CN114095780A - Panoramic video editing method, device, storage medium and equipment - Google Patents
Panoramic video editing method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN114095780A CN114095780A CN202010764998.8A CN202010764998A CN114095780A CN 114095780 A CN114095780 A CN 114095780A CN 202010764998 A CN202010764998 A CN 202010764998A CN 114095780 A CN114095780 A CN 114095780A
- Authority
- CN
- China
- Prior art keywords
- target
- panoramic video
- sky
- current
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000000007 visual effect Effects 0.000 claims abstract description 70
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 13
- 238000009877 rendering Methods 0.000 claims description 7
- 230000009977 dual effect Effects 0.000 claims description 4
- 230000007704 transition Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44016—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving splicing one content stream with another content stream, e.g. for substituting a video clip
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
-
- G06T3/047—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
- H04N21/440281—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display by altering the temporal resolution, e.g. by frame skipping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47205—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for manipulating displayed content, e.g. interacting with MPEG-4 objects, editing locally
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
Abstract
The invention is suitable for the technical field of panoramic videos, and provides a panoramic video editing method, a panoramic video editing device, a panoramic video editing storage medium and panoramic video editing equipment, wherein the panoramic video editing method comprises the following steps: acquiring a panoramic video shot by a panoramic camera, and recording the forward direction view angle of the panoramic camera during moving shooting; performing frame extraction operation on the obtained panoramic video to obtain a corresponding panoramic video frame and/or a double-fisheye image frame; identifying and acquiring a significant target, a symmetric target and a sky target according to the panoramic video frame and/or the double-fisheye image frame; tracking the saliency target, the symmetry target and the sky target by adopting a preset target tracking algorithm to obtain a visual angle of the saliency target, a visual angle of the symmetry target and a visual angle of the sky target; and editing the panoramic video according to the visual angle, generating a target video corresponding to the panoramic video, realizing automatic editing of the panoramic video, and simultaneously ensuring the smoothness of transition in the target video and the effectiveness and interestingness of contents.
Description
Technical Field
The invention belongs to the technical field of video processing, and particularly relates to a panoramic video editing method, a panoramic video editing device, a panoramic video editing storage medium and panoramic video editing equipment.
Background
The panoramic video is a video obtained by shooting 360 degrees in all directions by using a panoramic camera, and a user can watch a dynamic video within a shooting angle range of the panoramic camera at will. When watching a panoramic video, since a flat panel display can only display an image of one viewing angle of the panoramic video at a certain time, when a user wants to watch a certain object in a certain time period during the playing of the panoramic video, the user may need to continuously control the display to rotate the viewing angle because the object disappears at the current viewing angle, so that the operation is troublesome, and the watching experience is also affected.
Disclosure of Invention
The embodiment of the invention provides a panoramic video clipping method, a panoramic video clipping device, a storage medium and panoramic video clipping equipment, which are used for solving the problem that in the prior art, an effective panoramic video clipping method cannot be provided, so that the smoothness of a panoramic video is not high during output.
In one aspect, an embodiment of the present invention provides a method for clipping a panoramic video, where the method includes the following steps:
acquiring a panoramic video shot by a panoramic camera, and recording the forward direction view angle of the panoramic camera during shooting;
performing frame extraction operation on the obtained panoramic video to obtain a corresponding panoramic video frame and/or a double-fisheye image frame;
identifying and acquiring a significant target, a symmetric target and a sky target according to the panoramic video frame and/or the double-fisheye image frame;
tracking the salient target, the symmetrical target and the sky target by adopting a preset target tracking algorithm to obtain a visual angle of the salient target, a visual angle of the symmetrical target and a visual angle of the sky target;
traversing the panoramic video, and editing the panoramic video according to the forward direction view angle, the view angle of the salient object, the view angle of the symmetrical object and the view angle of the sky object to generate a target video corresponding to the panoramic video.
With reference to the first aspect, in a possible implementation manner, acquiring a panoramic video shot by a panoramic camera, and recording an angle of view of a forward direction of the panoramic camera during shooting specifically includes:
acquiring a forward direction of the panoramic camera during moving shooting according to the panoramic video, and acquiring a lens image corresponding to a forward direction visual angle;
obtaining the forward direction view angle of the panoramic camera during shooting according to the lens image;
and the panoramic video is an original spherical video.
With reference to the first aspect, in a possible implementation manner, identifying and acquiring a saliency object, a symmetry object, and a sky object according to the panoramic video frame and/or the dual-fisheye image frame specifically includes:
and detecting the panoramic video frame and/or the double fisheye image frame by adopting a preset saliency target detection and identification algorithm to obtain a saliency target.
With reference to the first aspect, in a possible implementation manner, the detecting the panoramic video frame and/or the dual fisheye image frame to obtain a saliency target specifically further includes:
when the preset saliency target type is detected in the current detected panoramic video frame and/or the double-fisheye image frame, the target with the largest saliency value is set as the current saliency target of the current detected panoramic video frame and/or the double-fisheye image frame.
With reference to the first aspect, in a possible implementation manner, identifying and acquiring a saliency object, a symmetry object, and a sky object according to the panoramic video frame and/or the dual-fisheye image frame specifically includes:
obtaining a time stamp of the panoramic video frame and/or the double-fisheye image frame according to the panoramic video frame and/or the double-fisheye image frame;
obtaining a first rotation matrix of the panoramic video frame and/or the double fisheye image frame according to the time stamp of the panoramic video frame and/or the double fisheye image frame;
rendering the panoramic video frame and/or the double fisheye image frame according to the first rotation matrix to obtain an image of the panoramic video frame and/or the double fisheye image frame in the vertical upward direction;
and detecting the images of the panoramic video frame and/or the double-fisheye image frame in the vertical upward direction by adopting a preset symmetrical target detection and identification algorithm to obtain a symmetrical target.
