IP Library › Granted Patent US 12,462,333
Granted Patent B2
US 12,462,333 · App. 18/463,179 · Granted Nov 4, 2025

Systems and methods for fusing images

Inventors: James Wilson Nash (San Diego, CA); Kalin Mitkov Atanassov (San Diego, CA); Sergiu Radu Goma (Sedona, AZ)
Assignee: QUALCOMM Incorporated
G06T3/053G06F18/22G06T3/4038G06T5/20G06T5/50G06T5/70G06T7/11G06T7/30H04N5/2621H04N9/76H04N23/45H04N23/698H04N23/81H04N23/951H04N25/60G06T2207/10016G06T2207/20004G06T2207/20221H04N23/58
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,462,333
App. No.
18/463,179
Granted
Nov 4, 2025
Kind
B2
Abstract

A method performed by an electronic device is described. The method includes obtaining a first image from a first camera, the first camera having a first focal length and a first field of view. The method also includes obtaining a second image from a second camera, the second camera having a second focal length and a second field of view disposed within the first field of view. The method further includes aligning at least a portion of the first image and at least a portion of the second image to produce aligned images. The method additionally includes fusing the aligned images based on a diffusion kernel to produce a fused image. The diffusion kernel indicates a threshold level over a gray level range. The method also includes outputting the fused image. The method may be performed for each of a plurality of frames of a video feed.

Claims (34)

1 . An apparatus comprising:

at least one memory; and

at least one processor coupled to the at least one memory and configured to:

select, for a fused image, pixels from a first area of a first image obtained using a first type of lens;

select, for the fused image, pixels from a first area of a second image obtained using a second type of lens that is different than the first type of lens, wherein the first area of the first image and the first area of the second image are within a region of interest, wherein a portion of the region of interest is outside of the first image and is smaller than the second image, and wherein the first area of the second image obtained using the second type of lens is used to fill in the portion of the region of interest not captured in the first area of the first image obtained using the first type of lens;

blend pixels in a second area of the first image and pixels in a second area of the second image to obtain blended pixels; and

include the pixels from the first area of the first image, the pixels from the first area of the second image, and the blended pixels in the fused image.

2 . The apparatus of claim 1 , wherein the at least one processor is configured to:

output the fused image.

3 . The apparatus of claim 1 , wherein the second area of the first image is within the first area of the first image, and wherein the second area of the second image is within the first area of the second image.

4 . The apparatus of claim 3 , wherein the second area of the first image overlaps with the second area of the second image.

5 . The apparatus of claim 1 , wherein the first area of the first image comprises a first composite region from the first image, and wherein the first area of the second image comprises a second composite region from the second image.

6 . The apparatus of claim 5 , wherein, to blend the pixels in the second area of the first image and the pixels in the second area of the second image, the at least one processor is configured to:

perform seam blending between the first composite region and the second composite region.

7 . The apparatus of claim 1 , wherein the at least one processor is configured to blend the pixels in the second area of the first image and the pixels in the second area of the second image to recover the portion of the region of interest based on replacing the portion of the region of interest that does not exist in the first image with at least a part of the second image.

8 . The apparatus of claim 1 , wherein the first type of lens is a telephoto lens, and wherein the second type of lens is a wide-angle lens.

9 . The apparatus of claim 1 , wherein the first image and the second image are captured concurrently.

10 . The apparatus of claim 1 , wherein the first image and the second image are captured at different times.

11 . A method performed by an electronic device, the method comprising:

selecting, for a fused image, pixels from a first area of a first image obtained using a first type of lens;

selecting, for the fused image, pixels from a first area of a second image obtained using a second type of lens that is different than the first type of lens, wherein the first area of the first image and the first area of the second image are within a region of interest, wherein a portion of the region of interest is outside of the first image and is smaller than the second image, and wherein the first area of the second image obtained using the second type of lens is used to fill in a portion of the region of interest not captured in the first area of the first image obtained using the first type of lens;

blending pixels in a second area of the first image and pixels in a second area of the second image to obtain blended pixels; and

including the pixels from the first area of the first image, the pixels from the first area of the second image, and the blended pixels in the fused image.

