A Research on Impressive Content Generation Using Multiple Viewed Sport Scene.
| Project/Area Number |
19500168
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Oita University |
|---|
Principal Investigator |
OHKI Hidehiro Oita University, 工学部, 助教 (80194091)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
末田 直道 大分大学, 工学部, 教授 (40347018)
|
|---|
| Project Period (FY) |
2007 – 2009
|
| Project Status |
Completed (Fiscal Year 2009)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2009: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2008: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2007: ¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
|
|---|
| Keywords | コンピュータビジョン / 多視点トラッキング / 多視点背景差分法 / データアニメーティング / 多視点背景差分 |
|---|
| Research Abstract |
To generate a impressive content from sport game movie, we proposed three new methods as follows : (i) a multiple view background subtraction for extraction of player silhouette without storing and updating background information, (ii) a robust multiple view player position estimation for occlusion and (iii) a data animating for impressive content generation. The validity of each method was confirmed in the experiments.
|
Report
(4 results)
Research Products
(12 results)