With reference to the first aspect, in a possible implementation manner, identifying and acquiring a saliency object, a symmetry object, and a sky object according to the panoramic video frame and/or the dual-fisheye image frame specifically includes:
obtaining a time stamp of the panoramic video frame and/or the double-fisheye image frame according to the panoramic video frame and/or the double-fisheye image frame;
obtaining a first rotation matrix of the panoramic video frame and/or the double fisheye image frame according to the time stamp of the panoramic video frame and/or the double fisheye image frame;
decomposing the travel direction matrix of the panoramic video frame and/or the double-fisheye image frame into first Euler angles (respectively Yaw, Pitch and Roll), and setting the Pitch angle to be PI/2 to obtain a second Euler angle;
converting the second Euler angle to obtain a second rotation matrix;
rendering the panoramic video frame and/or the double fisheye image frame according to the second rotation matrix to obtain an image of the panoramic video frame and/or the double fisheye image frame in the vertical upward direction;
and detecting the image of the panoramic video frame and/or the double-fisheye image frame in the vertical upward direction by adopting a preset sky target detection and identification algorithm to obtain a sky target.
With reference to the first aspect, in a possible implementation manner, a preset target tracking algorithm is adopted to track the saliency target, the symmetry target, and the sky target, so as to obtain a view angle of the saliency target, a view angle of the symmetry target, and a view angle of the sky target, where the saliency target is located, specifically including:
when a current saliency target, a current symmetry target and a current sky target are detected in a current detected panoramic video frame and/or a double-fisheye image frame, a preset target tracking algorithm is adopted to track the current saliency target, the current symmetry target and the current sky target in subsequent panoramic video frames and/or double-fisheye image frames in sequence, and a view angle of the current saliency target, a view angle of the current symmetry target and a view angle of the current sky target are obtained.
With reference to the first aspect, in a possible implementation manner, after obtaining the view angle of the current saliency target, the view angle of the current symmetry target, and the view angle of the current sky target, the method further includes:
and respectively detecting the stopping tracking events of the current saliency target, the current symmetry target and the current sky target, respectively skipping to the step of performing frame extraction operation on the panoramic video when the stopping tracking events of the current saliency target, the current symmetry target and the current sky target are detected, and continuously and respectively identifying and acquiring the saliency target, the symmetry target and the sky target.
With reference to the first aspect, in a possible implementation manner, a preset target tracking algorithm is adopted to sequentially track the current saliency target, the current symmetry target, and the current sky target in subsequent panoramic video frames and/or dual-fisheye image frames, and after acquiring a view angle of the current saliency target, a view angle of the current symmetry target, and a view angle of the current sky target, the method specifically includes:
respectively acquiring central coordinates of a current saliency target, a current symmetry target and a current sky target tracking frame in the current detected panoramic video frame and/or the double-fisheye image frame, and respectively calculating spherical viewpoint coordinates of the current saliency target, the current symmetry target and the current sky target according to the central coordinates;
according to the spherical viewpoint coordinates, lens images corresponding to the visual angle of the salient object, the visual angle of the symmetrical object and the visual angle of the sky object are respectively acquired;
and respectively generating a salient target view angle segment, a symmetrical target view angle segment and a sky target view angle segment according to the lens images corresponding to the view angle of the salient target, the view angle of the symmetrical target and the view angle of the sky target.
With reference to the first aspect, in one possible implementation manner, the stop tracking event is that the current saliency target, the current symmetry target and the current sky target are lost or the area of the tracking frame is smaller than a preset area.
With reference to the first aspect, in a possible implementation manner, according to the forward direction view, the view angle of the salient object, the view angle of the symmetric object, and the view angle of the sky object, the panoramic video is clipped, and a target video corresponding to the panoramic video is generated, which specifically includes:
according to the duration of the panoramic video;
and/or the number of occurrences and the corresponding duration of the saliency target perspective segment and/or the sky target perspective segment and/or the symmetry target perspective segment;
and/or the relationship between the visual angle of the saliency target and/or the visual angle of the symmetry target and/or the visual angle of the sky target and the forward direction visual angle;
setting the playing number and the corresponding playing speed of a salient target view angle segment and/or a sky target view angle segment and/or a symmetrical target view angle segment, automatically clipping the salient target view angle segment and/or the sky target view angle segment and/or the symmetrical target view angle segment, and generating a target video corresponding to the panoramic video;
the target video is a single-view video or a flat video.
With reference to the first aspect, in a possible implementation manner, before the setting of the number of plays and the corresponding play speed of the saliency target view segment and/or the sky target view segment and/or the symmetry target view segment, the method further includes:
and setting a lens rotation mode and/or a corresponding playing speed according to the panoramic video duration, the number and duration of the significant target view angle segments and/or the sky target view angle segments and/or the symmetrical target view angle segments.
In a second aspect, the present invention provides a panoramic video editing apparatus, comprising:
an acquisition module: the panoramic camera is used for acquiring a panoramic video shot by the panoramic camera and recording the forward direction view angle of the panoramic camera during shooting;
a frame extraction module: the frame extraction device is used for carrying out frame extraction operation on the obtained panoramic video to obtain corresponding panoramic video frames and/or double-fisheye image frames;
an identification module: the system comprises a panoramic video frame and/or a double-fisheye image frame, a video acquisition unit and a control unit, wherein the panoramic video frame and/or the double-fisheye image frame are used for identifying and acquiring a saliency target, a symmetry target and a sky target;
a tracking module: the system comprises a target tracking module, a target tracking module and a target tracking module, wherein the target tracking module is used for tracking the saliency target, the symmetry target and the sky target by adopting a preset target tracking algorithm to obtain a visual angle of the saliency target, a visual angle of the symmetry target and a visual angle of the sky target;
a processing module: the panoramic video is used for traversing the panoramic video, and according to the forward direction view angle, the view angle of the salient object, the view angle of the symmetrical object and the view angle of the sky object, the panoramic video is clipped to generate a target video corresponding to the panoramic video.
