Competition wonderful collection generation method and device, equipment and storage medium

Abstract

The invention discloses a competition wonderful collection generation method and device, equipment and a storage medium, and the method comprises the steps: monitoring whether a target enters a competition region or not in real time, and carrying out the real-time monitoring of each target entering the competition region, so as to determine the position track information of each target in the competition region; obtaining streaming media data collected by each camera arranged in the competition area; for each target, determining each video clip corresponding to the target based on the streaming media data collected by each camera and the position track information of the target; screening out each wonderful clip from each video clip corresponding to each target; constructing a wonderful video collection by each wonderful fragment; and displaying the wonderful video collection on a user client. The problem that response is not timely can be solved, each video clip is determined in combination with the position track information and the streaming media data, wonderful clips are screened, manpower and material resources are saved, and the watching experience of audiences is improved.

Description

Technical Field

[0001] The present application relates to the technical field of generating a highlight reel of a match, and in particular to a method, device, equipment and storage medium for generating a highlight reel of a match. Background Art

[0002] In today's booming digital competitive entertainment industry, in order to enable the audience to quickly review the highlights of the game and improve the dissemination efficiency and attractiveness of competitive content, it is crucial to capture the wonderful moments of the game and generate highlights. In the existing process of generating highlights, it is necessary to manually operate the camera, adjust the shooting angle and position, and then manually edit the video to summarize the wonderful moments.

[0003] However, this manual operation and editing method is prone to problems such as untimely response, waste of manpower and material resources, and low efficiency. Summary of the invention

[0004] In view of this, the present application provides a method, device, equipment and storage medium for generating a highlight collection of a match, which is used to solve the problem that the existing manual operation and editing methods are prone to untimely response, waste of manpower and material resources, and low efficiency.

[0005] To achieve the above objectives, the proposed solution is as follows:

[0006] In a first aspect, a method for generating a highlight reel of a competition includes:

[0007] Monitor in real time whether there is a target entering the competition area, and monitor in real time each target entering the competition area to determine the location and trajectory information of each target in the competition area;

[0008] Acquire streaming media data collected by various cameras arranged in the competition area;

[0009] For each of the targets, determine each video segment corresponding to the target based on the streaming media data collected by each camera and the location trajectory information of the target;

[0010] Filter out each wonderful clip from each video clip corresponding to each of the targets;

[0011] Constructing a wonderful video collection from each of the wonderful clips;

[0012] The wonderful video highlights are displayed on the user client.

[0013] Preferably, for each of the targets, determining each video segment corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target includes:

[0014] The streaming media data collected by each camera is divided into first streaming media segments respectively;

[0015] dividing the position trajectory information of the target into individual first position information;

[0016] Determining the camera coverage area of ​​each camera within the event area;

[0017] Based on the camera coverage area of ​​each camera and the first position information of the target, the first streaming media segments are screened to determine the video segments corresponding to the target.

[0018] Preferably, the screening from each of the first streaming media segments based on the camera coverage area of ​​each of the cameras and each of the first position information of the target to determine each of the video segments corresponding to the target includes:

[0019] For each piece of the first position information of the target, determine whether the first position information is located in a camera coverage area of ​​one or more cameras;

[0020] If so, then each target camera corresponding to the target is used;

[0021] Determine the entry timestamp and the exit timestamp of the target entering and exiting the camera coverage area of ​​each of the target cameras;

[0022] The entry timestamp and the exit timestamp are matched with each of the first streaming media segments to determine each video segment.

[0023] Preferably, the step of selecting each wonderful segment from each video segment corresponding to each target includes:

[0024] Determine the current event;

[0025] Determine each highlight moment corresponding to the current event in a pre-established event highlight time table;

[0026] According to each of the wonderful moments, determine each wonderful time stamp of the current event;

[0027] Based on the respective wonderful timestamps, the respective wonderful clips are screened out from the respective video clips corresponding to the respective targets.

[0028] Preferably, the selecting each of the wonderful clips from each of the video clips based on each of the wonderful timestamps includes:

[0029] Determine a championship time stamp from each of the wonderful time stamps, and determine a championship goal from each of the goals;

[0030] The video clip corresponding to the championship goal at the championship timestamp is used as a highlight clip;

[0031] Determine the video clips corresponding to the championship goal at other respective wonderful time stamps as the wonderful clips.

