Video processing technique for 3D target location identification

• US 10,089,751 B1
• Filed: 05/31/2017
• Issued: 10/02/2018
• Est. Priority Date: 05/31/2017
• Status: Active Grant

• Current Assignee: BOOZ Allen Hamilton Holding Corporation
• Original Assignee: BOOZ Allen Hamilton Holding Corporation
• Inventors: Ter Beest, III, James J., Montgomery-Recht, Evan R.
• Primary Examiner(s): Abdi, Amara
• Application Number:
  US15/609,150
• Time in Patent Office: 489 Days
• CPC Class Codes: G06T 2207/20088 Trinocular vision calculations; trifocal tensor
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/55 from multiple images
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A method and system for determining the location of objects using a plurality of full motion video cameras where the location is based on the intersecting portions of a plurality of three-dimensional shapes that are generated from the video data provided by the cameras. The three-dimensional shapes include two-dimensional shapes that contain predetermined traits in each of the frames of the video signals.

Claims

1. A method of determining the location of objects, the method comprising:

receiving a video signal from each of a plurality of full motion video cameras observing an area;

identifying predetermined traits in frames of each video signal, the predetermined traits being associated with the objects;

demarcating a portion of the video frame with a two-dimensional shape, the demarcated portion containing the identified predetermined traits in the frames of each video signal;

assigning geospatial information to the two-dimensional shape containing the identified predetermined traits, the geospatial information representing a location of a camera that acquired the frame;

defining a plurality of three-dimensional shapes, each three-dimensional shape extending from a distance beyond the objects to the location of the camera for each frame of the video signal including the predetermined traits, each three-dimensional shape including a two-dimensional shape with the geospatial information;

identifying each of the full motion video cameras associated with overlapping coverage of the area that provided the video signal where the two-dimensional shape demarcates the identified predetermined traits;

calculating intersecting portions of the plural three-dimensional shapes by applying an intersect function to the defined three-dimensional shapes obtained from the full motion video cameras with overlapping coverage of the area, the intersect function outputting an intersecting shape; and

determining a center of the intersecting shape, the center of the intercepting shape being a determined location of the object.

2. The method of claim 1, wherein an angle of expansion of the three-dimensional shape is in based on a focal length of the video camera.

3. The method of claim 1, wherein the three-dimensional shapes include a first plane closest to each of the plurality of full motion video cameras and a second plane further from each of the plurality of full motion video cameras, wherein boundaries of the three-dimensional shapes are defined by the first and second planes.

4. The method of claim 1, wherein the identified predetermined traits represent motion of an object in multiple frames of the video signal.

5. The method of claim 1, wherein the identified predetermined traits are recognized objects.

6. The method of claim 1, wherein the predetermined traits to be identified are changed based on additional detected signals.

7. The method of claim 1, wherein each frame of each video signal includes a timestamp.

8. The method of claim 1, wherein the calculation of the intersecting portions occurs based on the defined three-dimensional shapes created from two-dimensional shapes surrounding the identified predetermined traits in the frames of each video signal, wherein each of the frames have a common timestamp.

9. The method of claim 1, wherein a third party provides inputs that change the predetermined traits to be identified.

10. The method of claim 1, wherein the plurality of full motion video cameras includes cameras with different focal lengths.

11. A system for determining the location of an object, the system comprising:

a plurality of full motion video cameras observing an area;

a computing device configured to define three-dimensional shapes by;

receiving a video signal from each of the plurality of full motion video cameras;

identifying predetermined traits in frames of each video signal, the predetermined traits being associated with the objects;

demarcating a portion of the video frame with a two-dimensional shape, the demarcated portion containing the identified predetermined traits in the frames of each video signal;

assigning geospatial information to the two-dimensional shape containing the identified predetermined traits, the geospatial information representing a location of a camera that acquired the frame;

defining a plurality of three-dimensional shapes, each three-dimensional shape extending from a distance beyond the objects to the location of the camera for each frame of the video signal including the predetermined traits, each three-dimensional shape including a two-dimensional shape with the geospatial information; and

storing the defined three-dimensional shapes;

an intersecting shape computing device configured to define an intersecting shape by;

identifying each of the full motion video cameras associated with overlapping coverage of the area that provided the video signal where the two-dimensional shape demarcates the identified predetermined traits;

calculating intersecting portions of the plurality of three-dimensional shapes by applying an intersect function to the defined three-dimensional shapes obtained from the full motion video cameras with overlapping coverage of the area, the intersect function outputting an intersecting shape;

determining a center of the intersecting shape, the center of the intercepting shape being a determined location of the object; and

storing the determined location of the object.

12. The system of claim 11, wherein an angle of expansion of the three-dimensional shape is in based on a focal length of the video camera.

13. The system of claim 11, wherein the three-dimensional shapes include a first plane closest to each of the plurality of full motion video cameras and a second plane further from each of the plurality of full motion video cameras, wherein boundaries of the three-dimensional shapes are defined by the first and second planes.

14. The system of claim 11, wherein the identified predetermined traits represent motion of an object in multiple frames of the video signal.

15. The system of claim 11, wherein the identified predetermined traits are recognized objects.

16. The system of claim 11, wherein the predetermined traits to be identified are changed based on additional detected signals.

17. The system of claim 11, wherein each frame of each video signal includes a timestamp.

18. The system of claim 11, wherein the calculation of the intersecting portions occurs based on the defined three-dimensional shapes created from two-dimensional shapes surrounding the identified predetermined traits in the frames of each video signal, wherein each of the frames have a common timestamp.

19. The system of claim 11, wherein the center of the intersecting shape is transmitted to a third party.

20. The system of claim 11, wherein the plurality of full motion video cameras includes cameras with different focal lengths.