In a third aspect, the invention provides a computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to the first aspect.
In a fourth aspect, the present invention provides a panoramic video clip apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the computer program.
The invention provides a panoramic video editing method, which comprises the steps of acquiring a panoramic video shot by a panoramic camera and recording the forward direction view angle of the panoramic camera during shooting; performing frame extraction operation on the obtained panoramic video to obtain a corresponding panoramic video frame and/or a double-fisheye image frame; identifying and acquiring a significant target, a symmetric target and a sky target according to the panoramic video frame and/or the double-fisheye image frame; tracking the salient target, the symmetrical target and the sky target by adopting a preset target tracking algorithm to obtain a visual angle of the salient target, a visual angle of the symmetrical target and a visual angle of the sky target; according to the forward direction view, the view angle of the saliency target, the view angle of the symmetry target and the view angle of the sky target, the panoramic video is edited, the target video corresponding to the panoramic video is generated, automatic editing of the panoramic video is achieved, and meanwhile smoothness of transition in the target video and effectiveness and interestingness of content are guaranteed.
Drawings
Fig. 1 is a flowchart of an implementation of a panoramic video editing method according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a panoramic video editing apparatus according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a panoramic video editing device according to a third embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of specific implementations of the present invention is provided in conjunction with specific embodiments:
the first embodiment is as follows:
fig. 1 shows an implementation flow of a panoramic video clipping method according to an embodiment of the present invention. The panoramic video editing method provided by the embodiment of the invention can be applied to computing equipment, wherein the computing equipment can be but is not limited to various personal computers, notebook computers, smart phones, tablet computers and panoramic cameras.
For convenience of explanation, fig. 1 shows only portions related to the embodiment of the present invention, which are detailed as follows:
s101, acquiring a panoramic video shot by a panoramic camera, and recording an advancing direction view angle of the panoramic camera during shooting;
the embodiment of the invention is suitable for panoramic video editing to be used for editing panoramic video, the panoramic video is obtained by shooting through a panoramic camera, the panoramic camera is composed of 2 or more than 2 fisheye lenses, and the obtained panoramic video is original spherical video. When the forward direction visual angle of the panoramic camera during shooting is recorded, specifically, the forward direction of the panoramic camera during moving shooting is obtained according to the panoramic video, and then the lens image corresponding to the forward direction visual angle is obtained, so that the forward direction visual angle of the panoramic camera is recorded through the lens image corresponding to the forward direction visual angle.
Specifically, the forward direction of the panoramic camera during moving shooting is obtained according to the panoramic video, and then a lens image corresponding to the forward direction view angle is obtained, which further specifically includes:
obtaining the amount of rotation of the panoramic camera relative to the world coordinate system and the panoramic video when taking the current video frame
The method comprises the following steps that a plurality of paths of fisheye images corresponding to a current video frame and a previous video frame;
respectively extracting angular points of a plurality of paths of fisheye images corresponding to a previous video frame of the panoramic video, and acquiring an angular point sequence to be tracked;
respectively tracking the angular point sequences to be tracked, and acquiring matching point pairs to be tracked in fisheye images corresponding to the current video frame and the previous video frame;
optimizing the displacement of the current video frame of the panoramic camera relative to the previous video frame according to the matching point pair to obtain the optimized displacement;
and taking the optimized displacement as the advancing direction of the virtual camera, calculating a rotation matrix of the current virtual camera, and performing transition rendering on the current video frame of the panoramic video by using the rotation amount of the panoramic camera relative to the world coordinate system when the current video frame is shot and the rotation matrix of the current virtual camera.
Performing frame extraction operation on the obtained panoramic video to obtain a corresponding panoramic video frame and/or a double-fisheye image frame;
in the embodiment of the invention, frame extraction operation is carried out on the obtained panoramic video according to a preset time interval so as to obtain a corresponding panoramic video frame and/or a double-fisheye image frame.
Identifying and acquiring a significant target, a symmetric target and a sky target according to the panoramic video frame and/or the double-fisheye image frame;
in the first embodiment of the present invention, a panoramic video frame and/or a two-fish-eye image frame are sequentially detected, and a saliency target, a symmetry target, and a sky target are identified and acquired, which is implemented by the following steps:
(1) in the embodiment of the invention, when the saliency target detection is carried out on the panoramic video frame and/or the double-fisheye image frame, when the saliency target under the preset target type is detected in the currently detected panoramic video frame and/or double-fisheye image frame, the target with the largest saliency value is set as the current saliency target of the currently detected panoramic video frame and/or double-fisheye image frame, so that the saliency target to be tracked in the currently detected panoramic video frame and/or double-fisheye image frame is accurately acquired when a plurality of saliency targets are detected, and when the saliency target under the target type is not detected in the currently detected panoramic video frame and/or double-fisheye image frame, the currently detected panoramic video frame and/or double-fisheye image frame is confirmed to have no saliency target. The target types can be set according to the shooting scene preset by the panoramic camera so as to further improve the accuracy of target detection, for example, the target types can be sculpture types, stone tablet types, flower beds and landmark buildings, and the significant targets under the sculpture types can be animal sculptures, plant sculptures, human body sculptures and the like.