[0032] Preferably, constructing a wonderful video collection from each of the wonderful clips includes:

[0033] Determining a winning clip from each of the highlight clips;

[0034] Determine the time information corresponding to each of the wonderful clips except the championship-winning clip;

[0035] Sorting the other wonderful clips according to the time information;

[0036] splicing the various wonderful clips according to the sorting to form a first spliced ​​clip;

[0037] The first spliced ​​segment is spliced ​​after the championship segment to obtain a wonderful video collection.

[0038] Preferably, it also includes:

[0039] Sending a video segment selection window to the user client, so that the user can make a selection in the video segment selection window;

[0040] According to the user's selection, determining one or more corresponding video segments as respective selected segments;

[0041] The selected clips are used to form an intended video collection;

[0042] The intended video highlights are displayed on the user client.

[0043] In a second aspect, a device for generating a highlight collection of a competition includes:

[0044] A real-time monitoring module is used to monitor in real time whether there is a target entering the competition area, and to monitor in real time each target entering the competition area to determine the position trajectory information of each target in the competition area;

[0045] A streaming media data acquisition module, used to acquire streaming media data collected by various cameras arranged in the competition area;

[0046] A video segment determination module, for determining, for each of the targets, each video segment corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target;

[0047] A highlight segment screening module, used for screening out each highlight segment from each video segment corresponding to each target;

[0048] A wonderful video collection construction module, used for constructing a wonderful video collection from each of the wonderful clips;

[0049] A display module is used to display the wonderful video highlights on the user client.

[0050] In a third aspect, a device for generating a highlight reel of a competition includes a memory and a processor;

[0051] The memory is used to store programs;

[0052] The processor is used to execute the program to implement each step of the method for generating a highlight reel of a match as described in any one of the first aspects.

[0053] In a fourth aspect, a storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the method for generating a highlight collection of a match as described in any one of the first aspects are implemented.

[0054] It can be seen from the above technical scheme that the present application monitors whether there is a target entering the event area in real time, and monitors each target entering the event area in real time to determine the position trajectory information of each target in the event area; obtains the streaming media data collected by each camera arranged in the event area; for each target, determines each video clip corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target; selects each wonderful clip from each video clip corresponding to each target; constructs a wonderful video collection from each wonderful clip; and displays the wonderful video collection on the user client. The present application monitors the event area in real time, and when a target appears, it immediately responds to real-time monitoring, which can solve the problem of untimely response in the prior art, thereby grasping the movement of the target and determining the position trajectory information. In addition, the streaming media data collected by each camera arranged in the event area can be obtained, so that each video clip of the target can be determined by combining the position trajectory information and the streaming media data, and the wonderful clips can be selected from these clips, saving manpower and material resources, efficiently generating wonderful video highlights, and displaying them on the user client to enhance the viewing experience of the audience. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0056] Figure 1 An optional flow chart of a method for generating a highlight collection of a competition provided in an embodiment of the present application;

[0057] Figure 2 A schematic diagram of a video clip selection window provided in an embodiment of the present application;

[0058] Figure 3 A schematic diagram of the structure of a device for generating a highlight collection of a competition provided in an embodiment of the present application;

[0059] Figure 4 A schematic diagram of the structure of a device for generating highlights of a match provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0061] The present invention can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, distributed computing environments including any of the above devices or equipment, etc.

[0062] The embodiment of the present invention provides a method for generating a highlight collection of a competition. The method can be applied to various computer terminals or smart terminals. The execution subject can be a processor or a server of the computer terminal or the smart terminal. The method flow chart of the method is as follows: Figure 1 As shown, specifically including:

[0063] S1: Real-time monitoring of whether there is a target entering the competition area, and real-time monitoring of each target entering the competition area to determine the location trajectory information of each target in the competition area.

[0064] It is understandable that there are many types of events, covering multiple fields such as sports, culture, technology, and business. Among sports events, there are football matches, basketball matches, tennis matches, volleyball matches, etc., as well as track and field competitions, water competitions, ice and snow competitions, etc. TV stations will broadcast or rebroadcast these events. Existing technology usually relies on manual operation of the camera, adjusting the shooting angle and position, and capturing the important, highlights, and wonderful moments of athletes and competitions.

