Insight-driven augmented auto-coordination of multiple video streams for centralized processors
A method of providing video feeds from a plurality of cameras to a plurality of screens including determining a plurality of constraints on a centralized processor processing the video feeds, determining a camera semantic classification for each of the plurality of cameras, determining historical events captured by each of the plurality of cameras, and providing at least one video feed to at least one of the screens according to the plurality of constraints on the centralized processor, the camera semantic classifications and the historical events.
1. A method of providing video feeds from a plurality of cameras to a plurality of screens comprising:
determining a plurality of constraints on a centralized processor processing the video feeds;
determining a camera semantic classification for each of the plurality of cameras by assigning a plurality of semantic tags to describe a plurality of expected scenes of the plurality of cameras;
determining a plurality of historical events captured by each of the plurality of cameras;
providing at least one video feed from the plurality of cameras to at least one of the screens according to the plurality of constraints on the centralized processor, the camera semantic classifications and the historical events,
generating a plurality of camera groups according to the plurality of semantic tags; and
assigning an importance score to each of the plurality of camera groups, wherein the importance scores are determined based on an average number of events detected per camera for each of the plurality of camera groups and a parameterization of a configuration of the plurality of screens and an event risk of each of the plurality of camera groups.
2. The method of claim 1 , further comprising determining the importance score for each of the plurality of cameras.
3. The method of claim 2 , wherein the importance score is determined according to historic data of event capture.
4. The method of claim 1 , further comprising parameterizing the plurality of constraints according to a preference.
5. The method of claim 4 , wherein parameterizing the plurality of constraints further comprises organizing the plurality of constraints by resource unit, wherein the centralized processor comprises a plurality of resource units, and wherein each of the plurality of resource units is associated with an importance ranking.
6. The method of claim 5 , wherein the organizing includes an assignment one or more of the plurality of cameras to each of the resource units of the centralized processor according to importance scores assigned to the plurality of cameras and the importance rankings of the resource units, wherein each of the centralized processors is associated with a respective one of the plurality screens.
7. The method of claim 1 , further comprising generating a hierarchical tree organizing the plurality of semantic tags.
8. The method of claim 1 , wherein providing the at least one video feed to the at least one of the screens comprises generating an event camera linkage, wherein the event camera linkage is a spatial relationship between an event and a camera of the plurality of cameras.
9. A computer program product for providing video feeds from a plurality of cameras to a plurality of screens, the computer program product comprising:
a non-transitory computer readable storage medium storing the computer program product and having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code configured to determine a plurality of constraints on a centralized processor processing the video feeds;
computer readable program code configured to determine a camera semantic classification for each of the plurality of cameras;
computer readable program code configured to assign a plurality of semantic tags to describe a plurality of expected scenes of the plurality of cameras;
computer readable program code configured to determine a plurality of historical events captured by each of the plurality of cameras;
computer readable program code configured to provide at least one video feed from the plurality of cameras to at least one of the screens according to the plurality of constraints on the centralized processor, the camera semantic classifications and the historical events;
computer readable program code configured to generate a plurality of camera groups according to the plurality of semantic tags; and
computer readable program code configured to assign an importance score to each of the plurality of camera groups, wherein the importance scores are determined based on an average number of events detected per camera for each of the plurality of camera groups,
wherein the importance scores are based on a parameterization of a configuration of the plurality of screens and an event risk of each of the plurality of camera groups.
10. The computer program product of claim 9 , further comprising computer readable program code configured to determine the importance score for each of the plurality of cameras.
11. The computer program product of claim 9 , further comprising computer readable program code configured to determine parameterize the plurality of constraints according to a preference.
12. The computer program product of claim 11 , wherein parameterizing the plurality of constraints further comprises organizing the plurality of constraints by resource unit, wherein the centralized processor comprises a plurality of resource units, and wherein each of the plurality of resource units is associated with an importance ranking.
13. The computer program product of claim 12 , wherein the organizing includes an assignment one or more of the plurality of cameras to each of the resource units of the centralized processor according to importance scores assigned to the plurality of cameras and the importance rankings of the resource units, wherein each of the centralized processors is associated with a respective one of the plurality screens.
14. The method of claim 9 , further comprising computer readable program code configured to generate a hierarchical tree organizing the plurality of semantic tags.
15. The method of claim 9 , wherein providing the at least one video feed to the at least one of the screens comprises generating an event camera linkage, wherein the event camera linkage is a spatial relationship between an event and a camera of the plurality of cameras.
16. A system providing video feeds from a plurality of cameras to a plurality of screens comprising:
a processor basic unit determination circuit determining a plurality of constraints on a centralized processor processing the video feeds;
a camera parameterization circuit determining a camera semantic classification for each of the plurality of cameras by assigning a plurality of semantic tags to describe a plurality of expected scenes of the plurality of cameras and determining a plurality of historical events captured by each of the plurality of cameras;
an event camera linkages circuit providing at least one video feed to at least one of the screens according to the plurality of constraints on the centralized processor, the camera semantic classifications and the historical events,
generating a plurality of camera groups according to the plurality of semantic tags; and
assigning an importance score to each of the plurality of camera groups, the importance scores being determined based on an average number of events detected per camera for each of the plurality of camera groups and a parameterization of a configuration of the plurality of screens and an event risk of each of the plurality of camera groups,
wherein the centralized processor comprises a plurality of processing units, each of the processing units associated with a respective one of the plurality of screens.