IP Library › Granted Patent US 12,483,664
Granted Patent B2
US 12,483,664 · App. 18/635,737 · Granted Nov 25, 2025

Image stitching with electronic rolling shutter correction

Inventors: Bruno César Douady-Pleven (Orsay, FR); Antoine Meler (Chapareillan, FR); Christophe Clienti (Saint-Maur-des-Fosses, FR)
Assignee: GoPro, Inc.
H04N1/3876G06T3/18G06T5/77H04N23/45H04N23/698H04N25/531
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 12,483,664
App. No.
18/635,737
Granted
Nov 25, 2025
Kind
B2
Abstract

Systems and methods are disclosed for image signal processing. For example, methods may include receiving a first image from a first image sensor, receiving a second image from a second image sensor; obtaining corrected images based on the first image and the second image; obtaining stabilized images based on the corrected images; applying a parallax correction to the stabilized images to obtain a composite image; obtaining a transformed image from the composite image; and encoding an output image based on the transformed image.

Claims (66)

1 . A system comprising:

a first image sensor configured to detect a first image;

a second image sensor configured to detect a second image;

an angular rate sensor; and

a processing apparatus that is configured to:

obtain angular rate measurements from the angular rate sensor for a device including the first image sensor and the second image sensor for times during capture of the first image and the second image;

determine an electronic rolling shutter correction based on the angular rate measurements and times when portions of the first image and the second image were captured using an electronic rolling shutter;

obtain corrected images based on the first image and the second image, wherein the processing apparatus is configured to determine a near point for an initial epipolar line, and a compensated near point, wherein the compensated near point is determined based on the near point and electronic rolling shutter data associated with the near point;

obtain stabilized images based on the corrected images;

apply a parallax correction to the stabilized images to obtain a composite image;

obtain a transformed image from the composite image; and

encode an output image based on the transformed image.

2 . The system of claim 1 , wherein the processing apparatus is further configured to:

determine compensated epipolar lines based on the electronic rolling shutter data; and

determine one of the compensated epipolar lines based on the compensated near point.

3 . The system of claim 2 , in which an electronic rolling shutter correction is determined at a lower resolution than the parallax correction.

4 . The system of claim 3 , wherein the initial epipolar line is determined geometrically based on a relative position of the first image sensor and the second image sensor.

5 . The system of claim 1 , wherein the parallax correction is based on a pre-compensated electronic rolling shutter distortion.

6 . The system of claim 1 , in which the processing apparatus is configured to:

determine rotations for respective portions of the first image and the second image based on the angular rate measurements corresponding to times when respective portions were captured;

interpolate the rotations to determine interpolated rotations for portions of the first image and the second image; and

determine an electronic rolling shutter correction based on the interpolated rotations.

7 . The system of claim 6 , wherein the parallax correction is based on a one-dimensional search.

8 . The system of claim 6 , comprising:

a first fish-eye lens attached to the first image sensor; and

a second fish-eye lens attached to the second image sensor.

9 . The system of claim 1 , wherein the parallax correction is based on a pre-compensated electronic rolling shutter distortion.

10 . The system of claim 1 , further comprising:

a storage device configured to store the transformed image; and

a touchscreen display configured to display the transformed images.

11 . A method comprising:

detecting a first image;

detecting a second image;

obtaining angular rate measurements from an angular rate sensor for a device for times during capture of the first image and the second image;

determining an electronic rolling shutter correction based on the angular rate measurements and times when portions of the first image and the second image were captured using an electronic rolling shutter;

determining a near point for an initial epipolar line, and a compensated near point, wherein the compensated near point is determined based on the near point and electronic rolling shutter data associated with the near point, to obtain corrected images based on the first image and the second image;

obtaining stabilized images based on the corrected images;

applying a parallax correction to the stabilized images to obtain a composite image;

obtaining a transformed image from the composite image; and

encoding an output image based on the transformed image.

12 . The method of claim 11 , further comprising:

determining compensated epipolar lines based on the electronic rolling shutter data.

13 . The method of claim 12 , wherein determining the compensated epipolar lines comprises:

determining a far point for the initial epipolar line; and

determining one of the compensated epipolar lines based on the far point and the compensated near point.

14 . The method of claim 13 , wherein the parallax correction is based on a pre-compensated electronic rolling shutter distortion.

15 . The method of claim 14 , wherein the parallax correction includes a stitching profile.

16 . The method of claim 11 , comprising:

obtaining angular rate measurements from an angular rate sensor for a device including a first image sensor and a second image sensor for times during capture of the first image and the second image; and

determining the electronic rolling shutter correction based on the angular rate measurements and times when portions of the first image and the second image were captured using an electronic rolling shutter.

