IP Library › Granted Patent US 12,211,520
Granted Patent B2
US 12,211,520 · App. 18/364,637 · Granted Jan 28, 2025

Systems and methods for generating time-lapse videos

Inventors: Thomas Derbanne (Paris, FR); Cesar Douady (Orsay, FR); Maxim Karpushin (Paris, FR)
Assignee: GoPro, Inc.
G11B27/005G11B27/13G11B27/34H04N23/6812H04N23/683
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 12,211,520
App. No.
18/364,637
Granted
Jan 28, 2025
Kind
B2
Abstract

Video content may be captured by an image capture device during a capture duration. The video content may include video frames that define visual content viewable as a function of progress through a progress length of the video content. Rotational position information may characterize rotational positions of the image capture device during the capture duration. Time-lapse video frames may be determined from the video frames of the video content based on a spatiotemporal metric. The spatiotemporal metric may characterize spatial smoothness and temporal regularity of the time-lapse video frames. The spatial smoothness may be determined based on the rotational positions of the image capture device corresponding to the time-lapse video frames, and the temporal regularity may be determined based on moments corresponding to the time-lapse video frames. Time-lapse video content may be generated based on the time-lapse video frames.

Claims (38)

1. An image capture device for generating time-lapse videos, the image capture device comprising:

a housing;

an image sensor carried by the housing and configured to generate an image output signal conveying image information based on light that becomes incident thereon, the image information defining video frames;

an optical element carried by the housing and configured to guide light within a field of view to the image sensor; and

one or more physical processors configured by machine-readable instructions to:

determine time-lapse video frames from the video frames for generation of time-lapse video content, wherein the time-lapse video frames are determined based on regularity and/or consistency in spatial positions of the housing during capture of the video frames and based on regularity and/or consistency in time at which the video frames are captured, wherein determination of the time-lapse video frames from the video frames is limited by a lower skipping bound and an upper skipping bound, the lower skipping bound defining a minimum number of video frames for skipping and the upper skipping bound defining a maximum number of video frames for skipping in the determination of the time-lapse video frames from the video frames, the lower skipping bound and the upper skipping bound establishing a range of the video frames from which next time-lapse video frame is determined, wherein the determination of the time-lapse video frames from the video frames being limited by the lower skipping bound and the upper skipping bound includes the video frames outside the range of video frames not being captured by the image capture device; and

generate the time-lapse video content based on the time-lapse video frames.

2. The image capture device of claim 1 , wherein the time-lapse video frames are determined based on regularity and/or consistency in spatial positions of the housing during capture of the video frames to increase spatial smoothness of the time-lapse video frames.

3. The image capture device of claim 2 , wherein the spatial smoothness is determined further based on one or more transformations applied to the time-lapse video frames.

4. The image capture device of claim 1 , wherein temporal regularity of the time-lapse video frames is determined based on the moments corresponding to the time-lapse video frames, and the time-lapse video frames are determined to respect one or more constraints on the temporal regularity of the time-lapse video frames.

5. The image capture device of claim 4 , wherein the temporal regularity of the time-lapse video frames includes an extent of uniformity in temporal spacing of the moments corresponding to the time-lapse video frames.

6. The image capture device of claim 4 , wherein the temporal regularity of the time-lapse video frames includes an extent of match between perceived speed-up provided by the time-lapse video frames and desired speed-up for the time lapse video content.

7. The image capture device of claim 1 , wherein the one or more physical processors are, to determine the time-lapse video frames, further configured to:

select a set of video frames; and

stabilize at least some of the set of video frames.

8. The image capture device of claim 1 , wherein the time-lapse video content is generated based on storage of one or more sets of video frames in a frame selection buffer and a stabilization buffer.

9. The image capture device of claim 8 , wherein the frame selection buffer includes first memory to store video frames for use in determining the time-lapse video frames and the stabilization buffer includes second memory to store video frames for use in stabilizing the time-lapse video frames.

10. A method for generating time-lapse videos, the method performed by an image capture device, the image capture device including one or more processors, an image sensor, and an optical element, the image sensor configured to generate an image output signal conveying image information based on light that becomes incident thereon, the image information defining video frames, the optical element configured to guide light within a field of view to the image sensor, the method comprising:

determining time-lapse video frames from the video frames for generation of time-lapse video content, wherein the time-lapse video frames are determined based on regularity and/or consistency in spatial positions of the image capture device during capture of the video frames and based on regularity and/or consistency in time at which the video frames are captured, wherein determination of the time-lapse video frames from the video frames is limited by a lower skipping bound and an upper skipping bound, the lower skipping bound defining a minimum number of video frames for skipping and the upper skipping bound defining a maximum number of video frames for skipping in the determination of the time-lapse video frames from the video frames, the lower skipping bound and the upper skipping bound establishing a range of the video frames from which next time-lapse video frame is determined, wherein the determination of the time-lapse video frames from the video frames being limited by the lower skipping bound and the upper skipping bound includes the video frames outside the range of video frames not being captured by the image capture device; and

generating the time-lapse video content based on the time-lapse video frames.

11. The method of claim 10 , wherein the time-lapse video frames are determined based on regularity and/or consistency in spatial positions of the image capture device during capture of the video frames to increase spatial smoothness of the time-lapse video frames.

12. The method of claim 11 , wherein the spatial smoothness is determined further based on one or more transformations applied to the time-lapse video frames.