12 . The method of claim 11 , further comprising:

outputting the fused image.

13 . The method of claim 11 , wherein the second area of the first image is within the first area of the first image, and wherein the second area of the second image is within the first area of the second image.

14 . The method of claim 13 , wherein the second area of the first image overlaps with the second area of the second image.

15 . The method of claim 11 , wherein the first area of the first image comprises a first composite region from the first image, and wherein the first area of the second image comprises a second composite region from the second image.

16 . The method of claim 15 , wherein blending the pixels in the second area of the first image and the pixels in the second area of the second image comprises:

performing seam blending between the first composite region and the second composite region.

17 . The method of claim 11 , wherein blending the pixels in the second area of the first image and the pixels in the second area of the second image is performed in order to recover the portion of the region of interest based on replacing the portion of the region of interest that does not exist in the first image with at least a part of the second image.

18 . The method of claim 11 , wherein the first type of lens is a telephoto lens, and wherein the second type of lens is a wide-angle lens.

19 . The method of claim 11 , wherein the first image and the second image are captured concurrently.

20 . The method of claim 11 , wherein the first image and the second image are captured at different times.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 17, 2023
From: NASH, JAMES WILSON; ATANASSOV, KALIN MITKOV; GOMA, SERGIU RADU
To: QUALCOMM INCORPORATED
Reel/Frame 065248/0370 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 16, 2023
From: NASH, JAMES WILSON; ATANASSOV, KALIN MITKOV; GOMA, SERGIU RADU
To: QUALCOMM INCORPORATED
Reel/Frame 065230/0929 →
Continuity (4)
Continuation 16375795 · Apr 4, 2019
Continuation 15498905 · Apr 27, 2017
Provisional Application 62402182 · Sep 30, 2016
Related Publication 20230419437A1 · Dec 28, 2023
References Cited (67)
US 6545685B1 · Dorbie · 2003 [cited by examiner]
US 7009638B2 · Gruber et al. · 2006 [cited by applicant]
US 7305180B2 · Labaziewicz et al. · 2007 [cited by applicant]
US 8526779B1 · Simmons et al. · 2013 [cited by applicant]
US 8619148B1 · Watts · 2013 [cited by examiner]
US 8664579B2 · Olsen et al. · 2014 [cited by applicant]
US 8717412B2 · Linder et al. · 2014 [cited by applicant]
US 9185291B1 · Shabtay et al. · 2015 [cited by applicant]
US 9398264B2 · Georgiev et al. · 2016 [cited by applicant]
US 9414037B1 · Solh · 2016 [cited by applicant]
US 10297034B2 · Nash et al. · 2019 [cited by applicant]
US 11509837B2 · Liu et al. · 2022 [cited by applicant]
US 20020180759A1 · Park · 2002 [cited by examiner]
US 20070083114A1 · Yang et al. · 2007 [cited by applicant]
US 20080030592A1 · Border et al. · 2008 [cited by applicant]
US 20080218611A1 · Parulski et al. · 2008 [cited by applicant]
US 20080218613A1 · Janson · 2008 [cited by examiner]
US 20090073254A1 · Li et al. · 2009 [cited by applicant]
US 20100238327A1 · Griffith · 2010 [cited by examiner]
US 20120026366A1 · Golan et al. · 2012 [cited by applicant]
US 20130016186A1 · Atanassov et al. · 2013 [cited by applicant]
US 20130169834A1 · Herz et al. · 2013 [cited by applicant]
US 20140168444A1 · Bae et al. · 2014 [cited by applicant]
US 20140313353A1 · Echigo · 2014 [cited by examiner]
US 20150085174A1 · Shabtay et al. · 2015 [cited by applicant]
