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
|
Project Status |
Completed (Fiscal Year 2012)
|
Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2012: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2011: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2010: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
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 / ジャーク最小軌道 / トルク変化最小軌道 / 経由点 / 手話単語翻訳 / 躍度最小軌道 / ジェスチャー / 見真似運動学習 / 運動の経由点 / 経由点抽出法 / 位置と運動方向による経由点表現 |
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.
|
Report
(4 results)
Research Products
(29 results)