| D. Koller, G. Klinker, E. Rose, D. Breen, R. Whitaker, and M. Tuceryan. Automated camera calibration and 3d egomotion estimation for augmented reality applications. In 7th Int'l Conf. on Computer Analysis of Images and Patterns (CAIP-97), Kiel, Germany, September 10--12, 1997. |
....uses no independent tracking device, but follows a so called vision based approach, i.e. calibration information is derived solely from camera input. Many common vision based systems [10] use some kind of calibration pattern or fiducials still visible in the scene even after augmentation, e.g. [8, 16]. Other methods require manually selected control points [2] but do not use fiducials. In our approach, a metal cube with a side length of 6 cm is used that is painted with a different color on each side such that its position and orientation can be determined unambiguously. A real scene can be ....
D. Koller, G. Klinker, E. Rose, D. Breen, R. Whitaker, and M. Tuceryan. Automated camera calibration and 3D egomotion estimation for augmented reality applications. In Computer Analysis of Images and Patterns (CAIP), pages 199--206, Kiel, September 1997. Springer.
No context found.
D. Koller, G. Klinker, E. Rose, D. Breen, R. Whitaker, and M. Tuceryan. Automated camera calibration and 3d egomotion estimation for augmented reality applications. In 7th Int'l Conf. on Computer Analysis of Images and Patterns (CAIP-97), Kiel, Germany, September 10--12, 1997.
No context found.
D. Koller, G. Klinker, E. Rose, D. Breen, R. Whitaker, and M. Tuceryan. Automated Camera Calibration and 3D Egomotion Estimation for Augmented Reality Applications. 7 Int'l Conference on Computer Analysis of Images and Patterns (CAIP'97), Kiel, 1997.
.... To this end, information from two or more calibrated cameras can be combined via stereo triangulation into a consistent 3D [5] Sensor fusion techniques provide filtering schemes for adaptively combining more or less consistent information from different sensors with different sensing statistics [8, 15]. The result is a best guess of the mobile user s current location (x,y,z) and viewing direction (dx,dy,dz) 3.3. Fine Tuning on the Local Unit The hypothesized user position is then forwarded to the mobile AR unit for further fine tuning, according to the unit s own tracking capabilities ....
D. Koller, G. Klinker, E. Rose, D. Breen, R. Whitaker, and M. Tuceryan. Automated camera calibration and 3D egomotion estimation for augmented reality applications. 7 th Int'l Conference on Computer Analysis of Images and Patterns (CAIP'97), Kiel, 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC