| Project/Area Number |
18K02876
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 09070:Educational technology-related
|
|---|
| Research Institution | Kindai University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2020: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2019: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2018: ¥260,000 (Direct Cost: ¥200,000、Indirect Cost: ¥60,000)
|
|---|
| Keywords | スポーツ映像 / 映像観察支援 / 視点変更 / 視野拡大 / 敵対的生成ネットワーク / モーションキャプチャ / 観察支援 / 画像処理 / 関節認識 / ホモグラフィ変換 / カメラキャリブレーション / 協働学習 / 三次元認識 / 空手道競技 / 簡易モーションキャプチャ / タブレット端末 / ３次元位置推定 / ３次元CG / 体育協働学習 |
|---|
| Outline of Final Research Achievements |
In order to support the physical education using sport videos, we have developed two methods to facilitate video observation. The first is a method of changing the viewpoint of the sport video images by using a deep neural network for skeleton estimation and homography transformation of the competition court. This made it possible to observe the sport scenes taken from any viewpoint from a bird's-eye view. The second method is to use a generative adversarial network to expand the field of view of the video that is close-up to the player and convert it into a video of the entire court. It was confirmed that this facilitates the observation of the player's positioning and formation.
|
| Academic Significance and Societal Importance of the Research Achievements |
敵対的生成ネットワークを用いてスポーツ映像の視点や視野を変更する手法は，様々な視点や視野で撮影した競技場の画像と鳥瞰視点の画像の組み合わせを学習させた画像変換AIの実現であり，他に類を見ない成果である．また，本研究で蓄積した骨格推定技術は，体育のオンライン授業における実技評価に展開可能であることが確認でき，コロナ禍の経験を踏まえると社会的な意義が大きい．
|
