CN111182218A - Panoramic video processing method, device, equipment and storage medium - Google Patents
Panoramic video processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111182218A CN111182218A CN202010015749.9A CN202010015749A CN111182218A CN 111182218 A CN111182218 A CN 111182218A CN 202010015749 A CN202010015749 A CN 202010015749A CN 111182218 A CN111182218 A CN 111182218A
- Authority
- CN
- China
- Prior art keywords
- interest point
- video
- point target
- tracking
- panoramic video
- 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
Images
Classifications
-
- 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
- H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
-
- 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
-
- 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
- H04N21/4728—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 selecting a Region Of Interest [ROI], e.g. for requesting a higher resolution version of a selected region
-
- 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
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
Abstract
The invention is suitable for the technical field of computers, and provides a panoramic video processing method, which comprises the following steps: the method comprises the steps of obtaining a panoramic video, tracking interest points in the panoramic video to obtain corresponding tracking information, determining a picture playing visual angle corresponding to an interest point target according to the tracking information, and generating a tracking video corresponding to the interest point target according to the picture playing visual angle corresponding to the interest point target and the panoramic video, so that the panoramic video processed into the tracking video of each interest point target is provided for a user, the user does not need to manually select the visual angle of a playing picture, and the playing effect and the user experience of the panoramic video are effectively improved.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a panoramic video processing method, a panoramic video processing device, panoramic video processing equipment and a storage medium.
Background
The panoramic video is a dynamic video which is shot by a panoramic camera and contains 360-degree omnibearing picture contents, a static panoramic picture is converted into a dynamic video image, and a user can watch the dynamic video within the shooting angle range of the panoramic camera at will.
When a panoramic video is played, 360-degree screen contents cannot be completely displayed on a playback device at one time. The user, as an observer in front of the playback device, needs to select an observation angle suitable for the user, which is a current video image playback angle. The user has the following modes to select the picture playing view angle: the method comprises the steps that firstly, a picture playing visual angle is selected through sliding operation on a touch screen, operation is conducted on the time axis of a panoramic video, and other picture playing visual angles are selected when the panoramic video returns to the previous moment; and in the second mode, a gyroscope sensor arranged in the playing device is matched with the somatosensory gesture of the user to search a corresponding picture playing visual angle.
Therefore, when playing the panoramic video, the user needs to continuously adjust the playing angle of the picture to observe the video content that the user wants to see, which is very inconvenient. For example, when a user wants to continuously watch a specific target object, the user needs to continuously adjust the frame playing angle of view of the video to prevent the target object from disappearing on the currently playing frame. As another example, when a user is interested in multiple target objects, it is necessary to repeatedly watch the panoramic video multiple times to find the target objects, which is time consuming for the user.
Disclosure of Invention
The embodiment of the invention provides a panoramic video processing method, a panoramic video processing device, panoramic video processing equipment and a storage medium, and aims to solve the problems of poor panoramic video playing effect and poor user experience caused by the fact that an effective panoramic video processing method cannot be provided in the prior art.
In one aspect, an embodiment of the present invention provides a panoramic video processing method, where the method includes the following steps:
acquiring a panoramic video;
tracking the interest point target in the panoramic video to obtain corresponding tracking information;
determining a picture playing visual angle corresponding to the interest point target according to the tracking information;
and generating a tracking video corresponding to the interest point target according to the picture playing visual angle corresponding to the interest point target and the panoramic video.
In another aspect, an embodiment of the present invention provides a panoramic video processing apparatus, where the apparatus includes:
a panoramic video acquisition unit for acquiring a panoramic video;
the interest point tracking unit is used for tracking an interest point target in the panoramic video to obtain corresponding tracking information;
the playing visual angle determining unit is used for determining a picture playing visual angle corresponding to the interest point target according to the tracking information; and
and the interest point video generating unit is used for generating a tracking video corresponding to the interest point target according to the picture playing visual angle corresponding to the interest point target and the panoramic video.
In another aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor, when executing the computer program, implements the steps of the panoramic video processing method.
In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps of the panoramic video processing method.
According to the embodiment of the invention, the interest point targets in the panoramic video are tracked, the picture playing visual angles corresponding to the interest point targets are determined according to the tracking information of the interest point targets, and the tracking video corresponding to the interest point targets is generated according to the picture playing visual angles corresponding to the interest point targets and the panoramic video, so that a user can comprehensively know the video content of each interest point target in the panoramic video by watching the tracking videos corresponding to different interest point targets respectively, the user does not need to manually adjust the picture playing visual angles of the panoramic video in a reciprocating manner, and the playing effect and the user experience of the panoramic video are effectively improved.
Drawings
Fig. 1 is a flowchart illustrating an implementation of a panoramic video processing method according to an embodiment of the present invention;
fig. 2 is a flowchart of an implementation of a panoramic video processing method according to a second embodiment of the present invention;
fig. 3 is a flowchart of an implementation of a panoramic video processing method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a panoramic video processing apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a panoramic video processing apparatus according to a fifth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a panoramic video processing apparatus according to a fifth embodiment of the present invention;
fig. 7 is a schematic structural diagram of a panoramic video processing apparatus according to a sixth embodiment of the present invention;
fig. 8 is a schematic structural diagram of a panoramic video processing apparatus according to a sixth embodiment of the present invention; and
fig. 9 is a schematic structural diagram of a computer device according to a seventh embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more 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 processing method according to a first embodiment of the present invention, and for convenience of description, only the relevant portions related to the first embodiment of the present invention are shown, and the following details are described below:
in step S101, a panoramic video is acquired.
The embodiment of the invention is suitable for a video processing system or platform to process the panoramic video.