[0065] However, this application monitors the dynamics of the competition area in real time without relying on manual operation. In particular, it monitors whether there is a target entering the competition area in real time. If there is a target entering, the target is monitored in real time. The competition area refers to the venue of a specific competition. For example, for a basketball competition, the corresponding competition area is the area composed of the sideline and the end line. The competition area can also be expanded accordingly according to the specific live broadcast or broadcast needs, so that more video clips can be captured; for example, for racing, the corresponding competition area is the racing track. Therefore, the shape and layout of the competition venues corresponding to different events are diverse, and the competition area needs to be determined according to the current event.

[0066] Then the athletes (including real people or robots) or racing vehicles, sailboats, rowing boats, etc. that enter the competition area to participate in the competition are all targets set by this application. Each target entering the competition area is monitored in real time, and the position trajectory information of each target in the competition area is determined based on the real-time monitoring.

[0067] Determining the target's position trajectory information can help you understand the target's movement status, so you can determine where the target is moving to, whether it is close to the finish line of the race, etc., which is convenient for screening subsequent highlights.

[0068] Surveillance cameras can be used to monitor the event area and conduct real-time monitoring of incoming targets. Positioning systems can also be used, such as GPS, RFID (Radio Frequency Identification), UWB (Ultra-Wideband), etc. to accurately locate targets. The positioning accuracy of UWB can reach centimeter level.

[0069] This application can generate wonderful video highlights in real time during the event, and can also generate wonderful video highlights after the event.

[0070] S2: Acquire streaming media data collected by various cameras arranged in the competition area.

[0071] There are usually multiple cameras / camcorders deployed in the event area, including fixed cameras and mobile cameras, and additional cameras can also be deployed when applying the method provided in this application to meet specific needs.

[0072] Among them, fixed cameras are generally installed around the event area to cover the main range of the event area. Mobile cameras can be drones or automatic tracking cameras, etc., which can flexibly adjust the shooting angle.

[0073] After the game starts, the camera will record the game area to form streaming data. The streaming data collected by each camera may include all targets or some targets, which is not limited in this embodiment.

[0074] When acquiring streaming media data in real time, in order to speed up the process of determining subsequent highlights, some special moments (such as scoring, sprinting, overtaking opponents, rushing to the finish line, etc.) can be marked with tags in this step to provide reference and convenience for the subsequent screening process of highlights.

[0075] S3: For each of the targets, determine each video segment corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target.

[0076] In many types of competitions, there are multiple targets in varying numbers, and the situation in the competition area is complex and changeable. Therefore, in the process of generating the highlights of the competition, this application determines each video clip from each target.

[0077] For each target, since the location trajectory information of the target has been determined in the above steps, and the cameras arranged in the competition area also collect streaming media data, there is corresponding video data in the streaming media data for the target. Then, based on the location trajectory information and streaming media data, the state and situation of the target in the competition area can be clearly determined, and some video clips of the target can be determined.

[0078] The video clips determined in this step can be video clips that have been preliminarily screened, which can improve the efficiency of subsequent screening of highlight clips, or they can be multiple video clips divided from all video data about the target in the event area, which can provide more materials for subsequent screening of highlight clips and not miss any video clips that can become highlight clips.

[0079] S4: Filter out each wonderful segment from each video segment corresponding to each target.

[0080] When selecting highlights from various video clips, you can select them according to the type of the current event, including the following two methods:

[0081] 1) Start from the perspective of the goal.

[0082] For example, in basketball, football and other competitions, video clips that include goal-scoring, key passes or dribbling are considered highlights; in track and field competitions, clips that include rushing towards the finish line to win the championship are considered highlights.

[0083] 2) Start from the audience’s perspective.

[0084] Based on the on-site audio data, audience expressions, etc., clips with loud cheers or audience expressions mostly showing exaggerated expressions such as surprise and regret will be selected as highlights.

[0085] S5: constructing a wonderful video collection from each of the wonderful clips.

[0086] After selecting each wonderful clip in step S4, the wonderful video collection can be constructed. During the construction process:

[0087] You can first review each wonderful clip, such as checking whether the picture quality of each wonderful clip is qualified, whether the continuous action of the target in the clip is complete, etc., so as to ensure the quality of the wonderful video collection that is finally constructed.

