	US 12,437,419 B2
	Tracking-based motion deblurring via coded exposure
Suren Jayasuriya, Tempe, AZ (US); Odrika Iqbal, Tempe, AZ (US); and Andreas Spanias, Tempe, AZ (US)
Assigned to Arizona Board of Regents on Behalf of Arizona State University, Tempe, AZ (US)
Filed by Suren Jayasuriya, Tempe, AZ (US); Odrika Iqbal, Tempe, AZ (US); and Andreas Spanias, Tempe, AZ (US)
Filed on Nov. 21, 2023, as Appl. No. 18/516,679.
Application 18/516,679 is a division of application No. 17/348,392, filed on Jun. 15, 2021, granted, now 11,880,984.
Claims priority of provisional application 63/041,260, filed on Jun. 19, 2020.
Claims priority of provisional application 63/039,224, filed on Jun. 15, 2020.
Prior Publication US 2024/0153103 A1, May 9, 2024
Int. Cl. G06T 7/20 (2017.01); G06T 5/73 (2024.01); H04N 19/20 (2014.01); H04N 23/73 (2023.01)

CPC G06T 7/20 (2013.01) [G06T 5/73 (2024.01); H04N 19/20 (2014.11); H04N 23/73 (2023.01)]

7 Claims

1. An imaging device, comprising:

an image sensor; and

an image processor coupled to an optical sensor and configured to:

receive image data capturing a scene from the image sensor;

track a region of interest (ROI) corresponding to a blurred object across multiple frames in the image data;

perform coded exposure deblurring of the scene, to:

modulate one or more photodiodes of the image sensor based on the tracked ROI across the multiple frames of the image data; and

encode motion blur associated with the ROI in the scene from the image data captured by the image sensor as the ROI is tracked across the multiple frames of the image data,

wherein deblurring of the ROI in the scene is performed subsequent to the tracking and identification of the ROI, and

wherein mean shift tracking is employed to track the ROI to locate the ROI in each frame.