In the embodiment of the invention, when the panoramic video is manufactured, a group of cameras are used for simultaneously shooting 360-degree pictures around a shooting point, and the panoramic video is obtained through later-stage image splicing and stitching. Therefore, the panoramic video spliced and stitched by the later-stage images can be directly acquired, and the dynamic video shot by each camera without splicing and stitching the later-stage images can also be acquired. If the dynamic video shot by each camera without later image stitching is obtained, image stitching and stitching can be performed firstly, or in the subsequent step of tracking the interest point target in the panoramic video, the video images shot by each camera at the same moment are taken each time and the target tracking is performed at the same time.
In step S102, the interest point target in the panoramic video is tracked, and corresponding tracking information is obtained.
In the embodiment of the present invention, different types of interest point targets are preset, for example, the interest point targets may be people, vehicles, animals, robots, and the like, and meanwhile, the recognition and tracking models of the different interest point targets are trained in advance to recognize different interest point targets in each frame of video image in the panoramic video, and the recognized interest point targets are tracked to obtain tracking information of the interest point targets, and the training process of the recognition and tracking models of the interest point targets may use the existing target recognition and tracking algorithm, which is not limited herein. The tracking information of the interest point target comprises the image position of the interest point target in each frame of video image.
In step S103, a picture playing view angle corresponding to the interest point target is determined according to the tracking information.
In the embodiment of the invention, after the tracking information is obtained, the image position of the interest point target in each frame of video image in the panoramic video can be grasped, and certainly, if the interest point target leaves a scene monitored by the panoramic camera, the interest point target will not appear in the video image shot in the time period when the interest point target leaves. According to the appearance of the interest point target in the panoramic video or the image position of the tracked corresponding video image, the picture playing visual angle corresponding to the interest point target, namely the picture playing visual angle of each frame of video image in which the interest point target appears, can be determined, so that the interest point target always appears on the playing picture when the video is played.
In step S104, a tracking video corresponding to the interest point target is generated according to the frame playing view angle and the panoramic video corresponding to the interest point target.
In the embodiment of the invention, when the picture playing visual angle corresponding to the interest point target is determined, namely the picture playing visual angle of each frame of video image appearing in the interest point target, each frame of video image appearing in the interest point target is obtained from the panoramic video, the picture playing visual angles of the video images are set, and the video images are integrated into the tracking video corresponding to the interest point target according to the shooting time sequence. When a plurality of different interest point targets are identified in the panoramic video, a tracking video corresponding to each interest point target can be generated.
Preferably, the number of the tracking videos corresponding to each tracked interest point target is at least 1, so that the dynamic video content of a single interest point target is individually shown through one or more tracking videos.
Further preferably, video images of the point of interest target between the first appearance time and the first disappearance time of the panoramic video are acquired, and the first tracking video of the point of interest target is composed of the video images. And acquiring video images of the interest point target between the second appearance time and the second disappearance time of the panoramic video, and forming a second tracking video of the interest point target by the video images. By analogy, multiple tracking videos of the point-of-interest target may be generated, such that the dynamic video content of a single point-of-interest target is individually presented through one or more tracking videos. The first appearance time of the interest point target in the panoramic video is the time when the interest point target appears in the panoramic video for the first time, the first disappearance time of the interest point target in the panoramic video is the time when the interest point target disappears in the panoramic video after appearing in the panoramic video for the first time and the disappearance time exceeds the preset time, the second appearance time, the second disappearance time, the third appearance time, the third disappearance time and the like of the interest point target can be obtained in sequence, and the description is omitted again.
In the embodiment of the invention, the interest point targets in the panoramic video are tracked, the picture playing visual angles corresponding to the interest point targets are determined according to the tracking information of the interest point targets, and the tracking video corresponding to the interest point targets is generated according to the picture playing visual angles corresponding to the interest point targets and the panoramic video, so that a user can comprehensively know the video content of each interest point target in the panoramic video by watching the tracking videos corresponding to different interest point targets respectively, the user does not need to manually adjust the picture playing visual angles of the panoramic video in a reciprocating manner, and the playing effect and the user experience of the panoramic video are effectively improved.
Example two:
fig. 2 shows an implementation flow of a panoramic video processing method provided by the second embodiment of the present invention, and for convenience of description, only the relevant parts related to the second embodiment of the present invention are shown, which are detailed as follows:
in step S201, a panoramic video is acquired.
In the embodiment of the invention, the panoramic video spliced and stitched by the later-stage images can be directly obtained, and the dynamic video shot by each camera which is not spliced and stitched by the later-stage images can also be obtained. If the dynamic video shot by each camera without later image stitching is obtained, image stitching and stitching can be performed firstly, or in the subsequent step of tracking the interest point target in the panoramic video, the video images shot by each camera at the same moment are taken each time and the target tracking is performed at the same time.
In step S202, sequentially performing target identification on each frame of video image in the panoramic video and tracking the identified interest point target, obtaining tracking information of the interest point target, and meanwhile, adding the tracked interest point target to a preset interest point target set.
In the embodiment of the invention, an interest point target set is constructed in advance and used for storing interest point targets identified from a panoramic video. Different types of interest point targets are preset, and meanwhile, recognition and tracking models of the different interest point targets are trained in advance.
In the embodiment of the invention, according to the time sequence, the identification and tracking of the interest point target are sequentially carried out on each frame of video image in the panoramic video through the trained identification and tracking model of the interest point target, and when the interest point target which does not appear in all the previous frames is identified in the next frame of video image, the interest point target is added into the interest point target set, so that the tracked interest point target is counted through the interest point target set.
Preferably, when the interest point targets are identified in the current frame video image, the identified interest point targets are screened according to preset screening conditions, if the interest point targets do not meet the screening conditions, the interest point targets are not tracked, which is equivalent to the interest point targets not appearing in the video image, so that through screening of the interest point targets, the excessive number of the interest point targets is avoided, the processing effect of the panoramic video is effectively improved, and the quality of the tracked video is prevented from being poor.
Further preferably, the screening condition includes one or any combination of a shape and a size of the interest point target, a distance between the interest point target and the camera, and a number of frames of the interest point target appearing in the panoramic video, so as to improve quality of the tracked interest point target and avoid unnecessary tracking of the interest point target with an excessively small shape, an excessively long distance, and an excessively short appearing time in the picture.
