ABSTRACT

Accuracy assessment is an integral part of information extraction and requires a priori planning on the approach to measure the accuracy of the information derived from multispectral imagery. Remotely sensed information products are increasingly used in decision-making applications, such as computing taxes based on the area of impervious surfaces in a given parcel or estimating forest fire potential based on tree count, and others. Accuracy assessment is critical to ensuring the accuracy of the information used in the decision process. Often, ground truth or collateral information is required for statistical analysis. There are several protocols that have been developed to collect ground truth using global positioning systems (GPS). These protocols differ for linear features as compared to features such as land cover, and the user should employ an appropriate technique based on the information extracted.