| Project/Area Number |
17500059
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
ONAI Rikio The University of Electro-Communications, Faculty of Electro-Communications, Professor, 電気通信学部, 教授 (70323871)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TAKEUCHI Ikuo The University of Tokyo, Graduate School of Information Science and Technology, Professor, 大学院情報理工学系研究科, 教授 (90293109)
TADA Yoshikatu The University of Electro-Communications, Graduate School of Information Systems, Professor, 大学院情報システム学研究科, 教授 (30179709)
KOIKE Hideki The University of Electro-Communications, Graduate School of Information Systems, Professor, 大学院情報システム学研究科, 教授 (70234664)
INAMI Masahiko The University of Electro-Communications, Faculty of Electro-Communications, Professor, 電気通信学部, 教授 (00345117)
HAYASHI Takahiro The University of Electro-Communications, Faculty of Electro-Communications, Assistant, 電気通信学部, 助手 (60342490)
|
|---|
| Project Period (FY) |
2005 – 2006
|
| Project Status |
Completed (Fiscal Year 2006)
|
| Budget Amount *help |
¥3,400,000 (Direct Cost: ¥3,400,000)
Fiscal Year 2006: ¥1,700,000 (Direct Cost: ¥1,700,000)
Fiscal Year 2005: ¥1,700,000 (Direct Cost: ¥1,700,000)
|
|---|
| Keywords | Information Systems / Image Analysis / ソフトウェア工学 / ディレクトリ・情報検索 |
|---|
| Research Abstract |
To use the image and data effectively acquired by the image sensor developed for the team play sports image analysis, we developed the new image interface using past-images with spherical vision system. The past images were taken using the omnidirectional camera installed in the movable body. We can get virtual viewpoint from the third party by drawing the model of the movable body on the past image. It was confirmed that we can analyze the omnidirectional image based on the player's action even if the complex action of many objects like team play sports.
As research for classification of team play sports images, we researched a novel object extraction from 2D vector images. We have proposed a novel object extraction method using merits of vector images. The proposed method analyzes relations between individual primitives of vector images and the regions defined by these primitives. According to the analysis, a set of primitives defining object region is detected. We have compared accuracy and speed performance between the proposed method and ACM(Active Contour Model), which is a traditional raster-based object extraction method. Experimental results have shown that the proposed method has higher accuracy and speed performance than ACM.
The element technology of comparing standard data base with player' s action was researched by using the markers and the acceleration sensors to support the practice of specific actions in sports. We, tried to develop more adequate grading system by adding the acceleration sensor to the grading system of action only of markers in this research. The effect of the introduction of the acceleration sensors was confirmed by the evaluation experiment.
|
