EASY

DANS - Data Archiving and Networked Services

Archeologische data deponeer je voortaan niet meer hier in EASY.

Deponeren kan wel via de knop ‘Add data’ in het nieuwe Data Station Archaeology: https://archaeology.datastations.nl/

Lees hier meer



Search datasets

EASY offers sustainable archiving of research data and access to thousands of datasets.

Close Search help

UAVid-depth Dataset

Cite as:

Yang, Dr. M.Y. (Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente) (): UAVid-depth Dataset. DANS. https://doi.org/10.17026/dans-zux-xqv4

2021-05-27 Yang, Dr. M.Y. (Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente) 10.17026/dans-zux-xqv4

The UAVid-depth dataset is created from public UAVid dataset (Lyu et al. 2020) which is a high-resolution UAV semantic segmentation dataset focusing on street scenes. The UAVid dataset consists video sequences taken from Germany and China which are captured with 4K high-resolution in oblique views. For UAVid-depth dataset, the original video is converted to images at a frame rate of 5 images per second for Germnay dataset and 1 image per second for China. The reference depth for some of the test images are provided in the UAVid-depth dataset.

*Task Description
Self-supervised monocular depth estimation from UAV videos.
The original video files for each sequence will be provided upon request, or are available for download at UAVid homepage (https://www.uavid.nl/).

*Data Description
Training data, validation data and test data are provided for Germany and China dataset separately. The data is arranged in the folders based on the captured video files.

*Reference Depth
The reference depth for some of the test images (three sequences) are generated from the photogrammetric point clouds and are uploaded along with the corresponding test sequence.

*SMDE Model Depth
The depth for some of the test images (three sequences) are generated from SMDE model (Madhuanand et al. 2021) and are uploaded along with the corresponding test sequence.

*Copyright
UAVid-depth dataset is copyright by us and published under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license.

*Citation
When using this UAVid-depth dataset in your research, please cite:
@article{uaviddepth21,
Author = {Logambal Madhuanand and Francesco Nex and Michael Ying Yang},
Title = {Self-supervised monocular depth estimation from oblique UAV videos},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
year = {2021},
volume = {176},
pages = {1-14},
}

When using the UAVid dataset in your research, please cite:
@article{uavid20,
Author = {Ye Lyu and
George Vosselman and
Guisong Xia and
Alper Yilmaz and
Michael Ying Yang},
Title = {UAVid: A Semantic Segmentation Dataset for UAV Imagery},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
year = {2020},
}

*Contact
michael.yang@utwente.nl