Presentation | 2007-11-29 Improvement in Robustness of Vision-based Real-time Human Posture Analysis Using Incremental Learnable Self-Organizing Map Atsushi SHIMADA, Madoka KANOUCHI, Daisaku ARITA, Rin-ichiro TANIGUCHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose an approach to improve the accuracy of estimating feature points of human body on a vision-based motion capture system (MCS) by using the Variable-density Self-Organizing Map (VDSOM). The VDSOM is a kind of Self-Organizing Map (SOM) and is incremental learnable model. We let VDSOM learn 3-D feature points of human body when the MCS succeeded in estimating them correctly. Three abilities are required for the SOM in this case; 1) The ability to learn training data sequentially, 2) the ability to create a lot of patterns from a few number of training sample, 3) the ability to correlate the feature points of each body part in learning. The VDSOM is very effective for these issues. On the other hand, one or more than one 3-D feature point could not estimated correctly, we use the VDSOM for the other purpose. The SOM including VDSOM has an ability to recall a part of weight vector which have learned in the learning process. We use this ability to recall missing feature points. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Self-Organizing Map / Vision-Based Motion Capture System / Incremental Learning / Recall |
Paper # | PRMU2007-129,MVE2007-62 |
Date of Issue |
Conference Information | |
Committee | MVE |
---|---|
Conference Date | 2007/11/22(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 | Media Experience and Virtual Environment (MVE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Improvement in Robustness of Vision-based Real-time Human Posture Analysis Using Incremental Learnable Self-Organizing Map |
Sub Title (in English) | |
Keyword(1) | Self-Organizing Map |
Keyword(2) | Vision-Based Motion Capture System |
Keyword(3) | Incremental Learning |
Keyword(4) | Recall |
1st Author's Name | Atsushi SHIMADA |
1st Author's Affiliation | Department of Intelligent Systems, Kyushu University() |
2nd Author's Name | Madoka KANOUCHI |
2nd Author's Affiliation | Department of Electrical Engineering and Computer Science, Kyushu University |
3rd Author's Name | Daisaku ARITA |
3rd Author's Affiliation | Institute of Systems & Information Technologies KYUSHU |
4th Author's Name | Rin-ichiro TANIGUCHI |
4th Author's Affiliation | Department of Intelligent Systems, Kyushu University |
Date | 2007-11-29 |
Paper # | PRMU2007-129,MVE2007-62 |
Volume (vol) | vol.107 |
Number (no) | 360 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |