2012 Fiscal Year Final Research Report
Research about a human arm movement generation model and a new translation method of sign language using the model
| Project/Area Number |
22500278
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Bioinformatics/Life informatics
|
|---|
| Research Institution | Toyohashi University of Technology |
|---|
Principal Investigator |
FUKUMURA Naohiro 豊橋技術科学大学, 大学院・工学研究科, 准教授 (90293753)
|
|---|
| Project Period (FY) |
2010 – 2012
|
| Keywords | 脳型情報処理 / ヒト腕運動 / 運動規範 / 運動の知覚 / 手話翻訳 |
|---|
| Research Abstract |
Adding some via-points data, complex human arm movements are reproduced by the minimum-jerk model that is a motor planning model of a point-to-point movement. We verified the hypothesis under various conditions that the human arm movements are generated from such a series of via-points data and proposed a via-point extraction method from measured trajectory data. Moreover, we applied the hypothesis to a sign-language translation system. A few via-points were extracted from each sign-word movements based on the minimum-jerk model and a translation algorithm using these via-points information was proposed. In the translation experiments, the proposed method showed a high accuracy rate.
|
