CN112468735B - Video processing system and video processing method - Google Patents
Video processing system and video processing method Download PDFInfo
- Publication number
- CN112468735B CN112468735B CN202110100561.9A CN202110100561A CN112468735B CN 112468735 B CN112468735 B CN 112468735B CN 202110100561 A CN202110100561 A CN 202110100561A CN 112468735 B CN112468735 B CN 112468735B
- Authority
- CN
- China
- Prior art keywords
- video
- signal
- event
- target event
- camera terminal
- 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.)
- Active
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
- H04N23/80—Camera processing pipelines; Components thereof
-
- 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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/231—Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion
-
- 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
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
Abstract
The present application relates to a video processing system and a video processing method. The system comprises: the trigger signal generating equipment is used for generating a corresponding trigger signal according to the target event and sending the trigger signal to the camera terminal; wherein the trigger signal comprises at least one of a vibration signal, an audio signal and a real-time positioning signal; and the camera terminal is used for acquiring the original video, generating a corresponding clipping instruction according to the trigger signal, and clipping the acquired original video according to the clipping instruction to obtain a video corresponding to the target event. The system can improve the video processing efficiency.
Description
Technical Field
The present application relates to the field of video processing technologies, and in particular, to a video processing system and a video processing method.
Background
The short video is gradually pursued by people due to the characteristics of short time and concentrated information, and for example, when a wonderful event occurs in the process of a match, players or audiences may need to watch or share the video of the wonderful event again.
However, the conventional short video generation and processing method completely depends on manual identification of wonderful events and post-video clipping, and the videos are distributed according to the clipping result, so that the high efficiency and timeliness of the generation and processing of the short videos cannot be guaranteed.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a video processing system and a video processing method.
A video processing system, the system comprising:
the trigger signal generating equipment is used for generating a corresponding trigger signal according to a target event and sending the trigger signal to the camera terminal; the trigger signal comprises at least one of a vibration signal, an audio signal and a real-time positioning signal;
the camera terminal is used for acquiring an original video, generating a corresponding clipping instruction according to the trigger signal, and clipping the acquired original video according to the clipping instruction to obtain a video corresponding to a target event.
In one embodiment, the system further comprises:
and the intelligent short video cloud equipment is used for performing grouping storage and video processing on the videos corresponding to the target events uploaded by the camera terminal.
In one embodiment, the system further comprises:
and the intelligent short video cloud equipment is used for performing grouping storage and video processing on the videos corresponding to the target events uploaded by the camera terminal.
In one embodiment, the trigger signal generating device includes:
the vibration sensor is used for acquiring a vibration signal generated by a target event and sending the vibration signal to the camera terminal;
the audio sensor is used for collecting an audio signal generated by the target event and sending the audio signal to the camera terminal; and
and the positioning equipment is used for acquiring a positioning signal generated by the target event, analyzing the positioning signal to obtain event information of the target event corresponding to the positioning signal, and sending the event information of the target event to the camera terminal.
In one embodiment, the vibration sensor is further configured to analyze the vibration signal, and extract a vibration spectrum in the vibration signal;
and judging the vibration frequency spectrum according to a preset threshold value, and if the vibration frequency spectrum meets the preset threshold value, taking the vibration signal as a trigger signal and sending the trigger signal to the camera terminal in a Bluetooth broadcast mode.
In one embodiment, the audio sensor is further configured to analyze the audio signal, and extract voiceprint feature data in the obtained audio signal;
and judging the voiceprint characteristic data according to a preset threshold, and if the voiceprint characteristic data meet the preset threshold, taking the audio signal as the trigger signal and sending the trigger signal to the camera terminal in a Bluetooth broadcast mode.
In one embodiment, the audio sensor is integrated inside the camera terminal, and is further configured to analyze the acquired audio signal and extract voiceprint feature data in the acquired audio signal;
and judging the voiceprint characteristic data according to a preset threshold, and if the voiceprint characteristic data meet the preset threshold, taking the audio signal as the trigger signal and sending the trigger signal to a video cutting module in the camera terminal in a microelectronic signal mode.
In one embodiment, the positioning device is further configured to perform real-time positioning and tracking on the position information of each target object, so as to obtain a position data sequence of each target object;
analyzing and obtaining event information of the same target event where each target object is located according to the position data sequence, wherein the event information comprises an event type, an event principal angle, an event result and position information of the same target event;
and generating the real-time positioning signal according to the event information of the same target event, and sending the real-time positioning signal to the camera terminal in a Bluetooth broadcast mode as the trigger signal.
In one embodiment, the camera terminal is further configured to upload the video corresponding to the target event obtained by clipping to an intelligent short video cloud device, and delete the video file remaining after the video corresponding to the target event is clipped from the original video file.
In one embodiment, the intelligent short video cloud equipment is further configured to receive a video corresponding to a target event uploaded by at least one camera terminal, where the video carries packet identification information;
grouping the received videos according to the grouping identification information to obtain videos corresponding to the same target event;
identifying whether a video corresponding to the target event contains event information of the target event; the event information of the target event is the information which is obtained by analyzing the positioning equipment and is synchronously transmitted to the intelligent short video cloud equipment through the real-time positioning signal and the video;
if the video corresponding to the target event does not contain the event information, performing video analysis on the video corresponding to the target event, extracting image features in the video, and obtaining an event type, an event pivot and an event result contained in the video corresponding to the target event according to the extracted image features and a preset feature attribute rule.