In the embodiment of the invention, when the shape and size of the interest point target are the screening conditions, the interest point target with the shape and size exceeding a first preset threshold is screened out. And when the distance between the interest point target and the camera is a screening condition, screening out the interest point target of which the distance between the interest point target and the camera does not exceed a second preset threshold value. And when the frame number of the interest point target appearing in the panoramic video is a screening condition, screening out the interest point target of which the frame number appearing in the panoramic video exceeds a third preset threshold value.
Preferably, after the interest point target is identified and tracked, the interest point target is screened according to the tracked time length of the interest point target, so that the quality of a subsequently generated tracking video is improved, and the tracking video with too short time length is avoided. When the number of continuous non-appearing frames of the interest point target exceeds a preset frame number threshold, the tracking of the interest point can be finished.
In step S203, a picture playing view angle corresponding to the interest point target is determined according to the tracking information.
In the embodiment of the invention, after the tracking information is obtained, the image position of the interest point target in each frame of video image in the panoramic video can be grasped, and certainly, if the interest point target leaves a scene monitored by the panoramic camera, the interest point target will not appear in the video image shot in the time period when the interest point target leaves. According to the image position of the interest point target in each frame of video image in the panoramic video, the picture playing visual angle corresponding to the interest point target, namely the picture playing visual angle of each frame of video image in which the interest point target appears, can be determined, so that the interest point target always appears on the playing picture when the video is played.
In step S204, a tracking video corresponding to the interest point target is generated according to the frame playing view angle and the panoramic video corresponding to the interest point target.
In the embodiment of the invention, when the picture playing visual angle corresponding to the interest point target is determined, namely the picture playing visual angle of each frame of video image appearing in the interest point target, each frame of video image appearing in the interest point target is obtained from the panoramic video, the picture playing visual angles of the video images are set, and the video images are integrated into the tracking video corresponding to the interest point target according to the shooting time sequence. When a plurality of different interest point targets are identified in the panoramic video, a tracking video corresponding to each interest point target can be generated.
In the embodiment of the invention, target identification is sequentially carried out on each frame of video image in the panoramic video and the identified interest point target is tracked, the tracked interest point targets are counted through the interest point target set, the picture playing visual angle corresponding to the interest point target is determined according to the tracking information of the interest point targets, and the tracking video corresponding to the interest point target is generated according to the picture playing visual angle corresponding to the interest point target and the panoramic video, so that a user can comprehensively know the video content of each interest point target in the panoramic video by watching the tracking videos corresponding to different interest point targets, the user does not need to manually adjust the picture playing visual angle of the panoramic video repeatedly, and the playing effect and the user experience of the panoramic video are effectively improved.
Example three:
fig. 3 shows an implementation flow of a panoramic video processing method provided by the third embodiment of the present invention, and for convenience of description, only the relevant parts related to the third embodiment of the present invention are shown, and the details are as follows:
step S301, acquiring a panoramic video.
Step S302, tracking the interest point target in the panoramic video to obtain corresponding tracking information.
In this embodiment of the present invention, step S301 and step S302 may refer to the detailed descriptions of step S101 and step S102 in the first embodiment, and may also refer to the detailed descriptions of step S201 and step S202 in the second embodiment, which are not described herein again.
Step S303, acquiring the image position of the interest point target in the video image corresponding to the panoramic video from the tracking information.
In the embodiment of the present invention, the corresponding video image may be a video image in which the point of interest target appears, or may be all video images in a time period in which the point of interest target is tracked.
Step S304, determining a picture playing visual angle corresponding to the interest point target according to the image position of the interest point target so as to ensure that the interest point target is always positioned in the middle of the picture when the tracking video corresponding to the interest point target is played.
In the embodiment of the invention, when the image position in each frame of video image where the interest point target appears or in each frame of video image where the interest point target is tracked is obtained, the image position is set in the center of the playing picture, so that the picture playing view angle corresponding to the interest point target, namely the picture playing view angle of each frame of video image where the interest point target appears, can also be determined to comprise the picture playing view angle of each frame of video image where the interest point target is tracked, thereby ensuring that the interest point target is always positioned in the center of the picture when the tracked video of the interest point target is played, improving the playing effect of the panoramic video and improving the user experience.
Step S305, generating a tracking video corresponding to the interest point target according to the picture playing view angle and the panoramic video corresponding to the interest point target.
In the embodiment of the invention, after the picture playing visual angle corresponding to the interest point target (i.e. the picture playing visual angle of each frame of video image appearing in the interest point target or the picture playing visual angle of each frame of video image tracked by the interest point target) is obtained, the picture playing visual angle of each frame of video image tracked by the interest point target is set, and then the video images tracked by the interest point target are combined to generate the corresponding tracking video. And when a playing request of the user is received, sending the corresponding tracking video to the user for playing.
Preferably, when a video playing request of a user is received, video splicing is performed on the tracking video of the interest point target selected to be watched by the user according to the time sequence of the tracking video in the panoramic video, and then the video is sent to the user, so that the user can see the complete tracking content of the interest point target in a section of video without opening the tracking video of the interest point to watch, and the playing effect and the user experience of the panoramic video are effectively improved. The video splicing is to splice a plurality of tracking videos of the same interest point target selected by a user.
Preferably, after the tracking videos are obtained, all the tracking videos are sorted according to the video duration, and the tracking videos are recommended to the user to be watched according to the sorting sequence, so that the high-quality tracking videos are provided for the user. And when the videos are sorted according to the sequence from short to long, recommending from front to back according to the sorting sequence, and when the videos are sorted according to the sequence from short to long, recommending from back to front according to the sorting sequence.
Preferably, after the tracking video is obtained, counting the total tracking duration of each interest point target, sorting the interest point targets according to the sequence of the total tracking duration from long to short, and recommending the sorted interest point targets to the user according to the sorting sequence, so that the user can select the corresponding interest point targets to play the tracking video.
