Systems and methods for determining a region in an image

1. A method for determining a region of an image, comprising:

presenting an image of a scene comprising one or more objects;

receiving an input selecting a single point on the image corresponding to a target object;

obtaining a motion mask based on the image, wherein the motion mask indicates a local motion section and a global motion section of the image;

generating a section map based on the selected point, the section map comprising a target section corresponding to the selected point; and

combining the target section and at least a portion of the local motion section to produce a region.

2. The method of claim 1 , wherein the section map further comprises a probable target section, a probable non-target section, and a non-target section.

3. The method of claim 2 , wherein the region further comprises at least a portion of the probable target section.

4. The method of claim 2 , further comprising combining the global motion section, the probable non-target section, and the non-target section to produce a non-target region.

5. The method of claim 1 , further comprising segmenting the image based on the region to produce an object mask.

6. The method of claim 1 , further comprising fusing motion information and color information.

7. The method of claim 1 , wherein obtaining the motion mask comprises:

determining a set of local motion vectors within a region of interest between a previous frame and a current frame;

determining a set of global motion vectors between the previous frame and the current frame; and

calculating a global motion consistency measure based on the set of global motion vectors.

8. The method of claim 1 , further comprising tracking the target object based on the region, wherein the region corresponds to the target object.

9. The method of claim 1 , further comprising generating a region of interest (ROI) based on the region.

10. The method of claim 1 , further comprising selecting the target object based on the region.

11. The method of claim 1 , further comprising presenting an indication of the target object.

12. An electronic device for determining a region of an image, comprising:

a processor configured to:

present an image of a scene comprising one or more objects;

receive an input selecting a single point on the image corresponding to a target object;

obtain a motion mask based on the image, wherein the motion mask indicates a local motion section and a global motion section of the image;

generate a section map based on the selected point, the section map comprising a target section corresponding to the selected point; and

combine the target section and at least a portion of the local motion section to produce a region.

13. The electronic device of claim 12 , wherein the section map further comprises a probable target section, a probable non-target section, and a non-target section.

14. The electronic device of claim 13 , wherein the region further comprises at least a portion of the probable target section.

15. The electronic device of claim 13 , wherein the processor is configured to combine the global motion section, the probable non-target section, and the non-target section to produce a non-target region.

16. The electronic device of claim 12 , wherein the processor is configured to segment the image based on the region to produce an object mask.

17. The electronic device of claim 12 , wherein the processor is configured to fuse motion information and color information.

18. The electronic device of claim 12 , wherein the processor is configured to:

determine a set of local motion vectors within a region of interest between a previous frame and a current frame;

determine a set of global motion vectors between the previous frame and the current frame; and

calculate a global motion consistency measure based on the set of global motion vectors.

19. An apparatus for determining a region of an image, comprising:

means for presenting an image of a scene comprising one or more objects;

means for receiving an input selecting a single point on the image corresponding to a target object;

means for obtaining a motion mask based on the image, wherein the motion mask indicates a local motion section and a global motion section of the image;

means for generating a section map based on the selected point, the section map comprising a target section corresponding to the selected point; and

means for combining the target section and at least a portion of the local motion section to produce a region.

20. The apparatus of claim 19 , wherein the section map further comprises a probable target section, a probable non-target section, and a non-target section.

21. The apparatus of claim 20 , wherein the region further comprises at least a portion of the probable target section.

22. The apparatus of claim 20 , further comprising means for combining the global motion section, the probable non-target section, and the non-target section to produce a non-target region.

23. The apparatus of claim 19 , wherein the means for obtaining the motion mask comprises:

means for determining a set of local motion vectors within a region of interest between a previous frame and a current frame;

means for determining a set of global motion vectors between the previous frame and the current frame; and

means for calculating a global motion consistency measure based on the set of global motion vectors.

24. A computer-program product for determining a region of an image, comprising a non-transitory computer-readable medium having instructions thereon, the instructions comprising:

code for causing an electronic device to present an image of a scene comprising one or more objects;

code for causing the electronic device to receive an input selecting a single point on the image corresponding to a target object;

code for causing the electronic device to obtain a motion mask based on the image, wherein the motion mask indicates a local motion section and a global motion section of the image;

code for causing the electronic device to generate a section map based on the selected point, the section map comprising a target section corresponding to the selected point; and

code for causing the electronic device to combine the target section and at least a portion of the local motion section to produce a region.

25. The computer-program product of claim 24 , wherein the section map further comprises a probable target section, a probable non-target section, and a non-target section.

26. The computer-program product of claim 25 , wherein the region further comprises at least a portion of the probable target section.

27. The computer-program product of claim 25 , further comprising code for causing the electronic device to combine the global motion section, the probable non-target section, and the non-target section to produce a non-target region.

28. The computer-program product of claim 24 , wherein the code for causing the electronic device to obtain the motion mask comprises:

code for causing the electronic device to determine a set of local motion vectors within a region of interest between a previous frame and a current frame;

code for causing the electronic device to determine a set of global motion vectors between the previous frame and the current frame; and

code for causing the electronic device to calculate a global motion consistency measure based on the set of global motion vectors.