Presentation 2012-08-18
Posture identification for evaluation of multi-party interaction
Kazuaki KOMATSU, Kazutaka SHIMADA, Tsutomu ENDO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The goal of our study is to understand a user's state in multi-party conversation. To realize the task, we need to estimate the state of user's mind. There are many approaches to estimate the state: use of verbal information and non-varbal information such as posture and gesture. In this paper, we propose a method for posture estimation. Characteristics of our method are (1) use of a top-view image and (2) use of depth information. Using top-view images solves a problem of occlusion. Using depth information reduces mistakes for detection of a person area and is effective for extracting features. We apply seven features, such as depth histogram and body information to the Adaboost algorithm. Experimental results show the effectiveness of our method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Non-verbal information / Posture estimation / Top-view camera / Depth information / Depth sensor
Paper # HCS2012-37
Date of Issue

Conference Information
Committee HCS
Conference Date 2012/8/11(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 Human Communication Science (HCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Posture identification for evaluation of multi-party interaction
Sub Title (in English)
Keyword(1) Non-verbal information
Keyword(2) Posture estimation
Keyword(3) Top-view camera
Keyword(4) Depth information
Keyword(5) Depth sensor
1st Author's Name Kazuaki KOMATSU
1st Author's Affiliation Kyushu Institute of Technology()
2nd Author's Name Kazutaka SHIMADA
2nd Author's Affiliation Kyushu Institute of Technology
3rd Author's Name Tsutomu ENDO
3rd Author's Affiliation Kyushu Institute of Technology
Date 2012-08-18
Paper # HCS2012-37
Volume (vol) vol.112
Number (no) 176
Page pp.pp.-
#Pages 6
Date of Issue