(2) In the first embodiment of the present invention, the symmetric object detection on the panoramic video frame and/or the dual-fisheye image frame specifically includes:
obtaining a time stamp of the panoramic video frame and/or the double-fisheye image frame according to the panoramic video frame and/or the double-fisheye image frame;
obtaining a first rotation matrix of the panoramic video frame and/or the double fisheye image frame according to the time stamp of the panoramic video frame and/or the double fisheye image frame;
rendering the panoramic video frame and/or the double fisheye image frame according to the first rotation matrix to obtain an image of the panoramic video frame and/or the double fisheye image frame in the vertical upward direction;
and detecting the images of the panoramic video frame and/or the double-fisheye image frame in the vertical upward direction by adopting a preset symmetrical target detection and identification algorithm to obtain a symmetrical target.
(3) In the first embodiment of the present invention, the sky object detection on the panoramic video frame and/or the dual-fisheye image frame specifically includes:
obtaining a time stamp of the panoramic video frame and/or the double-fisheye image frame according to the panoramic video frame and/or the double-fisheye image frame;
obtaining a first rotation matrix of the panoramic video frame and/or the double fisheye image frame according to the time stamp of the panoramic video frame and/or the double fisheye image frame;
decomposing the travel direction matrix of the panoramic video frame and/or the double-fisheye image frame into first Euler angles (respectively Yaw, Pitch and Roll), and setting the Pitch angle to be PI/2 to obtain a second Euler angle;
converting the second Euler angle to obtain a second rotation matrix;
rendering the panoramic video frame and/or the double fisheye image frame according to the second rotation matrix to obtain an image of the panoramic video frame and/or the double fisheye image frame in the vertical upward direction;
and detecting the image of the panoramic video frame and/or the double-fisheye image frame in the vertical upward direction by adopting a preset sky target detection and identification algorithm to obtain a sky target.
(4) In the first embodiment of the present invention, the panoramic video frame and/or the dual-fisheye image frame are sequentially detected, and the saliency target, the symmetry target, and the sky target are identified and acquired, and specifically, when the target Detection and identification are performed on the panoramic video frame and/or the dual-fisheye image frame, algorithms including but not limited to FT (Frequency-tuned significant Region Detection) algorithm or super-pixel Convolutional Neural Network (e.g., a super-pixel Convolutional Neural Network for detecting the target) may be adopted, so as to improve the accuracy of the target Detection and ensure the stability of the target Detection.
Tracking the saliency target, the symmetry target and the sky target by adopting a preset target tracking algorithm to obtain a visual angle of the saliency target, a visual angle of the symmetry target and a visual angle of the sky target;
in the first embodiment of the present invention, when a current saliency target, a current symmetry target, and a current sky target are detected in a current detected panoramic video frame and/or a double-fisheye image frame, a preset target tracking algorithm is adopted to sequentially track the current saliency target, the current symmetry target, and the current sky target in a subsequent panoramic video frame and/or a double-fisheye image frame, and a view angle of the current saliency target, a view angle of the current symmetry target, and a view angle of the current sky target are obtained.
Specifically, the preset target Tracking algorithm may employ algorithms including, but not limited to, a KCF (High-speed Tracking with kernel-related filtering) algorithm or a DSST (Accurate Scale Estimation for Robust Visual Tracking) algorithm, and the like.
In the first embodiment of the present invention, after obtaining the view angle of the current saliency target, the view angle of the current symmetry target, and the view angle of the current sky target, the method further includes:
and respectively detecting the stopping tracking events of the current saliency target, the current symmetry target and the current sky target, respectively skipping to the step of performing frame extraction operation on the panoramic video when the stopping tracking events of the current saliency target, the current symmetry target and the current sky target are detected, and continuously and respectively identifying and acquiring the saliency target, the symmetry target and the sky target.
In the first embodiment of the present invention, a preset target tracking algorithm is adopted to sequentially track the current saliency target, the current symmetry target and the current sky target in subsequent panoramic video frames and/or dual fisheye image frames, and obtain a view angle of the current saliency target, a view angle of the current symmetry target and a view angle of the current sky target, and specifically, the method further includes:
respectively acquiring central coordinates of a current saliency target, a current symmetry target and a current sky target tracking frame in the current detected panoramic video frame and/or the double-fisheye image frame, and respectively calculating spherical viewpoint coordinates of the current saliency target, the current symmetry target and the current sky target according to the central coordinates;
according to the spherical viewpoint coordinates, lens images corresponding to the visual angle of the salient object, the visual angle of the symmetrical object and the visual angle of the sky object are respectively acquired;
and respectively generating a salient target view angle segment, a symmetrical target view angle segment and a sky target view angle segment according to the lens images corresponding to the view angle of the salient target, the view angle of the symmetrical target and the view angle of the sky target.
In the first embodiment of the present invention, the tracking stopping event is that the current saliency target, the current symmetry target and the current sky target are lost or the area of the tracking frame is smaller than a preset area.
Traversing the panoramic video, and editing the panoramic video according to the forward direction view angle, the view angle of the salient object, the view angle of the symmetrical object and the view angle of the sky object to generate a target video corresponding to the panoramic video.
In the first embodiment of the present invention, the editing the panoramic video according to the forward direction view, the view of the salient object, the view of the symmetric object, and the view of the sky object to generate a target video corresponding to the panoramic video specifically includes:
according to the duration of the panoramic video;
and/or the number of occurrences and the corresponding duration of the saliency target perspective segment and/or the sky target perspective segment and/or the symmetry target perspective segment;
and/or the relationship between the visual angle of the saliency target and/or the visual angle of the symmetry target and/or the visual angle of the sky target and the forward direction visual angle;
setting the playing number and the corresponding playing speed of a salient target view angle segment and/or a sky target view angle segment and/or a symmetrical target view angle segment, automatically clipping the salient target view angle segment and/or the sky target view angle segment and/or the symmetrical target view angle segment, and generating a target video corresponding to the panoramic video;
the target video is a single-view video or a flat video.
