SYSTEMS, DEVICES AND METHODS FOR TRACKING OBJECTS ON A DISPLAY

• US 20150063632A1
• Filed: 02/20/2014
• Published: 03/05/2015
• Est. Priority Date: 08/27/2013
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Deng, Fan, Yan, Ming, Ma, Lei, Gao, Dashan, Zhong, Xin, Liu, Shizhong
• Granted Patent: US 9,454,827 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20024 Filtering details
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/20224 Image subtraction
• CPC Class Codes: G06T 5/90 Dynamic range modification of images or parts thereof
• CPC Class Codes: G06T 5/92 based on global image properties
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80

Abstract

Systems, devices and methods for improved tracking with an electronic device are disclosed. The disclosures employ advanced exposure compensation and/or stabilization techniques. The tracking features may therefore be used in an electronic device to improve tracking performance under dramatically changing lighting conditions and/or when exposed to destabilizing influences, such as jitter. Historical data related to the lighting conditions and/or to the movement of a region of interest containing the tracked object are advantageously employed to improve the tracking system under such conditions.

Claims

1. A method of tracking an object with an electronic device, the method comprising:

defining a reference value based on an average light intensity of pixels in a region of an image frame comprising the object;

determining an average light intensity of pixels in the region of a current image frame comprising the object;

calculating a difference between the reference value and the determined average light intensity for the region in the current image frame;

adjusting the intensity of pixels in the current image frame when the difference is greater than an intensity limit;

applying a gain filter to the current image frame; and

tracking the object using the pixels in the current image frame.

2. The method of claim 1, wherein adjusting comprises subtracting the difference from every pixel of the current image frame.

3. The method of claim 1, further comprising periodically redefining the reference value, as the average light intensity of pixels in the region of the current image frame, when the difference is less than an intensity limit.

4. The method of claim 1, wherein applying a gain filter comprises calculating a variation indicator of the region based on current and historical parameters of the region.

5. The method of claim 4, wherein applying a gain filter further comprises determining a confidence level based on the variation indicator.

6. The method of claim 5, wherein applying a gain filter further comprises determining a gain based on the confidence level and determining the gain filter based on the gain.

7. The method of claim 6, wherein tracking the object comprises adjusting the region of the current image frame based on the gain filter.

8. A system for tracking an object with an electronic device, the system comprising:

a processor configured to;

define a reference value based on an average light intensity of pixels in a region of an image frame comprising the object;

determine an average light intensity of pixels in the region of a current image frame comprising the object;

calculate a difference between the reference value and the determined average light intensity for the region in the current image frame;

adjust the intensity of pixels in the current image frame when the difference is greater than an intensity limit;

apply a gain filter to the current image frame; and

track the object using the pixels in the current image frame.

9. The system of claim 8, wherein the processor is configured to adjust the intensity of pixels by subtracting the difference from every pixel of the current image frame.

10. The system of claim 8, wherein the processor is further configured to periodically redefine the reference value, as the average light intensity of pixels in the region of the current image frame, when the difference is less than an intensity limit.

11. The system of claim 8, wherein the processor is configured to apply a gain filter by calculating a variation indicator of the region based on current and historical parameters of the region.

12. The system of claim 11, wherein the current and historical parameters comprise, respectively, current and historical sizes of the region.

13. The system of claim 11, wherein the current and historical parameters comprise, respectively, current and historical locations of the region.

14. The system of claim 11, wherein the processor is configured to apply a gain filter by determining a confidence level based on the variation indicator.

15. The system of claim 14, wherein the processor is configured to apply a gain filter by determining a gain based on the confidence level and determining the gain filter based on the gain.

16. The system of claim 15, wherein the processor is configured to track the object by adjusting the region of the current image frame based on the gain filter.

17. The system of claim 16, wherein adjusting the region comprises adjusting the location of the region.

18. The system of claim 16, wherein adjusting the region comprises adjusting the size of the region.

19. A system for tracking an object with an electronic device, the system comprising:

means for defining a reference value based on an average light intensity of pixels in a region of an image frame comprising the object;

means for determining an average light intensity of pixels in the region of a current image frame comprising the object;

means for calculating a difference between the reference value and the determined average light intensity for the region in the current image frame;

means for adjusting the intensity of pixels in the current image frame when the difference is greater than an intensity limit;

means for applying a gain filter to the current image frame; and

means for tracking the object using the pixels in the current image frame.

20. The system of claim 19, wherein the means for adjusting comprises a means for subtracting the difference from every pixel of the current image frame.

21. The system of claim 19, wherein the system further comprises means for periodically redefining the reference value, as the average light intensity of pixels in the region of the current image frame, when the difference is less than an intensity limit.

22. The system of claim 19, wherein the means for applying a gain filter comprises:

means for calculating a variation indicator of the region based on current and historical parameters of the region; and

means for determining a confidence level based on the variation indicator.

23. The system of claim 22, wherein the means for applying a gain filter further comprises:

means for determining a gain based on the confidence level; and

means for determining the gain filter based on the gain.

24. The system of claim 23, wherein the means for tracking the object comprises means for adjusting the region of the current image frame based on the gain filter.

25. A non-transitory computer readable medium configured to store instructions that when executed by a processor perform a method for tracking an object with an electronic device, the method comprising:

defining a reference value based on an average light intensity of pixels in a region of an image frame comprising the object;

determining an average light intensity of pixels in the region of a current image frame comprising the object;

calculating a difference between the reference value and the determined average light intensity for the region in the current image frame;

adjusting the intensity of pixels in the current image frame when the difference is greater than an intensity limit;

applying a gain filter to the current image frame; and

tracking the object using the pixels in the current image frame.

26. The computer readable medium of claim 25, wherein adjusting comprises subtracting the difference from every pixel of the current image frame.

27. The computer readable medium of claim 25, wherein the method further comprises periodically redefining the reference value, as the average light intensity of pixels in the region of the current image frame, when the difference is less than an intensity limit.

28. The computer readable medium of claim 25, wherein applying a gain filter comprises:

calculating a variation indicator of the region based on current and historical parameters of the region; and

determining a confidence level based on the variation indicator.

29. The computer readable medium of claim 28, wherein applying a gain filter further comprises:

determining a gain based on the confidence level; and

determining the gain filter based on the gain.

30. The computer readable medium of claim 29, wherein tracking the object comprises adjusting the region of the current image frame based on the gain filter.