In one embodiment, the smart short video cloud device is further configured to store the obtained event type, event principal and event result included in the video corresponding to the target event as the related information of the video, together with the video, in a memory of the smart short video cloud device.
In one embodiment, the smart short video cloud device is further configured to identify a target object corresponding to the target event according to the event pivot included in the video corresponding to the target event; the target object is an event principal in the target event; and
and establishing an incidence relation with an account corresponding to the target object, and pushing the video to the account corresponding to the target object according to the incidence relation.
In one embodiment, the smart short video cloud device is further configured to, if the video corresponding to the target event includes the event information, store the event information as related information of the video together with the video in a memory of the smart short video cloud device.
A method of video processing, the method comprising:
generating a corresponding trigger signal according to a target event through trigger signal generating equipment, and sending the trigger signal to a camera terminal; the trigger signal comprises at least one of a vibration signal, an audio signal and a real-time positioning signal;
the method comprises the steps of collecting an original video through the camera terminal, generating a corresponding clipping instruction according to the trigger signal, clipping the collected original video according to the clipping instruction to obtain a video corresponding to a target event, and sending the video corresponding to the target event to the intelligent short video cloud equipment.
In one embodiment, the method further comprises:
and performing packet storage and video processing on the received video corresponding to the target event through the intelligent short video cloud equipment.
The video processing system and the video processing method, the video processing system comprises: the trigger signal generating equipment is used for generating a corresponding trigger signal according to a target event and sending the trigger signal to the camera terminal; the trigger signal comprises at least one of a vibration signal, an audio signal and a real-time positioning signal; the camera terminal is used for acquiring an original video, generating a corresponding clipping instruction according to the trigger signal, and clipping the acquired original video according to the clipping instruction to obtain a video corresponding to a target event. By adopting the system, the trigger signal generated by the trigger signal generating equipment triggers the camera terminal to automatically clip the video, and the video segment corresponding to the target event is obtained quickly and timely.
Drawings
FIG. 1 is a diagram of an exemplary video processing system;
FIG. 2 is a diagram of an embodiment of an environment in which a video processing system may be deployed at a basketball court;
FIG. 3 is a diagram illustrating the internal architecture of a video processing system in one embodiment;
FIG. 4 is a schematic diagram illustrating an implementation of an OpenPose technique to identify key nodes of a human body in one embodiment;
FIG. 5 is a flowchart illustrating a video processing method according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application 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 present application and are not intended to limit the present application.
The video processing system 100 provided by the present application is in an application environment as shown in fig. 1. The system comprises trigger signal generation equipment 102 and a camera terminal 104, wherein the trigger signal generation equipment 102 is used for generating a corresponding trigger signal according to a target event and sending the trigger signal to the camera terminal 104; the trigger signal comprises at least one of a vibration signal, an audio signal and a real-time positioning signal; and the camera terminal 104 is configured to acquire an original video, generate a corresponding clipping instruction according to the trigger signal, and clip the acquired original video according to the clipping instruction to obtain a video corresponding to the target event.
Optionally, the number of the camera terminals 104 may be one or multiple, and generally, a plurality of camera terminals 104 need to be equipped in one application scene for view diversity, and are laid out at different angles of the application scene for synchronous shooting; the camera terminal 104 may be a smart camera or a mobile phone equipped with a camera, and the like, and the embodiment is not limited. Optionally, an audio acquisition module may be integrated inside the camera terminal 104, and is configured to acquire the trigger signal of the audio type without using an external audio sensor to acquire data, and may also perform analysis and processing on the audio data inside the camera terminal.
Optionally, the video processing system 100 further includes: the intelligent short video cloud equipment is a system comprising a hardware server and computer software, and is used for performing packet storage and video processing on videos corresponding to target events uploaded by the camera terminal 104. The server may be an independent server or a server cluster composed of a plurality of servers.
Specifically, taking a basketball court as an example for illustration, the video processing system is configured, as shown in fig. 2, such that the camera terminals (i.e., shooting terminals) are disposed on two sides of the basketball court, for example, mounted on a wall surface in a stadium, on a basket on a basketball stand, on a ceiling, and the camera terminal of a smartphone type is mounted on a tripod. The audio sensors for generating the trigger signals are also arranged on two sides of the competition field (or integrated inside the camera terminal), the vibration sensors are arranged on the basketball net, the RTLS system (RTLS server (including a Bluetooth base station)) is arranged outside the field, the sensors (the vibration sensors and the audio sensors) and the RTLS communicate with the camera terminal in a Bluetooth broadcast or microelectronic circuit mode, the camera terminal is connected with the intelligent short video cloud equipment through a network and can perform file uploading operation, the intelligent short video cloud equipment is associated with the user account number of the client, and videos are transmitted to the user account number of the client through the network.
In one embodiment, as shown in FIG. 3, there is provided a video processing system comprising:
the trigger signal generation device 310 is used for generating a corresponding trigger signal according to the target event and sending the trigger signal to the camera terminal; the trigger signal includes at least one of a vibration signal, an audio signal, and a real-time positioning signal.
In implementation, the trigger signal generation device is used for generating a corresponding trigger signal according to a target event and sending the trigger signal to the camera terminal; wherein the trigger signal generating apparatus may include: the Real Time positioning system (RTLS) is used for acquiring a target event, and therefore, for a target event, each sensor and RTLS included in the trigger signal generating device can acquire at least one of a vibration signal, an audio signal and a Real Time positioning signal in the field.