In the first embodiment of the present invention, before setting the number and corresponding playing speed of the saliency target view segment and/or the sky target view segment and/or the symmetry target view segment, the method further includes:
and setting a lens rotation mode and/or a corresponding playing speed according to the panoramic video duration, the number and duration of the significant target view angle segments and/or the sky target view angle segments and/or the symmetrical target view angle segments.
In the first embodiment of the present invention, the steps may further include:
traversing the panoramic video frame and/or the double-fisheye image frame, when no significant target or symmetric target or sky target exists in the traversed panoramic video frame and/or the double-fisheye image frame, clipping a lens image corresponding to a forward direction visual angle in the panoramic video frame and/or the double-fisheye image frame, and setting the playing speed of the lens image;
when a salient object exists in the panoramic video frame and/or the double-fisheye image frame, according to the duration of the visual angle segment of the salient object and the time interval of two adjacent salient segments, a lens image corresponding to the visual angle of the salient object in the panoramic video frame and/or the double-fisheye image frame is clipped, and the playing speed of the lens image is set;
when symmetric targets exist in the panoramic video frame and/or the double-fisheye image frame, determining a lens image corresponding to the visual angle of the symmetric target in the edited panoramic video frame and/or the double-fisheye image frame according to the duration of the visual angle segment of the symmetric target and the duration of the panoramic video, and setting the playing speed of the lens image;
when a sky target exists in the panoramic video frame and/or the double-fisheye image frame, determining a lens image corresponding to the visual angle of the sky target in the clipped panoramic video frame and/or the double-fisheye image frame according to a preset rule, and setting the playing speed of the lens image;
generating a target video corresponding to the panoramic video according to the clipped lens image and the set corresponding playing speed;
the target video is a single-view video or a flat video.
In the first embodiment of the present invention, according to the duration of the view angle segment of the salient object and the time interval between two adjacent salient segments, a lens image corresponding to the view angle of the salient object in the panoramic video frame and/or the two fisheye image frames is clipped, and the playing speed of the lens image is set, which may further specifically be:
when the duration of the saliency target visual angle segment is smaller than a preset first threshold, discarding the saliency target visual angle segment; when the duration of the saliency target visual angle segment is greater than a preset first threshold and less than a preset second threshold, correspondingly expanding the saliency target visual angle segment according to a preset expansion rule, and if the expanded saliency target visual angle segment is still less than the preset second threshold, discarding the saliency target visual angle segment; when the duration of the saliency target view angle segment is greater than a preset first threshold and less than a preset second threshold, correspondingly expanding the saliency target view angle segment according to a preset expansion rule, if the expanded saliency target view angle segment is greater than the preset second threshold, retaining the expanded saliency target view angle segment, and setting the playing speed of the lens image to be a preset first speed; when the duration of the saliency target view angle segment is greater than a preset second threshold and the time interval between the saliency target view angle segment and a previous saliency target view angle segment is less than a preset threshold, setting the playing speed of the lens image to be a preset first speed; when the duration of the saliency target view segment is greater than a preset second threshold and the time interval between the saliency target view segment and a previous saliency target view segment is greater than a preset threshold, setting the playing speed of the lens image of the front half of the saliency view segment to a preset first speed and setting the playing speed of the lens image of the rear half of the saliency view segment to a preset second speed, wherein the first speed may be greater than or less than the second speed, and the duration of the front half of the saliency view segment may be greater than or less than the duration of the rear half of the saliency view segment;
in the first embodiment of the present invention, according to the duration of the view angle segment of the symmetric object and the duration of the panoramic video, determining a lens image corresponding to the view angle at which the symmetric object is located in the clipped panoramic video frame and/or the two fisheye image frames, and setting the play speed of the lens image, further specifically:
when the duration of the symmetrical target view angle segment is smaller than a preset threshold value, discarding the symmetrical target view angle segment; when the duration of the panoramic video is greater than a preset threshold and the duration of the symmetrical target view angle segment is also greater than the preset threshold, setting the playing speed of the lens image to be a preset third speed; when the duration of the panoramic video is less than a preset threshold and the duration of the symmetrical target view angle segment is greater than the preset threshold, setting the playing speed of the lens image to be a preset fourth speed, wherein the preset third speed can be greater than or less than the preset fourth speed.
Preferably, in the first embodiment of the present invention, the lens rotation mode and/or the corresponding play speed are set according to the panoramic video duration, the number and duration of the significant target view angle segments and/or the sky target view angle segments and/or the symmetric target view angle segments, which may further be specifically:
calculating the rotation direction from the visual angle of the advancing direction to the visual angle of the saliency target, and if the rotation direction is greater than a preset threshold value, clockwise rotating the lens image corresponding to the visual angle of the saliency target based on the rotation direction, and then anticlockwise rotating the lens image; if the rotating direction is smaller than a preset threshold value, based on the rotating direction, carrying out anticlockwise rotation on the lens image corresponding to the visual angle of the saliency target, and then carrying out clockwise rotation;
the rotation direction may be a rotation angle from the viewing angle of the forward direction to the viewing angle of the saliency target, and specifically may refer to a rotation angle from the viewing angle of the forward direction to the viewing angle of the saliency target in the Yaw direction (an axis perpendicular to the ground).
Generating a saliency target segment corresponding to the visual angle of the saliency target according to the rotation result;
preferably, in a first embodiment of the present invention, the salient target view angle segment and/or the sky target view angle segment and/or the symmetric target view angle segment are automatically clipped to generate a target video corresponding to the panoramic video, and further specifically, the method may include:
if the interval time between the first saliency target segment and the second saliency target segment is smaller than a preset threshold value, directly switching to a lens image corresponding to the forward direction view angle of the panoramic video frame and/or the double-fisheye image frame after the first saliency target segment is finished, and then switching to the second saliency target segment;
if the interval time between the first saliency target segment and the second saliency target segment is greater than a preset threshold, a preset symmetry target segment and/or a sky target segment are inserted between the first saliency target segment and the second saliency target segment.
