Extraction of Silhouettes and Estimation of Extrinsic Camera Parameters Through Volume Intersection
Project/Area Number |
22500146
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Perception information processing/Intelligent robotics
|
Research Institution | Utsunomiya University |
Principal Investigator |
SHOJI Kenji 宇都宮大学, 大学院・工学研究科, 教授 (70143188)
|
Co-Investigator(Kenkyū-buntansha) |
MORI Hiroshi 宇都宮大学, 大学院・工学研究科, 助教 (80538447)
|
Project Period (FY) |
2010 – 2012
|
Project Status |
Completed (Fiscal Year 2012)
|
Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2012: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2011: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2010: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
Keywords | 視体積交差 / 画像処理 / 最適化 |
Research Abstract |
The main objective of this research is to obtain a target object shape from a set of snapshots simultaneously taken by handheld cameras with little effort. Based on a technique iterating volume intersection and projection, we proposed a method to extract silhouettes from photographs with minimal conflict and a method to optimize camera poses for volume intersection. And experimental results show that the camera placements are good when the shapes of silhouettes taken by the cameras are distinct each other and each shape is preferably complex.
|
Report
(4 results)
Research Products
(6 results)