Alternatively, the target event may be a wonderful event in a live broadcast of an event, and taking a basketball event as an example, the target event may be a shooting hit event, a passing event, a capping event, a backboard event, etc., and thus the specific event type of the target event is not limited in this embodiment. Different reactions in the field can be triggered aiming at a target event, such as audience reaction (cheering), basketball net vibration reaction, player position change and the like, therefore, each sensor contained in the trigger signal generating device can acquire different trigger signal combinations correspondingly, and the specific combination mode is as follows: 1. a vibration signal; 2. an audio signal; 3. positioning the signal in real time; 4. a vibration signal and an audio signal; 5. vibration signals and real-time positioning signals; 6. an audio signal and a real-time positioning signal; 7. a vibration signal, an audio signal, and a real-time positioning signal.
And the camera terminal 320 is used for acquiring the original video, generating a corresponding clipping instruction according to the trigger signal, and clipping the acquired original video according to the clipping instruction to obtain a video corresponding to the target event.
In implementation, the camera terminal is configured to acquire an original video, generate a corresponding clipping instruction according to the trigger signal, and clip the acquired original video according to the clipping instruction to obtain a video corresponding to the target event.
The method comprises the steps that a camera terminal is always in a shooting state, meanwhile, a program running in the camera terminal monitors a received trigger signal in real time, a corresponding clipping instruction is generated according to the received trigger signal, and a collected original video (namely a video which is currently shot and cached) is clipped in response to the clipping instruction (the moment when the trigger signal is monitored is basically consistent with the moment when an event occurs, and the moment when the trigger signal reaches each camera terminal is basically consistent), so that a video corresponding to a target event is obtained.
Specifically, the camera terminal performs analysis and identification according to the received trigger signal to generate a clipping instruction executable by the camera terminal, then clips the acquired original video according to the clipping instruction, and considering the delay time, for example, m seconds, an operating program inside the camera terminal takes the current time of receiving the trigger signal as a reference, and captures m + n seconds of video, which is n seconds before the current time and m seconds after the current time, as the video corresponding to the target event.
Since the camera terminal can receive trigger signals of a plurality of different combination modes, in order to improve the processing efficiency of the camera terminal, the camera device has processing priorities for different trigger signals, that is, a real-time positioning signal (RTLS signal) is prior to a vibration signal and is prior to an audio signal, for example, if one combination mode of the trigger signals comprises the real-time positioning signal and other signals, the real-time positioning signal is preferentially processed, and meanwhile, other types of signals can be ignored and are not processed; if the combination mode of the trigger signal comprises a vibration signal and an audio signal (not comprising a real-time positioning signal), the vibration signal is processed preferentially, and the audio signal can be not processed.
Optionally, the vibration signal, the audio signal, and the real-time positioning signal may be converted into a bluetooth broadcast signal by a bluetooth communication technology and sent to the camera terminal. If the camera terminal is internally integrated with an audio acquisition module (or called as an audio acquisition device), the camera terminal can also directly receive and process audio signals.
In the video processing system, the trigger signal generating device is used for generating a corresponding trigger signal according to a target event and sending the trigger signal to the camera terminal; the trigger signal comprises at least one of a vibration signal, an audio signal and a real-time positioning signal; and the camera terminal is used for acquiring the original video, generating a corresponding clipping instruction according to the trigger signal, and clipping the acquired original video according to the clipping instruction to obtain a video corresponding to the target event. By adopting the system, the trigger signal generated by the trigger signal generating equipment triggers the camera terminal to automatically clip the video, and the video segment corresponding to the target event is obtained quickly and timely.
In one embodiment, the video processing system further comprises: and the intelligent short video cloud equipment is used for performing grouping storage and video processing on videos corresponding to the target events uploaded by the camera terminal.
In an implementation, the video processing system further comprises: and the intelligent short video cloud equipment (server equipment) is used for performing grouping storage and video processing on videos corresponding to the target events uploaded by the camera terminal.
Specifically, the camera terminal is connected to a public network through a wireless or wired network, and an internal running program of the camera terminal can associate a video (video file) corresponding to a target event obtained after clipping with file attribute information of the file, (if the video also carries event information contained in video content, the video also contains the event information), and upload the video to the intelligent short video cloud device in the public network through the network. Then, the intelligent short video cloud equipment receives a video corresponding to a target event uploaded by at least one camera terminal, wherein the video carries grouping identification information, the video uploaded by the camera terminal correspondingly generates a clipping instruction according to a trigger signal generated by the target event in the video generation method, and the original video is clipped according to the clipping instruction. The triggering signal which can trigger the camera terminal to perform the video clip comprises at least one of a vibration signal, an audio signal and a real-time positioning signal.
In one embodiment, the trigger signal generating apparatus includes: the vibration sensor is used for acquiring a vibration signal generated by a target event and sending the vibration signal to the camera terminal; the audio sensor is used for collecting an audio signal generated by a target event and sending the audio signal to the camera terminal; and the positioning equipment is used for acquiring a positioning signal generated by the target event, analyzing the positioning signal to obtain event information of the target event corresponding to the positioning signal, and sending the event information of the target event to the camera terminal.