Preferably, in a first embodiment of the present invention, the salient target view angle segment and/or the sky target view angle segment and/or the symmetric target view angle segment are automatically clipped to generate a target video corresponding to the panoramic video, and further specifically, the method may include:
selecting key points of the saliency target view angle segment and/or the sky target view angle segment and/or the symmetry target view angle segment, combining the key points into a smooth curve according to a preset rule, then interpolating any point between the key points according to the curve and the preset rule, and through the operation, smooth switching among multiple target view angles can be ensured;
the time of the key point can be selected as an abscissa, and the relative rotation angle is selected as an ordinate.
Example two:
fig. 2 shows a structure of a panoramic video editing apparatus according to a second embodiment of the present invention, and for convenience of explanation, only the portions related to the second embodiment of the present invention are shown.
In the embodiment of the present invention, the panoramic video clipping apparatus includes an obtaining module 21, a frame extracting module 22, an identifying module 23, a tracking module 24, and a processing module 25, wherein:
the acquisition module 21: the panoramic camera is used for acquiring a panoramic video shot by the panoramic camera and recording the forward direction view angle of the panoramic camera during shooting;
the frame extracting module 22: the frame extraction device is used for carrying out frame extraction operation on the obtained panoramic video to obtain corresponding panoramic video frames and/or double-fisheye image frames;
the recognition module 23: the system comprises a panoramic video frame and/or a double-fisheye image frame, a video acquisition unit and a control unit, wherein the panoramic video frame and/or the double-fisheye image frame are used for identifying and acquiring a saliency target, a symmetry target and a sky target;
the tracking module 24: the system comprises a target tracking module, a target tracking module and a target tracking module, wherein the target tracking module is used for tracking the saliency target, the symmetry target and the sky target by adopting a preset target tracking algorithm to obtain a visual angle of the saliency target, a visual angle of the symmetry target and a visual angle of the sky target;
the processing module 25: the panoramic video is used for traversing the panoramic video, and according to the forward direction view angle, the view angle of the salient object, the view angle of the symmetrical object and the view angle of the sky object, the panoramic video is clipped to generate a target video corresponding to the panoramic video.
In the embodiment of the present invention, each module of the panoramic video editing apparatus may be implemented by a corresponding hardware or software unit, and each module may be an independent software or hardware unit, or may be integrated into a software or hardware unit, which is not limited herein.
Example three:
in an embodiment of the present invention, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps in the above-described panoramic video clipping method embodiment, for example, steps S101 to S105 shown in fig. 1. Alternatively, the computer program may be adapted to perform the functions of the units of the above-described device embodiments, such as the functions of the units 21 to 25 shown in fig. 2, when executed by the processor.
The computer readable storage medium of the embodiments of the present invention may include any entity or device capable of carrying computer program code, a recording medium, such as a ROM/RAM, a magnetic disk, an optical disk, a flash memory, or the like.
Example four:
fig. 3 shows a structure of a panoramic video editing apparatus provided in a third embodiment of the present invention, and for convenience of explanation, only the portions related to the third embodiment of the present invention are shown.
The panoramic video clip device 3 of an embodiment of the present invention comprises a processor 30, a memory 31 and a computer program 32 stored in the memory 31 and executable on the processor 30. The processor 30, when executing the computer program 32, implements the steps in the panoramic video clipping method embodiment described above, such as steps S101 to S105 shown in fig. 1. Alternatively, the processor 30, when executing the computer program 32, implements the functions of the respective modules in the above-described apparatus embodiments, such as the functions of the modules 21 to 25 shown in fig. 2.
The panoramic video editing device of the embodiment of the invention can be a smart phone, a personal computer or a panoramic camera, and the like. The steps of the panoramic video clipping method implemented by the processor 30 executing the computer program 32 in the panoramic video clipping device 3 can refer to the description of the foregoing method embodiments, and are not repeated here.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (15)
1. A panoramic video automatic clipping method, characterized in that the method comprises:
acquiring a panoramic video shot by a panoramic camera, and recording the forward direction view angle of the panoramic camera during shooting;
performing frame extraction operation on the obtained panoramic video to obtain a corresponding panoramic video frame and/or a double-fisheye image frame;
identifying and acquiring a significant target, a symmetric target and a sky target according to the panoramic video frame and/or the double-fisheye image frame;
tracking the salient target, the symmetrical target and the sky target by adopting a preset target tracking algorithm to obtain a visual angle of the salient target, a visual angle of the symmetrical target and a visual angle of the sky target;
traversing the panoramic video, and editing the panoramic video according to the forward direction view angle, the view angle of the salient object, the view angle of the symmetrical object and the view angle of the sky object to generate a target video corresponding to the panoramic video.
2. The method of claim 1, wherein acquiring a panoramic video shot by a panoramic camera and recording a forward direction angle of view of the panoramic camera during shooting comprises:
acquiring a forward direction of the panoramic camera during moving shooting according to the panoramic video, and acquiring a lens image corresponding to a forward direction visual angle;
obtaining the forward direction view angle of the panoramic camera during shooting according to the lens image;
and the panoramic video is an original spherical video.
3. The method of claim 1, wherein identifying a salient object, a symmetric object, and a sky object from the panoramic video frame and/or the dual-fisheye image frame comprises:
and detecting the panoramic video frame and/or the double fisheye image frame by adopting a preset saliency target detection and identification algorithm to obtain a saliency target.
