| Project/Area Number |
17500132
|
|---|
| 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 | Fukuoka Institute of Technology |
|---|
Principal Investigator |
YOKOTA Masao Fukuoka Institute of Technology, Department of Information Engineering, Professor (50112313)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
小田 誠雄 福岡工業大学, 短期大学部, 教授 (10185598)
|
|---|
| Project Period (FY) |
2005 – 2007
|
| Project Status |
Completed (Fiscal Year 2007)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥270,000)
Fiscal Year 2007: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2006: ¥900,000 (Direct Cost: ¥900,000)
Fiscal Year 2005: ¥1,700,000 (Direct Cost: ¥1,700,000)
|
|---|
| Keywords | Nursery Support / Human Motion / Linguistic Understanding / Artificial Intelligence / Multimedia Understanding |
|---|
| Research Abstract |
Rapid increase of matured societies will necessarily bring a large number of handicapped people due to aging and thereby serious shortage of workers for them such as nurses, one of whose routines is to survey their actions through TV monitors in order to prevent accidents. However it is unfeasible and privacy-invasive for human workers to watch TV monitors for surveillance all day and night long. For such a purpose, certain kinds of intelligent systems can be very helpful that facilitate exploiting significant parts such as abnormal motions from video data and reporting it in natural language in real time and desirably linguistic summarization of immense amount of recorded ones.
We have proposed a methodology for systematic linguistic interpretation of human motion data based on our original semantic theory, Mental Image Directed Semantic Theory (MIDST), implemented it on the intelligent system IMAGES-M and confirmed its validity for about 40 verb concepts such as 'raise' and 'nod'. Our work's most remarkable advance to the others resides in the transparency of the description of word meanings and the processing algorithms due to the formal language L_<md>. In turn, this feature results in higher modularity of the program and higher order processing of human motion, for example, inference based on the knowledge formalized in L_<md>.
After this successful result, we have started to develop a robotic system with a good capability in natural language understanding in order to promote gentle nursery support for aged people.
|