17 . A non-transitory computer-readable medium comprising instructions, that when executed by a processor, cause the processor to perform operations comprising:

detecting a first image;

detecting a second image;

obtaining angular rate measurements from an angular rate sensor for a device for times during capture of the first image and the second image;

determining an electronic rolling shutter correction based on the angular rate measurements and times when portions of the first image and the second image were captured using an electronic rolling shutter;

determining a near point for an initial epipolar line, and a compensated near point, wherein the compensated near point is determined based on the near point and electronic rolling shutter data associated with the near point, to obtain corrected images based on the first image and the second image;

obtaining stabilized images based on the corrected images;

applying a parallax correction to the stabilized images to obtain a composite image;

obtaining a transformed image from the composite image; and

encoding an output image based on the transformed image.

18 . The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise:

determining compensated epipolar lines based on the electronic rolling shutter data.

19 . The non-transitory computer-readable medium of claim 18 , wherein determining the compensated epipolar lines comprises:

determining a far point for the initial epipolar line; and

determining one of the compensated epipolar lines based on the far point and the compensated near point.

20 . The non-transitory computer-readable medium of claim 17 , wherein the parallax correction is based on a pre-compensated electronic rolling shutter distortion.

Assignments (3)
SECURITY INTEREST Recorded Aug 4, 2025
From: GOPRO, INC.
To: FARALLON CAPITAL MANAGEMENT, L.L.C., AS AGENT
Reel/Frame 072340/0676 →
SECURITY INTEREST Recorded Aug 4, 2025
From: GOPRO, INC.
To: WELLS FARGO BANK, NATIONAL ASSOCIATION, AS AGENT
Reel/Frame 072358/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 11, 2024
From: DOUADY-PLEVEN, BRUNO CÉSAR; MELER, ANTOINE; CLIENTI, CHRISTOPHE
To: GOPRO, INC.
Reel/Frame 068553/0137 →
Continuity (4)
Continuation 17180153 · Feb 19, 2021
Continuation 16680732 · Nov 12, 2019
Continuation 15681764 · Aug 21, 2017
Related Publication 20240259514A1 · Aug 1, 2024
References Cited (84)
US 5963664A · Kumar · 1999 [cited by applicant]
US 6985619B1 · Seta · 2006 [cited by applicant]
US 8619082B1 · Ciurea · 2013 [cited by applicant]
US 8970675B2 · Morioka · 2015 [cited by applicant]
US 9639935B1 · Douady-Pleven · 2017 [cited by examiner]
US 10477064B2 · Douady-Pleven · 2019 [cited by examiner]
US 10931851B2 · Douady-Pleven · 2021 [cited by examiner]
US 11962736B2 · Douady-Pleven · 2024 [cited by applicant]
US 20060204040A1 · Freeman · 2006 [cited by applicant]
US 20070081081A1 · Cheng · 2007 [cited by examiner]
US 20080240612A1 · Liang · 2008 [cited by applicant]
US 20090290641A1 · Crinon · 2009 [cited by applicant]
US 20100085442A1 · Yamashita · 2010 [cited by examiner]
US 20100141799A1 · Yamashita · 2010 [cited by examiner]
US 20100189179A1 · Gu · 2010 [cited by applicant]
US 20100322306A1 · Au · 2010 [cited by applicant]
US 20110033130A1 · Poon · 2011 [cited by applicant]
US 20120105597A1 · Tajiri · 2012 [cited by applicant]
US 20120154545A1 · Choi · 2012 [cited by applicant]
US 20120188389A1 · Lin · 2012 [cited by examiner]
US 20120293608A1 · Doepke · 2012 [cited by examiner]
US 20120293610A1 · Doepke · 2012 [cited by examiner]
US 20120307085A1 · Mantzel · 2012 [cited by examiner]
US 20130021483A1 · Bennett · 2013 [cited by applicant]
US 20130051689A1 · Shimauchi · 2013 [cited by applicant]
US 20130051697A1 · Takahashi · 2013 [cited by applicant]
US 20130265460A1 · Wu · 2013 [cited by examiner]
US 20140028876A1 · Mills · 2014 [cited by applicant]
US 20140160309A1 · Karpenko · 2014 [cited by applicant]
US 20140341287A1 · Mody · 2014 [cited by applicant]
