Presentation 2007-09-28
A Study on Waveform Extraction for Footstep Detection
Taro ISOMURA, Yuki NOMURA, Akitoshi ITAI, Hisroshi YASUKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, it is verified that a personal identification using footsteps may become possible, and they make advances in their researches on the analyzing the characteristics of footsteps and increasing effectiveness of recognition of them [1]-[4]. However, most of their researches have not been discussed with footstep under surrounding acoustic noise and they assume the starting points of footsteps are known. This paper studies the accuracy of the extraction of the footstep starting points under the noises with using signal power and kurtosis as the previous step of them.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) footstep detection / signal power / kurtosis
Paper # SIP2007-107,SIS2007-43,SP2007-69
Date of Issue

Conference Information
Committee SIS
Conference Date 2007/9/21(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Waveform Extraction for Footstep Detection
Sub Title (in English)
Keyword(1) footstep detection
Keyword(2) signal power
Keyword(3) kurtosis
1st Author's Name Taro ISOMURA
1st Author's Affiliation Gradate School of Information Science and Technology()
2nd Author's Name Yuki NOMURA
2nd Author's Affiliation Gradate School of Information Science and Technology
3rd Author's Name Akitoshi ITAI
3rd Author's Affiliation Gradate School of Information Science and Technology
4th Author's Name Hisroshi YASUKAWA
4th Author's Affiliation Gradate School of Information Science and Technology
Date 2007-09-28
Paper # SIP2007-107,SIS2007-43,SP2007-69
Volume (vol) vol.107
Number (no) 237
Page pp.pp.-
#Pages 5
Date of Issue