公开(公告)号：US11651797B2

公开(公告)日：2023-05-16

申请号：US17819870

申请日：2022-08-15

Applicant: Snap Inc.

Inventor： Elena Shaburova

IPC: G06K9/36 ,  G06K9/00 ,  G11B27/031 ,  G06T5/00 ,  G06T11/00 ,  G06N20/00 ,  G06T7/246 ,  G06V10/40 ,  G06V10/42 ,  G06V10/56 ,  G06V10/60 ,  G06V20/40 ,  G06V40/20 ,  G06V40/16 ,  G06T13/40 ,  G06T17/20 ,  G06T19/20 ,  G06F3/01 ,  H04N5/262 ,  G06T11/60 ,  H04N9/79 ,  G06T7/33 ,  G06T7/90 ,  G06V10/46

CPC classification number: G11B27/031 ,  G06F3/011 ,  G06N20/00 ,  G06T5/005 ,  G06T7/246 ,  G06T7/251 ,  G06T7/33 ,  G06T7/90 ,  G06T11/001 ,  G06T11/60 ,  G06T13/40 ,  G06T17/20 ,  G06T19/20 ,  G06V10/40 ,  G06V10/42 ,  G06V10/56 ,  G06V10/60 ,  G06V20/40 ,  G06V20/46 ,  G06V40/167 ,  G06V40/168 ,  G06V40/171 ,  G06V40/174 ,  G06V40/20 ,  H04N5/262 ,  H04N9/79 ,  G06T2207/10016 ,  G06T2207/10021 ,  G06T2207/10024 ,  G06T2207/20036 ,  G06T2207/30201 ,  G06V10/467

Abstract: Method involving: providing an object in the video that at least partially and at least occasionally is presented in frames of a video; detecting the object in the video, wherein said detection comprises detecting feature reference points of the object; tracking the detected object in the video, wherein the tracking comprises creating a mesh that is based on the detected feature reference points of the object and aligning the mesh to the object in each frame; generating a first set of node points on the created mesh based on a request for changing proportions; generating a second set of node points based on the first set of node points; and transforming the frames of the video in such way that the object's proportions are transformed in accordance with the second set of the node points using the mesh.

公开(公告)号：US20220392491A1

公开(公告)日：2022-12-08

申请号：US17819870

申请日：2022-08-15

Applicant: Snap Inc.

Inventor： Elena Shaburova

IPC: G11B27/031 ,  G06T5/00 ,  G06T11/00 ,  G06N20/00 ,  G06T7/246 ,  G06V10/40 ,  G06V10/42 ,  G06V10/56 ,  G06V10/60 ,  G06V20/40 ,  G06V40/20 ,  G06V40/16 ,  G06T13/40 ,  G06T17/20 ,  G06T19/20 ,  G06F3/01 ,  H04N5/262 ,  G06T11/60 ,  H04N9/79 ,  G06T7/33 ,  G06T7/90

Abstract: Method involving: providing an object in the video that at least partially and at least occasionally is presented in frames of a video; detecting the object in the video, wherein said detection comprises detecting feature reference points of the object; tracking the detected object in the video, wherein the tracking comprises creating a mesh that is based on the detected feature reference points of the object and aligning the mesh to the object in each frame; generating a first set of node points on the created mesh based on a request for changing proportions; generating a second set of node points based on the first set of node points; and transforming the frames of the video in such way that the object's proportions are transformed in accordance with the second set of the node points using the mesh.

公开(公告)号：US11443772B2

公开(公告)日：2022-09-13

申请号：US17248812

申请日：2021-02-09

Applicant: Snap Inc.

Inventor： Elena Shaburova ,  Victor Shaburov

IPC: G11B27/031 ,  G06T13/40 ,  G06T17/20 ,  G06T19/20 ,  G06T7/33 ,  G06T7/246 ,  G06T7/90 ,  G06N20/00 ,  G06V10/40 ,  G06V10/42 ,  G06V10/56 ,  G06V10/60 ,  G06V20/40 ,  G06V40/20 ,  H04N9/79 ,  G06V40/16 ,  G06F3/01 ,  G06T5/00 ,  G06T11/00 ,  G06T11/60 ,  H04N5/262 ,  G06V10/46

Abstract: A computer implemented method of triggering events in a video, the method comprising: providing a list of objects with their states and corresponding events in video such that each state from the list triggers at least one event of the corresponding events, wherein each object from the list has at least one state triggering at least one event of the corresponding events from the list in video; detecting at least one object from the list that at least partially and at least occasionally is presented in frames of the video; tracking the at least one object and its state; triggering at least one event of the corresponding events from the list in video in case the state of the at least one object matches with one of its states from the list.

