Technique for automatically tracking an object in a defined tracking window by a camera based on identification of an object

• US 10,489,917 B2
• Filed: 06/29/2017
• Issued: 11/26/2019
• Est. Priority Date: 04/14/2008
• Status: Active Grant

• Current Assignee: Grass Valley Canada (Belden Inc.)
• Original Assignee: Gvbb Holdings SARL (Vislink Technologies, Inc.)
• Inventors: Holtz, Alex, Matics, Scott Raymond, Oisel, Lionel
• Primary Examiner(s): Murray, Daniel C.
• Application Number:
  US15/637,166
• Publication Number:
  US 20170309032A1
• Time in Patent Office: 880 Days
• Field of Search: 348143
• CPC Class Codes: G01S 3/7865 using correlation of the live video image with a stored image
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: H04N 23/62 Control of parameters via user interfaces
• CPC Class Codes: H04N 23/66 Remote control of cameras or camera parts, e.g. by remote control devices

Abstract

Automatic tracking by a camera of an object such as on-air talent appearing in a television show commences by first determining whether the object lies within the camera field of view matches a reference object. If so, tracking of the object then occurs to maintain the object in fixed relationship to a pre-set location in the camera'"'"'s field of view, provided the designated object has moved more than a threshold distance from the pre-set location.

Claims

1. A system for automatically tracking an object in an image during production of a television program, the system comprising:

a camera configured to capture the image for the production of the television program;

a tracking window setting module configured to define a tracking window in a field of view of the camera, such that the system will not track objects in the image that are outside the defined tracking window;

an object identifier configured to identify at least one object in the defined tracking window that matches at least one reference object;

a tracking location setting module configured to define a preset location in the field of view of the camera for the identified and tracked at least one object; and

an object tracker configured to automatically track the identified at least one object when the camera captures the image to maintain the identified and tracked at least one object in a fixed relationship relative to the defined preset location in the field of view of the camera.

2. The system according to claim 1, wherein the object tracker is further configured to automatically track the identified at least one object when the at least one object has moved more than a threshold distance from the preset location.

3. The system according to claim 2, wherein the preset location in the field of view of the camera is set for one of a right over-the-shoulder perspective or a left over-the-shoulder perspective of the at least one identified and tracked object.

4. The system according to claim 3, wherein the object tracker controls the robotic camera pedestal to automatically adjust the position of the camera to maintain the identified and tracked at least one object at the set right or left over-the-shoulder perspective when automatically tracking the identified at least one object.

5. The system according to claim 3, further comprising a robotic camera pedestal configured to physically adjust a position of the camera, wherein the object tracker is configured to control the robotic camera pedestal to automatically adjust the position of the camera when automatically tracking the identified at least one object.

6. The system according to claim 5, wherein the object tracker controls the robotic camera pedestal to automatically adjust the position of the camera by at least one of displacing the camera in an X and Y axis relative to the identified and tracked at least one object, panning the camera, and tilting the camera.

7. The system according to claim 1, wherein the object tracker is configured to automatically track the identified at least one object by adjusting at least one of an iris and a zoom of the camera.

8. The system according to claim 1, wherein the tracking window setting module is configured to define the tracking window based on an operator defined region of interest received by a user interface.

9. The system according to claim 1, wherein the object identifier is configured to identify the at least one object in the tracking window by comparing at least one characteristic of the object to at least one corresponding characteristic of the reference object.

10. The system according to claim 1, wherein the object tracker is further configured to:

determine if the identified and tracked at least one object remains motionless for a preselected time interval; and

automatically track the at least one object only when the identified at least one object in the defined tracking window matches the reference object and the identified at least one object remains motionless for the preselected time interval after the at least on object is matched with the reference object.

11. The system according to claim 10, wherein the object tracker is further configured to:

obtain a tolerance radius around the preset location; and

automatically track the identified at least one object when the identified at least one object moves outside the tolerance radius.

12. A system for automatically tracking an object in a field of view of a camera, the system comprising:

a camera for capturing a video image that includes the object;

a tracking window setter configured to define a tracking window in the field of view of the camera, such that objects in the video image will not be tracked that are outside the defined tracking window; and

an object tracker configured to automatically identify and track the object in the defined tracking window when the camera captures the video image.

