Identification of Abnormal Human Behavior in Intelligent Video Surveillance System

DOI

10.2991/wartia-18.2018.58How to use a DOI?

Keywords

KL distance similarity, abnormal population, attribute label, preference distribution model

Abstract

Focusing on the security issues of current group activities, strengthening the prevention of group incidents is the focus of current thinking. Combined with the above requirements, crowd abnormality recognition algorithms have begun to enter people's field of vision and are valued. In this regard, this paper combines crowd abnormality and intelligent monitoring video acquisition principles, proposes a crowd recognition algorithm based on preference distribution model, uses KL distance similarity to complete the labeling of common attribute labels, and then uses the preference distribution model to complete the classification of abnormal behavior, and get the judgment of abnormal behavior. Finally, through the test verification method, the verification of the above model is completed and its feasibility is proved.

Copyright

© 2018, 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  - Bo Zhai
PY  - 2018/09
DA  - 2018/09
TI  - Identification of Abnormal Human Behavior in Intelligent Video Surveillance System
BT  - Proceedings of the 4th Workshop on Advanced Research and Technology in Industry (WARTIA 2018)
PB  - Atlantis Press
SP  - 318
EP  - 324
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-18.2018.58
DO  - 10.2991/wartia-18.2018.58
ID  - Zhai2018/09
ER  -