公开(公告)号：US11380361B2

公开(公告)日：2022-07-05

申请号：US17248812

申请日：2021-02-09

Applicant: Snap Inc.

Inventor： Elena Shaburova ,  Victor Shaburov

IPC: G11B27/031 ,  G06T13/40 ,  G06T17/20 ,  G06T19/20 ,  G06T7/33 ,  G06T7/246 ,  G06T7/90 ,  G06N20/00 ,  G06V10/40 ,  G06V10/42 ,  G06V10/56 ,  G06V10/60 ,  G06V20/40 ,  G06V40/20 ,  H04N9/79 ,  G06T5/00 ,  G06T11/00 ,  G06V40/16 ,  G06F3/01 ,  H04N5/262 ,  G06T11/60 ,  G06V10/46

Abstract: A computer implemented method of triggering events in a video, the method comprising: providing a list of objects with their states and corresponding events in video such that each state from the list triggers at least one event of the corresponding events, wherein each object from the list has at least one state triggering at least one event of the corresponding events from the list in video; detecting at least one object from the list that at least partially and at least occasionally is presented in frames of the video; tracking the at least one object and its state; triggering at least one event of the corresponding events from the list in video in case the state of the at least one object matches with one of its states from the list.

公开(公告)号：US11514947B1

公开(公告)日：2022-11-29

申请号：US16732858

申请日：2020-01-02

Applicant: Snap Inc.

Inventor： Elena Shaburova

IPC: G06K9/20 ,  G06K9/36 ,  G11B27/031 ,  G06T13/40 ,  G06T19/20 ,  G06T17/20 ,  G06T7/246 ,  G06T11/00 ,  G06F3/01 ,  G06N20/00 ,  H04N5/262 ,  G06T5/00 ,  G06T7/33 ,  G06T11/60 ,  H04N9/79 ,  G06T7/90 ,  G06V10/40 ,  G06V10/42 ,  G06V10/56 ,  G06V10/60 ,  G06V20/40 ,  G06V40/20 ,  G06V40/16 ,  G06V10/46

Abstract: A method for real-time video processing for changing features of an object in a video, the method comprises: providing an object in the video, the object being at least partially and at least occasionally presented in frames of the video; detecting the object in the video; generating a list of at least one element of the object, the list being based on the object's features to be changed according to a request for modification; detecting the at least one element of the object in the video;
tracking the at least one element of the object in the video; and transforming the frames of the video such that the at least one element of the object is modified according to the request for modification.

公开(公告)号：US11450349B2

公开(公告)日：2022-09-20

申请号：US16749708

申请日：2020-01-22

Applicant: Snap Inc.

Inventor： Elena Shaburova

IPC: G06K9/36 ,  G06K9/00 ,  G11B27/031 ,  G06T5/00 ,  G06T11/00 ,  G06N20/00 ,  G06T7/246 ,  G06V10/40 ,  G06V10/42 ,  G06V10/56 ,  G06V10/60 ,  G06V20/40 ,  G06V40/20 ,  G06V40/16 ,  G06T13/40 ,  G06T17/20 ,  G06T19/20 ,  G06F3/01 ,  H04N5/262 ,  G06T11/60 ,  H04N9/79 ,  G06T7/33 ,  G06T7/90 ,  G06V10/46

Abstract: Method involving: providing an object in the video that at least partially and at least occasionally is presented in frames of a video; detecting the object in the video, wherein said detection comprises detecting feature reference points of the object; tracking the detected object in the video, wherein the tracking comprises creating a mesh that is based on the detected feature reference points of the object and aligning the mesh to the object in each frame; generating a first set of node points on the created mesh based on a request for changing proportions; generating a second set of node points based on the first set of node points; and transforming the frames of the video in such way that the object's proportions are transformed in accordance with the second set of the node points using the mesh.

公开(公告)号：US11468913B1

公开(公告)日：2022-10-11

申请号：US16548279

申请日：2019-08-22

Applicant: Snap Inc.

