Tracking human motions for security system

Junzo Watada, Zalili Binti Musaand

研究成果: Conference contribution

13 引用 (Scopus)

抄録

The aim of this study is to build a prototype of a multi-camera tracking system for a security system that enables us to track several human motions at one time. In this paper two innovative methods: foot step detection method and particle filtering method. Generally, to recognize a single human motion is easier than to link several human motions. This is because several human motions move different directions, while a single human motion moves one direction in a certain period, Therefore, we need a system that is reliable to track of several human motions in every frame. In this paper we propose a new method for human tracking systems using foot step direction with prediction formula to forecast the direction of human movement. Furthermore, an enhanced method based on particle filtering enables us to detect and track a human movement. This process can enable the system to predict which direction the object will move and also can give the signal to other cameras to aware about that the object will appear. The detail outcome and expected result are discussed in this paper.

元の言語English
ホスト出版物のタイトルProceedings of the SICE Annual Conference
ページ3344-3349
ページ数6
DOI
出版物ステータスPublished - 2008
外部発表Yes
イベントSICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology - Tokyo
継続期間: 2008 8 202008 8 22

Other

OtherSICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology
Tokyo
期間08/8/2008/8/22

Fingerprint

Security systems
Cameras

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

これを引用

Watada, J., & Musaand, Z. B. (2008). Tracking human motions for security system. : Proceedings of the SICE Annual Conference (pp. 3344-3349). [4655242] https://doi.org/10.1109/SICE.2008.4655242

Tracking human motions for security system. / Watada, Junzo; Musaand, Zalili Binti.

Proceedings of the SICE Annual Conference. 2008. p. 3344-3349 4655242.

研究成果: Conference contribution

Watada, J & Musaand, ZB 2008, Tracking human motions for security system. : Proceedings of the SICE Annual Conference., 4655242, pp. 3344-3349, SICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology, Tokyo, 08/8/20. https://doi.org/10.1109/SICE.2008.4655242
Watada J, Musaand ZB. Tracking human motions for security system. : Proceedings of the SICE Annual Conference. 2008. p. 3344-3349. 4655242 https://doi.org/10.1109/SICE.2008.4655242
Watada, Junzo ; Musaand, Zalili Binti. / Tracking human motions for security system. Proceedings of the SICE Annual Conference. 2008. pp. 3344-3349
@inproceedings{40563072106047099e74d7ed32064092,
title = "Tracking human motions for security system",
abstract = "The aim of this study is to build a prototype of a multi-camera tracking system for a security system that enables us to track several human motions at one time. In this paper two innovative methods: foot step detection method and particle filtering method. Generally, to recognize a single human motion is easier than to link several human motions. This is because several human motions move different directions, while a single human motion moves one direction in a certain period, Therefore, we need a system that is reliable to track of several human motions in every frame. In this paper we propose a new method for human tracking systems using foot step direction with prediction formula to forecast the direction of human movement. Furthermore, an enhanced method based on particle filtering enables us to detect and track a human movement. This process can enable the system to predict which direction the object will move and also can give the signal to other cameras to aware about that the object will appear. The detail outcome and expected result are discussed in this paper.",
keywords = "Detection, Hhuman behavior, Human tracking, Object representation, Particle filter, Security system, Tracking, Tracking system",
author = "Junzo Watada and Musaand, {Zalili Binti}",
year = "2008",
doi = "10.1109/SICE.2008.4655242",
language = "English",
isbn = "9784907764296",
pages = "3344--3349",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Tracking human motions for security system

AU - Watada, Junzo

AU - Musaand, Zalili Binti

PY - 2008

Y1 - 2008

N2 - The aim of this study is to build a prototype of a multi-camera tracking system for a security system that enables us to track several human motions at one time. In this paper two innovative methods: foot step detection method and particle filtering method. Generally, to recognize a single human motion is easier than to link several human motions. This is because several human motions move different directions, while a single human motion moves one direction in a certain period, Therefore, we need a system that is reliable to track of several human motions in every frame. In this paper we propose a new method for human tracking systems using foot step direction with prediction formula to forecast the direction of human movement. Furthermore, an enhanced method based on particle filtering enables us to detect and track a human movement. This process can enable the system to predict which direction the object will move and also can give the signal to other cameras to aware about that the object will appear. The detail outcome and expected result are discussed in this paper.

AB - The aim of this study is to build a prototype of a multi-camera tracking system for a security system that enables us to track several human motions at one time. In this paper two innovative methods: foot step detection method and particle filtering method. Generally, to recognize a single human motion is easier than to link several human motions. This is because several human motions move different directions, while a single human motion moves one direction in a certain period, Therefore, we need a system that is reliable to track of several human motions in every frame. In this paper we propose a new method for human tracking systems using foot step direction with prediction formula to forecast the direction of human movement. Furthermore, an enhanced method based on particle filtering enables us to detect and track a human movement. This process can enable the system to predict which direction the object will move and also can give the signal to other cameras to aware about that the object will appear. The detail outcome and expected result are discussed in this paper.

KW - Detection

KW - Hhuman behavior

KW - Human tracking

KW - Object representation

KW - Particle filter

KW - Security system

KW - Tracking

KW - Tracking system

UR - http://www.scopus.com/inward/record.url?scp=56849109128&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56849109128&partnerID=8YFLogxK

U2 - 10.1109/SICE.2008.4655242

DO - 10.1109/SICE.2008.4655242

M3 - Conference contribution

AN - SCOPUS:56849109128

SN - 9784907764296

SP - 3344

EP - 3349

BT - Proceedings of the SICE Annual Conference

ER -