Denmark. 99.abstract.html.Google Scholar
  47. Settle, J.J. 1996. On the relationship between spectral unmixing and subspace projection. IEEE Transactions on Geoscience and Remote Sensing, 34(4):1045–1046.Google Scholar
  48. Settle, J.J. and Drake, N.A. 1993. Linear mixing and the estimation Spectral Mixture Analysis 37 of ground cover proportions. International Journal of Remote Sensing, 14(6):1159–1177.Google Scholar
  49. Stan, S.S. 1997. Mineral identification and mapping by imaging spectroscopy data analysis. Ph.D. thesis, Computational and Applied Mathematics Department, University of the Witwatersrand, Johannesburg, South Africa.Google Scholar
  50. Strobl, P., Richter, R., Müller, A., Lehmann, F., Oertel, D., Tischler, S., and Nielsen, A.A. 1996. DAIS system performance, first results from the 1995 evaluation campaigns. In Proceedings from the Second International Airborne Remote Sensing Conference and Exhibition, Vol. II, ERIM (Ed.), San Francisco, California, USA, pp. 325–334.Google Scholar
  51. Switzer, P. and Green, A.A. 1984. Min/max autocorrelation factors for multivariate spatial imagery. Technical Report 6, Department of Statistics, Stanford University.Google Scholar
  52. Tu, T.-M., Chen, C.-H., and Chang, C.-I. 1998. A noise subspace projection approach to target signature detection and extraction in an unknown background for hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 36(1):171–181.Google Scholar
  53. van der Meer, F. 1999. Iterative spectral unmixing. International Journal of Remote Sensing, 20(17):3431–3436.Google Scholar
  54. Vane, G. and Goetz, A.F.H. 1988. Terrestrial imaging spectroscopy. Remote Sensing of Environment, 24:1–29.Google Scholar
  55. Vane, G., Green, R.O., Chrien, T.G., Enmark, H.T., Hansen, E.G., and Porter, W.M. 1993. The airborne/infrared imaging spectrometer (AVIRIS). Remote Sensing of Environment, 44:127–143.Google Scholar
  56. Venables, W.N. and Ripley, B.D. 1999. Modern Applied Statistics with S-PLUS, 3rd ed. Springer: New York.Google Scholar

Copyright information

© Kluwer Academic Publishers 2001

Authors and Affiliations

  • Allan Aasbjerg Nielsen
    • 1
  1. 1.IMM, Informatics and Mathematical ModellingTechnical University of DenmarkKgs. LyngbyDenmark

Personalised recommendations