COMPARISON OF SINGLE-STAGE AND MULTISTAGE CLASSIFICATION APPROACHES FOR COVER TYPE MAPPING WITH TM AND SPOT DATA

This article presents a comparison of the performance of TM and SPOT d ata for cover type mapping on the Central Sierra of Spain. A novel mul ti-stage iterative classification, and four single-step classification s are performed for each type of data. The single-stage classification s differ from one another in the band selection process, the use or no t of prior probabilities, and/or the supervised or unsupervised nature of the classification. The accuracy of each classification method and data type (TM vs. SPOT) is expressed as an error matrix from which K statistics and their large sample variances are derived. The values of the K statistics are used to compare the performance of the classific ation methods, two at time, by means of a Z statistic. Results from th is research show that the iterative classification approach is superio r to any other classification for both types of remotely sensed data. TM data proves superior to SPOT data only when the iterative classific ation approach is used. Overall comparison of the performance of TM an d SPOT data shows that there is not a statistically significant differ ence between these types of data for large-scale cover type mapping. ( C) Elsevier Science Inc., 1997