Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications.
@article{arxiv.1706.03038,
title = {Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection},
author = {Mohammadamin Barekatain and Miquel Martí and Hsueh-Fu Shih and Samuel Murray and Kotaro Nakayama and Yutaka Matsuo and Helmut Prendinger},
journal= {arXiv preprint arXiv:1706.03038},
year = {2017}
}
Comments
Computer Vision and Pattern Recognition Workshops (CVPRW), Hawaii, USA, 2017