Preferably, when the search keywords input by the user are received, the corresponding tracking video is screened according to the search keywords and pushed to the user, so that the pertinence of pushing the tracking video is improved, and the user experience is effectively improved.
In the embodiment of the invention, the interest point target in the panoramic video is tracked, the image position of the interest point target is obtained from the tracking information, the picture playing visual angle corresponding to the interest point target is determined according to the image position of the interest point target, so that the interest point target is always positioned in the middle of the picture when the tracking video corresponding to the interest point target is played, the tracking video corresponding to the interest point target is generated according to the picture playing visual angle corresponding to the interest point target and the panoramic video, the quality of the tracking video is improved, and the playing effect and the user experience of the panoramic video are effectively improved.
Example four:
fig. 4 shows a structure of a panoramic video processing apparatus according to a fourth embodiment of the present invention, and for convenience of explanation, only the portions related to the fourth embodiment of the present invention are shown, including:
a panoramic video acquisition unit 41 for acquiring a panoramic video.
In the embodiment of the invention, the panoramic video spliced and stitched by the later-stage images can be directly obtained, and the dynamic video shot by each camera which is not spliced and stitched by the later-stage images can also be obtained. If the dynamic video shot by each camera without later image stitching is obtained, image stitching and stitching can be performed firstly, or in the subsequent step of tracking the interest point target in the panoramic video, the video images shot by each camera at the same moment are taken each time and the target tracking is performed at the same time.
And the interest point tracking unit 42 is configured to track the interest point target in the panoramic video to obtain corresponding tracking information.
In the embodiment of the invention, different types of interest point targets are preset, the identification and tracking models of the different interest point targets are trained in advance at the same time to identify different interest point targets in each frame of video image in the panoramic video, the identified interest point targets are tracked to obtain the tracking information of the interest point targets, and the existing target identification and tracking algorithm can be adopted in the identification and tracking model training process of the interest point targets, so that the limitation is not carried out. The tracking information of the interest point target comprises the image position of the interest point target in each frame of video image.
And a playing angle-of-view determining unit 43, configured to determine, according to the tracking information, a picture playing angle of view corresponding to the interest point target.
In the embodiment of the invention, after the tracking information is obtained, the image position of the interest point target in each frame of video image in the panoramic video can be grasped, and certainly, if the interest point target leaves a scene monitored by the panoramic camera, the interest point target will not appear in the video image shot in the time period when the interest point target leaves. According to the appearance of the interest point target in the panoramic video or the image position of the tracked corresponding video image, the picture playing visual angle corresponding to the interest point target, namely the picture playing visual angle of each frame of video image in which the interest point target appears, can be determined, so that the interest point target always appears on the playing picture when the video is played.
And the interest point video generating unit 44 is configured to generate a tracking video corresponding to the interest point target according to the picture playing view angle and the panoramic video corresponding to the interest point target.
In the embodiment of the invention, when the picture playing visual angle corresponding to the interest point target is determined, namely the picture playing visual angle of each frame of video image appearing in the interest point target, each frame of video image appearing in the interest point target is obtained from the panoramic video, the picture playing visual angles of the video images are set, and the video images are integrated into the tracking video corresponding to the interest point target according to the shooting time sequence. When a plurality of different interest point targets are identified in the panoramic video, a tracking video corresponding to each interest point target can be generated.
Preferably, the number of the tracking videos corresponding to each tracked interest point target is at least 1, so that the dynamic video content of a single interest point target is individually shown through one or more tracking videos.
Further preferably, video images of the point of interest target between the first appearance time and the first disappearance time of the panoramic video are acquired, and the first tracking video of the point of interest target is composed of the video images. And acquiring video images of the interest point target between the second appearance time and the second disappearance time of the panoramic video, and forming a second tracking video of the interest point target by the video images. By analogy, multiple tracking videos of the point-of-interest target may be generated, such that the dynamic video content of a single point-of-interest target is individually presented through one or more tracking videos. The first appearance time of the interest point target in the panoramic video is the time when the interest point target appears in the panoramic video for the first time, the first disappearance time of the interest point target in the panoramic video is the time when the interest point target disappears in the panoramic video after appearing in the panoramic video for the first time and the disappearance time exceeds the preset time, the second appearance time, the second disappearance time, the third appearance time, the third disappearance time and the like of the interest point target can be obtained in sequence, and the description is omitted again.
In the embodiment of the invention, the interest point targets in the panoramic video are tracked, the picture playing visual angles corresponding to the interest point targets are determined according to the tracking information of the interest point targets, and the tracking video corresponding to the interest point targets is generated according to the picture playing visual angles corresponding to the interest point targets and the panoramic video, so that a user can comprehensively know the video content of each interest point target in the panoramic video by watching the tracking videos corresponding to different interest point targets respectively, the user does not need to manually adjust the picture playing visual angles of the panoramic video in a reciprocating manner, and the playing effect and the user experience of the panoramic video are effectively improved.
Example five:
fig. 5 shows a structure of a panoramic video processing apparatus according to a fifth embodiment of the present invention, and for convenience of explanation, only the portions related to the fifth embodiment of the present invention are shown, including:
a panoramic video acquisition unit 51 for acquiring a panoramic video.
In the embodiment of the invention, the panoramic video spliced and stitched by the later-stage images can be directly obtained, and the dynamic video shot by each camera which is not spliced and stitched by the later-stage images can also be obtained. If the dynamic video shot by each camera without later image stitching is obtained, image stitching and stitching can be performed firstly, or in the subsequent step of tracking the interest point target in the panoramic video, the video images shot by each camera at the same moment are taken each time and the target tracking is performed at the same time.
And the target identification tracking unit 52 is configured to sequentially perform target identification on each frame of video image in the panoramic video and track the identified interest point target to obtain tracking information of the interest point target, and add the tracked interest point target to a preset interest point target set.