Inventor： Elena Shaburova ,  Victor Shaburov

IPC: G06K9/46 ,  G06T5/00 ,  G11B27/031 ,  G06T13/40 ,  G06T19/20 ,  G06F3/01 ,  H04N5/262 ,  G06T11/60 ,  H04N9/79 ,  G06T7/33 ,  G06T7/246 ,  G06T7/90 ,  G06T11/00 ,  G06N20/00 ,  G06T17/20 ,  G06V10/40 ,  G06V10/42 ,  G06V10/56 ,  G06V10/60 ,  G06V20/40 ,  G06V40/20 ,  G06V40/16 ,  G06V10/46

Abstract: Method for real time video processing for retouching an object in a video, comprising: providing an object in the video steam, the object being at least partially and at least occasionally presented in frames of the video; setting a degree of retouching; generating a list of at least one element of the object selected based on a request of retouching and the degree of retouching; detecting the at least one element of the object in the video and parameters of the at least one element; calculating new parameters of the at least one element according to the degree of retouching; detecting characteristic points for each of the at least one element of the object; generating a mesh based on the characteristic points for each of the at least one element of the object; tracking the at least one element of the object in the video, wherein the tracking comprises aligning the mesh for each of the at least one element with a position of the corresponding each of the at least one element; and transforming the frames of the video such that the at least one element of the object is modified by the application of the new parameters to the at least one element of the object using the mesh.

公开(公告)号：US20210166732A1

公开(公告)日：2021-06-03

申请号：US17248812

申请日：2021-02-09

Applicant: Snap Inc.

Inventor： Elena Shaburova ,  Victor Shaburov

IPC: G11B27/031 ,  G06T11/60 ,  G06K9/00 ,  G06T13/40 ,  G06F3/01 ,  G06T7/90 ,  G06K9/46 ,  G06T7/246 ,  H04N5/262 ,  G06T11/00 ,  G06K9/52 ,  G06T19/20 ,  G06T7/33 ,  G06N20/00 ,  G06T17/20 ,  G06T5/00 ,  H04N9/79

Abstract: A computer implemented method of triggering events in a video, the method comprising: providing a list of objects with their states and corresponding events in video such that each state from the list triggers at least one event of the corresponding events, wherein each object from the list has at least one state triggering at least one event of the corresponding events from the list in video; detecting at least one object from the list that at least partially and at least occasionally is presented in frames of the video; tracking the at least one object and its state; triggering at least one event of the corresponding events from the list in video in case the state of the at least one object matches with one of its states from the list.

公开(公告)号：US20200160886A1

公开(公告)日：2020-05-21

申请号：US16749708

申请日：2020-01-22

Applicant: Snap Inc.

Inventor： Elena Shaburova

IPC: G11B27/031 ,  G06T7/90 ,  G06T7/246 ,  G06T7/33 ,  H04N9/79 ,  G06T11/60 ,  G06K9/46 ,  G06K9/00 ,  G06K9/52 ,  H04N5/262 ,  G06F3/01 ,  G06T19/20 ,  G06T17/20 ,  G06T13/40 ,  G06N20/00 ,  G06T11/00 ,  G06T5/00

Abstract: Method involving: providing an object in the video that at least partially and at least occasionally is presented in frames of a video; detecting the object in the video, wherein said detection comprises detecting feature reference points of the object; tracking the detected object in the video, wherein the tracking comprises creating a mesh that is based on the detected feature reference points of the object and aligning the mesh to the object in each frame; generating a first set of node points on the created mesh based on a request for changing proportions; generating a second set of node points based on the first set of node points; and transforming the frames of the video in such way that the object's proportions are transformed in accordance with the second set of the node points using the mesh.

公开(公告)号：US10586570B2

公开(公告)日：2020-03-10

申请号：US14314312

申请日：2014-06-25

Applicant: Snap Inc.

Inventor： Elena Shaburova

IPC: G06K9/36 ,  G06K9/00 ,  G11B27/031 ,  G06T5/00 ,  G06T11/00 ,  G06N20/00 ,  G06T7/246 ,  G06T13/40 ,  G06T17/20 ,  G06T19/20 ,  G06F3/01 ,  H04N5/262 ,  G06K9/46 ,  G06K9/52 ,  G06T11/60 ,  H04N9/79 ,  G06T7/33 ,  G06T7/90

Abstract: Methods and systems are presented for transforming frames of a video. The method provides an object in the video that at least partially and at least occasionally is presented in frames of a video. An object is detected in the video. Detection of the object comprises detecting feature reference points of the object. The object is tracked in the video. The tracking comprises creating a mesh that is based on the detected feature reference points of the object and aligning the mesh to the object in each frame. A first set of node points is generated on the mesh based on a request for changing proportions. A second set of nodes points is generated based on the first set of node points. The frames of the video are transformed in such way that the object's proportions are transformed in accordance with the second set of the node points using the mesh.