[0088] In order to streamline the wonderful video highlights, each wonderful clip can be screened again to determine a few key clips in a small range. These key clips can be slowed down, and the picture can also be enlarged and then spliced ​​with other wonderful clips. This allows the audience or users to see the wonderful moments clearly and accurately, enhancing the visual impact. However, it is also necessary to avoid the wonderful video highlights being too cumbersome as a whole, causing the audience or users to lose interest. Therefore, the duration of the entire wonderful video highlights must be controlled within a certain range.

[0089] When splicing, you can set transition effects to connect the various highlights to make the transition more natural and smooth. The transition effects can be selected as needed. For example, according to the type of the current event, whether it is fast-paced or slow-paced, different transition effects can be matched to improve the audience or user's appreciation.

[0090] Furthermore, you can choose background music that suits the current event style and highlight atmosphere, such as music with strong rhythm, elegance, soothing and beautiful, etc. Among them, build a highlight interlude library in advance, which contains corresponding relationships. For example, one type of event item corresponds to multiple types of music, and one type of music can be applied to multiple types of event items.

[0091] You can also dub the wonderful video highlights, such as providing live real-time commentary from a TV commentator, and provide corresponding subtitles to help viewers or users understand the commentator's explanation.

[0092] S6: Displaying the wonderful video highlights on the user client.

[0093] After the wonderful video highlights are produced, they are sent to the user client and presented to the user so that the user can watch them.

[0094] Among them, different user clients have different devices. In order to enable the wonderful video highlights to be played smoothly on different user-end devices, the format and encoding of the wonderful video highlights can be optimized to ensure its compatibility and compression efficiency.

[0095] It can be seen from the above technical scheme that the present application monitors whether there is a target entering the event area in real time, and monitors each target entering the event area in real time to determine the position trajectory information of each target in the event area; obtains the streaming media data collected by each camera arranged in the event area; for each target, determines each video clip corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target; selects each wonderful clip from each video clip corresponding to each target; constructs a wonderful video collection from each wonderful clip; and displays the wonderful video collection on the user client. The present application monitors the event area in real time, and when a target appears, it immediately responds to real-time monitoring, which can solve the problem of untimely response in the prior art, thereby grasping the movement of the target and determining the position trajectory information. In addition, the streaming media data collected by each camera arranged in the event area can be obtained, so that each video clip of the target can be determined by combining the position trajectory information and the streaming media data, and the wonderful clips can be selected from these clips, saving manpower and material resources, efficiently generating wonderful video highlights, and displaying them on the user client to enhance the viewing experience of the audience.

[0096] In the method provided in the embodiment of the present invention, for each of the targets, a process of determining each video clip corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target is specifically described as follows:

[0097] The streaming media data collected by each camera is divided into first streaming media segments respectively;

[0098] dividing the position trajectory information of the target into individual first position information;

[0099] Determining the camera coverage area of ​​each camera within the event area;

[0100] Based on the camera coverage area of ​​each camera and the first position information of the target, the first streaming media segments are screened to determine the video segments corresponding to the target.

[0101] Specifically, in the process of dividing the streaming media data collected by each camera into various first streaming media segments, a time range can be set, such as half a minute, 10 seconds, etc., and the streaming media data can be divided into various first streaming media data according to this time range; image recognition and other technologies can also be used to divide according to the target event actions, such as dividing a segment after an action is completed, and then waiting for the next action, and so on, to obtain various first streaming media segments.

[0102] The location track information can be segmented at the same time. If the streaming media data is segmented according to a set time range, the location track information must also be segmented according to the same time range; if the streaming media data is segmented according to the event action, the location track information is also segmented, that is, the streaming media data and the location track information are segmented in the same way, and the same segmentation method can maintain correspondence, so as to accurately obtain video clips. The first location information can be expressed in the form of coordinates, taking the event area as a coordinate system, and the location track information can be regarded as a straight line / curve in the coordinate system. Each first location information after segmentation is a coordinate point.

[0103] The above steps obtain each first streaming media segment and each first position information. It can be understood that since the camera monitors the event area, and the activity range of each target is the range of the event area, the position trajectory information is also within the range of the event area. Then, the first position information (also regarded as a position point) divided by the position trajectory information exists in the range monitored by any one or more cameras. Therefore, the camera coverage range of each camera in the event area is determined, and a target may appear in the camera coverage range of one or more cameras once or multiple times during the event. Then, each target has a corresponding relationship with each camera in the camera coverage range where it appears, as shown in Table 1 below:

[0104]

[0105] Correspondingly, one or more first position information of the target will also exist in the camera coverage of one or more cameras, so a corresponding relationship can be formed between the target, the first position information, and the camera. At the same time, the camera also collects streaming media data, so the corresponding first streaming media segment can be determined for each first position information of each target as a video segment.

