Optimization Technology of Sport Motion Analysis and Estimation System by Non-contact and Non-invasive Big Data
| Project/Area Number |
16K01647
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Sports science
|
|---|
| Research Institution | Iwate University |
|---|
Principal Investigator |
Akashi Takuya 岩手大学, 理工学部, 准教授 (50403655)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
張 潮 福井大学, 学術研究院工学系部門, 助教 (70803419)
|
|---|
| Project Period (FY) |
2016-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2016: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | スポーツ科学 / 3次元人物姿勢推定 / マルチモーダル学習 / 深層学習 / 人物スケルトンデータベース / スポーツバイオメカニクス / ヒューマンセンシング / コンピュータビジョン / 画像認識 |
|---|
| Outline of Final Research Achievements |
We have accumulated the non-contact and non-invasive sensing research up until now.
In this research, the big data obtained by these is scrutinized and the framework which determines the extraction method of data, a processing method, a contribution, etc. automatically is established. Thereby, we aim the construction of a more advanced educational foundation for an athlete's training, and use of the big data in the advanced sports science fields, such as teamwork analysis.
We achieved some results as follows, establishment of the new posture estimation technique; establishment of the multi-modal deep learning framework using different data, such as a sound and a image; discovery of the existence of the rhythm of the spontaneous brain in the neuroscience field; establishment of the tapping frequency analysis paradigm which may provide a simple and objective diagnostic tool for measuring implicit deficits of spontaneous rhythms/tempos generation.
|
| Academic Significance and Societal Importance of the Research Achievements |
一般的にコンピュータビジョン分野や市販の計測装置では単一のデータを用いる．本研究では，音声と画像など異なる複数種類のデータから構成されるビッグデータを扱う．このような量，種類，スケール（サンプリング周波数等）の異なる多数のデータを扱う手法は少ない．また，複雑なデータ処理をパラメータ化し，最適化問題として扱う試みは，独創的で，我々の知る限り例がない．また，タッピングの周波数を分析するパラダイムを提案し，パーキンソン病などの運動に影響する病気の診断にも役立つことが研究成果によって示されている．これらの成果は，スポーツ科学のみならず，他分野における今後の行動分析・推定の足掛かりになると考えられる．
|
Report
(5 results)
Research Products
(13 results)
