Human Abnormal Behavioral Detection for Video Surveillance

DOI

10.2991/icmemtc-16.2016.140How to use a DOI?

Keywords

Kinect;depth image;skeleton tracking technology;fall detection

Abstract

With the increasing proportion of the elderly, fall will be a serious threat to the health of the elderly, especially elderly people who lives alone. Therefore, how to automatically detect abnormal behavior has become a key problem.Because of image recognition ,which is captured from the general monitoring, is affected by light, shelter and other factors, resulting in performance degradation.This paper introduced the Kinect device as the research platform. Depth images are acquired by analyzing data of human body height change and skeletal points ,which are acquired by skeletal tracking technology. Build an automatic determining abnormal algorithm, which can be alarming for abnormal behavior. The experiment show that the system of strong real-time performance and high detection rate.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ying Qian
AU  - Wenjing Zhang
PY  - 2016/04
DA  - 2016/04
TI  - Human Abnormal Behavioral Detection for Video Surveillance
BT  - Proceedings of the 2016 3rd International Conference on Materials Engineering, Manufacturing Technology and Control
PB  - Atlantis Press
SP  - 699
EP  - 703
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmemtc-16.2016.140
DO  - 10.2991/icmemtc-16.2016.140
ID  - Qian2016/04
ER  -