Meeting room configuration and multiple camera calibration in meeting analysis
ICMI '05 Proceedings of the 7th international conference on Multimodal interfaces
3D head position estimation using a single omnidirectional camera for non-intrusive iris recognition
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
Hybrid camera surveillance system by using stereo omni-directional system and robust human detection
PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Self-calibration of hybrid central catadioptric and perspective cameras
Computer Vision and Image Understanding
| Hi-index | 0.00 |
Visual surveillance using a camera network has imposed newchallenges to camera calibration. An essential problem is that alarge number of cameras may not have a common field of view or evenbe synchronized well. We propose to use a hybrid camera networkthat consists of catadioptric and perspective cameras for a visualsurveillance task. The relations between multiple views of a scenecaptured from different cameras can be then calibrated under thecatadioptric camera's coordinate system. This paper addresses theimportant issue of how to calibrate the hybrid camera network. Wecalibrate the hybrid camera network in three steps. First, wecalibrate the catadioptric camera using only the vanishing points.In order to reduce computational complexity, we calibrate thecamera without the mirror first and then calibrate the catadioptriccamera system. Second, we determine 3D positions of some pointsusingas few as two spatial parallel lines and some equidistancepoints. Finally, we calibrate other perspective cameras based onthese known spatial points.