Global road extraction using a pseudo-label guided framework: From benchmark dataset to cross-region semi-supervised learning
- The GRSet contains 47210 samples from 121 cities across six continents: Europe, Africa, Asia, South America, Oceania, and North America. The area is 49503.27 km2.
- The global-scale validation set covers more than 30 cities, across four continents: Europe, Africa, Asia, and North America. The area is 2836.38 km2.
Please fill in a simple form to register information before downloading so that we can know the usage of the data set. The GRSet and the global-scale validation set can be downloaded from Baidu Drive, Code: road
The GRSet pre-trained LinkNet50 is released at Baidu Drive, Code: Link
Feel free to use these datasets and design your own models, and we are looking forward to your exciting results!
Massachusetts Road Dataset (2013)
LSRV: The Large-Scale Road Validation Dataset (2021)
If you are having difficulty processing this data, you can contact me at [email protected]
If you use GRSet and global-scale validation set in your research, please cite the following paper.
@article{lu2024global,
title={Global road extraction using a pseudo-label guided framework: from benchmark dataset to cross-region semi-supervised learning},
author={Xiaoyan Lu, Yanfei Zhong, Zhuo Zheng, Junjue Wang, Dingyuan Chen and Yu Su}
journal={Geo-spatial Information Science},
pages={1-19},
year={2024},
publisher={Taylor & Francis}
}
The owners of the data and of the copyright on the data are RSIDEA, Wuhan University. Use of the Google Earth images must respect the "Google Earth" terms of use. All images and their associated annotations in GRSet and the global-scale validation set can be used for academic purposes only, but any commercial use is prohibited.
