Research on Recognition of Pedestrians’ Abnormal Behaviors Based on Naive Bayesian Classifier

DOI

10.2991/icmcs-18.2018.68How to use a DOI?

Keywords

Abnormal behaviors; Naive Bayesian Classifier; Video frames; Kinetic features

Abstract

Recognition of abnormal behaviors is a prerequisite for effective stampedes prediction in crowded scenes. By tracking the trajectory of a pedestrian in the monitoring video, this paper has demonstrated that the kinetic features of pedestrians in the video dominate the judgment of abnormal behaviors. Using the Naive Bayesian Classifier(NBC), we have built a recognition model of abnormal behaviors, which precisely collected the kinetic features of pedestrians in the video and accurately made judgement of their behaviors. This model has been proved to be effective in predicting stampedes and is promising in various applications.

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  - Qiongqiong Wu
PY  - 2018/10
DA  - 2018/10
TI  - Research on Recognition of Pedestrians’ Abnormal Behaviors Based on Naive Bayesian Classifier
BT  - Proceedings of the 8th International Conference on Management and Computer Science (ICMCS 2018)
PB  - Atlantis Press
SP  - 336
EP  - 341
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmcs-18.2018.68
DO  - 10.2991/icmcs-18.2018.68
ID  - Wu2018/10
ER  -