FACILITATING IDENTIFICATION OF AN OBJECT RECORDED IN DIGITAL CONTENT RECORDS

• US 20090094188A1
• Filed: 10/03/2007
• Published: 04/09/2009
• Est. Priority Date: 10/03/2007
• Status: Abandoned Application

• Current Assignee: Eastman Kodak Company
• Original Assignee: Eastman Kodak Company
• Inventors: Fyson, John R., Covannon, Edward
• Application Number:
  US11/866,626
• Publication Number:
  US 20090094188A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/487 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 16/78 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/7837 using objects detected or recognised in the video content
• CPC Class Codes: G06V 10/62 relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata

Abstract

Embodiments of the present invention facilitate identification of one or more objects in digital content records at least by knowing or estimating what region of space-time was captured by the digital content records and where the objects were located at various points in time. An object'"'"'s location versus time is referred to herein as a space-time line. Any digital content record whose captured space-time region intersects with a particular object'"'"'s space-time line is identified as having a possibility of having recorded the particular object.

Claims

1. A method implemented at least in part by a data processing system, the method for identifying digital content records from a plurality of digital content records and comprising the steps of:

accessing information defining a space-time line for an object, the space-time line representing changes in the object'"'"'s position in space over time;

accessing information sets, each set defining a captured space-time region associated with one of the plurality of digital content records, each captured space-time region representing a region of space captured by its associated digital content record at a particular time;

identifying digital content records from the plurality based at least upon identified intersections of the object'"'"'s space-time line and the captured space-time regions; and

storing results of the identifying step in a processor-accessible memory system.

2. The method of claim 1, wherein the object'"'"'s space-time line, at different points in time, has different sizes.

3. The method of claim 2, wherein each of the different sizes is proportional to an amount of precision as to known or expected whereabouts of the object.

4. The method of claim 2, wherein the object'"'"'s space-time line has three space dimensions, and the different sizes are different volumes.

5. The method of claim 2, wherein the object'"'"'s space-time line has only two space dimensions, and the different sizes are different areas.

6. The method of claim 1, wherein the identified digital content records are selected digital content records, and wherein the method further comprises the steps of:

receiving an indication of a problematic representation of the object in a particular digital content record;

identifying, from the selected digital content records, a source digital content record having (a) similar characteristics as the particular digital content record, and (b) a preferred representation of the object; and

replacing the problematic representation of the object in the particular digital content record with the preferred representation of the object from the source digital content record.

7. The method of claim 6, wherein the problematic representation of the object is a blurred representation of the object.

9. The method of claim 6, wherein the similar characteristics include direction of capture, location of capture, and time-date of capture.

10. The method of claim 6, wherein the object is a background of the particular digital content record.

13. The method of claim 1, wherein the object is a person or a capture device.

8. (canceled)

11. (canceled)

12. (canceled)

14. (canceled)

15. (canceled)

16. (canceled)

17. A method implemented at least in part by a data processing system, the method for facilitating identification of an object in digital content records and comprising the steps of:

identifying first information indicating a first location of the object at a first particular time;

identifying second information indicating a second location of the object at a second particular time different than the first particular time;

generating a space-time line for the object based at least upon the first information and the second information, the space-time line representing changes in the object'"'"'s position in space over time;

storing the space-time line in a processor-accessible memory system; and

making the space-time line available to a data processing system to facilitate identification of the object in digital content records.

18. The method of claim 17, wherein the step of identifying the first information comprises identifying the object in a particular digital content record captured at the first location at the first particular time.

19. The method of claim 18, wherein the object is identified in the particular digital content record based at least upon an image-processing object-recognition technique.

20. The method of claim 18, wherein the object is identified in the particular digital content record based at least upon metadata that identifies the object, the metadata associated with the particular digital content record.

22. The method of claim 17, wherein the step of generating the space-time line includes interpolating points in space-time between the first particular time and the second particular time.

23. The method of claim 17, wherein the step of generating the space-time line includes projecting points in space-time before or beyond all known points of time associated with the object'"'"'s location.

24. The method of claim 17, wherein the space-time line, at different points in time, is generated to have different sizes.

25. The method of claim 24, wherein each of the different sizes is proportional to an amount of precision as to known or expected whereabouts of the object.

26. The method of claim 24, wherein the space-time line is generated to have three space dimensions, and the different sizes are different volumes.

27. The method of claim 24, wherein the object'"'"'s space-time line has only two space dimensions, and the different sizes are different areas.

21. (canceled)

28. (canceled)

29. (canceled)

30. A method implemented at least in part by a data processing system, the method for facilitating identification of an object in a digital content record and comprising the steps of:

identifying first information indicating a location of capture, a direction of capture, and a time of capture associated with the digital content record;

generating a captured space-time region associated with the digital content record based at least upon the first information, the captured space-time region representing a region of space captured by the digital content record at a particular time;

storing the captured space-time region in a processor-accessible memory system; and

making the captured space-time region available to a data processing system to facilitate identification of an object in the digital content record.

31. The method of claim 30, further comprising the step of:

identifying second information indicating regions of space not captured by the digital content record at the particular time,

wherein the generating step generates the captured space-time region based at least upon the first information and the second information.

32. The method of claim 31, wherein, in the generating step, the second information is used to reduce a size of the captured space-time region initially identified using the first information alone.

33. The method of claim 31, wherein the second information indicates at least characteristics of a physical barrier located within the direction of capture.

35. The method of claim 31, wherein the generating step includes:

identifying a captured-space-time super-region based at least upon the first information;

identifying a blocked-space-time region based at least upon the second information, the blocked-space-time region representing a region of space at the particular time that was obstructed from a capture device that generated the digital content record;

removing the blocked-space-time region from the captured-space-time super region to produce a reduced-captured-space-time region; and

generating the captured space-time region based at least upon the reduced-captured-space-time region.

34. (canceled)

36. (canceled)

37. (canceled)