公开(公告)号：US20180205909A1

公开(公告)日：2018-07-19

申请号：US15407089

申请日：2017-01-16

Applicant: GoPro, Inc.

Inventor： Aaron Staranowicz ,  Ryan Lustig

IPC: H04N7/01

CPC classification number: H04N7/014 ,  G06T3/40 ,  H04N11/20

Abstract: Methods and apparatus for the generation of interpolated frames of video data. In one embodiment, the interpolated frames of video data are generated by obtaining two or more frames of video data; performing Lagrangian interpolation on one or more portions of the obtained two or more frames of video data to generate a Lagrangian interpolated image; performing Eulerian interpolation on one or more portions of the obtained two or more frames to generate a Eulerian interpolated image; and when the Lagrangian interpolated image and the Eulerian interpolated image should be combined, computing an average interpolated image using the Lagrangian interpolated image and the Eulerian interpolated image; otherwise, selecting either the Lagrangian interpolated image or the Eulerian interpolated image; and generating an interpolated frame of video data using one or more of the average interpolated image, the Lagrangian interpolated image, or the Eulerian interpolated image.

公开(公告)号：US20180063551A1

公开(公告)日：2018-03-01

申请号：US15251980

申请日：2016-08-30

Applicant: GoPro, Inc.

Inventor： Balineedu Chowdary Adsumilli ,  Ryan Lustig ,  Aaron Staranowicz

IPC: H04N19/80 ,  H04N19/43 ,  H04L12/26

CPC classification number: H04N19/172 ,  H04N19/132 ,  H04N19/137 ,  H04N19/146 ,  H04N19/162 ,  H04N19/587 ,  H04N19/96

Abstract: Apparatus and methods for generating interpolated frames in digital image or video data. In one embodiment, the interpolation is based on a hierarchical tree sequence. At each level of the tree, an interpolated frame may be generated using original or interpolated frames of the video, such as those closest in time to the desired time of the frame to be generated. The sequence proceeds through lower tree levels until a desired number of interpolated frames, a desired video length, a desired level, or a desired visual quality for the video is reached. In some implementations, the sequence may use different interpolation algorithms (e.g., of varying computational complexity or types) at different levels of the tree. The interpolation algorithms can include for example those based on frame repetition, frame averaging, motion compensated frame interpolation, and motion blending.

公开(公告)号：US20170094194A1

公开(公告)日：2017-03-30

申请号：US15080292

申请日：2016-03-24

Applicant: GoPro, Inc.

Inventor： Balineedu Chowdary Adsumilli ,  Ryan Lustig

IPC: H04N5/272 ,  G06T7/20 ,  H04N13/00 ,  H04N5/235 ,  G06T5/00 ,  G06T7/00

CPC classification number: H04N5/272 ,  G06T5/002 ,  G06T7/11 ,  G06T7/143 ,  G06T7/174 ,  G06T7/194 ,  G06T7/20 ,  G06T7/254 ,  G06T11/60 ,  G06T15/503 ,  G06T2207/10016 ,  G06T2207/10021 ,  G06T2207/20036 ,  H04N5/2356 ,  H04N13/128 ,  H04N2013/0085 ,  H04N2013/0092

Abstract: A processing device generates composite images from a sequence of images. The composite images may be used as frames of video. A foreground/background segmentation is performed at selected frames to extract a plurality of foreground object images depicting a foreground object at different locations as it moves across a scene. The foreground object images are stored to a foreground object list. The foreground object images in the foreground object list are overlaid onto subsequent video frames that follow the respective frames from which they were extracted, thereby generating a composite video.

公开(公告)号：US11503209B2

公开(公告)日：2022-11-15

申请号：US16538641

申请日：2019-08-12

Applicant: GoPro, Inc.

Inventor： Ryan Lustig ,  Balineedu Chowdary Adsumilli

IPC: H04N5/232

Abstract: A target image captured from a fisheye lens or other lens with known distortion parameters may be transformed to align it to a reference image. Corresponding features may be detected in the target image and the reference image. The features may be transformed to a spherical coordinate space. In the spherical space, images may be re-pointed or rotated in three dimensions to align all or a subset of the features of the target image to the corresponding features of the reference image. For example, in a sequence of images, background features of the target image in the spherical image space may be aligned to background features of the reference image in the spherical image space to compensate for camera motion while preserving foreground motion. An inverse transformation may then be applied to bring the images back into the original image space.

公开(公告)号：US11151704B2

公开(公告)日：2021-10-19

申请号：US16692280

申请日：2019-11-22

Applicant: GoPro, Inc.

Inventor： Aaron Staranowicz ,  Ryan Lustig ,  Desmond Chik

IPC: G06T5/00 ,  G06T5/20 ,  G06T5/50 ,  G06T7/215 ,  H04N7/00 ,  H04N19/139 ,  H04N7/01

Abstract: Methods and apparatus for the generation of interpolated frames of video data. In one embodiment, the interpolated frames of video data are generated by obtaining two or more frames of video data from a video sequence; determining frame errors for the obtained two or more frames from the video sequence, determining whether the frame errors exceed a threshold value; performing a multi-pass operation; performing a single-pass operation; performing frame blending; performing edge correction; and generating the interpolated frame of image data.

公开(公告)号：US10382683B2

公开(公告)日：2019-08-13

申请号：US15967364

申请日：2018-04-30

Applicant: GoPro, Inc.