In the embodiment of the invention, an interest point target set is constructed in advance and used for storing interest point targets identified from a panoramic video. Different types of interest point targets are preset, and meanwhile, recognition and tracking models of the different interest point targets are trained in advance.
In the embodiment of the invention, according to the time sequence, the identification and tracking of the interest point target are sequentially carried out on each frame of video image in the panoramic video through the trained identification and tracking model of the interest point target, and when the interest point target which does not appear in all the previous frames is identified in the next frame of video image, the interest point target is added into the interest point target set, so that the tracked interest point target is counted through the interest point target set.
And the playing visual angle determining unit 53 is configured to determine, according to the tracking information, a picture playing visual angle corresponding to the interest point target.
In the embodiment of the invention, after the tracking information is obtained, the image position of the interest point target in each frame of video image in the panoramic video can be grasped, and certainly, if the interest point target leaves a scene monitored by the panoramic camera, the interest point target will not appear in the video image shot in the time period when the interest point target leaves. According to the image position of the interest point target in each frame of video image in the panoramic video, the picture playing visual angle corresponding to the interest point target, namely the picture playing visual angle of each frame of video image in which the interest point target appears, can be determined, so that the interest point target always appears on the playing picture when the video is played.
And the interest point video generating unit 54 is configured to generate a tracking video corresponding to the interest point target according to the picture playing view angle and the panoramic video corresponding to the interest point target.
In the embodiment of the invention, when the picture playing visual angle corresponding to the interest point target is determined, namely the picture playing visual angle of each frame of video image appearing in the interest point target, each frame of video image appearing in the interest point target is obtained from the panoramic video, the picture playing visual angles of the video images are set, and the video images are integrated into the tracking video corresponding to the interest point target according to the shooting time sequence. When a plurality of different interest point targets are identified in the panoramic video, a tracking video corresponding to each interest point target can be generated.
Preferably, as shown in fig. 6, the target recognition and tracking unit 52 includes:
the first screening unit 521 is configured to screen the identified interest point target according to a preset screening condition.
In the embodiment of the invention, when the interest point targets are identified in the current frame video image, the identified interest point targets are screened according to the preset screening condition, if the interest point targets do not meet the screening condition, the interest point targets are not tracked, which is equivalent to the fact that the interest point targets do not appear in the video image, so that through screening the interest point targets, the excessive number of the interest point targets is avoided, the processing effect of the panoramic video is effectively improved, and the quality of the tracked video is prevented from being poor.
Further preferably, the screening condition includes one or any combination of a shape and a size of the interest point target, a distance between the interest point target and the camera, and a number of frames of the interest point target appearing in the panoramic video, so as to improve quality of the tracked interest point target and avoid unnecessary tracking of the interest point target with an excessively small shape, an excessively long distance, and an excessively short appearing time in the picture.
In the embodiment of the invention, when the shape and size of the interest point target are the screening conditions, the interest point target with the shape and size exceeding a first preset threshold is screened out. And when the distance between the interest point target and the camera is a screening condition, screening out the interest point target of which the distance between the interest point target and the camera does not exceed a second preset threshold value. And when the frame number of the interest point target appearing in the panoramic video is a screening condition, screening out the interest point target of which the frame number appearing in the panoramic video exceeds a third preset threshold value.
Preferably, the target recognition and tracking unit 52 further comprises:
the second filtering unit 522 is configured to filter the interest point target according to the tracked time length of the interest point target.
In the embodiment of the invention, after the interest point target is identified and tracked, the interest point target is screened according to the tracked time length of the interest point target, so that the quality of a subsequently generated tracking video is improved, and the tracking video with too short time length is avoided. When the number of continuous non-appearing frames of the interest point target exceeds a preset frame number threshold, the tracking of the interest point can be finished.
In the embodiment of the invention, target identification is sequentially carried out on each frame of video image in the panoramic video and the identified interest point target is tracked, the tracked interest point targets are counted through the interest point target set, the picture playing visual angle corresponding to the interest point target is determined according to the tracking information of the interest point targets, and the tracking video corresponding to the interest point target is generated according to the picture playing visual angle corresponding to the interest point target and the panoramic video, so that a user can comprehensively know the video content of each interest point target in the panoramic video by watching the tracking videos corresponding to different interest point targets, the user does not need to manually adjust the picture playing visual angle of the panoramic video repeatedly, and the playing effect and the user experience of the panoramic video are effectively improved.
Example six:
fig. 7 shows a structure of a panoramic video processing apparatus according to a sixth embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiment of the present invention are shown, where the apparatus includes:
a panoramic video acquisition unit 71 configured to acquire a panoramic video.
And the interest point tracking unit 72 is configured to track the interest point target in the panoramic video to obtain corresponding tracking information.
In the embodiment of the present invention, the panoramic video obtaining unit 71 and the interest point tracking unit 72 may refer to the detailed description of the unit 41 and the unit 42 in the fourth embodiment, and may also refer to the detailed description of the unit 51 and the unit 52 in the fifth embodiment, which are not described herein again.
And an image position acquiring unit 73, configured to acquire, from the tracking information, an image position of the point of interest target in a video image corresponding to the panoramic video.
In the embodiment of the present invention, the corresponding video image may be a video image in which the point of interest target appears, or may be all video images in a time period in which the point of interest target is tracked.
The play visual angle determining subunit 74 determines, according to the image position of the interest point target, a picture play visual angle corresponding to the interest point target, so as to ensure that the interest point target is always located in the middle of the picture when the tracking video corresponding to the interest point target is played.
In the embodiment of the invention, when the image position in each frame of video image where the interest point target appears or in each frame of video image where the interest point target is tracked is obtained, the image position is set in the center of the playing picture, so that the picture playing view angle corresponding to the interest point target, namely the picture playing view angle of each frame of video image where the interest point target appears, can also be determined to comprise the picture playing view angle of each frame of video image where the interest point target is tracked, thereby ensuring that the interest point target is always positioned in the center of the picture when the tracked video of the interest point target is played, improving the playing effect of the panoramic video and improving the user experience.
