Mapping electrical towers in satellite imagery with smart-tracing

Fiona Gallagher; Laurens Hagendoorn; Geert Koster; Fang Fang; Cornelis Valk

doi:10.1117/12.2680200

19 October 2023 Mapping electrical towers in satellite imagery with smart-tracing

Fiona Gallagher, Laurens Hagendoorn, Geert Koster, Fang Fang, Cornelis Valk

Proceedings Volume 12735, Remote Sensing Technologies and Applications in Urban Environments VIII; 1273506 (2023) https://doi.org/10.1117/12.2680200
Event: SPIE Remote Sensing, 2023, Amsterdam, Netherlands

Abstract

The World Bank is interested in conducting least-cost electrification studies in developing countries with a view toward universal electricity access. Accurate and up-to-date knowledge of existing electrical transmission grid infrastructure is required for this purpose. To improve the quality of this data NEO has developed a novel smart-tracing algorithm to detect and trace electrical towers in Very High Resolution (VHR) satellite imagery. This smart-tracing approach uses existing open datasets alongside a deep learning model for object detection. The method is scalable and adaptable to arbitrary regions with satellite image coverage.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Fiona Gallagher, Laurens Hagendoorn, Geert Koster, Fang Fang, and Cornelis Valk "Mapping electrical towers in satellite imagery with smart-tracing", Proc. SPIE 12735, Remote Sensing Technologies and Applications in Urban Environments VIII, 1273506 (19 October 2023); https://doi.org/10.1117/12.2680200

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available