[0106] This method of determining video clips enables accurate correspondence and linkage between targets and cameras, improves the automation of the overall solution, significantly reduces manual operations, and reduces the error rate.

[0107] The process of screening the first streaming media segments based on the camera coverage area of ​​each camera and the first position information of the target to determine the video segments corresponding to the target may include the following steps:

[0108] For each piece of the first position information of the target, determine whether the first position information is located in a camera coverage area of ​​one or more cameras;

[0109] If so, then each target camera corresponding to the target is used;

[0110] Determine the entry timestamp and the exit timestamp of the target entering and exiting the camera coverage area of ​​each of the target cameras;

[0111] The entry timestamp and the exit timestamp are matched with each of the first streaming media segments to determine each video segment.

[0112] Specifically, in this process, starting from each first position information, it is determined within the camera coverage area of ​​one or several cameras that the first position information is located, and the determined camera is used as the target camera of the target corresponding to the first position information. It can be understood that there is a time record of each target entering and leaving the camera coverage area. Therefore, the timestamp of a target entering its target camera can be obtained as an entry timestamp, and the timestamp of the target leaving can be obtained as an exit timestamp. In this way, the time point and time range of the event experienced by the target within the camera coverage area of ​​the target camera can be determined. Combined with the streaming media data collected by the target camera, the video clip of the target within the range of the entry timestamp and the exit timestamp can be filtered out from the streaming media data. Since the above process has divided the streaming media data into various first streaming media clips, the first streaming media clip corresponding to the entry timestamp and the exit timestamp can be matched as the video clip.

[0113] It should be noted that the time period composed of the entry timestamp and the exit timestamp does not necessarily correspond to the above-mentioned segmentation method. That is to say, the segment of the streaming media data corresponding to the time period may partially overlap with a first streaming media segment, or the two may be in a relationship of inclusion and being included. For example, the first streaming media segment includes the segment of the streaming media data corresponding to the time period, or the segment of the streaming media data corresponding to the time period includes the first streaming media segment. Therefore, in the matching process, the first streaming media segment with the highest matching degree can be used as the video segment.

[0114] Optionally, if the first streaming media segment includes a segment of streaming media data corresponding to the time period, the first streaming media segment can be cut to retain only the segment including the target. The process of first cutting and then matching in this step can improve the efficiency of generating the entire wonderful video collection, reduce the probability of missing wonderful moments / highlight moments, and improve the quality of the wonderful video collection.

[0115] The following embodiments describe in detail the process of selecting each wonderful segment from each video segment corresponding to each target in the present application.

[0116] Determine the current event;

[0117] Determine each highlight moment corresponding to the current event in a pre-established event highlight time table;

[0118] According to each of the wonderful moments, determine each wonderful time stamp of the current event;

[0119] Based on the respective wonderful timestamps, the respective wonderful clips are screened out from the respective video clips corresponding to the respective targets.

[0120] Specifically, the types of wonderful moments / highlight moments of different events are also different. For example, in football events, there are wonderful moments when athletes score goals, goalkeepers save the ball, and athletes dribble past opponents; for example, in track and field events, there are wonderful moments when athletes make their final sprints, when athletes who are about to win the championship break through the finish line, and when athletes accelerate to surpass their opponents. Therefore, the timing of wonderful moments in different events is different. Therefore, this application pre-establishes a wonderful timetable, in which the wonderful moments of each event are recorded, as shown in Table 2 below:

[0121]

[0122] Then when filtering the highlights, you can first determine the current event, then call the highlight timetable for matching, determine when the highlights appear in the current event, and then determine the corresponding highlight timestamp in the current event according to the highlights, that is, the time point when the highlights appear, so that you can filter in each video clip.

[0123] The method of selecting each wonderful clip from each video clip based on each wonderful time stamp includes the following two methods:

[0124] 1) The goal of winning the championship is the main screening point.