The interest point video generating unit 75 generates a tracking video corresponding to the interest point target according to the picture playing view angle and the panoramic video corresponding to the interest point target.
In the embodiment of the invention, after the picture playing visual angle corresponding to the interest point target (i.e. the picture playing visual angle of each frame of video image appearing in the interest point target or the picture playing visual angle of each frame of video image tracked by the interest point target) is obtained, the picture playing visual angle of each frame of video image tracked by the interest point target is set, and then the video images tracked by the interest point target are combined to generate the corresponding tracking video. And when a playing request of the user is received, sending the corresponding tracking video to the user for playing.
Preferably, as shown in fig. 8, the point of interest video generating unit 75 includes:
and the tracking video splicing unit 751 is used for splicing the tracking videos selected by the user according to the time sequence of the tracking videos in the panoramic video and then sending the spliced tracking videos to the user when receiving a video playing request of the user.
In the embodiment of the invention, when a video playing request of a user is received, the tracking video of the interest point target selected to be watched by the user is subjected to video splicing according to the time sequence of the tracking video in the panoramic video and then is sent to the user, so that the user can see the complete tracking content of the interest point target in a section of video without opening the tracking video of the interest point one by one for watching, and the playing effect and the user experience of the panoramic video are effectively improved. The video splicing is to splice a plurality of tracking videos of the same interest point target selected by a user.
Preferably, the interest point video generating unit 75 further includes:
and the tracking video sorting unit 752 is configured to sort the tracking videos according to the video durations, and recommend the tracking videos to the user for viewing according to the sorting order.
In the embodiment of the invention, after the tracking videos are obtained, all the tracking videos are sequenced according to the video duration, and the tracking videos are recommended to the user to watch according to the sequencing sequence, so that the high-quality tracking videos are provided for the user. And when the videos are sorted according to the sequence from short to long, recommending from front to back according to the sorting sequence, and when the videos are sorted according to the sequence from short to long, recommending from back to front according to the sorting sequence.
Preferably, after the tracking video is obtained, counting the total tracking duration of each interest point target, sorting the interest point targets according to the sequence of the total tracking duration from long to short, and recommending the sorted interest point targets to the user according to the sorting sequence, so that the user can select the corresponding interest point targets to play the tracking video.
Preferably, when the search keywords input by the user are received, the corresponding tracking video is screened according to the search keywords and pushed to the user, so that the pertinence of pushing the tracking video is improved, and the user experience is effectively improved.
In the embodiment of the invention, the interest point target in the panoramic video is tracked, the image position of the interest point target is obtained from the tracking information, the picture playing visual angle corresponding to the interest point target is determined according to the image position of the interest point target, so that the interest point target is always positioned in the middle of the picture when the tracking video corresponding to the interest point target is played, the tracking video corresponding to the interest point target is generated according to the picture playing visual angle corresponding to the interest point target and the panoramic video, the quality of the tracking video is improved, and the playing effect and the user experience of the panoramic video are effectively improved.
In the embodiment of the present invention, each unit of the panoramic video processing apparatus may be implemented by a corresponding hardware or software unit, and each unit may be an independent software or hardware unit, or may be integrated into a software or hardware unit, which is not limited herein.
Example seven:
fig. 9 shows a structure of a computer device according to a seventh embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiment of the present invention are shown.
The computer device 9 of an embodiment of the invention comprises a processor 90, a memory 91 and a computer program 92 stored in said memory 91 and executable on said processor 90. The processor 90, when executing the computer program 92, implements the steps in the various method embodiments described above, such as steps S101 to S104 shown in fig. 1. Alternatively, the processor 90, when executing the computer program 92, implements the functions of the units in the above-described device embodiments, such as the functions of the modules 41 to 44 shown in fig. 4.
In the embodiment of the invention, the interest point targets in the panoramic video are tracked, the picture playing visual angles corresponding to the interest point targets are determined according to the tracking information of the interest point targets, and the tracking video corresponding to the interest point targets is generated according to the picture playing visual angles corresponding to the interest point targets and the panoramic video, so that a user can comprehensively know the video content of each interest point target in the panoramic video by watching the tracking videos corresponding to different interest point targets respectively, the user does not need to manually adjust the picture playing visual angles of the panoramic video in a reciprocating manner, and the playing effect and the user experience of the panoramic video are effectively improved.
Example eight:
in an embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps in the various method embodiments described above, e.g., steps 101 to 104 shown in fig. 1. Alternatively, the computer program, when executed by a processor, implements the functionality of the units in the above-described apparatus embodiments, such as the functionality of the modules 41 to 44 shown in fig. 4.
In the embodiment of the invention, the interest point targets in the panoramic video are tracked, the picture playing visual angles corresponding to the interest point targets are determined according to the tracking information of the interest point targets, and the tracking video corresponding to the interest point targets is generated according to the picture playing visual angles corresponding to the interest point targets and the panoramic video, so that a user can comprehensively know the video content of each interest point target in the panoramic video by watching the tracking videos corresponding to different interest point targets respectively, the user does not need to manually adjust the picture playing visual angles of the panoramic video in a reciprocating manner, and the playing effect and the user experience of the panoramic video are effectively improved.
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.
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 (10)
1. A panoramic video processing method, characterized in that it comprises the following steps:
acquiring a panoramic video;
tracking the interest point target in the panoramic video to obtain corresponding tracking information;
determining a picture playing visual angle corresponding to the interest point target according to the tracking information;
and generating a tracking video corresponding to the interest point target according to the picture playing visual angle corresponding to the interest point target and the panoramic video.
2. The panoramic video processing method of claim 1, wherein the step of tracking the point of interest object in the panoramic video comprises:
sequentially carrying out target identification on each frame of video image in the panoramic video, tracking the identified interest point target, and simultaneously adding the tracked interest point target to a preset interest point target set.
