Identification of Impervious Built-Up Surface Features Using ResourceSat-2 LISS-III-Based Novel Optical Built-Up Index

Abstract

In the context of urban planning, the increasing urban concentration and growth result in changes from natural landscape to impervious surface features. Remote sensing provides an efficient method in automated identification of land use/cover classes. However, a common challenge is the accurate extraction of built-up features from satellite images. The conventional Normalized Difference Built-up Index (NDBI) has been modified by several researchers in the anticipation of improvement of the built-up area classification. The indices adopted in the study are Index-based Built-up Index (IBI), Built-up Index (BUI), NDBI, and the newly developed Impervious Built-up Index (IBUI). These indices work on automated kernel-based probabilistic thresholding algorithm to group the index values into built-up and non-built-up areas. This study investigates the performance of the abovementioned spectral indices on ResourceSat-2 Linear Imaging Self-Scanner-III (LISS III) imageries of the city of Kolkata, India, and its adjoining areas in the delineation of built-up areas and compares them based on spectral feature space correlation and classification approach. Although all the built-up indices showed high mutual correlation, the performance varied greatly as showed by the accuracy in the classification. Overall accuracy values of built-up feature extraction using IBUI, IBI, BUI, and NDBI are 92.33%, 89%, 86%, and 80.67% respectively.