Virtual Viewpoint Image Generation from Multiple Omnidirectional Images for Navigation System
| Project/Area Number |
23700191
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | National Institute of Advanced Industrial Science and Technology (2012)
The University of Tokyo (2011) |
|---|
Principal Investigator |
BANNO Atsuhiko 独立行政法人産業技術総合研究所, 知能システム研究部門, 主任研究員 (70356187)
|
|---|
| 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: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2011: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
|
|---|
| Keywords | コンピュータビジョン / 全方位画像 / 3次元復元 / 任意視点画像 / 前景抽出 / 画像マッチング |
|---|
| Research Abstract |
In this application research, we developed an arbitrary viewpoint image generation method for navigation systems using omnidirectional image sequences. Specifically, our objectives are
(1) processing for a single video sequence
(2) multiple video sequence treatments, and
(3) a new video image sequence generation viewed from virtual viewpoints.
We generated virtual viewpoint images by reconstructing the three-dimensional environment and the camera path from the omnidirectional image sequence, and to set up a virtual camera in this virtual space. Besides them, we developed a robust 3-D reconstruc
|
Report
(3 results)
Research Products
(17 results)
