Anticipating Suspicious Actions using a Small Dataset of Action Templates

Renato Baptista, Michel Antunes, Djamila Aouada, Björn Ottersten

2018

Abstract

In this paper, we propose to detect an action as soon as possible and ideally before it is fully completed. The objective is to support the monitoring of surveillance videos for preventing criminal or terrorist attacks. For such a scenario, it is of importance to have not only high detection and recognition rates but also low time latency for the detection. Our solution consists in an adaptive sliding window approach in an online manner, which efficiently rejects irrelevant data. Furthermore, we exploit both spatial and temporal information by constructing feature vectors based on temporal blocks. For an added efficiency, only partial template actions are considered for the detection. The relationship between the template size and latency is experimentally evaluated. We show promising preliminary experimental results using Motion Capture data with a skeleton representation of the human body.

Download


Paper Citation


in Harvard Style

Baptista R., Antunes M., Aouada D. and Ottersten B. (2018). Anticipating Suspicious Actions using a Small Dataset of Action Templates. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 380-386. DOI: 10.5220/0006648703800386


in Bibtex Style

@conference{visapp18,
author={Renato Baptista and Michel Antunes and Djamila Aouada and Björn Ottersten},
title={Anticipating Suspicious Actions using a Small Dataset of Action Templates},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={380-386},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006648703800386},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Anticipating Suspicious Actions using a Small Dataset of Action Templates
SN - 978-989-758-290-5
AU - Baptista R.
AU - Antunes M.
AU - Aouada D.
AU - Ottersten B.
PY - 2018
SP - 380
EP - 386
DO - 10.5220/0006648703800386
PB - SciTePress