초록 ▼

A system for automatically expanding the zoom capability of a wide-angle video camera using images from multiple camera locations. One preferred embodiment achieves this using images from the wide-angle video camera that are analyzed to identify regions of interest (RoI). Pan-Tilt-Zoom (PTZ) control

A system for automatically expanding the zoom capability of a wide-angle video camera using images from multiple camera locations. One preferred embodiment achieves this using images from the wide-angle video camera that are analyzed to identify regions of interest (RoI). Pan-Tilt-Zoom (PTZ) controls are then sent to aim slave cameras toward the RoI. Processing circuitry is then used to replace the RoI from the wide-angle images with the higher-resolution images from one of the slave cameras. In addition, motion-detecting software can be utilized to automatically detect, track, and/or zoom in on moving objects.

대표청구항 ▼

1. A video camera system comprising: at least one first video camera capturing a wide angle image, a virtual camera image being an automatically extracted portion of specified direction and size within and smaller than said wide angle image; andat least one physically steerable second video camera c

1. A video camera system comprising: at least one first video camera capturing a wide angle image, a virtual camera image being an automatically extracted portion of specified direction and size within and smaller than said wide angle image; andat least one physically steerable second video camera capturing a second camera image, a region viewable by said second video camera at least partially overlapping with a region viewable by said first video camera, said second video camera being automatically steered in at least partial dependence on said direction;wherein a portion of said second camera image at least partially matching a region shown by said virtual camera image replaces said matching region shown by said virtual camera image to produce a single output image. 2. The system of claim 1, wherein said virtual camera image is automatically extracted from said wide angle image by at least one of said first camera and a base station. 3. The system of claim 1, wherein said second video camera is automatically steered to improve a quality of match between said second camera image and a region of interest within said virtual camera image. 4. The system of claim 1, wherein said second camera image has a higher resolution than said virtual camera image. 5. The system of claim 1, wherein a resolution of said second camera image is adjusted based at least partially on an output resolution of a base station. 6. The system of claim 1, wherein whether said second camera image replaces said matching region is at least partially dependent on whether an object of interest is detected within said wide angle image. 7. The system of claim 1, wherein said second camera is steered in at least partial dependence on a detected object of interest within said wide angle image. 8. The system of claim 1, wherein, prior to display of said output image, distortion correction is performed on at least one of said wide angle image, said virtual camera image, said second camera image and said output image. 9. The system of claim 1, wherein whether said second camera image replaces said matching region is at least partially dependent on whether said second camera image has a higher resolution than said matching region. 10. A video generating method comprising: capturing a wide angle image using at least one first video camera, a virtual camera image being an automatically extracted portion of specified direction and size within and smaller than said wide angle image; andcapturing a second camera image using at least one physically steerable second video camera, a region viewable by said second video camera at least partially overlapping with a region viewable by said first video camera, said second video camera being automatically steered in at least partial dependence on said direction;wherein a portion of said second camera image at least partially matching a region shown by said virtual camera image replaces said matching region shown by said virtual camera image to produce a single output image. 11. The method of claim 10, wherein said virtual camera image is automatically extracted from said wide angle image by at least one of said first camera and a base station. 12. The method of claim 10, wherein said second video camera is automatically steered to improve a quality of match between said second camera image and a region of interest within said virtual camera image. 13. The method of claim 10, wherein said second camera image has a higher resolution than said virtual camera image. 14. The method of claim 10, wherein a resolution of said second camera image is adjusted based at least partially on an output resolution of a base station. 15. The method of claim 10, wherein whether said second camera image replaces said matching region is at least partially dependent on whether an object of interest is detected within said wide angle image. 16. The method of claim 10, wherein said second camera is steered in at least partial dependence on a detected object of interest within said wide angle image. 17. The method of claim 10, wherein, prior to display of said output image, distortion correction is performed on at least one of said wide angle image, said virtual camera image, said second camera image and said output image. 18. The method of claim 10, wherein whether said second camera image replaces said matching region is at least partially dependent on whether said second camera image has a higher resolution than said matching region. 19. The method of claim 10, wherein said second camera is zoomed out if a region of interest in said virtual camera image is moving and is zoomed in if said region of interest slows or stops moving. 20. A computer-readable medium having stored thereon instructions that, when executed, direct a computing apparatus to: capture a wide angle image using at least one first video camera, a virtual camera image being an automatically extracted portion of specified direction and size within and smaller than said wide angle image; andcapture a second camera image using at least one physically steerable second video camera, a region viewable by said second video camera at least partially overlapping with a region viewable by said first video camera, said second video camera being automatically steered in at least partial dependence on said direction;wherein a portion of said second camera image at least partially matching a region shown by said virtual camera image replaces said matching region shown by said virtual camera image to produce a single output image.