Presentation 2012-07-19
Model-Based Human Activity Classification using Doppler Sensor with Support Vector Machine
Franck DIRHOLDI, Tomoaki OHTSUKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The feasibility of classifying different human activities based on micro Doppler signatures is investigated. We simulate six activities using our own human model. These activities are walking, falling, sitting down, making squats, punching, and picking up an object on the ground. We extract four features from the model generated Doppler spectrogram. We collect data from a human subject performing six activities. A support vector machine (SVM) is then trained using the data extracted from our model. We extract the same data from the Doppler spectrogram obtained during experiments. The activities are correctly detected more than 90 % of the time and falling is detected 100
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Dopler spectrogram / microDoppler / human activities / human model
Paper # USN2012-19
Date of Issue

Conference Information
Committee USN
Conference Date 2012/7/12(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Model-Based Human Activity Classification using Doppler Sensor with Support Vector Machine
Sub Title (in English)
Keyword(1) Dopler spectrogram
Keyword(2) microDoppler
Keyword(3) human activities
Keyword(4) human model
1st Author's Name Franck DIRHOLDI
1st Author's Affiliation School of Science for Open and Environmental Systems, Graduate School of Science and Technology, Keio University()
2nd Author's Name Tomoaki OHTSUKI
2nd Author's Affiliation School of Science for Open and Environmental Systems, Graduate School of Science and Technology, Keio University
Date 2012-07-19
Paper # USN2012-19
Volume (vol) vol.112
Number (no) 133
Page pp.pp.-
#Pages 6
Date of Issue