[0125] Determine a championship time stamp from each of the wonderful time stamps, and determine a championship goal from each of the goals;

[0126] The video clip corresponding to the championship goal at the championship timestamp is used as a highlight clip;

[0127] Determine the video clips corresponding to the championship goal at other respective wonderful time stamps as the wonderful clips.

[0128] If the goal of winning is used as the main screening point, it is assumed that the event has ended. It is understandable that the goal of winning is the most watched, so the winning timestamp is determined from each highlight timestamp, thereby determining the winning goal, and then taking the winning goal as the main point, the corresponding video clips of the winning goal under the highlight timestamp are used as each highlight clip.

[0129] In an example, the current event is a football match, and the participating teams are Team A and Team B. The winning timestamp can be the last moment of the countdown, the lore moment, or the moment of the last penalty kick in the penalty shootout after overtime. The winning target is a player on Team A, such as the captain, or the player corresponding to the last penalty kick, or the player who scored the lore goal. Then one or more video clips of the winning target under the wonderful timestamps of scoring, saving the ball, and dribbling past the opponent are the highlights.

[0130] Taking the goal of winning the championship as the main screening point can ensure that the selected highlights are more accurate and concise.

[0131] 2) Use the highlight timestamp as the main filtering point.

[0132] The video clips corresponding to each target under each wonderful time stamp are all taken as wonderful clips, or each video clip where each wonderful time stamp falls is taken as a wonderful clip.

[0133] Using the highlight timestamp as the main screening point can ensure that the screened highlight clips contain all the highlights of the current event.

[0134] Optionally, the step of constructing a wonderful video collection from each of the wonderful clips in the present application includes:

[0135] Determining a winning clip from each of the highlight clips;

[0136] Determine the time information corresponding to each of the wonderful clips except the championship-winning clip;

[0137] Sorting the other wonderful clips according to the time information;

[0138] splicing the various wonderful clips according to the sorting to form a first spliced ​​clip;

[0139] The first spliced ​​segment is spliced ​​after the championship segment to obtain a wonderful video collection.

[0140] Specifically, it is understandable that in competitive sports, the winning moment is the most important moment, so the highlight clip corresponding to the winning moment is identified as the winning clip, and when constructing a highlight video collection, the winning clip is placed at the front of the highlight video collection, so that users or viewers can first see the video of the winning moment, and then sort the other highlight clips in chronological order and splice them to form a first spliced ​​clip, which is then spliced ​​after the winning clip.

[0141] The wonderful video highlights constructed in this way are clearer and neater, which can improve the viewing experience of viewers or users.

[0142] Furthermore, in order to increase the degree of freedom of viewers or users, the present application also provides a method for viewers or users to independently select the video corresponding to the target they want to watch or replay, or the video corresponding to a special moment, which includes the following steps:

[0143] Sending a video segment selection window to the user client, so that the user can make a selection in the video segment selection window;

[0144] According to the user's selection, determining one or more corresponding video segments as respective selected segments;

[0145] The selected clips are used to form an intended video collection;

[0146] The intended video highlights are displayed on the user client.

[0147] Specifically, a video segment selection window is pre-built and sent to the user client. The video segment selection window is as follows: Figure 2 As shown in the figure, three options are included, namely the first option, the second option and the third option. The first option allows users to select the targets they want to make in the intended video highlights. The first option includes all the targets in the current event. Users can select one or more targets at will, and the circle in front of each target in the window is the selection button; the second option allows users to select video data collected by the camera. The second option includes all the cameras arranged in the event area. Users can select one or more cameras at will, and the circle in front of each camera in the window is the selection button; the third option allows users to select highlight timestamps. The third option includes all the highlight timestamps corresponding to the current event. Users can select one or more highlight timestamps, and the circle in front of each highlight timestamp in the window is the selection button.

[0148] In an example, if the user selects target 2, camera a, and highlight timestamp D in the video clip selection window, then the corresponding selected clip is: the video clip under the highlight timestamp D when target 2 appears in the camera coverage area of ​​camera a; if the user only selects one of the three options, then the video clips corresponding to all other options under one option will be regarded as selected clips.

[0149] This method of providing users with choices greatly improves the flexibility of generating video highlights. The intended video highlights are not limited to wonderful videos, but can meet the intentions of every user, allowing users to watch the event from multiple aspects, which greatly improves the user experience and satisfaction, and can also expand the popularity of the event.

