Sub-pixel land cover composition estimation using a linear mixture model and fuzzy membership functions

Abstract Mixed pixels occur commonly in remotely-sensed imagery, especially those with a coarse spatial resolution. They are a problem in land-cover mapping applications since image classification routines assume ‘pure’ or homogeneous pixels. By unmixing a pixel into its component parts it is possible to enableinter alia more accurate estimation of the areal extent of different land cover classes. In this paper two approaches to estimating sub-pixel land cover composition are investigated. One is a linear mixture model the other is a regression model based on fuzzy membership functions. For both approaches significant correlation coefficients, all >0·7, between the actual and predicted proportion of a land cover type within a pixel were obtained. Additionally a case study is presented in which the accuracy of the estimation of tropical forest extent is increased significantly through the use of sub-pixel estimates of land-cover composition rather than a conventional image classification.

[1]  S. Gregory.  Statistical methods and the geographer , 1963 .

[2]  J. Townshend.  The spatial resolving power of earth resources satellites , 1980 .

[3]  Christopher O. Justice,et al.  Information extraction from remotely sensed data. , 1981 .

[4]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[5]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[6]  John R. Townshend,et al.  Agricultural land-cover discrimination using thematic mapper spectral bands , 1984 .

[7]  Alex B. McBratney,et al.  Application of fuzzy sets to climatic classification , 1985 .

[8]  M. L. Labovitz,et al.  Issues arising from sampling designs and band selection in discriminating ground reference attributes using remotely sensed data , 1986 .

[9]  J. L. Smith,et al.  Using classification error matrices to improve the accuracy of weighted land-cover models , 1987 .

[10]  Giles M. Foody,et al.  The effects of viewing geometry on image classification , 1988 .

[11]  Roger G. Barry,et al.  Cloud classification from satellite data using a fuzzy sets algorithm - A polar example , 1989 .

[12]  C. Justice,et al.  Spatial degradation of satellite data , 1989 .

[13]  Giles M. Foody,et al.  Analysis and representation of vegetation continua from Landsat Thematic Mapper data for lowland heaths , 1989 .

[14]  P. S. Eagleson,et al.  Estimation of subpixel vegetation cover using red-infrared scattergrams , 1990 .

[15]  Alan R. Gillespie,et al.  Vegetation in deserts. I - A regional measure of abundance from multispectral images. II - Environmental influences on regional abundance , 1990 .

[16]  Peter F. Fisher,et al.  The evaluation of fuzzy membership of land cover classes in the suburban zone , 1990 .

[17]  P. Bierwirth,et al.  Mineral mapping and vegetation removal via data-calibrated pixel unmixing, using multispectral images , 1990 .

[18]  Examining spectral mixture modelling using in situ spectroradiometric measurements , 1991 .

[19]  David S. Gilmer,et al.  Inventory of wintering geese with a multispectral scanner , 1991 .

[20]  Gerardo Beni,et al.  A Validity Measure for Fuzzy Clustering , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  J. Settle,et al.  Subpixel measurement of tropical forest cover using AVHRR data , 1991 .

[22]  N. A. Quarmby,et al.  Linear mixture modelling applied to AVHRR data for crop area estimation , 1992 .

[23]  J. Settle,et al.  Linear mixing and the estimation of ground cover proportions , 1993 .