Unusual behavior detection in the entry gate scenes of subway station using Bayesian networks and inference

Sooyeong Kwak, Guntae Bae, Manbae Kim, Hyeran Byun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a method for detecting unusual human behavior using monocular camera which is not moving. Our system composed of three modules which are moving object detection, tracking, and event recognition. The key part is event recognition module. We define unusual events which are composed of two simple events (drop off luggage, unattended luggage) and two complex events (abandoned luggage and steal luggage). In order to detect the simple event, we construct Bayesian network in each unusual event. We extract evidences using bounding box properties which are the location of moving objects, speed, distance between the person and the other moving object (such as bag), existing time. And then, we use finite state automaton which shows the temporal relation of two simple events to detect complex events. To evaluate the performance, we compare the frame number when an even is triggered with our results and the ground truth. The proposed algorithm showed good results on the real world environment and also worked at real time speed.

Original languageEnglish
Title of host publicationImage Processing
Subtitle of host publicationMachine Vision Applications
Volume6813
DOIs
Publication statusPublished - 2008 Mar 31
EventImage Processing: Machine Vision Applications - San Jose, CA, United States
Duration: 2008 Jan 292008 Jan 31

Other

OtherImage Processing: Machine Vision Applications
CountryUnited States
CitySan Jose, CA
Period08/1/2908/1/31

Fingerprint

Subway stations
Bayesian networks
Bayesian inference
Bayesian Networks
inference
entry
stations
Finite automata
Cameras
Moving Objects
modules
human behavior
Moving Object Detection
Module
Finite State Automata
ground truth
Human Behavior
bags
boxes
Person

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Kwak, S., Bae, G., Kim, M., & Byun, H. (2008). Unusual behavior detection in the entry gate scenes of subway station using Bayesian networks and inference. In Image Processing: Machine Vision Applications (Vol. 6813). [681311] https://doi.org/10.1117/12.766946
Kwak, Sooyeong ; Bae, Guntae ; Kim, Manbae ; Byun, Hyeran. / Unusual behavior detection in the entry gate scenes of subway station using Bayesian networks and inference. Image Processing: Machine Vision Applications. Vol. 6813 2008.
@inproceedings{52266665ef454b8f973f7761353bc869,
title = "Unusual behavior detection in the entry gate scenes of subway station using Bayesian networks and inference",
abstract = "In this paper, we propose a method for detecting unusual human behavior using monocular camera which is not moving. Our system composed of three modules which are moving object detection, tracking, and event recognition. The key part is event recognition module. We define unusual events which are composed of two simple events (drop off luggage, unattended luggage) and two complex events (abandoned luggage and steal luggage). In order to detect the simple event, we construct Bayesian network in each unusual event. We extract evidences using bounding box properties which are the location of moving objects, speed, distance between the person and the other moving object (such as bag), existing time. And then, we use finite state automaton which shows the temporal relation of two simple events to detect complex events. To evaluate the performance, we compare the frame number when an even is triggered with our results and the ground truth. The proposed algorithm showed good results on the real world environment and also worked at real time speed.",
author = "Sooyeong Kwak and Guntae Bae and Manbae Kim and Hyeran Byun",
year = "2008",
month = "3",
day = "31",
doi = "10.1117/12.766946",
language = "English",
isbn = "9780819469854",
volume = "6813",
booktitle = "Image Processing",

}

Kwak, S, Bae, G, Kim, M & Byun, H 2008, Unusual behavior detection in the entry gate scenes of subway station using Bayesian networks and inference. in Image Processing: Machine Vision Applications. vol. 6813, 681311, Image Processing: Machine Vision Applications, San Jose, CA, United States, 08/1/29. https://doi.org/10.1117/12.766946

Unusual behavior detection in the entry gate scenes of subway station using Bayesian networks and inference. / Kwak, Sooyeong; Bae, Guntae; Kim, Manbae; Byun, Hyeran.

Image Processing: Machine Vision Applications. Vol. 6813 2008. 681311.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Unusual behavior detection in the entry gate scenes of subway station using Bayesian networks and inference

AU - Kwak, Sooyeong

AU - Bae, Guntae

AU - Kim, Manbae

AU - Byun, Hyeran

PY - 2008/3/31

Y1 - 2008/3/31

N2 - In this paper, we propose a method for detecting unusual human behavior using monocular camera which is not moving. Our system composed of three modules which are moving object detection, tracking, and event recognition. The key part is event recognition module. We define unusual events which are composed of two simple events (drop off luggage, unattended luggage) and two complex events (abandoned luggage and steal luggage). In order to detect the simple event, we construct Bayesian network in each unusual event. We extract evidences using bounding box properties which are the location of moving objects, speed, distance between the person and the other moving object (such as bag), existing time. And then, we use finite state automaton which shows the temporal relation of two simple events to detect complex events. To evaluate the performance, we compare the frame number when an even is triggered with our results and the ground truth. The proposed algorithm showed good results on the real world environment and also worked at real time speed.

AB - In this paper, we propose a method for detecting unusual human behavior using monocular camera which is not moving. Our system composed of three modules which are moving object detection, tracking, and event recognition. The key part is event recognition module. We define unusual events which are composed of two simple events (drop off luggage, unattended luggage) and two complex events (abandoned luggage and steal luggage). In order to detect the simple event, we construct Bayesian network in each unusual event. We extract evidences using bounding box properties which are the location of moving objects, speed, distance between the person and the other moving object (such as bag), existing time. And then, we use finite state automaton which shows the temporal relation of two simple events to detect complex events. To evaluate the performance, we compare the frame number when an even is triggered with our results and the ground truth. The proposed algorithm showed good results on the real world environment and also worked at real time speed.

UR - http://www.scopus.com/inward/record.url?scp=41149136097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41149136097&partnerID=8YFLogxK

U2 - 10.1117/12.766946

DO - 10.1117/12.766946

M3 - Conference contribution

SN - 9780819469854

VL - 6813

BT - Image Processing

ER -