Realization of high function of free-viewpoint TV using a small number of non-calibrated cameras
| Project/Area Number |
23500220
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | The University of Aizu |
|---|
Principal Investigator |
OKA Ryuichi 会津大学, コンピュータ理工学部, その他 (60347242)
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2013: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2012: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2011: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | シーン理解 / 3次元復元 / 画像マッチング / 動作理解 / 動くカメラ / DP / 3次元画像復元 / ピクセルマッチング / カメラモデル / 実時間処理 / 対応問題 / ダイナミックプログラミング / 自由視点テレビ / ３次元画像レジストレーション / マッチング / ３次元モザイキング / 自由視点テレビ（スイス、ディズニー研究所 ） |
|---|
| Research Abstract |
Technology for free-viewpoint TV using a small number of non-calibrated cameras is available to realize the 3D reconstruction of scene using a single and moving camera. We realized this technology based on two algorithms: two-dimensional Continuous Dynamic Programming (proposed R.Oka etc) for full pixel and optimal matching between two images captured by a single camera, and factorization
(proposed by T.Kanade etc). In order to more advanced recognition of a scene, we developed a method for recognizing moving objects in a scene by a motion image captured by a moving camera. These developed two algorithms reveled a new paradigm of scene understanding.
|
Report
(4 results)
Research Products
(35 results)
