专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20210098023A1 SYSTEM AND METHODS FOR GENERATING MEDIA ASSETS 有权
公开(公告)号：US20210098023A1
公开(公告)日：2021-04-01
申请号：US17074424
申请日：2020-10-19
申请人： FUSIT, INC.
发明人： Michal SHAFIR NIR , Florian GMEINER , Liat Sade Sternberg
IPC分类号： G11B27/036 , G11B20/10 , G11B27/34 , H04N21/218 , H04N21/266 , H04N21/472 , H04N21/44 , H04N21/85
摘要： There are provided methods and systems for media processing, comprising: providing a plurality of media asset sources, via a network to a user device; processing said plurality of media asset sources, wherein said processing comprises selecting at least one image asset at each of said media asset sources and detecting features at the selected image asset sources along the media asset sources frames; receiving via the network from the user device a media recording; processing said user media recording, wherein said processing comprises selecting at least one element in the media recording and applying the detected features on the at least one element; mixing the processed media assets with the processed media recording according to input data to yield one or multiple variations of mixed media assets.

2. 发明申请

US20200349978A1 SYSTEM AND METHODS FOR CONCATENATING VIDEO SEQUENCES USING FACE DETECTION 审中-公开
公开(公告)号：US20200349978A1
公开(公告)日：2020-11-05
申请号：US16934562
申请日：2020-07-21
申请人： Fusit, Inc.
发明人： Michal Shafir Nir , Liat Sade-Sternberg , Rhona Horiner Rosen , Tamar Raviv
IPC分类号： G11B27/036 , G06K9/00 , H04N21/472 , H04N21/4402 , H04N21/2365 , H04N21/44 , H04N21/234 , H04N21/4788 , G11B27/28 , H04N21/854 , H04N21/2343 , G11B27/031 , H04N21/2665
摘要： There are provided methods and devices for media processing, comprising: providing at least one media asset source selected from a media asset sources library, the at least one media asset source comprising at least one source video, via a network or client device; receiving via the network or the client device a media recording comprising a client video recorded by a user of the client device; parsing the client video and the source video, respectively, to a plurality of client video frames and a plurality of source video frames; identifying at least one face in at least one frame of the plurality of source video frames and at least another face in at least one frame of the plurality of client video frames by face detection; superposing one or more markers on the identified at least one face of the plurality of source video frames; processing said client video frames to fit the size or shape of said source video frames by using said one or more markers; concatenating said processed client video frames with said source video frames, wherein said concatenation comprises matching the frame rate and resolution of the processed client video frames to the frame rate and resolution of the plurality of client video frames to yield a mixed media asset.

3. 发明授权

US11189320B2 System and methods for concatenating video sequences using face detection 有权
公开(公告)号：US11189320B2
公开(公告)日：2021-11-30
申请号：US16934562
申请日：2020-07-21
申请人： Fusit, Inc.
发明人： Michal Shafir Nir , Liat Sade-Sternberg , Rhona Horiner Rosen , Tamar Raviv
IPC分类号： H04N21/854 , G11B27/036 , G06K9/00 , H04N21/472 , H04N21/4402 , H04N21/2365 , H04N21/44 , H04N21/234 , H04N21/4788 , G11B27/28 , H04N21/2343 , G11B27/031 , H04N21/2665
摘要： There are provided methods and devices for media processing, comprising: providing at least one media asset source selected from a media asset sources library, the at least one media asset source comprising at least one source video, via a network or client device; receiving via the network or the client device a media recording comprising a client video recorded by a user of the client device; parsing the client video and the source video, respectively, to a plurality of client video frames and a plurality of source video frames; identifying at least one face in at least one frame of the plurality of source video frames and at least another face in at least one frame of the plurality of client video frames by face detection; superposing one or more markers on the identified at least one face of the plurality of source video frames; processing said client video frames to fit the size or shape of said source video frames by using said one or more markers; concatenating said processed client video frames with said source video frames, wherein said concatenation comprises matching the frame rate and resolution of the processed client video frames to the frame rate and resolution of the plurality of client video frames to yield a mixed media asset.

