Geo-relevance for images

• US 8,774,520 B2
• Filed: 10/30/2012
• Issued: 07/08/2014
• Est. Priority Date: 10/04/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ofek, Eyal, Epshtein, Boris
• Primary Examiner(s): STREGE, JOHN B
• Application Number:
  US13/663,659
• Publication Number:
  US 20130051623A1
• Time in Patent Office: 616 Days
• Field of Search: 382/190, 382/224
• US Class Current: 382/190
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59

Abstract

Images may be sorted and categorized by defining a frustum for each image and overlaying the frustums in two, three, or four dimensions to create a density map and identify points of interest. Images that contain a point of interest may be grouped, sorted, and categorized to determine representative images of the point. By including many images from different sources, common points of interest may be defined. Points of interest may be defined in two or three Euclidian dimensions, or may include a dimension of time.

Claims

1. A computer system having a processor and a memory coupled to the processor, the memory containing instructions, when executed by the processor, causing the processor to perform a method comprising:

determining a plurality of physical areas in space covered by one or more cameras carried by one or more users, each of the physical areas defined by an approximate point of origin and an approximate direction;

overlapping the determined plurality of physical areas relative to one another in a geographic representation, the overlapped physical areas having a density of coverage;

identifying an area of interest based on the density of coverage of the overlapped physical areas; and

associating one of the users with the area of interest if the camera carried by the user has a physical area that at least partially overlaps the area of interest.

2. The computer system of claim 1 wherein:

the area of interest is associated with at least one of a structure, an object, or a tourist destination; and

the method further includes associating one of the users with the at least one of structure, object, or tourist destination if the camera carried by the user has a physical area that at least partially overlaps the area of interest.

3. The computer system of claim 1 wherein:

the area of interest is associated with at least one of a structure, an object, or a tourist destination;

the method further includes;

associating a first one of the users with the at least one of structure, object, or tourist destination if a first camera carried by the first user has a first physical area that at least partially overlaps the area of interest; and

associating a second one of the users with the at least one of structure, object, or tourist destination if a second camera carried by the second user has a second physical area that at least partially overlaps the area of interest; and

wherein the first physical area of the first camera at least partially overlaps the second physical area of the second camera.

4. The computer system of claim 1 wherein:

the area of interest is associated with at least one of a structure, an object, or a tourist destination;

the method further includes;

associating a first one of the users with the at least one of structure, object, or tourist destination if a first camera carried by the first user has a first physical area that at least partially overlaps the area of interest, the first camera having a first approximate point of origin and a first approximate direction; and

associating a second one of the users with the at least one of structure, object, or tourist destination if a second camera carried by the second user has a second physical area that at least partially overlaps the area of interest, the second camera having a second approximate point of origin and a second approximate direction; and

wherein the first approximate point of origin is different than the second approximate point of origin, and/or the first approximate direction is different than the second approximate direction.

5. The computer system of claim 1 wherein:

the area of interest is associated with at least one of a structure, an object, or a tourist destination;

the method further includes;

associating a first one of the users with the at least one of structure, object, or tourist destination if a first camera carried by the first user has a first physical area that at least partially overlaps the area of interest, the first camera having a first approximate point of origin and a first approximate direction; and

associating a second one of the users with the at least one of structure, object, or tourist destination if a second camera carried by the second user has a second physical area that at least partially overlaps the area of interest, the second camera having a second approximate point of origin and a second approximate direction; and

wherein the first physical area of the first camera at least partially overlaps the second physical area of the second camera, and wherein the first approximate point of origin is different than the second approximate point of origin, and/or the first approximate direction is different than the second approximate direction.

6. The computer system of claim 1 wherein identifying the area of interest includes identifying an area on the geographic representation that is most densely covered as the area of interest.

7. The computer system of claim 1 wherein identifying the area of interest includes:

calculating a distribution of density of coverage on the geographic representation; and

identifying an area on the geographic representation as the area of interest based on the calculated distribution.

8. The computer system of claim 1 wherein the area of interest is a first area of interest, and wherein identifying the area of interest includes:

calculating a distribution of density of coverage on the geographic representation; and

identifying a second area of interest based on the calculated distribution, the second area of interest being different than the first area of interest.

9. A computer-implemented method for identifying an area of interest, the method comprising:

determining a plurality of frustums individually associated with a field of view of individual cameras, each of the frustums having an approximate point of origin and an approximate direction, wherein the individual frustums represent a geographic coverage area or volume of the corresponding cameras in space;

arranging the plurality of frustums relative to one another based on the approximate point of origin and the approximate direction in a geographic representation;

identifying a density of coverage of the plurality of frustums on the geographic representation; and

determining the area of interest based on the identified density of coverage.

10. The method of claim 9 wherein the cameras are associated with one or more users, and wherein the method further includes:

determining if one of the cameras has a frustum that at least partially overlaps the determined area of interest on the geographic representation, the camera being associated with one of the users; and

if the frustum overlaps the determined area of interest, associating the user with the determined area of interest.

11. The method of claim 9 wherein arranging the plurality of frustums includes:

representing the individual frustums as at least one of a triangle, a truncated triangle, a parallelogram, a ray, or a vector; and

overlaying the plurality of the at least one of triangle, truncated triangle, parallelogram, ray, or vector on a map.

12. The method of claim 9 wherein arranging the plurality of frustums includes:

representing the individual frustums as a triangle or a truncated triangle; and

overlaying the plurality of triangles or truncated triangles on a two-dimensional map.

13. The method of claim 9 wherein arranging the plurality of frustums includes:

representing the individual frustums as a pyramid; and

overlaying the plurality of pyramids on a three-dimensional map.

14. The method of claim 9 wherein arranging the plurality of frustums includes:

arranging the plurality of frustums relative to one another based on the approximate point of origin, the approximate direction, and time in the geographic representation;

wherein identifying the density of coverage includes identifying a density of coverage with respect to time; and

wherein the method further includes determining an event based on the identified density of coverage with respect to time.

15. The method of claim 9 wherein determining the area of interest includes determining the area of interest as at least one of a point, an area, or a volume based on the identified density of coverage.

16. A computer system for identifying an area of interest, the computer system comprising:

means for determining a plurality of physical areas in space covered by one or more cameras, each of the physical areas having an approximate point of origin and an approximate direction, and wherein each of the cameras being associated with a user;

means for arranging the determined plurality of physical areas relative to one another in a geographic representation, at least some of the physical areas overlap one another;

means for selecting the area of interest based on the overlapping of at least some of the physical areas;

means for determining if one of the cameras has a physical area that at least partially overlaps the selected area of interest; and

means for associating one of the users with the area of interest if the physical area of the camera associated with the user at least partially overlaps the area of interest.

17. The computer system of claim 16 wherein the means for arranging the determined plurality of physical areas includes means for arranging the determined plurality of physical areas as triangles or truncated triangles in a two-dimensional geographic representation.

18. The computer system of claim 16 wherein the means for arranging the determined plurality of physical areas includes means for arranging the determined plurality of physical areas as pyramids in a three-dimensional geographic representation.

19. The computer system of claim 16 wherein the means for selecting the area of interest includes:

means for calculating a distribution of density of coverage of the physical areas on the geographic representation; and

means for identifying an area on the geographic representation as the area of interest based on the calculated distribution.

20. The computer system of claim 16 wherein the area of interest is a first area of interest, and wherein the means for selecting the area of interest includes:

means for calculating a distribution of density of coverage of the physical areas on the geographic representation; and

means for identifying a second area of interest based on the calculated distribution, the second area of interest being different than the first area of interest.