Search

The accuracy of thematic maps derived by image classification analyses is often compared in remote sensing studies. This comparison is typically achieved by a basic subjective assessment of the observed difference in accuracy but should be undertaken in a statistically rigorous fashion. One approach for the evaluation of the statistical significance of a difference in map accuracy that has been widely used in remote sensing research is based on the comparison of the kappa coefficient of agreement derived for each map. The conventional approach to the comparison of kappa coefficients assumes that the samples used in their calculation are independent, an assumption that is commonly unsatisfied because the same sample of ground data sites is often used for each map. Alternative methods to evaluate the statistical significance of differences in accuracy are available for both related and independent samples. Approaches for map comparison based on the kappa coefficient and proportion of correctly allocated cases, the two most widely used metrics of thematic map accuracy in remote sensing, are discussed. An example illustrates how classifications based on the same sample of ground data sites may be compared rigorously and highlights the importance of distinguishing between one- and two-sided statistical tests in the comparison of classification accuracy statements. [ABSTRACT FROM AUTHOR]

Mis-registration of data sets is one of the largest sources of error in many remote sensing studies. An initial contribution to this error arises through the mis-location of ground control points (GCPs) used to derive geometrical transformation equations. Here, it is proposed that a soft classification of land cover may be used to direct the estimation of GCP location. The soft classification provides an estimate of the class composition of each image pixel. The spatial distribution of a pixel's component land covers may then be modeled over the area it represents and used to reduce the error in estimating the location of a GCP that lies within this area. An example is provided in which the error in locating a set of GCPs was reduced by up to 35.7 percent when information from a soft classification was available to aid the estimation of their location at a sub-pixel scale. [ABSTRACT FROM AUTHOR]

Thematic mapping from remotely sensed data is generally achieved through the application of a supervised image classification. Although this is one of the most common applications of remote sensing, the maps derived are often of insufficient accuracy for operational use. Consequently, considerable research effort has been directed at increasing the accuracy of thematic mapping, particularly through the development of classification techniques that make fuller use of the information content of remotely sensed data. One major set of problems limiting the accuracy of thematic maps derived from remotely sensed data relates to conceptual issues associated with the use of classificationtechniques as the tool for mapping. It is shown that the conventional 'hard' classifications may be less appropriate than fuzzy classifications and that a continuum of classification fuzziness can be defined. The potential for classification at any point along this continuum, from completely crisp to fully fuzzy, is discussed and may provide a framework for realizing more fully the potential of remote sensing as a source of thematic map data. The implications of the continuum on spatial data standards and reporting are also briefly discussed. [ABSTRACT FROM AUTHOR]