Device layout optimization for surveillance devices

• US 9,984,544 B2
• Filed: 02/17/2015
• Issued: 05/29/2018
• Est. Priority Date: 02/17/2015
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP SE
• Inventors: Wang, Mengjiao, Li, Wen-Syan
• Primary Examiner(s): Rahaman, Mohammed
• Application Number:
  US14/624,241
• Publication Number:
  US 20160240054A1
• Time in Patent Office: 1,197 Days
• Field of Search: None
• CPC Class Codes: G08B 13/19645 Multiple cameras, each having view on one of a plurality of scenes, e.g. multiple cameras for multi-room surveillance or for tracking an object by view hand-over
• CPC Class Codes: G08B 13/1968 Interfaces for setting up or customising the system
• CPC Class Codes: G08B 29/18 Prevention or correction of operating errors G08B29/02, G08B29/12 take precedence
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A candidate position selector determines locations for M candidate positions along pathways within an area defining potential routes for moving objects within the area. A coverage rate calculator calculates a coverage rate for a device layout of N media capture devices among the M candidate positions, including calculating the coverage rate as a ratio of the moving objects captured by the N media capture devices in the device layout to a total number of the moving objects in the area within a defined period of time. A layout selector iteratively tests different device layouts of the N media capture devices among the M candidate positions, based on corresponding coverage rates calculated by the coverage rate calculator for each tested device layout, until a termination condition is reached and a final device layout of the tested device layouts is selected.

Claims

1. A computer program product, the computer program product being tangibly embodied on a non-transitory computer-readable storage medium and comprising instructions that, when executed, are configured to cause at least one processor to:

determine M candidate positions within an area for deployment of N media capture devices, where N<

M and the N media capture devices are configured to capture data characterizing moving objects within the area;

assign the N media capture devices to N of the M candidate positions to obtain a device layout, including (M−

N) open positions;

select a selected media capture device N_S from the device layout;

calculate a set of coverage rates characterizing rates of coverage of the moving objects, each coverage rate calculated for a tested device layout in which N_S is positioned at a different one of the (M−

N) open positions;

select a coverage rate, and corresponding tested device layout, from the set of coverage rates;

iterate, including selecting a new N_S from the corresponding tested device layout and calculating a new set of coverage rates in which the new N_S is positioned at different ones of new (M−

N) open positions, to thereby obtain a new tested device layout;

terminate the iterating upon reaching a termination condition; and

select a final device layout from among all tested device layouts,

wherein the moving objects have movement patterns defined by pathways through the area, and the final device layout is selected based on the movement patterns and the pathways, and wherein the instructions, when executed, are further configured to cause the at least one processor to

compare, following a change of a subset of the movement patterns, a coverage rate for each media capture device prior to the change in movement patterns with a coverage rate for the same media capture device following the change in movement patterns,

generate a list of media capture devices for which a coverage rate decreased following the change in movement patterns, and

use the list of media capture devices as the N media capture devices during subsequent iterations to obtain an updated final device layout.

2. The computer program product of claim 1, wherein the moving objects include vehicles, and the media capture devices include video cameras.

3. The computer program product of claim 1, wherein the M candidate positions are defined at center points of intervals along pathways through the area.

4. The computer program product of claim 1, wherein the instructions, when executed, are configured to cause the at least one processor to:

assign the N media capture devices to N of the M candidate positions randomly.

5. The computer program product of claim 1, wherein the instructions, when executed, are configured to cause the at least one processor to:

calculate the set of coverage rates including calculating each coverage rate as a ratio of the moving objects captured by the N media capture devices to a total number of the moving objects in the area, within a defined period of time.

6. The computer program product of claim 1, wherein the instructions, when executed, are configured to cause the at least one processor to:

calculate each coverage rate including

selecting a moving object and its routes through the area from a database of the moving objects and their routes,

identifying, from the N media capture devices, a media capture device along the routes,

adding the moving object to a list for the media capture device, and

calculating a coverage rate for the media capture device including comparing the list to the moving objects from the database having at least one route past the media capture device.

7. The computer program product of claim 1, wherein N is a fixed number and the final device layout is selected as having a best-available coverage rate for the N media capture devices.

8. The computer program product of claim 1, wherein the instructions, when executed, are configured to cause the at least one processor to:

determine whether the final device layout satisfies a required coverage rate;

select an updated value for N, where the updated value for N is increased if the coverage rate of the final device layout is less than the required coverage rate, or decreased if the coverage rate of the final device layout is more than the required coverage rate; and

continue iterations until a final value of N is determined that provides the required coverage rate.

9. The computer program product of claim 1, wherein the termination condition is defined by at least one of a maximum number of iterations or converging coverage rate values.

10. The computer program product of claim 1, wherein the coverage rate is selected using Gibbs sampling.

11. A computer-implemented method for executing instructions stored on a non-transitory computer readable storage medium, the method comprising:

determining M candidate positions within an area for deployment of N media capture devices, where N<

M and the N media capture devices are configured to capture data characterizing moving objects within the area;

assigning the N media capture devices to N of the M candidate positions to obtain a device layout, including (M−

N) open positions;

selecting a selected media capture device N_S from the device layout;

calculating a set of coverage rates characterizing rates of coverage of the moving objects, each coverage rate calculated for a tested device layout in which N_S is positioned at a different one of the (M−

N) open positions;

selecting a coverage rate, and corresponding tested device layout, from the set of coverage rates;

iterating, including selecting a new N_S from the corresponding tested device layout and calculating a new set of coverage rates in which the new N_S is positioned at different ones of new (M−

N) open positions, to thereby obtain a new tested device layout;

terminating the iterating upon reaching a termination condition; and

selecting a final device layout from among all tested device layouts,

wherein the moving objects have movement patterns defined by pathways through the area, and the final device layout is selected based on the movement patterns and the pathways, the method further comprising

comparing, following a change of a subset of the movement patterns, a coverage rate for each media capture device prior to the change in movement patterns with a coverage rate for the same media capture device following the change in movement patterns,

generating a list of media capture devices for which a coverage rate decreased following the change in movement patterns, and

using the list of media capture devices as the N media capture devices during subsequent iterations to obtain an updated final device layout.

12. The method of claim 11, wherein calculating the set of coverage rates comprises:

calculating each coverage rate as a ratio of the moving objects captured by the N media capture devices to a total number of the moving objects in the area, within a defined period of time.

13. The method of claim 11, wherein calculating the set of coverage rates comprises:

calculate each coverage rate including

selecting a moving object and its routes through the area from a database of the moving objects and their routes,

identifying, from the N media capture devices, a media capture device along the routes,

adding the moving object to a list for the media capture device, and

calculating a coverage rate for the media capture device including comparing the list to the moving objects from the database having at least one route past the media capture device.

14. The method of claim 11, wherein N is a fixed number and the final device layout is selected as having a best-available coverage rate for the N media capture devices.

15. The method of claim 11, comprising:

determining whether the final device layout satisfies a required coverage rate;

selecting an updated value for N, where the updated value for N is increased if the coverage rate of the final device layout is less than the required coverage rate, or decreased if the coverage rate of the final device layout is more than the required coverage rate; and

continuing iterations until a value of N is determined that provides the required coverage rate.