Modification of urban built-up area extraction method based on the thematic index-derived bands

Abstract

This research aims to develop new automatic and quicker spectral signature analysis tools to separate urban built-up area and determines urban area changes. Nowadays, researcher uses thematic index-derived bands for automatic urban data extraction. The extraction of urban built-up land can be automatically done with New Built-Up Index (NBUI) although it has a limitation on separating built-up land and water body. This study attempts to obtain the maximum accuracy of the extraction by merging several indices including Enhanced Built-Up and Bareness Index (EBBI), Soil Adjusted Vegetation Index (SAVI), Modified Normalized Difference Water Index (MNDWI), New Water Index (NWI) and Normalized Different Pond Index (NDPI) and compared its accuracy with NBUI. The results showed that merging EBBI, SAVI, MNDWI and NDPI produces the highest accuracy of 98.21% by addition and subtraction. The combined application of EBBI, SAVI and NWI also gives a good effect for extracting urban built-up areas and has 94.64% mapping accuracy.