ABSTRACT
This chapter deals with a discussion of change detection accuracy assessment. A key issue in any change detection accuracy assessment is the realization that change is a rare event, and sampling must occur to specifically deal with this issue. The complexities of conducting such an assessment are presented along with the formulation of the change detection error matrix. The collection of valid reference data is central to any accuracy assessment, whether it is a single-date assessment or for evaluating a change detection. There are many other factors to consider when sampling for change detection accuracy assessment. An increasingly popular and extremely important application of remotely sensed data is for use in change detection. Change detection is the process of identifying differences in the state of an object or phenomenon by observing it at different times. The collection of valid reference data is central to any accuracy assessment, whether it is a single-date assessment or for evaluating a change detection.
