| Presentation | 2021-03-04 Leveraging Human Pose Estimation Model for Sports Video Classification Soichiro Sato, Masaki Aono, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a motion classification method of sports videos based on a posture estimation model.Specifically, we introduced features to estimate the coordinates of 17 types of human skeletons, representing the transition of the estimated coordinates, which in turn were generated by PoseNet. In addition to this, we cropped the video frames based on the estimated coordinates of the skeleton were used as input to several DNN models that extended the conventional models. The proposed method for motion classification based on this posture estimation model was applied to the data provided by the MediaEval2020 Sports Video Classification task. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Video Action Recognition / Human Pose Estimation / Deep Learning / 3D CNN |
| Paper # | PRMU2020-76 |
| Date of Issue | 2021-02-25 (PRMU) |
| Conference Information | |
| Committee | PRMU / IPSJ-CVIM |
|---|---|
| Conference Date | 2021/3/4(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Computer Vision and Pattern Recognition for specific environment |
| Chair | Yoichi Sato(Univ. of Tokyo) |
| Vice Chair | Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.) |
| Secretary | Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.) |
| Assistant | Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Leveraging Human Pose Estimation Model for Sports Video Classification |
| Sub Title (in English) | |
| Keyword(1) | Video Action Recognition |
| Keyword(2) | Human Pose Estimation |
| Keyword(3) | Deep Learning |
| Keyword(4) | 3D CNN |
| 1st Author's Name | Soichiro Sato |
| 1st Author's Affiliation | Toyohashi University of Technology(TUT) |
| 2nd Author's Name | Masaki Aono |
| 2nd Author's Affiliation | Toyohashi University of Technology(TUT) |
| Date | 2021-03-04 |
| Paper # | PRMU2020-76 |
| Volume (vol) | vol.120 |
| Number (no) | PRMU-409 |
| Page | pp.pp.41-46(PRMU), |
| #Pages | 6 |
| Date of Issue | 2021-02-25 (PRMU) |