| Presentation | 2015-03-19 Articulated pose estimation from ego-centric vision for action recognition Haruka YONEMOTO, Kazuhiko MURASAKI, Tatsuya OSAWA, Kyoko SUDO, Jun SHIMAMURA, Yukinobu TANIGUCHI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we present a novel method to estimate articulated human pose for ego-centric action recognition. Many researches of action recognition from third-person vision have shown that articulated human pose is a feature which directly dscribes human motion, and is invaliant to the view from camera. However, they assume the whole figure of subjects appears in the image and ,in our best knowlege, no method for estimating articulated pose from ego-centric vision is proposed. Our method can extract the pose by integrating hand detection, camera pose estimation, and time-series filtering with the constraint of body shape. The experimental evaluations show that joint positions are correctly estimated even though they do not appear in the image, and that the accuracy of action recognition is improved through motion features based on estimated poses compared with motion features extracted from only hand position in the image. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | action recognition / articulated pose estimation / ego-centric vision |
| Paper # | BioX2014-56,PRMU2014-176 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2015/3/12(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 | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Articulated pose estimation from ego-centric vision for action recognition |
| Sub Title (in English) | |
| Keyword(1) | action recognition |
| Keyword(2) | articulated pose estimation |
| Keyword(3) | ego-centric vision |
| 1st Author's Name | Haruka YONEMOTO |
| 1st Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION, NTT Media Intelligence Laboratories() |
| 2nd Author's Name | Kazuhiko MURASAKI |
| 2nd Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION, NTT Media Intelligence Laboratories |
| 3rd Author's Name | Tatsuya OSAWA |
| 3rd Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION, NTT Media Intelligence Laboratories |
| 4th Author's Name | Kyoko SUDO |
| 4th Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION, NTT Media Intelligence Laboratories |
| 5th Author's Name | Jun SHIMAMURA |
| 5th Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION, NTT Media Intelligence Laboratories |
| 6th Author's Name | Yukinobu TANIGUCHI |
| 6th Author's Affiliation | NIPPON TELEGRAPH AND TELEPHONE CORPORATION, NTT Media Intelligence Laboratories |
| Date | 2015-03-19 |
| Paper # | BioX2014-56,PRMU2014-176 |
| Volume (vol) | vol.114 |
| Number (no) | 521 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |