Presentation 2001/2/16
Estimating Areas of Moving Objects for a Remote Surveillance System Using Omnidirectional Sensors
Masahiko Terazawa, Kazumasa Yamazawa, Haruo Takemura, Naokazu Yokoya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently demands for remote surveillance by camera are increasing. One of important factors in a remote surveillance system is to estimate positions of interesting objects. But, it is difficult to detect positions of the objects that freely move around in a wide environment. This fact suggests to use omnidirectional sensors. However, representing object's location as a point is not accurate and contains an error when the object is large enough. When the object is close to or on the baseline of multiple omnidirectional sensors, it is difficult to make precise estimation of its position. Taking these problems into consideration, we propose a method to represent an object's position as a domain or area where the object is most likely located. We also report on a surveillance system using the proposed method. The system effectively tracks multiple objects in the environment.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) remote surveillance system / omnidirectional image sensor / directional range / estimating areas
Paper # PRMU2000-195
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/2/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimating Areas of Moving Objects for a Remote Surveillance System Using Omnidirectional Sensors
Sub Title (in English)
Keyword(1) remote surveillance system
Keyword(2) omnidirectional image sensor
Keyword(3) directional range
Keyword(4) estimating areas
1st Author's Name Masahiko Terazawa
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Kazumasa Yamazawa
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Haruo Takemura
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
4th Author's Name Naokazu Yokoya
4th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2001/2/16
Paper # PRMU2000-195
Volume (vol) vol.100
Number (no) 634
Page pp.pp.-
#Pages 6
Date of Issue