US 20140369584A1 · Fan · 2014 [cited by applicant]
US 20150002734A1 · Lee · 2015 [cited by applicant]
US 20150016543A1 · Rapaka · 2015 [cited by applicant]
US 20150042767A1 · Ciurea · 2015 [cited by applicant]
US 20150049193A1 · Gupta · 2015 [cited by applicant]
US 20150085149A1 · Tsubaki · 2015 [cited by examiner]
US 20150254868A1 · Srikanth · 2015 [cited by applicant]
US 20150271483A1 · Sun · 2015 [cited by examiner]
US 20150278988A1 · MacMillan · 2015 [cited by examiner]
US 20150293328A1 · Laroia · 2015 [cited by applicant]
US 20150302561A1 · Pekkucuksen · 2015 [cited by applicant]
US 20150317781A1 · Napier · 2015 [cited by applicant]
US 20160037061A1 · Lim · 2016 [cited by applicant]
US 20160050370A1 · Campbell · 2016 [cited by examiner]
US 20160063676A1 · Donovan · 2016 [cited by examiner]
US 20160125570A1 · Macmillan · 2016 [cited by examiner]
US 20160142643A1 · Jiang · 2016 [cited by applicant]
US 20160205381A1 · Macmillan · 2016 [cited by examiner]
US 20160234437A1 · Kuwada · 2016 [cited by examiner]
US 20160307346A1 · Staudenmaier · 2016 [cited by applicant]
US 20160309134A1 · Venkataraman · 2016 [cited by examiner]
US 20160358355A1 · Lin · 2016 [cited by applicant]
US 20170006219A1 · Adsumilli · 2017 [cited by examiner]
US 20170053392A1 · Sun · 2017 [cited by examiner]
US 20170084007A1 · Rakhshanfar · 2017 [cited by applicant]
US 20170085796A1 · Rangam · 2017 [cited by examiner]
US 20170091970A1 · Adsumilli · 2017 [cited by examiner]
US 20170111652A1 · Davies · 2017 [cited by applicant]
US 20170287184A1 · Pettersson · 2017 [cited by applicant]
US 20170366803A1 · Kerstein · 2017 [cited by examiner]
US 20180040150A1 · Saporetti · 2018 [cited by examiner]
US 20180253875A1 · Gorur Sheshagiri · 2018 [cited by examiner]
US 20180262683A1 · Meler · 2018 [cited by applicant]
US 20190020802A1 · Melkote Krishnaprasad · 2019 [cited by examiner]
US 20190058811A1 · Douady-Pleven · 2019 [cited by examiner]
US 20200084338A1 · Douady-Pleven · 2020 [cited by examiner]
US 20200092474A1 · Kuwada · 2020 [cited by examiner]
US 20210281710A1 · Douady-Pleven · 2021 [cited by applicant]
US 20210405518A1 · Lablans · 2021 [cited by examiner]
CN 105389776A · 2016 [cited by applicant]
CN 106415391A · 2017 [cited by applicant]
JP 2017059998A · 2017 [cited by examiner]
WO 2015172235A1 · 2015 [cited by applicant]
WO 2017205597 · 2017 [cited by applicant]
Y. Dai, H. Li and L. Kneip, “Rolling Shutter Camera Relative Pose: Generalized Epipolar Geometry,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 4132-4140, doi: 10… [cited by examiner]
J. - H. Kim, Y. Latif and I. Reid, “RRD-SLAM: Radial-distorted rolling-shutter direct SLAM,” 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017, pp. 5148-5154, doi: 10.1109/ICRA.2017.7… [cited by examiner]
Form PCT/ISA/206 and Annex to Form PCT/ISA/206 Communication Relating to the Results of the Partial International Search for International Application No. PCT/US2017/034231 dated Sep. 13, 2017 (14 pgs). [cited by applicant]
International Preliminary Report on Patentability for Application No. PCT/US2018/047129, mailed Mar. 5, 2020, 7 pages. [cited by applicant]
International Search Report and Written Opinion for PCT/US2018/047129, mailed Dec. 12, 2018, 10 pages. [cited by applicant]
PCT International Preliminary Report and Written Opinion for PCT/US2017/034231 dated Nov. 27, 2018, 11 pages. [cited by applicant]
PCT International Preliminary Report and Writtten Opinion for PCT/US2017/034422, Nov. 27, 2018, 10 pages. [cited by applicant]
PCT International Search Report and Written Opinion for PCT/US16/31076, Aug. 8, 2016, 19 Pages. [cited by applicant]
PCT International Search Report and Written Opinion for PCT/US2017/034231 dated Nov. 7, 2017, 19 pages. [cited by applicant]
Pesquet-Popescu et al., “Motion Estimation Techniques,” TELECOM Paris Tech, 2016, https://pdfs.semanticscholar.org/98ca/f8325abb40aa6bbddd0e7f5d3a6c366d03e6.pdf, 76 pages. [cited by applicant]