-
1.发明授权公开(公告)号：US12277800B2
公开(公告)日：2025-04-15
申请号：US17529808
申请日：2021-11-18
Applicant: Google LLC
Inventor： Chia-Kai Liang , Fuhao Shi
Abstract: The subject matter described in this disclosure can be embodied in methods and systems for stabilizing video. A computing system determines a stabilized location of a facial feature in a frame of video accounting for its location in a previous frame. The computing system determines a physical camera pose in virtual space and maps the frame into virtual space. The computing system determines an optimized virtual camera pose using an optimization process that determines (1) a difference between the stabilized location of the facial feature and a location of the facial feature when viewed from a potential virtual camera pose, (2) a difference between the potential virtual camera pose and a previous virtual camera pose, and (3) a difference between the potential virtual camera pose and the physical camera pose. The computing system generates the stabilized view of the frame using the optimized virtual camera pose.
-
公开(公告)号：US20240107163A1
公开(公告)日：2024-03-28
申请号：US18520855
申请日：2023-11-28
Applicant: Google LLC
Inventor： Youyou Wang , Fuhao Shi , Chia-Kai Liang
CPC classification number: H04N23/683 , H04N23/6811 , H04N23/69 , H04N23/90
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for multi-camera video stabilization. In some implementations, a video capture device has a first camera and a second camera. The video capture device provides a digital zoom capability permitting user-specified magnification changes within a digital zoom range during video recording. The video capture device is configured to use video data from different cameras over different portions of the digital zoom range. The video capture device can process image data captured using the second camera by applying a set of transformations including (i) a first transformation to a canonical reference space for the second camera, (ii) a second transformation to a canonical reference space for the first camera, and (iii) a third transformation to apply electronic image stabilization to image data in the canonical reference space for the first camera.
-
公开(公告)号：US20190104255A1
公开(公告)日：2019-04-04
申请号：US15724241
申请日：2017-10-03
Applicant: Google LLC
Inventor： Fuhao Shi , Chia-Kai Liang , Xue Tu
IPC: H04N5/232
CPC classification number: H04N5/23287 , G06T5/003 , G06T5/50 , G06T7/246 , G06T2207/10016 , G06T2207/20201 , H04N5/23254 , H04N5/23258 , H04N5/23267
Abstract: Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for video stabilization. In some implementations, a computer system obtains frames of a video captured by a recording device using an optical image stabilization (OIS) system. The computing system receives (i) OIS position data indicating positions of the OIS system during capture of the frames, and (ii) device position data indicating positions of the recording device during capture of the frames. The computing system determines a first transformation for a particular frame based on the OIS position data for the particular frame and device position data for the particular frame. The computing system determines a second transformation for the particular frame based on the first transformation and positions of the recording device occurring after capture of the particular frame. The computing system generates a stabilized version of the particular frame using the second transformation.
-
公开(公告)号：US11683586B2
公开(公告)日：2023-06-20
申请号：US17336194
申请日：2021-06-01
Applicant: Google LLC
Inventor： Fuhao Shi , Chia-Kai Liang , Xue Tu
CPC classification number: H04N23/687 , G06T5/003 , G06T5/50 , G06T7/246 , H04N23/683 , H04N23/6811 , H04N23/6812 , G06T2207/10016 , G06T2207/20201
Abstract: Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for video stabilization. In some implementations, a computer system obtains frames of a video captured by a recording device using an optical image stabilization (OIS) system. The computing system receives (i) OIS position data indicating positions of the OIS system during capture of the frames, and (ii) device position data indicating positions of the recording device during capture of the frames. The computing system determines a first transformation for a particular frame based on the OIS position data for the particular frame and device position data for the particular frame. The computing system determines a second transformation for the particular frame based on the first transformation and positions of the recording device occurring after capture of the particular frame. The computing system generates a stabilized version of the particular frame using the second transformation.
-
公开(公告)号：US20190342497A1
公开(公告)日：2019-11-07
申请号：US16235037
申请日：2018-12-28
Applicant: Google LLC
Inventor： Chia-Kai Liang , Fuhao Shi
Abstract: The subject matter described in this disclosure can be embodied in methods and systems for stabilizing video. A computing system determines a stabilized location of a facial feature in a frame of video accounting for its location in a previous frame. The computing system determines a physical camera pose in virtual space and maps the frame into virtual space. The computing system determines an optimized virtual camera pose using an optimization process that determines (1) a difference between the stabilized location of the facial feature and a location of the facial feature when viewed from a potential virtual camera pose, (2) a difference between the potential virtual camera pose and a previous virtual camera pose, and (3) a difference between the potential virtual camera pose and the physical camera pose. The computing system generates the stabilized view of the frame using the optimized virtual camera pose.
