Presentation 2008-05-22
Identifying a Moving Object with an Accelerometer in a Stationary Camera View
Osamu SHIGETA, Shingo KAGAMI, Koichi HASHIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a method for identifying an object with an accelerometer from many moving objects in a camera view. The camera and the accelerometer are connected with a network but not synchronized. To evaluate correlation despite the unknown time lag between them, NCC (Normalized Cross-Correlation) of the signals is computed. Since the coordinate system of the accelerometer is unknown, NCC is computed for the norms of the acceleration vectors, which are compensated for the gravitational acceleration component beforehand, obtained by the camera and the accelerometer. The experimental results show the proposed method successfully identified the person wearing the accelerometer from three walking people.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Sensor Fusion / Image Processing / Accelerometer / Normalized Cross-Correlation / Sequential Bayesian Estimation
Paper # USN2008-3
Date of Issue

Conference Information
Committee USN
Conference Date 2008/5/15(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 Ubiquitous and Sensor Networks(USN)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Identifying a Moving Object with an Accelerometer in a Stationary Camera View
Sub Title (in English)
Keyword(1) Sensor Fusion
Keyword(2) Image Processing
Keyword(3) Accelerometer
Keyword(4) Normalized Cross-Correlation
Keyword(5) Sequential Bayesian Estimation
1st Author's Name Osamu SHIGETA
1st Author's Affiliation Graduate School of Information Sciences, Tohoku University()
2nd Author's Name Shingo KAGAMI
2nd Author's Affiliation Graduate School of Information Sciences, Tohoku University
3rd Author's Name Koichi HASHIMOTO
3rd Author's Affiliation Graduate School of Information Sciences, Tohoku University
Date 2008-05-22
Paper # USN2008-3
Volume (vol) vol.108
Number (no) 43
Page pp.pp.-
#Pages 6
Date of Issue