In an implementation, the trigger signal generating device may include various signal acquiring devices, configured to acquire a signal caused by a target event and send the signal to the camera terminal as a trigger signal, for example, the trigger signal generating device includes a vibration sensor, an audio sensor, an RTLS, and the like, the vibration sensor is configured to acquire a vibration signal generated by the target event and send the vibration signal to the camera terminal as the trigger signal; the audio sensor is used for acquiring an audio signal generated by a target event and sending the audio signal to the camera terminal as a trigger signal; taking a basketball game as an example, for different wonderful events (target events), when watching the wonderful events (target events), the live spectators can emit corresponding drinking sounds, and corresponding audio signals can be obtained according to the collection of the sound information of the drinking sounds, and the audio sensors can collect the audio signals. And the RTLS (positioning device) is used for acquiring a positioning signal generated by the target event, analyzing the positioning signal to obtain event information of the target event corresponding to the positioning signal, and sending the event information of the target event to the camera terminal as a trigger signal.
In one embodiment, the vibration sensor is further configured to analyze the vibration signal, and extract a vibration spectrum in the vibration signal; and judging the vibration frequency spectrum according to a preset threshold, and if the vibration frequency spectrum meets the preset threshold, taking the vibration signal as a trigger signal and sending the trigger signal to the camera terminal in a Bluetooth broadcast mode.
In implementation, a micro-processing chip for data analysis and processing is integrated in the vibration sensor, so that the vibration signal can be analyzed, the vibration spectrum of the vibration signal is extracted and is judged in combination with a preset threshold rule, and if the vibration spectrum meets a preset threshold, the vibration sensor sends the vibration signal to the image pickup device as a trigger signal.
Optionally, for example, in a basketball event, if the trigger signal includes a vibration signal, it indicates that a shooting hit event (target event) occurs. When the vibration sensor is arranged on the basketball net, a player shoots a ball in the process of a game to cause the basketball net to vibrate, the vibration sensor arranged on the vibration sensor collects the vibration and generates a vibration signal, the vibration signal is analyzed and judged, if vibration data contained in the vibration frequency spectrum of the vibration signal meet a preset threshold value, the result of shooting is shot hit, otherwise, the result of shooting is shot miss, and when the event is shot hit, the Bluetooth signal corresponding to the vibration signal is sent to the camera terminal in a broadcasting mode.
In one embodiment, the audio sensor is further configured to analyze the audio signal and extract voiceprint feature data in the obtained audio signal; and judging the voiceprint characteristic data according to a preset threshold, and if the voiceprint characteristic data meet the preset threshold, taking the audio signal as a trigger signal and sending the trigger signal to the camera terminal in a Bluetooth broadcast mode.
In implementation, a micro-processing chip for data processing is integrated in the audio sensor, and the micro-processing chip can be used for analyzing the audio signal and extracting voiceprint characteristic data in the audio signal; and judging the voiceprint characteristic data according to a preset threshold, and if the voiceprint characteristic data meet the preset threshold, taking the audio signal as a trigger signal and sending the trigger signal to the camera terminal in a Bluetooth broadcast mode. The preset threshold corresponding to the voiceprint feature data may be a voiceprint feature data threshold determined according to voiceprint information of preset feature keywords or keywords.
In this embodiment, the audio sensor collects sound caused by an event to obtain an audio signal, and performs voiceprint judgment on a voiceprint characteristic data value extracted from the audio signal according to a preset threshold value to determine that a target event occurs, and then sends the audio signal to the camera terminal as a trigger signal to trigger the camera terminal to perform automatic video editing, so that the generation efficiency of a video corresponding to the target event is improved.
In one embodiment, the audio sensor is integrated inside the camera terminal and is further used for analyzing the acquired audio signal and extracting voiceprint feature data in the acquired audio signal; and judging the voiceprint characteristic data according to a preset threshold, and if the voiceprint characteristic data meet the preset threshold, sending the audio signal as a trigger signal to a video cutting module in the camera terminal in a microelectronic signal form.
In implementation, the audio sensor is integrated inside the camera terminal, the audio sensor may also be referred to as an audio acquisition module inside the camera terminal, and a micro-processing chip for data processing is integrated in the audio acquisition module and is used for analyzing the acquired audio signal and extracting voiceprint feature data in the acquired audio signal; and judging the voiceprint characteristic data according to a preset threshold, and if the voiceprint characteristic data meet the preset threshold, sending the audio signal as a trigger signal to a video cutting module in the camera terminal in a microelectronic signal form.
In one embodiment, the positioning device is further configured to perform real-time positioning and tracking on the position information of each target object to obtain a position data sequence of each target object; analyzing and obtaining event information of the same target event where each target object is located according to the position data sequence, wherein the event information comprises an event type, an event principal angle, an event result and position information of the same target event; and generating a real-time positioning signal according to the event information of the same target event, and sending the real-time positioning signal to the camera terminal in a Bluetooth broadcast mode by taking the real-time positioning signal as a trigger signal.
In implementation, the positioning device is further configured to perform real-time positioning and tracking on the position information of each target object to obtain a position data sequence of each target object; analyzing and obtaining event information of the same target event where each target object is located according to the position data sequence, wherein the event information comprises an event type, an event principal angle, an event result and position information of the same target event; the positioning device is used for generating a real-time positioning signal (RTLS signal) according to the event information of the same target event, and sending the RTLS signal to the camera terminal in a Bluetooth broadcast mode as a trigger signal.
