A generalized confusion matrix for assessing area estimates from remotely sensed data

The formulation of a generalized area-based confusion matrix for exploring the accuracy of area estimates is presented. The generalized confusion matr ix is appropriate for both traditional classification algorithms and sub-pi xel area estimation models. An error matrix, derived from the generalized c onfusion matrix, allows the accuracy of maps generated using area estimatio n models to be assessed quantitatively and compared to the accuracies obtai ned from traditional classification techniques, The application of this app roach is demonstrated for an area estimation model applied to Landsat data of an urban area of the United Kingdom.