3. The panoramic video processing method of claim 2, wherein the steps of sequentially performing target recognition on each frame of video image in the panoramic video and tracking the recognized interest point target comprise:
and screening the identified interest point target according to a preset screening condition, wherein the preset screening condition comprises one or any combination of the shape and the size of the interest point target, the distance between the interest point target and a camera and the number of frames of the interest point target appearing in the panoramic video.
4. The panoramic video processing method of claim 2, wherein the steps of sequentially performing target recognition on each frame of video image in the panoramic video and tracking the recognized interest point target comprise:
and screening the interest point target according to the tracked time length of the interest point target.
5. The panoramic video processing method of claim 1, wherein the step of determining the picture playing view angle corresponding to the point of interest object comprises:
acquiring the image position of the interest point target in a video image corresponding to the panoramic video from the tracking information;
and determining a picture playing visual angle corresponding to the interest point target according to the image position of the interest point target.
6. The panoramic video processing method of claim 1, wherein the step of generating the tracking video corresponding to the point of interest object comprises:
when a video playing request of the user is received, the tracking videos selected by the user are spliced according to the time sequence of the tracking videos in the panoramic video and then sent to the user.
7. The panoramic video processing method of claim 1, wherein the step of generating the tracking video corresponding to the point of interest object comprises:
and sequencing the tracking videos according to the video duration, and recommending the tracking videos to the user for watching according to the sequencing sequence.
8. A panoramic video processing apparatus, characterized in that the apparatus comprises:
a panoramic video acquisition unit for acquiring a panoramic video;
the interest point tracking unit is used for tracking an interest point target in the panoramic video to obtain corresponding tracking information;
the playing visual angle determining unit is used for determining a picture playing visual angle corresponding to the interest point target according to the tracking information; and
and the interest point video generating unit is used for generating a tracking video corresponding to the interest point target according to the picture playing visual angle corresponding to the interest point target and the panoramic video.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when executing the computer program.
10. 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 7.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010015749.9A CN111182218A (en) | 2020-01-07 | 2020-01-07 | Panoramic video processing method, device, equipment and storage medium |
PCT/CN2021/070675 WO2021139728A1 (en) | 2020-01-07 | 2021-01-07 | Panoramic video processing method, apparatus, device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010015749.9A CN111182218A (en) | 2020-01-07 | 2020-01-07 | Panoramic video processing method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111182218A true CN111182218A (en) | 2020-05-19 |
Family
ID=70652548
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010015749.9A Pending CN111182218A (en) | 2020-01-07 | 2020-01-07 | Panoramic video processing method, device, equipment and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111182218A (en) |
WO (1) | WO2021139728A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021139728A1 (en) * | 2020-01-07 | 2021-07-15 | 影石创新科技股份有限公司 | Panoramic video processing method, apparatus, device, and storage medium |
CN113472999A (en) * | 2020-09-11 | 2021-10-01 | 青岛海信电子产业控股股份有限公司 | Intelligent device and control method thereof |
CN113473244A (en) * | 2020-06-23 | 2021-10-01 | 青岛海信电子产业控股股份有限公司 | Free viewpoint video playing control method and device |
CN115529451A (en) * | 2021-06-25 | 2022-12-27 | 北京金山云网络技术有限公司 | Data transmission method and device, storage medium and electronic equipment |
WO2023125358A1 (en) * | 2021-12-27 | 2023-07-06 | 影石创新科技股份有限公司 | Video processing method and apparatus, computer device, and storage medium |
WO2023179692A1 (en) * | 2022-03-25 | 2023-09-28 | 影石创新科技股份有限公司 | Motion video generation method and apparatus, terminal device, and storage medium |
CN117197195A (en) * | 2023-09-15 | 2023-12-08 | 南京芯传汇电子科技有限公司 | Video processing method and system based on target recognition and tracking |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116366785A (en) * | 2021-12-22 | 2023-06-30 | 华为技术有限公司 | Video generation system, method and related device |
CN116567294A (en) * | 2023-05-19 | 2023-08-08 | 上海国威互娱文化科技有限公司 | Panoramic video segmentation processing method and system |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105843541A (en) * | 2016-03-22 | 2016-08-10 | 乐视网信息技术(北京)股份有限公司 | Target tracking and displaying method and device in panoramic video |
US20170180680A1 (en) * | 2015-12-21 | 2017-06-22 | Hai Yu | Object following view presentation method and system |
CN106961597A (en) * | 2017-03-14 | 2017-07-18 | 深圳Tcl新技术有限公司 | The target tracking display methods and device of panoramic video |
CN107872731A (en) * | 2017-11-22 | 2018-04-03 | 三星电子(中国)研发中心 | Panoramic video player method and device |
CN107888987A (en) * | 2016-09-29 | 2018-04-06 | 华为技术有限公司 | A kind of panoramic video player method and device |
CN108848304A (en) * | 2018-05-30 | 2018-11-20 | 深圳岚锋创视网络科技有限公司 | A kind of method for tracking target of panoramic video, device and panorama camera |
CN109275020A (en) * | 2018-08-31 | 2019-01-25 | 惠州Tcl移动通信有限公司 | Memory, mobile terminal and the method for reducing its capacity for storing video |
CN109698952A (en) * | 2017-10-23 | 2019-04-30 | 腾讯科技(深圳)有限公司 | Playback method, device, storage medium and the electronic device of full-view video image |
CN110324641A (en) * | 2019-07-12 | 2019-10-11 | 青岛一舍科技有限公司 | The method and device of targets of interest moment display is kept in panoramic video |
