Integration of Omnidirectional and Movable Cameras for Indoor Surveillance

In this paper, an omnidirectional camera and a movable PTZ (Pan, Tilt, Zoom) camera are utilized to the proposed indoor surveillance system. The traditional foreground-background extraction method and frame difference method are combined together in this paper; the combined method not only can ignore noises generated form background subtraction and focus on moving objects but also can eliminate fragments problem of frame difference method. In the proposed surveillance system, the omnidirectional camera can trace people among the scene, and transfer the location information to the PTZ camera, which can move itself and take a zoomed image of the target. Our system is demonstrated in real image experiments.

[1]  Yasushi Yagi,et al.  Real-time human feature acquisition and human tracking by omnidirectional image sensor , 2003, Proceedings of IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI2003..

[2]  Yasushi Yagi,et al.  Face identification using an omnidirectional image sequence , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Naokazu Yokoya,et al.  Arbitrary viewpoint rendering from multiple omnidirectional images for interactive walkthroughs , 2002, Object recognition supported by user interaction for service robots.

[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]  G. Thiel Automatic CCTV surveillance-towards the VIRTUAL GUARD , 2000 .