Investigations on extraction of buildings from RS imagery using deep learning models

ABSTRACT

Building roofs are crucial elements that must be extracted from satellite images for use in services like updating geodatabases, risk analysis and rescue maps. The diversity and complexity of the building structures present challenges for accurate and efficient building rooftop extraction from very high resolution (VHR) images. The significance of building extraction from satellite imagery in various applications has attracted the attention of the research community in this domain. In this paper, the progression of the research in building extraction is presented based on two streams, such as Traditional building extraction techniques and Evolving DL-based building extraction techniques. Furthermore, the categorization of traditional techniques into transform-based techniques, indices-based methodologies and machine learning-based methodologies are summarized. An enhanced comprehension of the challenges associated with extracting buildings from aerial images using DL models is given. A performance analysis of the popular Deep Learning models used for building extraction, such as UNet, SegNet, ResUNet, UNet⁺⁺, ENRUNet and Dilated ResUNet, in terms of Accuracy, IoU and Dice Loss is presented. We hope that this paper will improve researchers’ understanding of the problems associated with extraction of buildings from images and ultimately to develop new models with better performance.

Acknowledgements

The authors acknowledge ISRO Sponsored Research (RESPOND) Programme, and Director, Indian Institute of Remote Sensing (IIRS), Dehradun for funding, guidance and support to this work. Authors extend thanks to the management of St. Joseph’s College of Engineering, Chennai for their support for this study.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This is a collaborative sponsored research work between Indian Institute of Remote Sensing (IIRS), Dehradun and St. Joseph’s College of Engineering, Chennai. It is funded by the Indian Space Research Organization (ISRO), Department of Space and the Government of India under RESPOND-BASKET 2021 Project scheme of India, Grant No. ISRO/RES/4/687/21-22.