Specifically, the real-time positioning signal is a signal sent to the camera terminal by a positioning device implementing a real-time positioning system (RTLS), the positioning device can determine the event type, event pivot and event result (which may be collectively referred to as event three elements) of an occurring target event through the position change of target objects and the relative position relationship among the target objects, taking the case that the RTLS is deployed on a basketball court, by tracking positioning and relative position analysis of the position information of a basketball and a plurality of players, it can determine events such as shooting hit (or corresponding failure), passing through the basketball, blocking and breaking, capping and the like occurring in one basketball game, for each target event, the event three elements are identified, after the event three elements are identified, the RTLS system sends the event three elements and the position information of the event occurrence to the camera terminal in the form of a bluetooth broadcast signal through a bluetooth communication technology, the three elements of the event and the position information of the event occurrence are sent in the form of a bluetooth broadcast signal, that is, the real-time positioning signal in the trigger signal corresponds to this embodiment.
In one embodiment, the camera terminal is further configured to upload the video corresponding to the clipped target event to the intelligent short video cloud device, and delete the video file remaining after the video corresponding to the target event is clipped from the original video file.
In implementation, the camera terminal is further configured to upload the video corresponding to the clipped target event to the intelligent short video cloud device, and delete the video file remaining after the video corresponding to the target event is clipped from the original video file. Specifically, when a plurality of camera terminals shoot simultaneously, the camera terminals are further configured to determine, for the same target event, a group of videos acquired at one shooting angle corresponding to each camera terminal according to a clipping signal (carrying synchronization time information) of the camera terminal, upload the group of videos to the intelligent short video cloud, and delete the video files remaining after the videos corresponding to the target event are clipped from the original video files.
In order to ensure the sufficient storage space of the camera terminal, the video files cached during field acquisition and the files left after the editing of the original files can be deleted after the field acquisition is finished, so that the memory resources of the camera terminal are saved.
In this embodiment, the camera terminal immediately cleans the remaining files after the clipping and video files that are too long in time, so that the camera terminal internally maintains a sufficient storage space for new video storage.
In one embodiment, the intelligent short video cloud equipment is further used for receiving videos corresponding to target events uploaded by at least one camera terminal, and the videos carry grouping identification information; grouping the received videos according to the grouping identification information to obtain videos corresponding to the same target event; identifying whether a video corresponding to a target event contains event information of the target event; the event information of the target event is information which is obtained by analyzing based on positioning equipment and is synchronously transmitted to the intelligent short video cloud equipment through a real-time positioning signal and a video; if the video corresponding to the target event does not contain the event information, performing video analysis on the video corresponding to the target event, extracting image features in the video, and obtaining an event type, an event pivot and an event result contained in the video corresponding to the target event according to the extracted image features and a preset feature attribute rule.
In implementation, the intelligent short video cloud equipment is further used for receiving videos corresponding to target events uploaded by at least one camera terminal, and each video carries grouping identification information; and grouping the plurality of received videos according to the grouping identification information to obtain videos corresponding to the same target event.
Specifically, the videos uploaded by the camera terminals all carry the grouping identifiers, so that the intelligent short video cloud equipment can perform grouping processing of the same target event dimension on the videos uploaded by the camera terminals or the videos uploaded by one camera terminal according to the grouping identifier information, and each group of videos after grouping corresponds to the video of the same target event. One or more camera terminals can be deployed in a target camera scene, for example, a basketball venue, and when only one camera terminal is deployed, only a video segment at a shooting angle can be correspondingly acquired for each target event (for example, a shooting event), so that the intelligent short video cloud equipment groups one video segment corresponding to the same target event according to the group identifier; when a plurality of camera terminals are deployed, for each target event (for example, a shooting event), the plurality of camera terminals can correspondingly acquire video segments of the same target event at a plurality of shooting angles, so that the intelligent short video cloud equipment divides the plurality of video segments corresponding to the same target event into one group according to the grouping identifier, that is, each group of videos correspondingly shows the same target event.
In implementation, the intelligent short video cloud equipment is further used for identifying whether a video corresponding to a target event contains event information of the target event; the event information of the target event is obtained based on analysis of the positioning equipment and is synchronously transmitted to the intelligent short video cloud equipment through a real-time positioning signal and a video; if the video corresponding to the target event does not contain the event information, performing video analysis on the video corresponding to the target event, extracting image features in the video, and obtaining an event type, an event pivot and an event result contained in the video corresponding to the target event according to the extracted image features and a preset feature attribute rule.
Specifically, the trigger signal received by the camera terminal may include an RTLS signal, and if the trigger signal includes the RTLS signal, the RTLS signal carries event information and event location information, the camera terminal generates a clipping instruction according to the RTLS signal to clip the original video, and the obtained video file corresponding to the target event also has the event information and the event location information of the target event carried in the RTLS signal. And then the camera terminal uploads the video file, the related event information and the event position information to the intelligent short video cloud equipment in the public network through the network. The intelligent short video cloud equipment needs to identify whether the uploaded video carries event information or not; the event information comprises three elements of a target event: the event type, the event principal and the event result, and the event position information is the position coordinate of the target event.
