Land-use change dynamics and automated feature extraction using high-resolution satellite imagery

Loading...
Thumbnail Image

Date

2022-08

Journal Title

Journal ISSN

Volume Title

Publisher

Sri Lanka Society of Transport and Logistics

Abstract

The mapping of urban landscapes is a challenging task due to their dense and diverse characteristics. The changing urban environment with developing infrastructure demands constant updates and accurate extraction techniques. Recent advancement in geospatial technology has led to the capture of high-resolution data and its analysis at a finer scale. However, a sustainable development framework necessitates the understanding of spatial patterns incorporating vertical and horizontal components of the built-up volume. This study aims to understand the changing landscape at the pixel level by analysing features along with their volumetric expansion. The findings highlight that Bangalore city’s urban growth has shown increment over the period with volumetric expansion in all parts of the city based on events of changing demand and growth. The evaluation metrics indicate that the model can be generalised for any geographical location as well as to different sensor type images.

Description

Keywords

Land use, Urban built-up volume, Deep learning, Convolutional neural network, Feature extraction

Citation

*****

DOI

Collections