Adaptive Multiple Camera Calibration
General Info
Thesis by: Amin AboueeAdvisor: Professor Nassir Navab
Supervision by: Yuji Oyamada, Alexandru Duliu
Contact: Yuji Oyamada, Alexandru Duliu
Status: finished
Motivation
 | Multiple Camera calibration is similar to single camera calibration, the main difference being that the affine transformation between all possible pairs of cameras in each frame is considered rigid. This type of calibration is especially challenging in setups where the cameras do not have a good overlap in their fields of view and as such the calibration pattern cannot be seen by all of them. The standard chessboard calibration pattern is ill suited for calibrating multiple cameras, as its detection requires that the entire pattern be visible by the camera. Random Dot Markers have been developed to enable tracking even when the calibration pattern is partially oculded or partially outside the image [4]. The recognition and tracking of the markers are based on keypoint matching using local geometrical relationship of keypoints with LLAH (Locally Likely Arrangement Hashing) [2,4]. |
Goals
Goal of this work is the implementation of a robust approach to multiple camera calibration. This type of calibration has gained significant attention in past years due to its application to 3D model recovery.References
| Author | Title | Year | Journal/Proceedings | Reftype | DOI/URL |
|---|---|---|---|---|---|
| Geiger, A. | [1] AUTOMATIC MULTIPLE CAMERA CALIBRATION USING A PLANAR CALIBRATION PATTERN</td | 2006 | School |
mastersthesis | |
| Nakai, T., Kise, K. & Iwamura, M. | [2] Use of affine invariants in locally likely arrangement hashing for camera-based document image retrieval | 2006 | Document Analysis Systems VII, pp. 541-552 | article | URL |
| Svoboda, T., Martinec, D. & Pajdla, T. | [3] A Convenient Multi-Camera Self-Calibration for Virtual Environments | 2005 | PRESENCE Vol. 14(4), pp. 407-422 |
article | |
| Uchiyama, H. & Marchand, E. | [4] Deformable random dot markers | 2011 | Mixed and Augmented Reality (ISMAR), 2011 10th IEEE International Symposium on, pp. 237-238 | inproceedings | URL |
| Uchiyama, H. & Saito, H. | [5] Random dot markers | 2011 | Virtual Reality Conference (VR), 2011 IEEE, pp. 35-38 | inproceedings | URL |
| Students.ProjectForm | |
|---|---|
| Title: | Adaptive Multiple Camera Calibration |
| Abstract: | Goal of this work is the implementation of a robust approach to multiple camera calibration. This type of calibration has gained significant attention in past years due to its application to 3D model recovery. |
| Student: | Amin Abouee |
| Director: | Professor Nassir Navab |
| Supervisor: | Yuji Oyamada, Alexandru Duliu |
| Type: | IDP/Klinisches Anwendungsprojekt |
| Area: | Registration / Visualization, Computer Vision |
| Status: | finished |
| Start: | |
| Finish: | |
| Thesis (optional): | |
| Picture: | |