US 9,811,910 B1
Cloud-based image improvement
Leo Benedict Baldwin, San Jose, CA (US)
Assigned to AMAZON TECHNOLOGIES, INC., Reno, NV (US)
Filed by Amazon Technologies, Inc., Reno, NV (US)
Filed on May 18, 2015, as Appl. No. 14/714,747.
Application 14/714,747 is a continuation of application No. 13/830,936, filed on Mar. 14, 2013, granted, now 9,036,943.
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/54 (2006.01); G06T 7/00 (2017.01); G06F 17/30 (2006.01)
CPC G06T 7/0038 (2013.01) [G06F 17/3028 (2013.01); G06F 17/30247 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20216 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving, from an image sensor of a computing device, video data representing a first image resolution;
receiving a selection of first image data of the video data;
determining a first position of a first representation of an object in the first image data;
determining a second position of a second representation of the object in second image data of the video data;
determining a movement of the object based at least in part on the first position and the second position;
separating the first representation into one or more first sections based at least in part on the movement;
separating the second representation into one or more second sections based at least in part on the movement;
determining an image stack including at least a portion of the first image data overlaying at least a portion of the second image data by aligning the one or more first sections and the one or more second sections;
generating composite image data representing a second image resolution greater than the first image resolution based at least in part on pixel values of the image stack; and
sending the composite image data to the computing device.