Systems and methods for combining multiple frames to produce media content with simulated exposure effects

US9774784B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9774784-B2
Application numberUS-201615295127-A
CountryUS
Kind codeB2
Filing dateOct 17, 2016
Priority dateDec 17, 2014
Publication dateSep 26, 2017
Grant dateSep 26, 2017

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames. Multiple frames within each stabilized subset in the plurality of stabilized subsets of frames can be combined to produce a plurality of combined frames. Each stabilized subset of frames can be utilized to produce a respective combined frame in the plurality of combined frames. A time-lapse media content item can be provided based on the plurality of combined frames.

First claim

Opening claim text (preview).

What is claimed is: 1. A computer-implemented method comprising: determining, by a computing system, a plurality of subsets of frames of an original set of frames; applying, by the computing system, an orientation-based image stabilization process to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames, wherein the applying the orientation-based image stabilization process comprises minimizing a rate of rotation between successive frames within each subset while minimizing empty regions below a threshold; combining, by the computing system, multiple frames within each stabilized subset in the plurality of stabilized subsets of frames to produce a plurality of combined frames, wherein each stabilized subset of frames is utilized to produce a respective combined frame in the plurality of combined frames; and generating, by the computing system, a time-lapse media content item based on the plurality of combined frames. 2. The computer-implemented method of claim 1 , wherein the applying of the orientation-based image stabilization process to each subset in the plurality of subsets of frames to produce the plurality of stabilized subsets of frames further comprises: acquiring timestamps for multiple frames within each subset in the plurality of subsets of frames; acquiring camera orientation data associated with a camera utilized to capture a media content including the original set of frames and associated with the timestamps for the multiple frames within each subset; generating a smoothed set of camera orientation data by minimizing the rate of rotation between the successive frames within each subset while minimizing the empty regions below the threshold; and warping the multiple frames within each subset based on the smoothed set of camera orientation data to produce each stabilized subset in the plurality of stabilized subsets of frames. 3. The computer-implemented method of claim 2 , wherein the orientation-based image stabilization process causes the multiple frames within each subset to be aligned relative to at least one of a respective first frame of the multiple frames within each subset or a specified alignment. 4. The computer-implemented method of claim 2 , wherein the camera incurs undesirable motion while capturing the media content including the original set of frames, and wherein the orientation-based image stabilization process reduces instability, caused by the undesirable motion, with respect to each subset in the plurality of subsets of frames. 5. The computer-implemented method of claim 1 , wherein a moving object is represented in at least one stabilized subset in the plurality of stabilized subsets, wherein the combining of the multiple frames within each stabilized subset comprises combining multiple frames within the at least one stabilized subset, and wherein the combining of the multiple frames within the at least one stabilized subset causes one or more motion trails associated with the moving object to appear in a combined frame produced based on the at least one stabilized sub set. 6. The computer-implemented method of claim 1 , wherein the combining of the multiple frames within each stabilized subset in the plurality of stabilized subsets of frames to produce the plurality of combined frames further comprises: blending pixels included in the multiple frames within each stabilized subset. 7. The computer-implemented method of claim 6 , wherein the blending of the pixels included in the multiple frames within each stabilized subset further comprises: calculating at least one of average pixel values for the pixels included in the multiple frames within each stabilized subset, maximum pixel values for the pixels included in the multiple frames within each stabilized subset, or minimum pixel values for the pixels included in the multiple frames within each stabilized subset. 8. The computer-implemented method of claim 1 , further comprising obtaining a subset selection input, wherein the subset selection input corresponds to at least one of a user command or a system setting, and wherein the subset selection input is obtained prior to at least one of the determining of the plurality of subsets of frames or the generating of the time-lapse media content item. 9. The computer-implemented method of claim 8 , wherein the subset selection input indicates a quantity of frames, and wherein the subset selection input causes each subset in the plurality of subsets to include the quantity of frames. 10. The computer-implemented method of claim 9 , wherein the quantity of frames is greater than one. 11. A system comprising: at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the system to perform: determining a plurality of subsets of frames of an original set of frames; applying an orientation-based image stabilization process to each subset in the plurality of subsets of frames to produce a plurality of stabilized subsets of frames, wherein the applying the orientation-based image stabilization process comprises minimizing a rate of rotation between successive frames within each subset while minimizing empty regions below a threshold; combining multiple frames within each stabilized subset in the plurality of stabilized subsets of frames to produce a plurality of combined frames, wherein each stabilized subset of frames is utilized to produce a respective combined frame in the plurality of combined frames; and generating a time-lapse media content item based on the plurality of combined frames. 12. The system of claim 11 , wherein the applying of the orientation-based image stabilization process to each subset in the plurality of subsets of frames to produce the plurality of stabilized subsets of frames further comprises: acquiring timestamps for multiple frames within each subset in the plurality of subsets of frames; acquiring camera orientation data associated with a camera utilized to capture a media content including the original set of frames and associated with the timestamps for the multiple frames within each subset; generating a smoothed set of camera orientation data by minimizing the rate of rotation between the successive frames within each subset while minimizing the empty regions below the threshold; and warping the multiple frames within each subset based on the smoothed set of camera orientation data to produce each stabilized subset in the plurality of stabilized subsets of frames. 13. The system of claim 11 , wherein a moving object is represented in at least one stabilized subset in the plurality of stabilized subsets, wherein the combining of the multiple frames within each stabilized subset comprises combining multiple frames within the at least one stabilized subset, and wherein the combining of the multiple frames within the at least one stabilized subset causes one or more motion trails associated with the moving object to appear in a combined frame produced based on the at least one stabilized subset. 14. The system of claim 11 , wherein the combining of the multiple frames within each stabilized subset in the plurality of stabilized subsets of frames to produce the plurality of combined frames further comprises: blending pixels included in the multiple frames within each stabilized subset. 15. The system of claim 14 , wherein the blending of the pixels included in the multiple frames within each stabilized subset further comprises: calculating at least one of average pixel values for the pixels included in the multiple frames within each sta

Assignees

Inventors

Classifications

  • G06T5/50Primary

    using two or more images, e.g. averaging or subtraction · CPC title

  • performed by a processor, e.g. controlling the readout of an image memory · CPC title

  • for stable pick-up of the scene, e.g. compensating for camera body vibrations · CPC title

  • based on additional sensors, e.g. acceleration sensors · CPC title

  • by combination of a plurality of images sequentially taken · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9774784B2 cover?
Systems, methods, and non-transitory computer-readable media can capture media content including an original set of frames. A plurality of subsets of frames can be identified, based on a subset selection input, out of the original set of frames. An orientation-based image stabilization process can be applied to each subset in the plurality of subsets of frames to produce a plurality of stabiliz…
Who is the assignee on this patent?
Facebook Inc
What technology area does this patent fall under?
Primary CPC classification G06T5/50. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Sep 26 2017 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 1 related publication on this page (citations in our corpus or others sharing the same primary CPC).