4. The method of claim 3, wherein detecting the panoramic video frame and/or the dual fisheye image frame to obtain a salient object, further comprises:
when the preset saliency target type is detected in the current detected panoramic video frame and/or the double-fisheye image frame, the target with the largest saliency value is set as the current saliency target of the current detected panoramic video frame and/or the double-fisheye image frame.
5. The method of claim 1, wherein identifying a salient object, a symmetric object, and a sky object from the panoramic video frame and/or the dual-fisheye image frame comprises:
obtaining a time stamp of the panoramic video frame and/or the double-fisheye image frame according to the panoramic video frame and/or the double-fisheye image frame;
obtaining a first rotation matrix of the panoramic video frame and/or the double fisheye image frame according to the time stamp of the panoramic video frame and/or the double fisheye image frame;
rendering the panoramic video frame and/or the double fisheye image frame according to the first rotation matrix to obtain an image of the panoramic video frame and/or the double fisheye image frame in the vertical upward direction;
and detecting the images of the panoramic video frame and/or the double-fisheye image frame in the vertical upward direction by adopting a preset symmetrical target detection and identification algorithm to obtain a symmetrical target.
6. The method of claim 1, wherein identifying a salient object, a symmetric object, and a sky object from the panoramic video frame and/or the dual-fisheye image frame comprises:
obtaining a time stamp of the panoramic video frame and/or the double-fisheye image frame according to the panoramic video frame and/or the double-fisheye image frame;
obtaining a first rotation matrix of the panoramic video frame and/or the double fisheye image frame according to the time stamp of the panoramic video frame and/or the double fisheye image frame;
decomposing the travel direction matrix of the panoramic video frame and/or the double-fisheye image frame into first Euler angles (respectively Yaw, Pitch and Roll), and setting the Pitch angle to be PI/2 to obtain a second Euler angle;
converting the second Euler angle to obtain a second rotation matrix;
rendering the panoramic video frame and/or the double fisheye image frame according to the second rotation matrix to obtain an image of the panoramic video frame and/or the double fisheye image frame in the vertical upward direction;
and detecting the image of the panoramic video frame and/or the double-fisheye image frame in the vertical upward direction by adopting a preset sky target detection and identification algorithm to obtain a sky target.
7. The method of claim 1, wherein tracking the salient object, the symmetric object, and the sky object by using a preset object tracking algorithm to obtain an angle of view of the salient object, an angle of view of the symmetric object, and an angle of view of the sky object, specifically comprises:
when a current saliency target, a current symmetry target and a current sky target are detected in a current detected panoramic video frame and/or a double-fisheye image frame, a preset target tracking algorithm is adopted to track the current saliency target, the current symmetry target and the current sky target in subsequent panoramic video frames and/or double-fisheye image frames in sequence, and a view angle of the current saliency target, a view angle of the current symmetry target and a view angle of the current sky target are obtained.
8. The method of claim 7, wherein obtaining the current saliency target from the perspective, the current symmetry target from the perspective, and the current sky target from the perspective further comprises:
and respectively detecting the stopping tracking events of the current saliency target, the current symmetry target and the current sky target, respectively skipping to the step of performing frame extraction operation on the panoramic video when the stopping tracking events of the current saliency target, the current symmetry target and the current sky target are detected, and continuously and respectively identifying and acquiring the saliency target, the symmetry target and the sky target.
9. The method of claim 7, wherein a preset target tracking algorithm is used to track the current saliency target, the current symmetry target and the current sky target in subsequent panoramic video frames and/or dual fisheye image frames in sequence, and after obtaining a view angle of the current saliency target, a view angle of the current symmetry target and a view angle of the current sky target, the method further comprises:
respectively acquiring central coordinates of a current saliency target, a current symmetry target and a current sky target tracking frame in the current detected panoramic video frame and/or the double-fisheye image frame, and respectively calculating spherical viewpoint coordinates of the current saliency target, the current symmetry target and the current sky target according to the central coordinates;
according to the spherical viewpoint coordinates, lens images corresponding to the visual angle of the salient object, the visual angle of the symmetrical object and the visual angle of the sky object are respectively acquired;
and respectively generating a salient target view angle segment, a symmetrical target view angle segment and a sky target view angle segment according to the lens images corresponding to the view angle of the salient target, the view angle of the symmetrical target and the view angle of the sky target.
10. The method of claim 6, wherein the stop tracking event is a loss of the current saliency target, current symmetry target, and current sky target or an area of the tracking box is less than a preset area.
11. The method of claims 1-10, wherein clipping the panoramic video according to the forward direction view, the view of the salient object, the view of the symmetric object, and the view of the sky object to generate a target video corresponding to the panoramic video comprises:
according to the duration of the panoramic video;
and/or the number of occurrences and the corresponding duration of the saliency target perspective segment and/or the sky target perspective segment and/or the symmetry target perspective segment;
and/or the relationship between the visual angle of the saliency target and/or the visual angle of the symmetry target and/or the visual angle of the sky target and the forward direction visual angle;
setting the playing number and the corresponding playing speed of a salient target view angle segment and/or a sky target view angle segment and/or a symmetrical target view angle segment, automatically clipping the salient target view angle segment and/or the sky target view angle segment and/or the symmetrical target view angle segment, and generating a target video corresponding to the panoramic video;
the target video is a single-view video or a flat video.
12. The method of claim 11, wherein setting the number of plays and corresponding play speeds of the saliency target perspective segment and/or the sky target perspective segment and/or the symmetry target perspective segment further comprises:
and setting a lens rotation mode and/or a corresponding playing speed according to the panoramic video duration, the number and duration of the significant target view angle segments and/or the sky target view angle segments and/or the symmetrical target view angle segments.
