Semantic Riverscapes is a new drone-based oblique semantic segmentation open dataset focused on riverscapes. This dataset has 400 high-resolution images spanning the river and surrounding areas, each with a size of 1800 x 1480 pixels. Each image was manually labelled. A total of 14 categories are selected for annotation, namely:
- building
- cottage
- under construction place
- tree
- grass
- water grass
- soil
- hard ground
- water
- sky
- human
- car
- boat
- void
A DJI Mavic Air 2 UAV was used to obtain geo-tagged aerial oblique imagery from an altitude range of 30 to 60 metres. The data collection area is located in the Tianjin section of the Grand Canal and the Hai river. The aerial photography data collection took place over four days from 10 am to 6 pm during the period from July to September 2021 under stable light conditions.
This dataset is available for download on Google Drive.
A paper about the work was published in Landscape and Urban Planning. It is available open access here.
If you use Semantic Riverscapes Dataset in your research, please cite the article:
Luo J, Zhao T, Cao L, Biljecki F (2022): Semantic Riverscapes: Perception and evaluation of linear landscapes from oblique imagery using computer vision. Landscape and Urban Planning, 228: 104569.
@article{2022_land_semantic_riverscapes,
year = {2022},
title = {{Semantic Riverscapes: Perception and evaluation of linear landscapes from oblique imagery using computer vision}},
author = {Luo, Junjie and Zhao, Tianhong, and Cao, Lei and Biljecki, Filip},
journal = {Landscape and Urban Planning},
doi = {10.1016/j.landurbplan.2022.104569},
pages = {104569},
volume = {228}
}
This dataset is released under the CC BY-NC-SA 4.0 license.
We thank the members of the NUS Urban Analytics Lab for the discussions, and Zexin Lei and Wenzheng Zhang for the help with the UAV data collection. This research is part of the projects (i) Research on the theory and digital technologies of the Grand Canal's cultural heritage protection, which is supported by the National Social Science Foundation of China (19ZDA193); (ii) The Technical Key Project of Shenzhen Science and Technology Innovation Commission Grant JSGG20201103093401004; and (iii) Large-scale 3D Geospatial Data for Urban Analytics, which is supported by the National University of Singapore under the Start Up Grant R-295-000-171-133.
For comments and feedback, contact the lead researcher Junjie Luo at luojunjie4669@gmail.com or the principal investigator Filip Biljecki at filip@nus.edu.sg.
For more information about our research, please visit the website of our Urban Analytics Lab at the National University of Singapore.