Articles in press 04



Authors: Alpesh M. Patel, Anil Suthar

Abstract: Urbanization generally serves as a key navigator of the economic growth and development of the country. There is a need for fast and accurate urban planning to accommodate more and more people in the city area. Remote sensing technology has been used for planning the expansion and design of city areas. A novel machine learning (ML) classifier formed by combining AdaBoost and extra trees algorithm have been investigated for change detection in the urban area of three cities in the Gujarat region of India. Using Indian Remote Sensing (IRS) Resourcesat-2 LISS IV satellite images, the performance of the object-based AdaBoosted extra trees classifier (ABETC) in terms of overall accuracy (OA) and kappa coefficient (KC) for urban area change detection was compared to benchmarked object-based algorithms. As the first step in object-based classification (OBC), the Shepherd segmentation algorithm was used to segment satellite images. For all three cities, the object-based ABETC demonstrated the highest efficiency when compared to conventional classifiers. The rise in the built-up area of Ahmedabad city has been noted by 87.39 sq km from the year 2011 to 2020 showing the urban development of the city. This increase in the built-up area of Ahmedabad was compensated by the depletion of 30.26 sq. km. vegetation area, and 57.13 sq. km. of open land class. The built-up area of Vadodara and Rajkot city has been enlarged by 17.24 sq km and 6.79 sq km respectively. The highest OA of 96.04% and KC of 0.94 has been noted for a satellite image of Vadodara city with a novel object based ABETC algorithm.

Keywords: urbanization; change detection; object based classification; multispectral image

DOI: 10.5937/gp26-39440

Article info:

Received: July 31, 2022 | Revised: September 29, 2022 | Accepted: October 20, 2022

Full text: