Download

Dataset Overview

The dataset provides videos, video frames, and ground truth, therefore offering a superiorly comprehensive dataset for the area of crowd understanding. The sequences are diverse, representing dense crowd in the public spaces in various scenarios such as i-park, school, station, marathon, civic center and basketball court.

Features

Copyright

All of the Gigapixel Video Dataset on this page are copyright by Smart Imaging Laboratory, Tsinghua-Berkeley Shenzhen Institute and published under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 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 our datasets in your research, we will be happy if you cite us!
For all of the datasets, please cite:

@inproceedings{yuan2017multiscale,
title={Multiscale gigapixel video: A cross resolution image matching and warping approach},
author={Yuan, Xiaoyun and Fang, Lu and Dai, Qionghai and Brady, David J and Liu, Yebin},
booktitle={Computational Photography (ICCP), 2017 IEEE International Conference on},
pages={1--9},
year={2017},
organization={IEEE}
}

Details

  • i-park
    • Video length: 5000 frames
    • Frame size: 32000x24000
    • Frame rate: 12 Hz
  • School
    • Video length: 5000 frames
    • Frame size: 32000x24000
    • Frame rate: 12 Hz
  • Station
    • Video length: 9000 frames
    • Frame size: 26000x14000
    • Frame rate: 30 Hz
  • Marathon
    • Video length: 9000 frames
    • Frame size: 27000x15000
    • Frame rate: 30 Hz
  • Civic Center
    • Video length: 5000 frames
    • Frame size: 32000x24000
    • Frame rate: 12 Hz
  • Basketball Court
    • Video length: 5000 frames
    • Frame size: 32000x24000
    • Frame rate: 12 Hz