Nagoya University Extremely Low-resolution FIR Image Action Dataset (Version 2018)
Action dataset obtained from a 16*16 far-infrared sensor array mounted on the ceiling.
For more detail of the dataset, please refer to "Dataset_detail.pdf".
This dataset contains the following files:
- [date(ex. 20170203,20170206,...] : date
- [date]/[raw]/*csv : action data files obtained a far-infrared sensor array
- [date]/[video]/*mp4 : action data files obtained visible-light camera (for reference) (h264 format; not provided yet)
- [annotation]/*csv : annotation files
Citation
Please cite these papers in your publications if it helps your research
@inproceedings{kawashima2017,
author = {Takayuki Kawashima and Yasutomo Kawanishi and Ichiro Ide and Hiroshi Murase and Daisuke Deguchi and Tomoyoshi Aizawa and Masato Kawade},
booktitle = {Proceedings of the 14th IEEE International Conference on Advanced Video and Signal Based Surveillance},
title = {Action recognition from extremely low-resolution thermal image sequence},
year = {2017},
pages = {1--6},
month=aug
}
License
This dataset is licensed by CC BY-NC-SA 4.0.
Contact
If you have comments and questions, please feel free to send e-mail to Yasutomo Kawanishi.
Contact:
Yasutomo Kawanishi
Visiting Associate Professor
Graduate School of Informatics,
Nagoya University, Nagoya, Japan
Team Leader
Multimodal Data Recognition Research Team
RIKEN Guardian Robot Project, Japan