| Project/Area Number |
24500239
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Oita University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2012-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2012: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
|
|---|
| Keywords | 局所特徴量 / 射影不変性 / 自動撮影 / 自動編集 / 試合状況抽出 / 映像コンテンツ生成 / テンプレート照合 / 背景差分 / 強化学習 / 射影変換 / 正規化ヒストグラム / 物体追跡 / 物体認識 / 超解像度 |
|---|
| Outline of Final Research Achievements |
In spite of we are acquiring a lot of benefit of the advanced technology in video and computer processing, Any automatic video content summarization system for sport game is not appeared. We aim to design an automatic method of game recognition, capturing various scenes by robot cameras and video content summarization. Through the processing series from the game recognition to the video summarization, we researched the following methods. In game recognition, (1) we measured the projectivity of local descriptor to contribute the recognition, and (2) we extended the traditional background subtraction to moving camera. In the automatic capturing, we also developed (3) a camera parameter generation method to control the robot cameras and (4) a machine learning method to learn the relationship between video scene composition, camera parameters and the four-part video story structure such as introduction, development, turn, and conclusion.
|
