GUI: A Comprehensive Dataset of Global Urban Infrastructure Based on Geospatial Visual Foundation Models
Name
3678717.3691242.pdf
Size
1.32 MB
Format
Adobe PDF
Checksum (MD5)
64949cfaaad4aee899fb74827954fc17
Author(s)
Han, Zhenyu
Zhang, Xin
Xi, Yanxin
Luo, Yan
Xia, Tong
Li, Yong
Date Issued
October 29, 2024
Publisher
ACM|The 32nd ACM International Conference on Advances in Geographic Information Systems
Citation
Han, Zhenyu, Zhang, Xin, Xi, Yanxin, Luo, Yan, Xia, Tong et al. 2024. "GUI: A Comprehensive Dataset of Global Urban Infrastructure Based on Geospatial Visual Foundation Models."
Version
Final published version
Abstract
The substantial social and financial costs of infrastructure identification impede in-depth analyses of sustainable urban design, especially in developing countries. In this paper, we present a novel framework with interactive web visualization based on geospatial visual foundation models. Leveraging this framework, we examine the urban infrastructure information in 1,178 cities worldwide, covering 93, 088 km2 areas. Cross-validation reveals that the overall accuracy of identified infrastructure achieves 67.0%. It sheds light on the sustainable development of cities and exposes the stark inequity in urban infrastructure provision for vulnerable populations. The identified urban infrastructure dataset of this study are available at https://github.com/tsinghua-fib-lab/GUI, and the interactive web application is at https://tinyurl.com/yz7xbfy3.
Description
SIGSPATIAL ’24, October 29-November 1, 2024, Atlanta, GA, USA
MIT Department
Massachusetts Institute of Technology. Media Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3678717.3691242
