Project/Area Number |
13680456
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | Osaka Prefecture University |
Principal Investigator |
FUKUNAGA Kunio Osaka Prefecture University, Dept. of Computer and Systems Sciences, Professor, 大学院・工学研究科, 教授 (60081296)
|
Co-Investigator(Kenkyū-buntansha) |
SASHIKAWA Tadashi Mainichi Broadcasting Station Co. Ltd., Dater Center, Director of Data Center, データセンター長(研究職)
KOJIMA Atsuhiro Osaka Prefecture University, Library and Science Information Center, Research Associate, 総合情報センター, 助手 (80291607)
|
Project Period (FY) |
2001 – 2002
|
Project Status |
Completed (Fiscal Year 2002)
|
Budget Amount *help |
¥4,200,000 (Direct Cost: ¥4,200,000)
Fiscal Year 2002: ¥1,300,000 (Direct Cost: ¥1,300,000)
Fiscal Year 2001: ¥2,900,000 (Direct Cost: ¥2,900,000)
|
Keywords | Computer Vision / Production of Video Imags / Distant Learning System / Recognition of Human Motion / Video Image Processing |
Research Abstract |
High-speed digital data transmission becomes possible accompanied with the development of network techniques, and distant learning systems are developed. In this project, we propose a method of producing vivid video images of the distance learning using a computer controlled camera operation and switching of plural camera images. (1) Shooting the scene based on distribution of spatiotemporal mutual information We define spatiotemporal mutual information on the pixels of a given video image on the basis of information theory, which can be interpreted as the theoretical estimation of interested spots for human being. Using the distribution of the spatiotemporal mutual information, we propose an algorithm of computer controlled camera operation and switching of plural camera images to take vivid video images of distance learning with real time image processing. (2) Shooting the scene based on situation understanding and evaluation of video images A shooting camera system estimates actions of a teacher in front of the blackboard considering the movement of the head and the hands and written characters on a blackboard. Each camera chooses a shooting area based on the actions of the teacher, then computer controlled switching system selects the best image among plural imagss by evaluation each image.
|