Uncalibrated Camera Parameter Estimation Using Intrinsic Camera Parameter Database

2016 Fiscal Year Final Research Report

• Project/Area Number: 26730091
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Perceptual information processing
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: Taketomi Takafumi 奈良先端科学技術大学院大学, 情報科学研究科, 助教 (50610664)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: カメラ位置・姿勢推定 / 拡張現実感 / カメラキャリブレーション

Outline of Final Research Achievements

In this project, we developed the method for estimating intrinsic camera parameters and camera poses in the online process. In our method, we used pre-calibrated relationship between camera parameters and camera zoom values. By using our method, accurate intrinsic camera parameters and camera poses were estimeted. In addition, we also tried to achieve accurate camera pose estimation with rolling shutter camera. In our approach, camera poses for each scan line is estimated by interpolating the first and the last scanlines' camera poses. Finally, we developed augmented reality applications and evaluated them.

Free Research Field

拡張現実感