MEASURING A COHORT'S VELOCITY, ACCELERATION AND DIRECTION USING DIGITAL VIDEO

• US 20090208054A1
• Filed: 02/20/2008
• Published: 08/20/2009
• Est. Priority Date: 02/20/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kraemer, James R., Angell, Robert Lee, Friedlander, Robert R., Cosby, David Wayne
• Granted Patent: US 8,107,677 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06Q 90/00 Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/285 using a sequence of stereo image pairs
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

A computer implemented method, apparatus, and computer program product for identifying positional data for an object moving in an area of interest. Positional data for each camera in a set of cameras associated with the object is retrieved. The positional data identifies a location of each camera in the set of cameras within the area of interest. The object is within an image capture range of each camera in the set of cameras. Metadata describing video data captured by the set of cameras is analyzed using triangulation analytics and the positional data for the set of cameras to identify a location of the object. The metadata is generated in real time as the video data is captured by the set of cameras. The positional data for the object is identified based on locations of the object over a given time interval. The positional data describes motion of the object.

Claims

1. A computer implemented method for identifying positional data for an object in motion, the computer implemented method comprising:

retrieving location data a set of cameras associated with the object, wherein the location data identifies a location of each camera in the set of cameras within the area of interest, and wherein the object is within an image capture range of the each camera in the set of cameras;

analyzing metadata associated with the object using triangulation analytics and the location data for the set of cameras to identify a location of the object at a point in time, wherein the metadata describes events in video data captured by the set of cameras, and wherein the metadata is generated automatically in real time as the video data is captured by the set of cameras; and

identifying the positional data for the object based on locations of the object over a given time interval, wherein the positional data describes motion of the object.

2. The computer implemented method of claim 1 wherein the set of cameras comprises two or more cameras, and wherein the positional data comprises a direction of motion of the object.

3. The computer implemented method of claim 1 wherein the set of cameras comprises three or more cameras, and wherein the positional data comprises a velocity of the motion of the object.

4. The computer implemented method of claim 1 wherein the set of cameras comprises three or more cameras and wherein the positional data comprises an acceleration of the object over time.

5. The computer implemented method of claim 1 further comprising:

analyzing metadata describing the object using object identification analytics to identify the object.

6. The computer implemented method of claim 1 further comprising:

analyzing the metadata using a set of data models, wherein the set of data models comprises at least one of a statistical method, a data mining method, a causal model, a mathematical model, a marketing model, a behavioral model, a psychological model, a sociological model, a simulation model or a unifying data model.

7. The computer implemented method of claim 1 further comprising:

receiving a continuous video stream from the set of cameras, wherein the set of cameras is located with the area of interest to form video data, and wherein the object is within an image capture range of each camera in the set of cameras; and

processing the video data using video analytics to generate the metadata describing the object.

8. The computer implemented method of claim 7 wherein the video analytics comprises at least one of behavior analysis analytics, license plate recognition analytics, and facial recognition analytics.

9. The computer implemented method of claim 1 further comprising:

generating the location data for the set of cameras using data from a global positioning system receiver associated with the each camera.

10. The computer implemented method of claim 1 wherein the positional data for the object comprises a direction, velocity, and acceleration of the object and further comprising:

identifying probable goods and services desirable for the object based on the direction, velocity, and acceleration of the object over a set of time intervals; and

identifying a set of vendors and service providers associated with providing the probable goods and services.

11. A computer program product for identifying positional data for an object in motion, the computer program product comprising:

a computer readable medium;

program code stored on the computer readable medium for retrieving location data a set of cameras associated with the object, wherein the location data identifies a location of each camera in the set of cameras within the area of interest, and wherein the object is within an image capture range of the each camera in the set of cameras;

program code stored on the computer readable medium for analyzing metadata associated with the object using triangulation analytics and the location data for the set of cameras to identify a location of the object at a point in time, wherein the metadata describes events in video data captured by the set of cameras, and wherein the metadata is generated automatically in real time as the video data is captured by the set of cameras; and

program code stored on the computer readable medium for identifying the positional data for the object based on locations of the object over a given time interval, wherein the positional data describes motion of the object.

