Extraction of 3-D coordinates from fusion of omnicamera images

Fusion of images obtained from a new type of imaging sensor called an omnicamera is considered. The omnicamera has a hemisphere field of view with a single view point. We propose using multiple omnicameras to increase the capability of a tracking or surveillance system. A method to register the coordinate systems of the two cameras is provided which uses only some landmarks in the input images. The registration also provides 3-D information about objects in the space monitored by the surveillance system. The accuracy of the 3-D information is studied. It is illustrated that there are great advantages to using multiple omnicameras instead of traditional video cameras in a surveillance system.

[1]  Takeo Kanade,et al.  Constructing virtual worlds using dense stereo , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[2]  W. Eric L. Grimson,et al.  Using adaptive tracking to classify and monitor activities in a site , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[3]  C. Qian,et al.  Frame-rate Multi-body Tracking for Surveillance , 1998 .

[4]  Naokazu Yokoya,et al.  Visual surveillance and monitoring system using an omnidirectional video camera , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[5]  Terrance E. Boult,et al.  Applications of omnidirectional imaging: multi-body tracking and remote reality , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[6]  Shree K. Nayar,et al.  Stereo with mirrors , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[7]  Shree K. Nayar,et al.  Catadioptric omnidirectional camera , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.