13. The method of claim 10 , wherein temporal regularity of the time-lapse video frames is determined based on the moments corresponding to the time-lapse video frames, and the time-lapse video frames are determined to respect one or more constraints on the temporal regularity of the time-lapse video frames.

14. The method of claim 13 , wherein the temporal regularity of the time-lapse video frames includes an extent of uniformity in temporal spacing of the moments corresponding to the time-lapse video frames.

15. The method of claim 13 , wherein the temporal regularity of the time-lapse video frames includes an extent of match between perceived speed-up provided by the time-lapse video frames and desired speed-up for the time lapse video content.

16. The method of claim 10 , wherein determining the time-lapse video frames includes:

selecting a set of video frames; and

stabilizing at least some of the set of video frames.

17. The method of claim 10 , wherein the time-lapse video content is generated based on storage of one or more sets of video frames in a frame selection buffer and a stabilization buffer.

18. The method of claim 17 , wherein the frame selection buffer includes first memory to store video frames for use in determining the time-lapse video frames and the stabilization buffer includes second memory to store video frames for use in stabilizing the time-lapse video frames.

19. An image capture device for generating time-lapse videos, the image capture device comprising:

a housing;

an image sensor carried by the housing and configured to generate an image output signal conveying image information based on light that becomes incident thereon, the image information defining video frames;

an optical element carried by the housing and configured to guide light within a field of view to the image sensor; and

one or more physical processors configured by machine-readable instructions to:

determine time-lapse video frames from the video frames for generation of time-lapse video content, wherein the time-lapse video frames are determined based on regularity and/or consistency in spatial positions of the housing during capture of the video frames and based on regularity and/or consistency in time at which the video frames are captured, further wherein the time-lapse video frames are determined based on regularity and/or consistency in spatial positions of the housing during capture of the video frames to increase spatial smoothness of the time-lapse video frames, temporal regularity of the time-lapse video frames is determined based on the moments corresponding to the time-lapse video frames, and the time-lapse video frames are determined to respect one or more constraints on the temporal regularity of the time-lapse video frames, wherein determination of the time-lapse video frames from the video frames is limited by a lower skipping bound and an upper skipping bound, the lower skipping bound defining a minimum number of video frames for skipping and the upper skipping bound defining a maximum number of video frames for skipping in the determination of the time-lapse video frames from the video frames, the lower skipping bound and the upper skipping bound establishing a range of the video frames from which next time-lapse video frame is determined, wherein the determination of the time-lapse video frames from the video frames being limited by the lower skipping bound and the upper skipping bound includes the video frames outside the range of video frames not being captured by the image capture device; and

generate the time-lapse video content based on the time-lapse video frames.

20. The image capture device of claim 19 , wherein the time-lapse video content is generated based on storage of one or more sets of video frames in a frame selection buffer and a stabilization buffer.

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 Aug 3, 2023
From: DERBANNE, THOMAS; DOUADY, CESAR; KARPUSHIN, MAXIM
To: GOPRO, INC.
Reel/Frame 064481/0712 →
Continuity (5)
Continuation 17575284 · Jan 13, 2022
Continuation 17118296 · Dec 10, 2020
Continuation 16786947 · Feb 10, 2020
Continuation 15978813 · May 14, 2018
Related Publication 20230377605A1 · Nov 23, 2023
References Cited (21)
US 10593363B2 · Derbanne · 2020 [cited by applicant]
US 10916272B2 · Derbanne · 2021 [cited by applicant]
US 11257521B2 · Derbanne · 2022 [cited by applicant]
US 11735225B2 · Derbanne · 2023 [cited by applicant]
US 20030185450A1 · Garakani · 2003 [cited by applicant]
US 20140105564A1 · Johar · 2014 [cited by applicant]
US 20150248916A1 · Kopf · 2015 [cited by examiner]
US 20160004390A1 · Laska · 2016 [cited by applicant]
US 20170094195A1 · Adsumilli · 2017 [cited by applicant]
US 20170180645A1 · Weckel · 2017 [cited by applicant]
US 20170195568A1 · Leizerovich, Jr. · 2017 [cited by examiner]
US 20170359549A1 · Baran · 2017 [cited by applicant]
US 20190348075A1 · Derbanne · 2019 [cited by applicant]
US 20200185005A1 · Derbanne · 2020 [cited by applicant]
US 20210090607A1 · Derbanne · 2021 [cited by applicant]
US 20220139425A1 · Derbanne · 2022 [cited by applicant]
Extended European Search Report for App. No. EP19802924.1, dated Nov. 24, 2021, 7 pages. [cited by applicant]
Grundmann, Matthias, Vivek Kwatra, and Irfan Essa. “Auto-directed video stabilization with robust L1 optimal camera paths.” IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE, 2011. pp. 225-232. [cited by applicant]
International Search Report and Written Opinion for Application No. PCT/US2019/031482, date of mailing Jul. 17, 2019, 9 pages. [cited by applicant]
Jia, Chao, and Brian L. Evans. “Constrained 3D Rotation Smoothing via Global Manifold Regression for Video Stabilization.” IEEE Trans. Signal Processing 62.13 (2014): 3293-3304. [cited by applicant]
Joshi, Neel, et al. “Real-time hyperlapse creation via optimal frame selection.” ACM Transactions on Graphics (TOG) 34.4 (2015): 63. 9 pages. [cited by applicant]