13. The system according to claim 12, further comprising an object identifier configured to identify the object in the defined tracking window that matches a stored reference object, wherein the object tracker automatically tracks the identified object to maintain the tracked object in a fixed relationship relative to the field of view of the camera.

14. The system according to claim 13, wherein the object identifier is configured to identify the object in the defined tracking window by comparing at least one characteristic of the object to at least one corresponding characteristic of the stored reference object.

15. The system according to claim 12, further comprising a tracking location setting module configured to define a preset location in the field of view of the camera for the tracked object, and wherein the object tracker is further configured to automatically track the object when the object has moved more than a threshold distance from the preset location.

16. The system according to claim 12, further comprising a robotic camera pedestal configured to physically adjust a position of the camera, wherein the object tracker is configured to control the robotic camera pedestal to automatically adjust the position of the camera to automatically track the object when the camera captures the video image.

17. The system according to claim 16, wherein the object tracker controls the robotic camera pedestal to automatically adjust the position of the camera by at least one of displacing the camera in an X and Y axis relative to the tracked one object, panning the camera, and tilting the camera.

18. The system according to claim 12, wherein the object tracker is configured to automatically track the object by adjusting at least one of an iris and a zoom of the camera to track the object in the defined tracking window.

19. The system according to claim 12, wherein the tracking window setter is further configured to define the tracking window based on an operator defined region of interest received by a user interface.

20. The system according to claim 12, wherein the object tracker is further configured to:

determine if the object remains motionless for a preselected time interval; and

automatically track the object only when the object in the defined tracking window matches a reference object and the matched object remains motionless for the preselected time interval.

21. The system according to claim 20, wherein the object tracker is further configured to:

obtain a tolerance radius around a preset location in the field of view of the camera; and

automatically track the object when the object moves outside the tolerance radius in the field of view.

22. A method for tracking an object in a field of view of a robotically controlled camera, the method comprising:

defining a tracking window in the field of view of the camera, wherein tracking will not be performed on objects in the field of view that are outside the defined tracking window;

identifying at least one object in the tracking window that matches a reference object; and

automatically tracking the identified at least one object to maintain the identified and tracked at least one object in a fixed relationship relative to the field of view of the camera.

23. The method according to claim 22, further comprising defining the fixed relationship as a preset location in the field of view of the camera for the identified and tracked at least one object.

24. The method according to claim 23, wherein the preset location in the field of view of the camera is set for one of a right over-the-shoulder perspective or a left over-the-shoulder perspective of the at least one identified and tracked object.

25. The method according to claim 24, further comprising adjusting at least one of a position and a setting of the robotically controlled camera to maintain the identified and tracked at least one object at the set right or left over-the-shoulder perspective when automatically tracking the identified at least one object.

26. The method according to claim 23, further comprising automatically tracking the identified at least one object has moved more than a threshold distance from the preset location.

27. The method according to claim 23, further comprising automatically adjusting at least one of a position and a setting of the robotically controlled camera to automatically track the identified at least one object.

28. The method according to claim 27, wherein the automatic adjusting of the position of the robotically controlled camera comprises at least one of displacing the camera in an X and Y axis relative to the identified and tracked at least one object, panning the camera, and tilting the camera.

29. The method according to claim 27, wherein the automatic adjusting of the setting of the robotically controlled camera comprises at least one of adjusting an iris and a zoom of the camera.

30. The method according to claim 22, further comprising receiving an operator defined region of interest as the defined tracking window in the field of view of the camera.

31. The method according to claim 22, wherein the identifying of the at least one object in the tracking window comprises comparing at least one characteristic of the object to at least one corresponding characteristic of the reference object.

32. The method according to claim 22, further comprising:

determining if the identified and tracked at least one object remains motionless for a selected time interval; and

automatically tracking the at least one object only when the identified at least one object in the defined tracking window matches the reference object and the identified at least one object remains motionless for the selected time interval.

33. The method according to claim 22, further comprising:

defining a preset location in the field of view of the camera for the identified and tracked at least one object;

obtaining a tolerance radius around the preset location; and

automatically tracking the identified at least one object when the identified at least one object moves outside the tolerance radius.

34. The method according to claim 22, further comprising automatically tracking the identified at least one object in a video image captured by the camera for production of a television program.