Abstract
A geostatistical optimization algorithm is proposed for super-resolution land cover classification from remotely sensed imagery. The algorithm requires as input, a soft classification of land cover obtained from a remotely sensed image. A super-resolution (sub-pixel scale) grid is defined. The soft land cover proportions (pixel scale) are then transformed into a hard classification (subpixel scale) by allocating hard classes randomly to the sub-pixels. The number allocated per pixel is determined in proportion to the original land cover proportion per pixel. The algorithm optimizes the match between a target and current realization of the two-point histogram by swapping sub-pixel classes within pixels such that the original class proportions defined per pixel are maintained. The algorithm is demonstrated for two simple simulated images. The advantages of the approach are its ability to recreate any target spatial distribution and to work with features that are both large and small relative to the pixel size, in combination.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Adams, J.B., Smith, M.O. and Johnson, P.E. (1985) Spectral mixture modelling: a new analysis of rock and soil types at the Viking Lander 1 site, Journal of Geophysical Research, vol. 91, pp. 8098–8112.
Atkinson, P.M. (1997) Mapping sub-pixel boundaries from remotely sensed images, in Innovations in GIS IV (ed., Z. Kemp) (Taylor an1d Francis: London), p. 166–180.
Atkinson, P.M., Cutler, M.E.J. and Lewis, H. (1997) Mapping sub-pixel proportional land cover with AVHRR imagery, International Journal of Remote Sensing, vol.18, pp. 917–935.
Atkinson, P.M. and Tate, N.J. (2000) Spatial scale problems and geostatistical solutions: a review, Professional Geographer, vol. 52, pp. 607–623.
Atkinson, P.M. (2001) Super-resolution target mapping from soft classified remotely sensed imagery, Fifth International Conference on GeoComputation. University of Leeds: Leeds, CD-ROM.
Bezdek, J.C., Ehrlich, R. and Full, W. (1984) FCM: The fuzzy c-means clustering algorithm, Computers and Geosciences, vol. 10, pp. 191–203.
Brown, M., Gunn, S.R. and Lewis, H.G. (1999) Support vector machines for optimal classification and spectral unmixing, Ecological Modelling, vol.120, pp. 167–179.
Deutsch, C.V. and Journel, A. G. (1998) GSLIB: Geostatistical Software and User’s Guide, Second Edition. Oxford University Press: Oxford.
Flack, J., Gahegan, M. and West, G. (1994) The use of sub-pixel measures to improve the classification of remotely sensed imagery of agricultural land, Proceedings of the 7th Australasian Remote Sensing Conference, Melbourne, pp. 531–541.
Foody, G.M. (1998) Sharpening fuzzy classification output to refine the representation of sub-pixel land cover distribution, International Journal of Remote Sensing, vol.19, pp. 2593–2599.
Hopfield, J. and Tank, D.W. (1985) Neural computation of decisions in optimization problems, Biological Cybernetics, vol.52, pp. 141–152.
Journel, A.G. and Huijbregts, C. J. (1978) Mining Geostatistics. Academic Press: London.
Jupp, D.L.B., Strahler, A.H. and Woodcock, C.E. (1988) Autocorrelation and regularization in digital images I. Basic theory, IEEE Transactions on Geoscience and Remote Sensing, vol. 26, pp. 463–473.
Schneider, W. (1999) Land cover mapping from optical satellite images employing subpixel segmentation and radiometric calibration, in I. Kanellopoulos, G. Wilkinson and T. Moons, Machine Vision and Advanced Image Processing in Remote Sensing. Springer: London.
Steinwendner, J., Schneider, W. and Suppan, F. (1998) Vector segmentation using spatial subpixel analysis for object extraction, International Archives of Photogrammetry and Remote Sensing, vol. 32, pp. 265–271.
Tatem, A.J., Lewis, H.G., Atkinson, P.M. and Nixon, M.S. (2001a) Super-resolution target identification from remotely sensed images using a Hopfield neural network, IEEE Transactions on Geoscience and Remote Sensing, vol. 39, pp. 781–796.
Tatem, A.J., Lewis, H.G., Atkinson, P.M. and Nixon, M.S. (2001b) Multiple class land cover mapping at the sub-pixel scale using a Hopfield neural network, International Journal of Applied Earth Observation and Geoinformation (in press).
Tatem, A.J., Lewis, H.G., Atkinson, P.M. and Nixon, M.S. (2002) Land cover simulation and estimation at the sub-pixel scale using a Hopfield neural network, Remote Sensing of Environment, vol. 79, pp. 1–14.
Thomas, I.L., Benning, V.M., and Ching, N.P. (1987) Classification of Remotely Sensed Images, Bristol, Adam Hilger.
Verhoeye et al. (2000) IGARSS2001 Scanning The Present and Resolving the Future, IEEE, Sydney, Australia, CD-ROM.
Van Groenigen, J.-W. (1999) Constrained optimisation of spatial sampling. A Geostatistical Approach, ITC Publication Series, No. 65, ITC: Enschede, the Netherlands.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Kluwer Academic Publishers
About this paper
Cite this paper
Atkinson, P.M. (2004). Super-Resolution Land Cover Classification Using the Two-Point Histogram. In: Sanchez-Vila, X., Carrera, J., Gómez-Hernández, J.J. (eds) geoENV IV — Geostatistics for Environmental Applications. Quantitative Geology and Geostatistics, vol 13. Springer, Dordrecht. https://doi.org/10.1007/1-4020-2115-1_2
Download citation
DOI: https://doi.org/10.1007/1-4020-2115-1_2
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-2007-0
Online ISBN: 978-1-4020-2115-2
eBook Packages: Springer Book Archive