Motion blur aware visual pose tracking
Various methods, apparatuses and/or articles of manufacture are provided which may be implemented for use by an electronic device to track objects across two or more digital images. For example, an electronic device may generate a plurality of warped patches corresponding to a reference patch of a reference image, and combine two or more warped patches to form a blurred warped patch corresponding to the reference patch with a motion blur effect applied to a digital representation corresponding to a keypoint of an object to be tracked.
1. A method comprising, with an electronic device:
identifying a reference patch corresponding to at least a portion of an object as represented in a reference digital image, said reference patch representing at least a keypoint of said object to track within a plurality of digital images;
generating a plurality of warped patches corresponding to said reference patch by selectively applying modeled pose change effects to a digital representation of said keypoint; and
combining at least two of said plurality of warped patches to form a blurred warped patch corresponding to said reference patch with a motion blur effect applied to at least said digital representation of said keypoint, said combining of said at least two of said plurality of warped patches being based, at least in part, on an image capture exposure time of said electronic device.
2. The method as recited in claim 1 , and further comprising, with said electronic device:
determining whether said blurred warped patch substantially matches at least a portion of a digital image of said plurality of digital images.
3. The method as recited in claim 2 , and further comprising, with said electronic device:
adaptively determining a value representing how many of said plurality of warped patches to be combined to form said blurred warped patch that substantially matches at least said portion of said digital image of said plurality of images.
4. The method as recited in claim 1 , wherein generating said blurred warped patch further comprises:
generating said blurred warped patch corresponding to said reference patch based, at least in part, on a backward mapping approach.
5. An apparatus for use in an electronic device, the apparatus comprising:
means for identifying a reference patch corresponding to at least a portion of an object as represented in a reference digital image, said reference patch representing at least a keypoint of said object to track within a plurality of digital images;
means for generating a plurality of warped patches corresponding to said reference patch by selectively applying modeled pose change effects to a digital representation of said keypoint; and
means for combining at least two of said plurality of warped patches to form a blurred warped patch corresponding to said reference patch with a motion blur effect applied to at least said digital representation of said keypoint, said combining of said at least two of said plurality of warped patches being based, at least in part, on an image capture exposure time of said electronic device.
6. The apparatus as recited in claim 5 , and further comprising:
means for determining whether said blurred warped patch substantially matches at least a portion of a digital image of said plurality of digital images.
7. The apparatus as recited in claim 6 , and further comprising:
means for adaptively determining a value representing how many of said plurality of warped patches to be combined to form said blurred warped patch that substantially matches at least said portion of said digital image.
8. The apparatus as recited in claim 5 , and further comprising:
means for generating said blurred warped patch corresponding to said reference patch based, at least in part, on a backward mapping approach.
9. An electronic device comprising:
memory; and
a processing unit to:
identify a reference patch corresponding to at least a portion of an object as represented in a reference digital image, said reference patch representing at least a keypoint of said object to track within a plurality of digital images;
generate a plurality of warped patches corresponding to said reference patch by selectively applying modeled pose change effects to a digital representation of said keypoint; and
combine at least two of said plurality of warped patches to form a blurred warped patch corresponding to said reference patch with a motion blur effect applied at least to said digital representation of said keypoint, said combining of said at least two of said plurality warped patches being based, at least in part, on an image capture exposure time of said electronic device.
10. The electronic device as recited in claim 9 , said processing unit to further:
determine whether said blurred warped patch substantially matches at least a portion of a digital image of said plurality of digital images.
11. The electronic device as recited in claim 10 , said processing unit to further:
adaptively determine a value representing how many of said plurality of warped patches to be combined to form said blurred warped patch that substantially matches at least said portion of said digital image.
12. The electronic device as recited in claim 11 , said processing unit to further:
generate said blurred warped patch corresponding to said reference patch based, at least in part, on a backward mapping approach.
13. An article comprising:
a non-transitory computer readable medium having stored therein computer implementable instructions executable by a processing unit in electronic device to:
identify a reference patch corresponding to at least a portion of an object as represented in a reference digital image, said reference patch representing at least a keypoint of said object to track within a plurality of digital images;
generate a plurality of warped patches corresponding to said reference patch by selectively applying modeled pose change effects to a digital representation of said keypoint; and
combine at least two of said plurality of warped patches to form a blurred warped patch corresponding to said reference patch with a motion blur effect applied to at least said digital representation of said keypoint, said combining of said at least two of said plurality of warped patches being based, at least in part, on an image capture exposure time of said electronic device.
14. The article as recited in claim 13 , said computer implementable instructions being further executable by said processing unit to:
determine whether said blurred warped patch substantially matches at least a portion of a digital image of said plurality of digital images.
15. The article as recited in claim 14 , said computer implementable instructions being further executable by said processing unit to:
adaptively determine a value representing how many of said plurality of warped patches to be combined to form said blurred warped patch that substantially matches at least said portion of said digital image.
16. The article as recited in claim 13 , said computer implementable instructions being further executable by said processing unit to:
generate said blurred warped patch corresponding to said reference patch based, at least in part, on a backward mapping approach.