12. The computer program product of claim 11 wherein the set of cameras comprises two or more cameras and wherein the positional data is a direction of motion of the object.

13. The computer program product of claim 11 wherein the set of cameras comprises three or more cameras and wherein the positional data is a velocity of the motion of the object.

14. The computer program product of claim 11 wherein the set of cameras comprises three or more cameras and wherein the positional data is an acceleration of the object over time.

15. The computer program product of claim 11 comprising:

program code stored on the computer readable medium for analyzing metadata describing the object using object identification analytics to identify the object.

16. The computer program product of claim 11 further comprising:

program code stored on the computer readable medium for receiving a continuous video stream from the set of cameras, wherein the set of cameras is located with the area of interest to form video data, and wherein the object is within an image capture range of each camera in the set of cameras; and

program code stored on the computer readable medium for processing the video data using video analytics to generate the metadata describing the object.

17. The computer program product of claim 16 wherein the video analytics comprises at least one of behavior analysis analytics, license plate recognition analytics, and facial recognition analytics.

18. The computer program product of claim 11 further comprising:

program code stored on the computer readable medium for generating the location data for the set of cameras using data from a global positioning system receiver associated with the each camera.

19. The computer program product of claim 11 wherein the positional data for the object comprises a direction, velocity, and acceleration of the object and further comprising:

program code stored on the computer readable medium for identifying probable goods and services desirable for the object based on the direction, velocity, and acceleration of the object over a set of time intervals; and

program code stored on the computer readable medium for identifying a set of vendors and service providers associated with providing the probable goods and services.

20. An apparatus comprising:

a bus system;

a communications system coupled to the bus system;

a memory connected to the bus system, wherein the memory includes computer usable program code; and

a processing unit coupled to the bus system, wherein the processing unit executes the computer usable program code to retrieve positional data for each camera in a set of cameras associated with the object, wherein the positional data identifies a location of the each camera in the set of cameras within the area of interest, and wherein the object is within an image capture range of the each camera in the set of cameras;

analyze metadata describing video data captured by the set of cameras using triangulation analytics and the positional data for the set of cameras to identify a location of the object, wherein the metadata is generated in real time as the video data is captured by the set of cameras; and

identify the positional data for the object based on locations of the object over a given time interval, wherein the positional data describes motion of the object.

21. The apparatus of claim 20 wherein the processor unit further executes the computer usable program code to receive a continuous video stream from the set of cameras, wherein the set of cameras is located with the area of interest to form video data, and wherein the object is within an image capture range of each camera in the set of cameras;

and process the video data using video analytics to generate the metadata describing the object.

22. A system for identifying positional data for an object in motion, the system comprising:

a set of cameras associated with an object in an area of interest, wherein the object is within an image capture range of the each camera in the set of cameras;

a video analysis server, wherein the video analysis server retrieves location data for the set of cameras, wherein the location data identifies a location of each camera in the set of cameras within the area of interest and analyze metadata associated with the object using triangulation analytics and the location data for the set of cameras to identify a location of the object at a point in time, wherein the metadata describes events in video data captured by the set of cameras, and wherein the metadata is generated automatically in real time as the video data is captured by the set of cameras; and

identify the positional data for the object based on locations of the object over a given time interval, wherein the positional data describes motion of the object.

23. The system of claim 22 further comprising:

a video analysis engine, wherein the video analysis engine receives a continuous video stream from the set of cameras to form video data, and wherein the video analysis engine processes the video data using video analytics to generate the metadata describing the object.

24. The system of claim 22 wherein the set of cameras comprises two or more cameras, and wherein the positional data is a direction of motion of the object.

25. The system of claim 22 wherein the set of cameras comprises three or more cameras, and wherein the positional data comprises a velocity of the motion of the object and an acceleration of the object over time.