Modelling Object Manipulation from Shape, Motion and Context in Video
| Project/Area Number |
21700224
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
OGAWARA Koichi Kyushu University, 工学系研究院, 特任准教授 (70452810)
|
|---|
| Project Period (FY) |
2009 – 2010
|
| Project Status |
Completed (Fiscal Year 2010)
|
| Budget Amount *help |
¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2010: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2009: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | インテリジェントルーム / 知能ロボティックス / 画像、文章、音声等認識 / ユーザインターフェース |
|---|
| Research Abstract |
Partly Locality Sensitive Hashing is proposed to efficiently extract frequent patterns from motion capture data or video so as to train recognizers automatically. The 3D shape and articulation of unknown objects found in frequent patterns are also recovered based on the variant of SFM methods. As a result, manipulation tasks can be trained and recognized from video in an unsupervised way.
|
Report
(3 results)
Research Products
(24 results)