If the video corresponding to the target event does not include event information and event position information, the intelligent short video cloud device needs to analyze and process the video, and identifies the action type of the event pivot in the event by using a third-party human multi-pose evaluation technology, for example, taking a basketball event as an example, identifying the action type of each action object in the video may include: shooting, passing people, covering caps and the like, and also judging results generated by the action, and according to event main roles in videos corresponding to target events determined by action executors, specifically, all video image analysis algorithms applied by the intelligent short video cloud equipment: the event pivot can be identified by using the body pix under the CV (Computer Vision) framework of a third party, and the features of the face, the hair length and color, the ball cover number, the ball cover name and the like of the event pivot are extracted. Furthermore, the whole process of the target event is analyzed by using a visual technology, and the colors of the jerseys are distinguished by using third-party image processing software such as OpenCV (open computer vision correction) and the like so as to be used for distinguishing teams to which the players belong. Detecting a basketball and a basket in a video and each marking area in the basketball court, such as a three-line area, a three-second area, a central circle and the like, by using a third-party detection frame (such as SSD, fast RCNN and the like), and realizing the identification of 14 key nodes of all athlete bodies in the video by using OpenPose by using a third-party human body multi-posture evaluation frame, as shown in FIG. 4; the event type and event outcome are identified by changes in the frame sequence (i.e., the sequence in the video in the time dimension) for each player's joint and basketball location information, or changes in two or more player's joint and basketball location information for both parties. The specific judgment process is as follows:
step one, judging a ball holding player: traversing the relative positions of all the players and the basketball in the whole field, identifying that the position of the node of the palm of the player A who goes into the attack side is superposed with the position of the basketball, and judging that the player A holds the basketball in the video at the moment;
step two (a), judging shooting action: the subsequent frame sequence in the video shows that the palm node of the player A is higher than the top of the head, the basketball leaves the palm of the player A, moves towards the basket in the horizontal direction, moves upwards firstly in the vertical direction and then downwards, and finally falls near the basket, so that the target event is judged to be a shooting event and the player A is an event principal angle;
and step three (a), analyzing the positions of the basketball and the basket in the video, and if the positions of the basketball and the basket are overlapped and the descending speed is obviously reduced in the process of passing through the net, judging that the event is shot by the system.
Step two (b), the judgement of the defensive player: traversing the relative positions of all players and the basketball in the whole field, wherein the relative position of the player is different from the color of the coat of the player A, the player A faces the player A, and when the distance between the two arms of the player A and the player A is smaller than a certain threshold value, the system judges the player as a defensive player B;
step three (b) judging the action of the cap: and displaying a subsequent frame sequence in the video, wherein after the basketball holding player A plays a shooting action, a joint point of a palm of the defending player B is higher than the top of the head, the distance between the joint point and the center of the basketball is less than a certain threshold value, or the displacement speed or direction of the basketball after leaving the palm of the ball holding player A is obviously changed, the target event is judged to be a cap event, the cap event is successfully covered, and the player B is an event main angle.
Optionally, the event pivot is determined according to the action performer, wherein an attacking player such as shooting and passing is the event pivot, and a defending player such as a cap and a snapping is the event pivot.
In one embodiment, the intelligent short video cloud device is further configured to store the event type, the event principal and the event result included in the video corresponding to the obtained target event as the related information of the video, together with the video, in the memory of the intelligent short video cloud device.
In implementation, the intelligent short video cloud device is further configured to associate the event type, the event principal and the event result included in the video corresponding to the obtained target event with the corresponding video as related information of the video, and store the related information and the video into a memory of the intelligent short video cloud device, so as to search and push the video according to the related information.
Optionally, the intelligent short video cloud device may further perform video search according to conventional search conditions, such as an event type, video time information, and a video title, included in the video.
Optionally, the video files corresponding to the target events are stored in a distributed file system, and mass storage and high-speed retrieval of the video files are realized based on a distributed file system structure. And the related information (used as metadata for describing the video) of the video file is stored in the distributed database, and the video file and the related information of the video file establish a correlation relationship, and the correlation relationship assists the query of the video file.
In one embodiment, the intelligent short video cloud equipment is further configured to identify a target object corresponding to a target event according to an event pivot contained in a video corresponding to the target event; the target object is an event principal in the target event; and establishing an incidence relation with the account corresponding to the target object, and pushing the video to the account corresponding to the target object according to the incidence relation.
Optionally, the user may log in a personal account of the user through an APP or an applet to obtain a video corresponding to a target event with the user as an event principal, and the subsequent intelligent short video cloud device may automatically push the video to a corresponding user entity account according to a preset period, a video file uploading condition and the like, and the user may also manually establish an association relationship between the video and the account in a "follow-up" manner, so that the clipped video is automatically pushed to the account in the subsequent process.
Optionally, the video distribution mode may be a push mode of the smart short video cloud device (server) to the user account (client), and may also be a pull mode of the client from the server, so that the embodiment is not limited to the specific implementation of video distribution.
In the embodiment, the video file is pushed to the event pivot in the video through the association relationship established between the video file and the video related information, so that the automatic distribution of the video is completed, and the video distribution efficiency is improved. Specifically, a short video is typically not longer than 3 minutes from live editing, uploading, analyzing, to an account number pushed to the target object.
In one embodiment, the smart short video cloud device is further configured to, if the video corresponding to the target event contains event information, store the event information as related information of the video together with the video in a memory of the smart short video cloud device.
In implementation, the intelligent short video cloud device is further configured to, if the identified video file uploaded by the camera terminal carries RTLS information, that is, event information and event location information carried by an RTLS signal are included, directly establish an association relationship between the video and the event information corresponding to the video without performing video analysis, and store the association relationship together in a memory of the intelligent short video cloud.