13. A panoramic video editing apparatus, characterized in that the apparatus comprises:
an acquisition module: the panoramic camera is used for acquiring a panoramic video shot by the panoramic camera and recording the forward direction view angle of the panoramic camera during shooting;
a frame extraction module: the frame extraction device is used for carrying out frame extraction operation on the obtained panoramic video to obtain corresponding panoramic video frames and/or double-fisheye image frames;
an identification module: the system comprises a panoramic video frame and/or a double-fisheye image frame, a video acquisition unit and a control unit, wherein the panoramic video frame and/or the double-fisheye image frame are used for identifying and acquiring a saliency target, a symmetry target and a sky target;
a tracking module: the system comprises a target tracking module, a target tracking module and a target tracking module, wherein the target tracking module is used for tracking the saliency target, the symmetry target and the sky target by adopting a preset target tracking algorithm to obtain a visual angle of the saliency target, a visual angle of the symmetry target and a visual angle of the sky target;
a processing module: the panoramic video is used for traversing the panoramic video, and according to the forward direction view angle, the view angle of the salient object, the view angle of the symmetrical object and the view angle of the sky object, the panoramic video is clipped to generate a target video corresponding to the panoramic video.
14. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 12.
15. A panoramic video clip apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method of any of claims 1 to 12.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010764998.8A CN114095780A (en) | 2020-08-03 | 2020-08-03 | Panoramic video editing method, device, storage medium and equipment |
| PCT/CN2021/110259 WO2022028407A1 (en) | 2020-08-03 | 2021-08-03 | Panoramic video editing method, apparatus and device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010764998.8A CN114095780A (en) | 2020-08-03 | 2020-08-03 | Panoramic video editing method, device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114095780A true CN114095780A (en) | 2022-02-25 |
Family
ID=80119986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010764998.8A Pending CN114095780A (en) | 2020-08-03 | 2020-08-03 | Panoramic video editing method, device, storage medium and equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114095780A (en) |
| WO (1) | WO2022028407A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114660097A (en) * | 2022-03-23 | 2022-06-24 | 成都智元汇信息技术股份有限公司 | Synchronous correction method and system based on double sources and double visual angles |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115243101B (en) * | 2022-06-20 | 2024-04-12 | 上海众源网络有限公司 | Video dynamic and static ratio identification method and device, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018223370A1 (en) * | 2017-06-09 | 2018-12-13 | 深圳大学 | Temporal and space constraint-based video saliency testing method and system |
| WO2019041276A1 (en) * | 2017-08-31 | 2019-03-07 | 深圳市大疆创新科技有限公司 | Image processing method, and unmanned aerial vehicle and system |
| CN110197126A (en) * | 2019-05-06 | 2019-09-03 | 深圳岚锋创视网络科技有限公司 | A kind of target tracking method, device and portable terminal |
| CN111242975B (en) * | 2020-01-07 | 2023-08-25 | 影石创新科技股份有限公司 | Panoramic video rendering method capable of automatically adjusting viewing angle, storage medium and computer equipment |
| CN111163267B (en) * | 2020-01-07 | 2021-12-21 | 影石创新科技股份有限公司 | Panoramic video editing method, device, equipment and storage medium |
-
2020
- 2020-08-03 CN CN202010764998.8A patent/CN114095780A/en active Pending
-
2021
- 2021-08-03 WO PCT/CN2021/110259 patent/WO2022028407A1/en active Application Filing
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114660097A (en) * | 2022-03-23 | 2022-06-24 | 成都智元汇信息技术股份有限公司 | Synchronous correction method and system based on double sources and double visual angles |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022028407A1 (en) | 2022-02-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10540773B2 (en) | System and method for infinite smoothing of image sequences | |
| US11727626B2 (en) | Damage detection from multi-view visual data | |
| Lai et al. | Semantic-driven generation of hyperlapse from 360 degree video | |
| US10818029B2 (en) | Multi-directional structured image array capture on a 2D graph | |
| CN111163267B (en) | Panoramic video editing method, device, equipment and storage medium | |
| US10650574B2 (en) | Generating stereoscopic pairs of images from a single lens camera | |
| US11748907B2 (en) | Object pose estimation in visual data | |
| CN106875431B (en) | Image tracking method with movement prediction and augmented reality implementation method | |
| CN111242975B (en) | Panoramic video rendering method capable of automatically adjusting viewing angle, storage medium and computer equipment | |
| US10586378B2 (en) | Stabilizing image sequences based on camera rotation and focal length parameters | |
| US11776142B2 (en) | Structuring visual data | |
| WO2020037881A1 (en) | Motion trajectory drawing method and apparatus, and device and storage medium | |
| CN111080776B (en) | Human body action three-dimensional data acquisition and reproduction processing method and system | |
| KR102374404B1 (en) | Device and method for providing content | |
| CN111928842B (en) | Monocular vision based SLAM positioning method and related device | |
| WO2018176929A1 (en) | Image background blurring method and apparatus | |
| CN114095780A (en) | Panoramic video editing method, device, storage medium and equipment | |
| WO2017041740A1 (en) | Methods and systems for light field augmented reality/virtual reality on mobile devices | |
| CN105809664B (en) | Method and device for generating three-dimensional image | |
| CN110490131B (en) | Positioning method and device of shooting equipment, electronic equipment and storage medium | |
| CN113610865B (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN109587572B (en) | Method and device for displaying product, storage medium and electronic equipment | |
| CN114881901A (en) | Video synthesis method, device, equipment, medium and product | |
| CN115294493A (en) | Visual angle path acquisition method and device, electronic equipment and medium | |
| US20210037230A1 (en) | Multiview interactive digital media representation inventory verification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |