Real-Time Action Recognition in Surveillance Videos Using ConvNets

Sheng Luo, Haojin Yang, Cheng Wang, Xiaoyin Che, Christoph Meinel

Abstract

The explosive growth of surveillance cameras and its 7 * 24 recording period brings massive surveillance videos data. Therefore how to efficiently retrieve the rare but important event information inside the videos is eager to be solved. Recently deep convolutinal networks shows its outstanding performance in event recognition on general videos. Hence we study the characteristic of surveillance video context and propose a very competitive ConvNets approach for real-time event recognition on surveillance videos. Our approach adopts two-steam ConvNets to respectively recognition spatial and temporal information of one action. In particular, we propose to use fast feature cascades and motion history image as the template of spatial and temporal stream. We conducted our experiments on UCF-ARG and UT-interaction dataset. The experimental results show that our approach acquires superior recognition accuracy and runs in real-time.
BibTeX
@inproceedings{luo2016real,
  author = {Sheng Luo and Haojin Yang and Cheng Wang and Xiaoyin Che and Christoph Meinel},
  title = {{Real-Time Action Recognition in Surveillance Videos Using ConvNets}},
  booktitle = {ICONIP},
  year = {2016},
  doi = {10.1007/978-3-319-46675-0\_58},
}

Loading related content...

Figure