Development of an Intelligent desk using computer vision and augmented reality
| Project/Area Number |
11558018
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 展開研究 |
|---|
| Research Field |
Educational technology
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
KOIKE Hideki The University of Electro-Communications, Graduate School of Information Systems, Associate Professor, 大学院・情報システム学研究科, 助教授 (70234664)
|
|---|
| Project Period (FY) |
1999 – 2001
|
| Project Status |
Completed (Fiscal Year 2001)
|
| Budget Amount *help |
¥14,200,000 (Direct Cost: ¥14,200,000)
Fiscal Year 2001: ¥2,900,000 (Direct Cost: ¥2,900,000)
Fiscal Year 2000: ¥6,100,000 (Direct Cost: ¥6,100,000)
Fiscal Year 1999: ¥5,200,000 (Direct Cost: ¥5,200,000)
|
|---|
| Keywords | computer vision / perceptual user interface / angmented reality / CAI / education / hand recognition / gaze recognition / two-handed drawing |
|---|
| Research Abstract |
We developed augmented desk system, named Enhanced Desk, which smoothly integrates paper and digital information on a desk. The system provides users an intelligent environment that automatically retrieves and displays digital information corresponding to the real objects (e.g. books) on the desk by using computer vision. The system also provides users direct manipulation of digital information by using their own hands and fingers for more natural and more intuitive interaction.
We developed a novel method for real-time finger tracking on Enhanced Desk by introducing a infrared camera, pattern matching with normalized correlation, a pan-tilt camera. We extended the method from 2-D to 3-D by using multiple cameras. In order to recognize objects on Enhanced Desk, we first used 2-D barcode. However, it is sometimes difficult to attach the barcode to some objects. In order to, solve this problem, we developed a new method for interactive object registration and registration by using color information of the objects. Then we discussed the use of head pose and position for human-interaction by using real-time face tracking system.
Finally, we developed some applications on Enhanced Desk. The first application is Interactive Textbook, which is aimed at providing an effective learning environment. The second application is the Interactive Venn Diagram, which is aimed at supporting effective information retrieval. The third application is Snap Link, which enable interactive object registration and recognition. The forth application is a two-handed drawing tool on Enhanced Desk
|
Report
(4 results)
Research Products
(10 results)