US 20150145950A1 · Murphy et al. · 2015 [cited by applicant]
US 20150189140A1 · Sutton · 2015 [cited by examiner]
US 20150207999A1 · Han · 2015 [cited by examiner]
US 20150296154A1 · Laroia · 2015 [cited by examiner]
US 20160028949A1 · Lee · 2016 [cited by examiner]
US 20160050351A1 · Lee · 2016 [cited by examiner]
US 20160173883A1 · Lawrence · 2016 [cited by examiner]
US 20160309095A1 · Laroia et al. · 2016 [cited by applicant]
US 20170041553A1 · Cao et al. · 2017 [cited by applicant]
US 20170230585A1 · Nash et al. · 2017 [cited by applicant]
US 20180070018A1 · Bian · 2018 [cited by examiner]
US 20180096487A1 · Nash et al. · 2018 [cited by applicant]
US 20180183982A1 · Lee et al. · 2018 [cited by applicant]
US 20180227505A1 · Baltz · 2018 [cited by examiner]
US 20180278884A1 · Abe · 2018 [cited by applicant]
US 20180315156A1 · Shin · 2018 [cited by applicant]
US 20190122349A1 · Cohen et al. · 2019 [cited by applicant]
US 20190236794A1 · Nash et al. · 2019 [cited by applicant]
US 20200120284A1 · Kini et al. · 2020 [cited by applicant]
US 20210360172A1 · Liu et al. · 2021 [cited by applicant]
CN 103152518A · 2013 [cited by applicant]
CN 105141807A · 2015 [cited by applicant]
CN 105308947A · 2016 [cited by applicant]
CN 105491278A · 2016 [cited by applicant]
CN 105657237A · 2016 [cited by applicant]
CN 105681633A · 2016 [cited by applicant]
CN 106303258A · 2017 [cited by applicant]
WO 2012024830A1 · 2012 [cited by applicant]
WO 2014062481 · 2014 [cited by applicant]
WO 2014199338A2 · 2014 [cited by applicant]
Atanassov K., et al., “Temporal Image Stacking for Noise Reduction and Dynamic Range Improvement”, Proceedings Optical Diagnostics of Living Cells II, vol. 8667, Feb. 26, 2013, 86671P, 11 pages, XP055417957, ISSN: 0277-… [cited by applicant]
Co-pending U.S. Appl. No. 16/667,662, inventor Liu; Shizhong, filed on Oct. 29, 2019. [cited by applicant]
International Preliminary Report on Patentability—PCT/US2017/043769, The International Bureau of WIPO—Geneva, Switzerland, Apr. 11, 2019. [cited by applicant]
International Search Report and Written Opinion—PCT/US2017/043769—ISA/EPO—Nov. 6, 2017. [cited by applicant]
International Search Report and Written Opinion—PCT/US2021/027278—ISA/EPO—Jul. 1, 2021. [cited by applicant]
Kahraman F., et al., “Image Frame Fusion Using 3D Anisotropic Diffusion”, 23rd International Symposium on Computer and Information Sciences, Oct. 27, 2008, pp. 1-6, XP031375516, DOI: 10.1109/ISCIS.2008.4717968. [cited by applicant]
Kumar B.K.S., “Image Fusion Based on Pixel Significance Using Cross Bilateral Filter”, Signal, Image and Video Processing, vol. 9, No. 5, Oct. 5, 2013, pp. 1193-1204, XP055330239, ISSN: 1863-1703, DOI: 10.1007/s11760-01… [cited by applicant]
Li S., et al., “Image Fusion With Guided Filtering”, IEEE Transactions on Image Processing, vol. 22, No. 7, Jul. 1, 2013, pp. 2864-2875, XP011510936, ISSN: 1057-7149, DOI: 10.1109/TIP.2013.2244222. [cited by applicant]
Zitova B., et al., “Image registration methods: a survey,” Image and Vision Computing, Oct. 2003, vol. 21, No. 11, pp. 977-1000. [cited by applicant]
Kylmamaa M., “Creating A Post-Processing Framework: Tips Tricks”, Internet Citation, Oct. 3, 2006 (Oct. 3, 2006), XP001543462, 10 Pages. [cited by applicant]
Weickert J., et al., “Theoretical Foundations of Anisotropic Diffusion in Image Processing”, Theoretical Foundations of Computer Vision, Computing Supplement 11, 1996, pp. 221-236, DOI: 10.1007/978-3-7091-6586-7_13, (Ye… [cited by applicant]
European Search Report—EP24171445—Search Authority—The Hague—Oct. 7, 2024. [cited by applicant]