CN110570448A (en) * | 2019-09-07 | 2019-12-13 | 深圳岚锋创视网络科技有限公司 | Target tracking method and device of panoramic video and portable terminal |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105847379A (en) * | 2016-04-14 | 2016-08-10 | 乐视控股(北京)有限公司 | Tracking method and tracking apparatus for panoramic video moving direction |
US9947108B1 (en) * | 2016-05-09 | 2018-04-17 | Scott Zhihao Chen | Method and system for automatic detection and tracking of moving objects in panoramic video |
CN110225402B (en) * | 2019-07-12 | 2022-03-04 | 青岛一舍科技有限公司 | Method and device for intelligently keeping interesting target time display in panoramic video |
CN111182218A (en) * | 2020-01-07 | 2020-05-19 | 影石创新科技股份有限公司 | Panoramic video processing method, device, equipment and storage medium |
-
2020
- 2020-01-07 CN CN202010015749.9A patent/CN111182218A/en active Pending
-
2021
- 2021-01-07 WO PCT/CN2021/070675 patent/WO2021139728A1/en active Application Filing
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170180680A1 (en) * | 2015-12-21 | 2017-06-22 | Hai Yu | Object following view presentation method and system |
CN105843541A (en) * | 2016-03-22 | 2016-08-10 | 乐视网信息技术(北京)股份有限公司 | Target tracking and displaying method and device in panoramic video |
CN107888987A (en) * | 2016-09-29 | 2018-04-06 | 华为技术有限公司 | A kind of panoramic video player method and device |
CN106961597A (en) * | 2017-03-14 | 2017-07-18 | 深圳Tcl新技术有限公司 | The target tracking display methods and device of panoramic video |
CN109698952A (en) * | 2017-10-23 | 2019-04-30 | 腾讯科技(深圳)有限公司 | Playback method, device, storage medium and the electronic device of full-view video image |
CN107872731A (en) * | 2017-11-22 | 2018-04-03 | 三星电子(中国)研发中心 | Panoramic video player method and device |
CN108848304A (en) * | 2018-05-30 | 2018-11-20 | 深圳岚锋创视网络科技有限公司 | A kind of method for tracking target of panoramic video, device and panorama camera |
CN109275020A (en) * | 2018-08-31 | 2019-01-25 | 惠州Tcl移动通信有限公司 | Memory, mobile terminal and the method for reducing its capacity for storing video |
CN110324641A (en) * | 2019-07-12 | 2019-10-11 | 青岛一舍科技有限公司 | The method and device of targets of interest moment display is kept in panoramic video |
CN110570448A (en) * | 2019-09-07 | 2019-12-13 | 深圳岚锋创视网络科技有限公司 | Target tracking method and device of panoramic video and portable terminal |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021139728A1 (en) * | 2020-01-07 | 2021-07-15 | 影石创新科技股份有限公司 | Panoramic video processing method, apparatus, device, and storage medium |
CN113473244A (en) * | 2020-06-23 | 2021-10-01 | 青岛海信电子产业控股股份有限公司 | Free viewpoint video playing control method and device |
CN113472999A (en) * | 2020-09-11 | 2021-10-01 | 青岛海信电子产业控股股份有限公司 | Intelligent device and control method thereof |
CN113472999B (en) * | 2020-09-11 | 2023-04-18 | 青岛海信电子产业控股股份有限公司 | Intelligent device and control method thereof |
CN115529451A (en) * | 2021-06-25 | 2022-12-27 | 北京金山云网络技术有限公司 | Data transmission method and device, storage medium and electronic equipment |
WO2023125358A1 (en) * | 2021-12-27 | 2023-07-06 | 影石创新科技股份有限公司 | Video processing method and apparatus, computer device, and storage medium |
WO2023179692A1 (en) * | 2022-03-25 | 2023-09-28 | 影石创新科技股份有限公司 | Motion video generation method and apparatus, terminal device, and storage medium |
CN117197195A (en) * | 2023-09-15 | 2023-12-08 | 南京芯传汇电子科技有限公司 | Video processing method and system based on target recognition and tracking |
CN117197195B (en) * | 2023-09-15 | 2024-04-26 | 南京芯传汇电子科技有限公司 | Video processing method and system based on target recognition and tracking |
Also Published As
Publication number | Publication date |
---|---|
WO2021139728A1 (en) | 2021-07-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111182218A (en) | Panoramic video processing method, device, equipment and storage medium | |
CN109326310B (en) | Automatic editing method and device and electronic equipment | |
US10152826B2 (en) | Augmented reality display system, terminal device and augmented reality display method | |
US20180192146A1 (en) | Method and Apparatus for Playing Video Content From Any Location and Any Time | |
CN107105315A (en) | Live broadcasting method, the live broadcasting method of main broadcaster's client, main broadcaster's client and equipment | |
CN105939481A (en) | Interactive three-dimensional virtual reality video program recorded broadcast and live broadcast method | |
US20100128118A1 (en) | Identification of visual fixations in a video stream | |
US20230040548A1 (en) | Panorama video editing method,apparatus,device and storage medium | |
JP2007265125A (en) | Content display | |
US20230388455A1 (en) | Duration and potential region of interest for suspicious activities | |
CN111861572A (en) | Advertisement putting method and device, electronic equipment and computer readable storage medium | |
CN111726518A (en) | System for capturing images and camera device | |
CN112543343A (en) | Live broadcast picture processing method and device based on live broadcast with wheat and electronic equipment | |
CN111241872A (en) | Video image shielding method and device | |
CN110351579B (en) | Intelligent video editing method | |
US11622099B2 (en) | Information-processing apparatus, method of processing information, and program | |
CN113497977A (en) | Video processing method, model training method, device, equipment and storage medium | |
WO2022041182A1 (en) | Method and device for making music recommendation | |
CN108960130B (en) | Intelligent video file processing method and device | |
CN110971924B (en) | Method, device, storage medium and system for beautifying in live broadcast process | |
CN112166599A (en) | Video editing method and terminal equipment | |
US20190164298A1 (en) | System and Method for Tracking the Speed of an Object Using Video | |
CN116208843A (en) | Panoramic live broadcast method and device, readable storage medium and computer equipment | |
CN113259734B (en) | Intelligent broadcasting guide method, device, terminal and storage medium for interactive scene | |
CN115294493A (en) | Visual angle path acquisition method and device, electronic equipment and medium |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |