Detection of discrepancies in existing land-use classification using IKONOS satellite data

Geoinformation systems (GIS) and other spatial databases containing land-use data are usually subjected to intensive change processes that impact the quality of their inherent classification and diminish its relevance. Consequently, with time, these databases accumulate various types of erroneous information (discrepancies) that inconsistent with reality. The aim of the study was to investigate how well the discrepancies in land-use classification could be detected using high-resolution optical IKONOS satellite data based on iterative discriminant analyses (IDA). The approach proposed in the research is intended to update an existing land-use classification with one derived from the IDA classifier. Seven land-use classes were extracted from outdated Israeli National GIS spatial database for the area which was also the extent of recent IKONOS satellite image. In order to detect the discrepancies in the land-use classification, IDA algorithm was applied, utilizing the spectral properties of the land-use polygons, acquired from the image. As result IDA has changed, the classification of discrepant polygons which was found inconsistent with the up-to-date spectral data. The polygons with spectral properties that were found consistent with the original classification have remained assigned to initial land-use classes. The overall fraction of the polygons that were correctly classified by IDA was estimated as 92.6% and the fraction of polygons correctly detected as discrepant was estimated as 84.1%. The main advantage of the proposed detection of discrepancies by the IDA is its analytical simplicity that allows for straightforward employment of original bands and ratio (indices) bands in the classification process. The continuous revision of land-use classification databases by IDA may assist the overcoming of interpreter's errors and the misclassifications caused by changes in land-use.