Optimal camera selection in array of monitoring cameras
View Patent ↗Technologies are generally described for automatically optimizing an efficiency of camera placement, numbers, and resolution in multi-camera monitoring and surveillance applications. In some examples, a fraction of a total area may be monitored at a higher resolution than the rest. Employing techniques such as combinatorial state Viterbi technique or combinatorial state trellis technique, a minimum number of cameras that provide the coverage at the needed resolution may be selected. Similarly, a number of points may be covered with at least a predefined number of cameras. For example, a subject of interest may be tracked in a public area, where specific camera(s) may be used to image the subject's face at a higher resolution than the background.
1. A method executed on a computing device to optimize an efficiency of camera placement, numbers of cameras, and resolution associated with each of the cameras in a multi-camera monitoring system, the method comprising:
determining a maximum resolution matrix,
wherein elements of the maximum resolution matrix represent a maximum resolution with which each of the cameras are capable to monitor a distinct coverage area along a linear axis in the multi-camera monitoring system, and
wherein the distinct coverage area is defined by a length of coverage along the linear axis in the multi-camera monitoring system;
receiving a desired resolution vector, wherein each element of the desired resolution vector represents a desired resolution for each of the cameras in the multi-camera monitoring system;
determining whether any of the cameras violate a resolution consistency with one or more other cameras while monitoring the distinct coverage area in the multi-camera monitoring system;
excluding any of the cameras from the multi-camera monitoring system that violate the resolution consistency; and
performing a discrete optimization to determine an optimal camera from the cameras with a reduced resolution error by:
evaluating the elements of the maximum resolution matrix in view of the desired resolution vector to:
compute a cost function to scan the coverage area for each of the cameras as a product of the desired resolution for each of the cameras and the length of coverage along the linear axis in the multi-camera monitoring system; and
determine the optimal camera from the cameras and an optimal resolution based on the cost function, wherein the cost function includes at least a resolution error that is assigned to each of the cameras; and
minimizing the assigned resolution error by:
switching on a camera in response to a detection of a first resolution coverage of the cameras; and
switching off the camera in response to a detection of a second resolution coverage of the cameras, wherein the first resolution coverage of the cameras is greater than the second resolution coverage of the cameras.
2. The method according to claim 1 , further comprising:
evaluating the elements of the maximum resolution matrix in view of a weighting parameter for the cost function.
3. The method according to claim 2 , further comprising:
linearly combining a number of a cost of the cameras and a resolution cost error with the weighting parameter to determine a total cost.
4. The method according to claim 3 , further comprising:
minimizing the total cost to determine the optimal camera and the optimal resolution for each point in the multi-camera monitoring system.
5. A computing device operable to optimize an efficiency of camera placement, numbers of cameras, and a resolution associated with each of the cameras in a multi-camera monitoring system, the computing device comprising:
a memory configured to store instructions;
an input device configured to receive a desired resolution vector, wherein elements of the desired resolution vector represent a desired resolution for each of the cameras in the multi-camera monitoring system; and
a processor configured to:
determine a maximum resolution matrix,
wherein each element of the maximum resolution matrix represents a maximum resolution with which each of the cameras are capable to monitor a distinct coverage area along a linear axis in the multi-camera monitoring system, and
wherein the distinct coverage area is defined by a length of coverage along the linear axis in the multi-camera monitoring system;
determine whether any of the cameras violate a resolution consistency with one or more other cameras while monitoring the distinct coverage area in the multi-camera monitoring system;
exclude any of the cameras from the multi-camera monitoring system that violate the resolution consistency; and
perform a discrete optimization to determine an optimal camera from the cameras with a reduced resolution error by a process to:
evaluate the elements of the maximum resolution matrix in view of the desired resolution vector to:
compute a cost function to scan the coverage area for each of the cameras as a product of the desired resolution for each of the cameras and the length of coverage along the linear axis in the multi-camera monitoring system; and
determine the optimal camera from the cameras and an optimal resolution based on the cost function, wherein the cost function includes at least a resolution error that is assigned to each of the cameras; and
minimize the assigned resolution error by a process to:
switch on a camera in response to a detection of a first resolution coverage of the cameras; and
switch off the camera in response to a detection of a second resolution coverage of the cameras, wherein the first resolution coverage of the cameras is greater than the second resolution coverage of the cameras.
6. The computing device according to claim 5 , wherein the processor is further configured to:
employ a greedy technique to minimize a total cost iteratively.
7. The computing device according to claim 6 , wherein the processor is further configured to:
select another camera from the cameras and assign another resolution to the other camera from the cameras such that the other camera and the other resolution impose a largest reduction on the total cost at each iteration; and
continue the iterations until no other camera from the cameras or resolution selection decreases the cost function.
8. The computing device according to claim 5 , wherein each resolution represents a level of zoom.
9. The method of claim 1 , further comprising:
employing a greedy technique to minimize a total cost iteratively;
selecting another camera from the cameras and assigning another resolution to the other camera from the cameras such that the other camera and the other resolution impose a largest reduction on the total cost at each iteration; and
continuing the iterations until no other camera or resolution selection decreases his cost function.
10. The method of claim 1 , wherein each of the cameras includes one of: a single resolution camera, a multi-resolution camera, a multidirectional camera, a multi-resolution/multidirectional camera, and a pan-tilt-zoom (PTZ) camera.
11. The computing device of claim 5 , wherein the processor is further configured to:
evaluate the elements of the maximum resolution matrix in view of a weighting parameter for the cost function; and
linearly combine a number of a cost of each of the cameras and a resolution cost error with the weighting parameter to determine a total cost.
12. The computing device of claim 11 , wherein the processor is further configured to:
minimize the total cost to determine the optimal camera and the optimal resolution for each point in the multi-camera monitoring system.