In this embodiment, as shown in fig. 5, a video processing method is provided, which includes the following specific steps:
In one embodiment, the method further comprises: and performing packet storage and video processing on the video corresponding to the received target event through the intelligent short video cloud equipment.
For specific limitations of the video processing method, reference may be made to the above limitations of the video processing system, which are not described herein again.
It should be understood that, although the steps in the flowchart of fig. 5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 5 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (14)
1. A video processing system, the system comprising:
the trigger signal generating equipment is used for generating a corresponding trigger signal according to a target event and sending the trigger signal to the camera terminal; the trigger signal comprises at least one of a vibration signal, an audio signal and a real-time positioning signal;
the camera terminal is used for acquiring an original video, monitoring the trigger signal in real time, processing the trigger signal according to the processing priority of the trigger signal, generating a corresponding clipping instruction according to the trigger signal, and clipping the acquired original video according to the clipping instruction to obtain a video corresponding to a target event; wherein the processing priority is that a real-time positioning signal is prioritized over the vibration signal over the audio signal; when a combination mode of the trigger signals comprises the real-time positioning signal, the vibration signal and the audio signal, the camera terminal is used for preferentially processing the real-time positioning signal, and other types of signals are not processed; when a combination mode of the trigger signals includes the vibration signal and the audio signal but does not include the real-time positioning signal, the camera terminal is configured to preferentially process the vibration signal, and the audio signal is not processed.
2. The system of claim 1, further comprising:
and the intelligent short video cloud equipment is used for performing grouping storage and video processing on the videos corresponding to the target events uploaded by the camera terminal.
3. The system of claim 1, wherein the trigger signal generating device comprises:
the vibration sensor is used for acquiring a vibration signal generated by a target event and sending the vibration signal to the camera terminal;
the audio sensor is used for collecting an audio signal generated by the target event and sending the audio signal to the camera terminal; and
and the positioning equipment is used for acquiring a positioning signal generated by the target event, analyzing the positioning signal to obtain event information of the target event corresponding to the positioning signal, and sending the event information of the target event to the camera terminal.
4. The system of claim 3, wherein the vibration sensor is further configured to analyze the vibration signal, extract a vibration spectrum in the vibration signal;
and judging the vibration frequency spectrum according to a preset threshold value, and if the vibration frequency spectrum meets the preset threshold value, taking the vibration signal as a trigger signal and sending the trigger signal to the camera terminal in a Bluetooth broadcast mode.
5. The system of claim 3, wherein the audio sensor is further configured to analyze the audio signal and extract voiceprint feature data from the audio signal;
and judging the voiceprint characteristic data according to a preset threshold, and if the voiceprint characteristic data meet the preset threshold, taking the audio signal as the trigger signal and sending the trigger signal to the camera terminal in a Bluetooth broadcast mode.
6. The system according to claim 3, wherein the audio sensor is integrated inside the camera terminal, and is further configured to analyze the acquired audio signal and extract voiceprint feature data in the acquired audio signal;
and judging the voiceprint characteristic data according to a preset threshold, and if the voiceprint characteristic data meet the preset threshold, taking the audio signal as the trigger signal and sending the trigger signal to a video cutting module in the camera terminal in a microelectronic signal mode.
7. The system according to claim 3, wherein the positioning device is further configured to perform real-time positioning and tracking on the position information of each target object, so as to obtain a position data sequence of each target object;
analyzing and obtaining event information of the same target event where each target object is located according to the position data sequence, wherein the event information comprises an event type, an event principal angle, an event result and position information of the same target event;
and generating the real-time positioning signal according to the event information of the same target event, and sending the real-time positioning signal to the camera terminal in a Bluetooth broadcast mode as the trigger signal.
8. The system according to claim 1, wherein the camera terminal is further configured to upload the video corresponding to the target event obtained by clipping to an intelligent short video cloud device, and delete the video file remaining after the video corresponding to the target event is clipped from the original video file.
9. The system according to claim 2, wherein the intelligent short video cloud device is further configured to receive a video corresponding to a target event uploaded by at least one camera terminal, and the video carries packet identification information;
grouping the received videos according to the grouping identification information to obtain videos corresponding to the same target event;
identifying whether a video corresponding to the target event contains event information of the target event; the event information of the target event is information which is obtained by analyzing based on positioning equipment and is synchronously transmitted to the intelligent short video cloud equipment through the real-time positioning signal and the video;
if the video corresponding to the target event does not contain the event information, performing video analysis on the video corresponding to the target event, extracting image features in the video, and obtaining an event type, an event pivot and an event result contained in the video corresponding to the target event according to the extracted image features and a preset feature attribute rule.
10. The system according to claim 9, wherein the intelligent short video cloud device is further configured to store the obtained event type, event principal and event result included in the video corresponding to the target event as the related information of the video, together with the video, in a memory of the intelligent short video cloud device.
11. The system according to claim 9, wherein the smart short video cloud device is further configured to identify a target object corresponding to the target event according to the event hero included in the video corresponding to the target event; the target object is an event principal in the target event; and
and establishing an incidence relation with an account corresponding to the target object, and pushing the video to the account corresponding to the target object according to the incidence relation.
12. The system according to claim 9, wherein the smart short video cloud device is further configured to, if the video corresponding to the target event includes the event information, store the event information as related information of the video together with the video in a memory of the smart short video cloud device.
