Object trackability via parametric camera tuning

• US 6,952,224 B2
• Filed: 03/30/2001
• Issued: 10/04/2005
• Est. Priority Date: 03/30/2001
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Sun, Wei, Martins, Fernando
• Primary Examiner(s): MOE, AUNG SOE
• Application Number:
  US09/822,549
• Publication Number:
  US 20040201719A1
• Time in Patent Office: 1,649 Days
• Field of Search: 348/222.1, 348/223.1, 348/224.1, 348/225.1, 348/229.1, 348/208.14, 348/169, 382/103, 382/274, 382/275, 358/518, 358/516, 358/520
• US Class Current: 348/222.1
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems

Abstract

A method and apparatus are described for improving object trackability via parametric camera tuning. According to one embodiment the improving of object trackability comprises loading prior camera settings if any stored prior camera settings are available. If no stored prior camera settings are available, loading one of a plurality of predetermined camera settings. A determination is made whether the camera settings loaded cause saturation of the image and hue differences between objects and between the objects and a background of the video image. If the saturation and hue differences do not exceed the threshold, a search of camera settings is performed to increase saturation and hue differences between objects and between the objects and a background of the video image.

Claims

1. A method of improving trackability of at least one object within a video image comprising:

loading prior camera settings if any stored prior camera settings are available;

loading one of a plurality of predetermined camera settings;

determining whether the camera settings loaded cause saturation of the video image and hue differences between objects to be tracked and between the objects and a background of the video image to exceed a threshold; and

if the saturation and hue differences do not exceed said threshold, searching camera settings to find settings that cause saturation and hue differences between objects and between the objects and the background of the image to exceed said threshold.

2. The method of claim 1, wherein said camera settings comprise saturation, hue, brightness and white balance.

3. The method of claim 1, wherein said loading one of a plurality of predetermined camera settings comprises:

reading a user selection describing lighting conditions; and

selecting one of said plurality of predetermined camera settings responsive to said user selection.

4. The method of claim 1, wherein said searching comprises:

selecting one of said plurality of predetermined camera settings;

selecting a range of camera settings near a selected predetermined camera setting;

performing a full search of a selected range of camera settings; and

saving results of said full search.

5. The method of claim 4, wherein said selecting one of said predetermined camera settings is based on the settings causing saturation and hue differences between objects and between the objects and a background of the video image to exceed a threshold.

6. The method of claim 4, wherein said selecting a range of camera settings near a selected predetermined camera setting is based on the settings causing saturation and hue differences between objects and between the objects and the background of the video image to exceed a threshold.

7. The method of claim 4, wherein said performing a full search of a selected range of camera settings comprises testing all possible camera settings within the range to find settings that cause saturation and hue differences between objects and between the object and a background of the video image to exceed a threshold.

8. A system comprising:

a storage device having stored therein one or more routines for improving trackability of at least one object within a video image; and

a processor coupled to the storage device that when executing the one or more routines improves trackability of objects within the video image by;

loading prior camera settings if any stored prior camera settings are available;

loading one of a plurality of predetermined camera settings;

determining whether the camera settings loaded cause saturation of the video image and hue differences between objects to be tracked and between the objects and a background of the video image to exceed a threshold; and

if the saturation and hue differences do not exceed said threshold, searching camera settings to find settings that cause saturation and hue differences between objects and between the objects and the background of the image to exceed said threshold.

9. The system of claim 8, wherein said camera settings comprise saturation, hue, brightness and white balance.

10. The system of claim 8, wherein loading one of a plurality of predetermined camera settings comprises:

reading a user selection describing lighting conditions; and

selecting one of said plurality of predetermined camera settings responsive to said user selection.

11. The system of claim 8, wherein searching comprises:

selecting one of said plurality of predetermined camera settings;

selecting a range of camera settings near a selected predetermined camera setting;

performing a full search of a selected range of camera settings; and

saving results of said full search.

12. The system of claim 11, wherein said selecting one of said predetermined camera settings is based on the settings causing saturation and hue differences between objects and between the object and a background of the video image to exceed a threshold.

13. The system of claim 11, wherein said selecting a range of camera settings near a selected predetermined camera setting is based on the settings causing saturation and hue differences between objects and between the object and a background of the video image to exceed a threshold.

14. The system of claim 11, wherein said performing a full search of a selected range of camera settings comprises testing all possible camera settings within the range to find settings that cause saturation and hue differences between objects and between the object and a background of the video image to exceed a threshold.

15. A machine readable medium having stored thereon data representing sequences of instructions, said sequences of instructions which, when executed by a processor, cause the processor to maximize trackability of at least one object within an image by:

loading prior camera settings if any stored prior camera settings are available;

loading one of a plurality of predetermined camera settings;

determining whether the camera settings loaded cause saturation of the video image and hue differences between objects to be tracked and between the objects and a background of the video image to exceed a threshold; and

if the saturation and hue differences do not exceed said threshold, searching camera settings to find settings that cause saturation and hue differences between objects and between the objects and the background of the image to exceed said threshold.

16. The machine readable medium of claim 15, wherein said camera settings comprise saturation, hue, brightness and white balance.

17. The machine readable medium of claim 15, wherein said loading one of a plurality of predetermined camera settings comprises:

reading a user selection describing lighting conditions; and

selecting one of said plurality of predetermined camera settings responsive to said user selection.

18. The machine readable medium of claim 15, wherein said searching comprises:

selecting one of said plurality of predetermined camera settings;

selecting a range of camera settings near a selected predetermined camera setting;

performing a full search of a selected range of camera settings; and

saving results of said full search.

19. The machine readable medium of claim 18, wherein said selecting one of said predetermined camera settings is based on the settings causing saturation and hue differences between objects and between the object and a background of the video image to exceed a threshold.

20. The machine readable medium of claim 18, wherein said selecting a range of camera settings near a selected predetermined camera setting is based on the settings causing saturation and hue differences between objects and between the objects and a background of the video image to exceed a threshold.

21. The machine readable medium of claim 18, wherein said performing a full search of a selected range of camera settings comprises testing all possible camera settings within the range to find settings that cause saturation and hue differences between and between the objects and a background of the video image to exceed a threshold.