Inventor： Ryan Lustig ,  Balineedu Chowdary Adsumilli

IPC: H04N5/232

Abstract: A target image captured from a fisheye lens or other lens with known distortion parameters may be transformed to align it to a reference image. Corresponding features may be detected in the target image and the reference image. The features may be transformed to a spherical coordinate space. In the spherical space, images may be re-pointed or rotated in three dimensions to align all or a subset of the features of the target image to the corresponding features of the reference image. For example, in a sequence of images, background features of the target image in the spherical image space may be aligned to background features of the reference image in the spherical image space to compensate for camera motion while preserving foreground motion. An inverse transformation may then be applied to bring the images back into the original image space.

公开(公告)号：US10129464B1

公开(公告)日：2018-11-13

申请号：US15436639

申请日：2017-02-17

Applicant: GOPRO, INC.

Inventor： Joven Matias ,  Daryl Stimm ,  Ryan Lustig ,  Kyler Schwartz ,  Joseph VanDalsem

IPC: H04N5/232

Abstract: Systems and methods for image compositing. Image capture devices may be used for documenting various activities. An image capture device may be configured to operate in image acquisition mode configured for image compositing. The image acquisition mode may be characterized by one or more of a given image acquisition interval, number of acquired images, camera shutter setting, and/or other settings. The image capture device may provide a user interface configured to facilitate acquiring an image sequence suitable for compositing. A live compositing preview may enable users to select one or more composite images for viewing and/or sharing.

公开(公告)号：US20180322369A1

公开(公告)日：2018-11-08

申请号：US15973184

申请日：2018-05-07

Applicant: GoPro, Inc.

Inventor： Balineedu Chowdary Adsumilli ,  Ryan Lustig

IPC: G06K9/62 ,  G06N99/00 ,  G06N3/12 ,  G06K9/00

CPC classification number: G06K9/6262 ,  G06K9/00228 ,  G06K9/00744 ,  G06K9/6227 ,  G06K9/6229 ,  G06K9/6256 ,  G06N3/126 ,  G06N7/005 ,  G06N20/00

Abstract: An algorithm for performing an image or video processing task is generated that may be used to combine a plurality of different independent solutions to the image or video processing task in an optimized manner. A plurality of base algorithms may be applied to a training set of images or video and a first generation of different combining algorithms may be applied to combine the respective solutions from each of the respective base algorithms into respective combined solutions. The respective combined solutions may be evaluated to generate respective fitness scores representing measures of how well the plurality of different combining algorithms each perform the image or video processing task. The algorithms may be iteratively updated to generate an optimized combining algorithm that may be applied to an input image or video.

公开(公告)号：US20180091768A1

公开(公告)日：2018-03-29

申请号：US15278976

申请日：2016-09-28

Applicant: GoPro, Inc.

Inventor： Balineedu Chowdary Adsumilli ,  Ryan Lustig

IPC: H04N7/01

CPC classification number: H04N7/0137 ,  G06T3/40 ,  H04N7/0127 ,  H04N7/014

Abstract: Apparatus and methods for the generation of interpolated frames of video data. In one embodiment, a computerized apparatus is disclosed that includes a video data interface configured to receive frames of video data; a processing apparatus in data communication with the video data interface; and a storage apparatus in data communication with the processing apparatus. The computerized apparatus is further configured to: receive frames of captured video data; retrieve capture parameters associated with the frames of captured video data; generate optical flow parameters from the frames of captured video data; ascribe differing weights based on the capture parameters and/or the optical flow parameters; generate frames of interpolated video data for the frames of captured video data based at least in part on the ascribed weights; and compile a resultant video stream using the frames of interpolated video data and the frames of captured video data.

公开(公告)号：US09646652B2

公开(公告)日：2017-05-09

申请号：US14705864

申请日：2015-05-06

Applicant: GoPro, Inc.

Inventor： Balineedu Chowdary Adsumilli ,  Ryan Lustig ,  David A. Newman

IPC: H04N9/80 ,  H04N5/93 ,  G11B27/10 ,  G06K9/00 ,  G11B27/30 ,  G11B27/031 ,  G10L15/06 ,  G10L15/22 ,  H04N5/77 ,  H04N5/91 ,  H04N9/82 ,  G11B27/13 ,  G11B27/34 ,  G10L25/57 ,  G10L25/54

CPC classification number: G11B27/10 ,  G06K9/00718 ,  G06K9/00751 ,  G06K2009/00738 ,  G10L15/063 ,  G10L15/22 ,  G10L25/54 ,  G10L25/57 ,  G10L2015/0631 ,  G10L2015/223 ,  G11B27/031 ,  G11B27/13 ,  G11B27/28 ,  G11B27/3081 ,  G11B27/34 ,  H04N5/77 ,  H04N5/772 ,  H04N5/91 ,  H04N9/8205

Abstract: Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. In one example, best scenes are identified based on the motion values associated with frames or portions of a frame of a video. Motion values are determined for each frame and portions of the video including frames with the most motion are identified as best scenes. Best scenes may also be identified based on the motion profile of a video. The motion profile of a video is a measure of global or local motion within frames throughout the video. For example, best scenes are identified from portion of the video including steady global motion. A video summary can be generated including one or more of the identified best scenes.