13. A method of video processing, the method comprising:
generating a corresponding trigger signal according to a target event through trigger signal generating equipment, and sending the trigger signal to a camera terminal; the trigger signal comprises at least one of a vibration signal, an audio signal and a real-time positioning signal;
acquiring an original video through the camera terminal, monitoring the trigger signal in real time, processing the trigger signal according to the processing priority of the trigger signal, generating a corresponding clipping instruction according to the trigger signal, clipping the acquired original video according to the clipping instruction to obtain a video corresponding to a target event, and sending the video corresponding to the target event to the intelligent short video cloud equipment; wherein the processing priority is that a real-time positioning signal is prioritized over the vibration signal over the audio signal; when a combination mode of the trigger signals comprises the real-time positioning signal, the vibration signal and the audio signal, the camera terminal is used for preferentially processing the real-time positioning signal, and other types of signals are not processed; when a combination mode of the trigger signals includes the vibration signal and the audio signal but does not include the real-time positioning signal, the camera terminal is configured to preferentially process the vibration signal, and the audio signal is not processed.
14. The method of claim 13, further comprising:
and performing packet storage and video processing on the received video corresponding to the target event through the intelligent short video cloud equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110100561.9A CN112468735B (en) | 2021-01-26 | 2021-01-26 | Video processing system and video processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110100561.9A CN112468735B (en) | 2021-01-26 | 2021-01-26 | Video processing system and video processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112468735A CN112468735A (en) | 2021-03-09 |
| CN112468735B true CN112468735B (en) | 2021-05-11 |
Family
ID=74802375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110100561.9A Active CN112468735B (en) | 2021-01-26 | 2021-01-26 | Video processing system and video processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112468735B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599179A (en) * | 2009-07-17 | 2009-12-09 | 北京邮电大学 | Method for automatically generating field motion wonderful scene highlights |
| CN104883607A (en) * | 2015-06-05 | 2015-09-02 | 广东欧珀移动通信有限公司 | Video screenshot or clipping method, video screenshot or clipping device and mobile device |
| CN107079201A (en) * | 2014-08-13 | 2017-08-18 | 英特尔公司 | technology and device for editing video |
| CN110717071A (en) * | 2018-06-26 | 2020-01-21 | 北京深蓝长盛科技有限公司 | Image clipping method, image clipping device, computer device, and storage medium |
| CN111494912A (en) * | 2019-01-31 | 2020-08-07 | 北京深蓝长盛科技有限公司 | Basketball exercise assisting system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8731239B2 (en) * | 2009-12-09 | 2014-05-20 | Disney Enterprises, Inc. | Systems and methods for tracking objects under occlusion |
-
2021
- 2021-01-26 CN CN202110100561.9A patent/CN112468735B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599179A (en) * | 2009-07-17 | 2009-12-09 | 北京邮电大学 | Method for automatically generating field motion wonderful scene highlights |
| CN107079201A (en) * | 2014-08-13 | 2017-08-18 | 英特尔公司 | technology and device for editing video |
| CN104883607A (en) * | 2015-06-05 | 2015-09-02 | 广东欧珀移动通信有限公司 | Video screenshot or clipping method, video screenshot or clipping device and mobile device |
| CN110717071A (en) * | 2018-06-26 | 2020-01-21 | 北京深蓝长盛科技有限公司 | Image clipping method, image clipping device, computer device, and storage medium |
| CN111494912A (en) * | 2019-01-31 | 2020-08-07 | 北京深蓝长盛科技有限公司 | Basketball exercise assisting system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112468735A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20050265603A1 (en) | Image processing | |
| JPWO2018198373A1 (en) | Video surveillance system | |
| US9451178B2 (en) | Automatic insertion of video into a photo story | |
| CN111163259A (en) | Image capturing method, monitoring camera and monitoring system | |
| CN107247733B (en) | Video clip watching popularity analysis method and system | |
| WO2021068553A1 (en) | Monitoring method, apparatus and device | |
| CN108028969A (en) | system and method for video processing | |
| WO2014106384A1 (en) | Method, apparatus and video monitoring system for providing monitoring video information | |
| CN103377268B (en) | System for carrying out target identification and event reproduction by using post-set data | |
| CN108540757B (en) | Monitoring system and monitoring method | |
| CN111757148A (en) | Method, device and system for processing sports event video | |
| CN111586432B (en) | Method and device for determining air-broadcast live broadcast room, server and storage medium | |
| CN108537088B (en) | Monitoring method and system | |
| CN105245845A (en) | Method for controlling camera to follow and shoot automatically based on gathering trend in match field | |
| CN105320958B (en) | A kind of image-recognizing method and system based on location information | |
| CN111741325A (en) | Video playing method and device, electronic equipment and computer readable storage medium | |
| CN112437233B (en) | Video generation method, video processing device and camera equipment | |
| CN107092636A (en) | The retrieval device and method of CCTV images | |
| CN110717071B (en) | Image clipping method, image clipping device, computer device, and storage medium | |
| CN108540817B (en) | Video data processing method, device, server and computer readable storage medium | |
| CN112468735B (en) | Video processing system and video processing method | |
| CN108881119B (en) | Method, device and system for video concentration | |
| US20230075621A1 (en) | Golf digest creating system, mobile imaging unit, and digest creating device | |
| CN112287771A (en) | Method, apparatus, server and medium for detecting video event | |
| CN104170367A (en) | Virtual shutter image capture |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |