Simultaneous 3D Shape and Multi-view Silhouette Estimation with Error Detection and Correction by Spatiotemporal Constraints

Research Project

Project/Area Number	23700204
Research Category	Grant-in-Aid for Young Scientists (B)
Allocation Type	Multi-year Fund
Research Field	Perception information processing/Intelligent robotics
Research Institution	Kyoto University
Principal Investigator	NOBUHARA Shohei 京都大学, 大学院・情報学研究科, 講師 (00423020)
Project Period (FY)	2011 – 2012
Project Status	Completed (Fiscal Year 2012)
Budget Amount *help	¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000) Fiscal Year 2012: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000) Fiscal Year 2011: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Keywords	多視点画像 / 対象領域抽出 / 3次元形状 / 3次元ビデオ / 多視点映像処理 / ３次元形状・運動復元 / ３次元形状復元
Research Abstract	This research proposed a new algorithm utilizing spatiotemporal multiple-view consistency among the 3D shape and its silhouettes of a single object. The key contribution is the computational model to make the estimation robust against uncontrolled real world. In addition, this research proposed a new novel-view synthesis algorithm which well suits for such real-world environment.