-
Patent Agency Ranking
公开(公告)号：US10171738B1
公开(公告)日：2019-01-01
申请号：US15972044
申请日：2018-05-04
Applicant: Google LLC
Inventor： Chia-Kai Liang , Fuhao Shi
Abstract: The subject matter described in this disclosure can be embodied in methods and systems for stabilizing video. A computing system determines a stabilized location of a facial feature in a frame of video accounting for its location in a previous frame. The computing system determines a physical camera pose in virtual space and maps the frame into virtual space. The computing system determines an optimized virtual camera pose using an optimization process that determines (1) a difference between the stabilized location of the facial feature and a location of the facial feature when viewed from a potential virtual camera pose, (2) a difference between the potential virtual camera pose and a previous virtual camera pose, and (3) a difference between the potential virtual camera pose and the physical camera pose. The computing system generates the stabilized view of the frame using the optimized virtual camera pose.
-
公开(公告)号：US20220345621A1
公开(公告)日：2022-10-27
申请号：US17754261
申请日：2019-12-11
Applicant: Google LLC
Inventor： Fuhao Shi , Chia-Kai Liang , Youyou Wang
Abstract: An example method includes outputting, for display, a frame having one or more images that are captured by at least one camera device; responsive to receiving an input to select the frame, storing the frame as a reference frame having one or more reference images, wherein the one or more reference images include the one or more images of the frame; determining, based on the reference images included in the reference frame, a reference pose of the at least one camera device; outputting, for display, a current frame having current images captured by the at least one camera device; determining, based on the current images, a current pose of the at least one camera device; and responsive to determining that the current pose is different from the reference pose, outputting an indication of instructions to manipulate the at least one camera device from the current into the reference pose.
-
8.发明授权公开(公告)号：US11227146B2
公开(公告)日：2022-01-18
申请号：US16989566
申请日：2020-08-10
Applicant: Google LLC
Inventor： Chia-Kai Liang , Fuhao Shi
Abstract: The subject matter described in this disclosure can be embodied in methods and systems for stabilizing video. A computing system determines a stabilized location of a facial feature in a frame of video accounting for its location in a previous frame. The computing system determines a physical camera pose in virtual space and maps the frame into virtual space. The computing system determines an optimized virtual camera pose using an optimization process that determines (1) a difference between the stabilized location of the facial feature and a location of the facial feature when viewed from a potential virtual camera pose, (2) a difference between the potential virtual camera pose and a previous virtual camera pose, and (3) a difference between the potential virtual camera pose and the physical camera pose. The computing system generates the stabilized view of the frame using the optimized virtual camera pose.
-
公开(公告)号：US11064119B2
公开(公告)日：2021-07-13
申请号：US16568931
申请日：2019-09-12
Applicant: Google LLC
Inventor： Fuhao Shi , Chia-Kai Liang , Xue Tu
Abstract: Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for video stabilization. In some implementations, a computer system obtains frames of a video captured by a recording device using an optical image stabilization (OIS) system. The computing system receives (i) OIS position data indicating positions of the OIS system during capture of the frames, and (ii) device position data indicating positions of the recording device during capture of the frames. The computing system determines a first transformation for a particular frame based on the OIS position data for the particular frame and device position data for the particular frame. The computing system determines a second transformation for the particular frame based on the first transformation and positions of the recording device occurring after capture of the particular frame. The computing system generates a stabilized version of the particular frame using the second transformation.
-
10.发明申请公开(公告)号：US20200374460A1
公开(公告)日：2020-11-26
申请号：US16989566
申请日：2020-08-10
Applicant: Google LLC
Inventor： Chia-Kai Liang , Fuhao Shi
Abstract: The subject matter described in this disclosure can be embodied in methods and systems for stabilizing video. A computing system determines a stabilized location of a facial feature in a frame of video accounting for its location in a previous frame. The computing system determines a physical camera pose in virtual space and maps the frame into virtual space. The computing system determines an optimized virtual camera pose using an optimization process that determines (1) a difference between the stabilized location of the facial feature and a location of the facial feature when viewed from a potential virtual camera pose, (2) a difference between the potential virtual camera pose and a previous virtual camera pose, and (3) a difference between the potential virtual camera pose and the physical camera pose. The computing system generates the stabilized view of the frame using the optimized virtual camera pose.
-
-
-
-
-
-
-
-
-
Search Results
21
records
(took 0.015 seconds)