4. 发明申请

US20220068313A1 SYSTEMS AND METHODS FOR MIXING DIFFERENT VIDEOS 有权
公开(公告)号：US20220068313A1
公开(公告)日：2022-03-03
申请号：US17466473
申请日：2021-09-03
申请人： FUSIT, INC.
发明人： Michal SHAFIR NIR
IPC分类号： G11B27/031 , H04N19/40 , G06K9/00 , G06T7/194 , G06T3/60
摘要： There are provided methods and systems for media processing, comprising: providing at least one media asset source selected from a media asset sources library, the at least one media asset source comprising at least one source video, via a network to a client device; receiving via the network or the client device a media recording comprising a client video recorded by a user of the client device; transcoding the at least one source video and the client video which includes parsing the client video and the source video, respectively, to a plurality of client video frames and a plurality of source video frames based on the matching; segmenting one or more frames of the plurality of source video frames to one or more character frames; detecting one or more face images in one or more frames of the plurality of client video frames and provide face markers; resizing the one or more character frames according to the face markers compositing the resized character frames with the background frames using one or more blending methods to yield a mixed media asset frames; and encoding the mixed media asset frames to yield a mixed media asset video.

5. 发明授权

US11581018B2 Systems and methods for mixing different videos 有权
公开(公告)号：US11581018B2
公开(公告)日：2023-02-14
申请号：US17466473
申请日：2021-09-03
申请人： FUSIT, INC.
发明人： Michal Shafir Nir
IPC分类号： G11B27/031 , H04N19/40 , G06T7/194 , G06T3/60 , G06V20/40 , G06V40/16
摘要： There are provided methods and systems for media processing, comprising: providing at least one media asset source selected from a media asset sources library, the at least one media asset source comprising at least one source video, via a network to a client device; receiving via the network or the client device a media recording comprising a client video recorded by a user of the client device; transcoding the at least one source video and the client video which includes parsing the client video and the source video, respectively, to a plurality of client video frames and a plurality of source video frames based on the matching; segmenting one or more frames of the plurality of source video frames to one or more character frames; detecting one or more face images in one or more frames of the plurality of client video frames and provide face markers; resizing the one or more character frames according to the face markers compositing the resized character frames with the background frames using one or more blending methods to yield a mixed media asset frames; and encoding the mixed media asset frames to yield a mixed media asset video.

6. 发明申请

US20220068315A1 SYSTEM AND METHODS FOR CONCATENATING VIDEO SEQUENCES USING FACE DETECTION 有权
公开(公告)号：US20220068315A1
公开(公告)日：2022-03-03
申请号：US17523368
申请日：2021-11-10
申请人： Fusit, Inc.
发明人： Michal Shafir Nir , Liat Sade-Sternberg , Rhona Horiner Rosen , Tamar Raviv
IPC分类号： G11B27/036 , G06K9/00 , H04N21/472 , H04N21/4402 , H04N21/2365 , H04N21/44 , H04N21/234 , H04N21/4788 , G11B27/28 , H04N21/854 , H04N21/2343 , G11B27/031 , H04N21/2665
摘要： There are provided methods and devices for media processing, comprising: providing at least one media asset source selected from a media asset sources library, the at least one media asset source comprising at least one source video, via a network or client device; receiving via the network or the client device a media recording comprising a client video recorded by a user of the client device; parsing the client video and the source video, respectively, to a plurality of client video frames and a plurality of source video frames; identifying at least one face in at least one frame of the plurality of source video frames and at least another face in at least one frame of the plurality of client video frames by face detection; superposing one or more markers on the identified at least one face of the plurality of source video frames; processing said client video frames to fit the size or shape of said source video frames by using said one or more markers; concatenating said processed client video frames with said source video frames, wherein said concatenation comprises matching the frame rate and resolution of the processed client video frames to the frame rate and resolution of the plurality of client video frames to yield a mixed media asset.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式