A suspicious action detection system considering time series

Noriaki Kozuka, Koji Kimura, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

The paper proposes a new system that can detect suspicious actions such as a car break-in and surroundings in an open space parking, based on image processing. The proposed system focuses on three points of "order", "time", and "location" of human actions. The proposed system has the following features: it 1) deals time series data flow, 2) estimates human actions and the location, 3) extracts suspicious action detection rules automatically, 4) detects suspicious actions using the suspicious score. We carried out experiments using real image sequences. As a result, we obtained about 7.8% higher estimation rate than the conventional system.

Original languageEnglish
Pages (from-to)2014-2021
Number of pages8
JournalIEEJ Transactions on Electronics, Information and Systems
Volume131
Issue number11
DOIs
Publication statusPublished - 2011

Fingerprint

Time series
Parking
Image processing
Railroad cars
Experiments

Keywords

  • Action features
  • Location features
  • Suspicious action detection rule
  • Suspicious score
  • Time series

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

A suspicious action detection system considering time series. / Kozuka, Noriaki; Kimura, Koji; Hagiwara, Masafumi.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 131, No. 11, 2011, p. 2014-2021.

Research output: Contribution to journalArticle

@article{461bb53f8d714a69a3da41c7a1b3c41a,
title = "A suspicious action detection system considering time series",
abstract = "The paper proposes a new system that can detect suspicious actions such as a car break-in and surroundings in an open space parking, based on image processing. The proposed system focuses on three points of {"}order{"}, {"}time{"}, and {"}location{"} of human actions. The proposed system has the following features: it 1) deals time series data flow, 2) estimates human actions and the location, 3) extracts suspicious action detection rules automatically, 4) detects suspicious actions using the suspicious score. We carried out experiments using real image sequences. As a result, we obtained about 7.8{\%} higher estimation rate than the conventional system.",
keywords = "Action features, Location features, Suspicious action detection rule, Suspicious score, Time series",
author = "Noriaki Kozuka and Koji Kimura and Masafumi Hagiwara",
year = "2011",
doi = "10.1541/ieejeiss.131.2014",
language = "English",
volume = "131",
pages = "2014--2021",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "11",

}

TY - JOUR

T1 - A suspicious action detection system considering time series

AU - Kozuka, Noriaki

AU - Kimura, Koji

AU - Hagiwara, Masafumi

PY - 2011

Y1 - 2011

N2 - The paper proposes a new system that can detect suspicious actions such as a car break-in and surroundings in an open space parking, based on image processing. The proposed system focuses on three points of "order", "time", and "location" of human actions. The proposed system has the following features: it 1) deals time series data flow, 2) estimates human actions and the location, 3) extracts suspicious action detection rules automatically, 4) detects suspicious actions using the suspicious score. We carried out experiments using real image sequences. As a result, we obtained about 7.8% higher estimation rate than the conventional system.

AB - The paper proposes a new system that can detect suspicious actions such as a car break-in and surroundings in an open space parking, based on image processing. The proposed system focuses on three points of "order", "time", and "location" of human actions. The proposed system has the following features: it 1) deals time series data flow, 2) estimates human actions and the location, 3) extracts suspicious action detection rules automatically, 4) detects suspicious actions using the suspicious score. We carried out experiments using real image sequences. As a result, we obtained about 7.8% higher estimation rate than the conventional system.

KW - Action features

KW - Location features

KW - Suspicious action detection rule

KW - Suspicious score

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=82255169185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82255169185&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.131.2014

DO - 10.1541/ieejeiss.131.2014

M3 - Article

VL - 131

SP - 2014

EP - 2021

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 11

ER -