[0150] Furthermore, the present application can not only generate intended video highlights, but also allow users to select targets or cameras for real-time broadcast. For example, users can select the target they want to watch in real time, and then call any one or more cameras to broadcast the target in real time; or if the user wants to watch the event from a specific camera position, the real-time monitoring data of the camera will be broadcast to the user. Split-screen broadcast can also be set up to improve user operability.

[0151] For events with many targets in the event area, the camera monitoring process can be pre-set. After the event starts, the camera positions are rotated according to the pre-set monitoring process.

[0152] Furthermore, in order to better implement the method for generating the highlights of the event provided by this application, fixed cameras can be installed and debugged in the event area before the event starts to ensure that all fixed cameras can cover and monitor the entire event area / key areas of the event. For mobile cameras, for special events where the target moving route can be determined, such as racing, the positioning equipment can be configured and debugged for the participating vehicles in advance, and the paths of the mobile cameras can be configured in advance on both sides of the racing track. At the same time, the tracking strategy can be planned, and automatic jib tracking can be performed during the event. According to the positioning data of the participating vehicles determined by the positioning equipment, the shooting angle and position of the tracking camera can be adjusted in real time to ensure that the complete video is captured.

[0153] and Figure 1 Corresponding to the method described above, the embodiment of the present invention also provides a device for generating a highlight collection of a match, for Figure 1 In the specific implementation of the method, the generation device of the game highlights provided by the embodiment of the present invention can be in a computer terminal or various mobile devices, combined with Figure 3 , introduces the device for generating the highlights of the event, such as Figure 3 As shown, the device may include:

[0154] A real-time monitoring module 10 is used to monitor in real time whether there is a target entering the competition area, and to monitor in real time each target entering the competition area to determine the position trajectory information of each target in the competition area;

[0155] A streaming media data acquisition module 20, used to acquire streaming media data collected by various cameras arranged in the competition area;

[0156] A video segment determination module 30 is used to determine, for each of the targets, the video segments corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target;

[0157] A wonderful segment screening module 40 is used to screen out each wonderful segment from each video segment corresponding to each target;

[0158] A wonderful video collection construction module 50, used for constructing a wonderful video collection from each of the wonderful clips;

[0159] The display module 60 is used to display the wonderful video highlights on the user client.

[0160] It can be seen from the above technical scheme that the present application monitors whether there is a target entering the event area in real time, and monitors each target entering the event area in real time to determine the position trajectory information of each target in the event area; obtains the streaming media data collected by each camera arranged in the event area; for each target, determines each video clip corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target; selects each wonderful clip from each video clip corresponding to each target; constructs a wonderful video collection from each wonderful clip; and displays the wonderful video collection on the user client. The present application monitors the event area in real time, and when a target appears, it immediately responds to real-time monitoring, which can solve the problem of untimely response in the prior art, thereby grasping the movement of the target and determining the position trajectory information. In addition, the streaming media data collected by each camera arranged in the event area can be obtained, so that each video clip of the target can be determined by combining the position trajectory information and the streaming media data, and the wonderful clips can be selected from these clips, saving manpower and material resources, efficiently generating wonderful video highlights, and displaying them on the user client to enhance the viewing experience of the audience.

[0161] Furthermore, the embodiment of the present application provides a device for generating a highlight reel of a match. Figure 4 The hardware structure diagram of the equipment for generating the highlights of the game is shown in FIG. Figure 4The hardware structure of the device for generating the highlights of a match may include: at least one processor 01, at least one communication interface 02, at least one memory 03 and at least one communication bus 04.

[0162] In the embodiment of the present application, the number of the processor 01 , the communication interface 02 , the memory 03 , and the communication bus 04 is at least one, and the processor 01 , the communication interface 02 , and the memory 03 communicate with each other through the communication bus 04 .

[0163] The processor 01 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0164] The memory 03 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory.

[0165] The memory stores a program, and the processor can call the program stored in the memory, and the program is used to execute the following method for generating a highlight collection of a competition, including:

[0166] Monitor in real time whether there is a target entering the competition area, and monitor in real time each target entering the competition area to determine the location and trajectory information of each target in the competition area;

[0167] Acquire streaming media data collected by various cameras arranged in the competition area;

[0168] For each of the targets, determine each video segment corresponding to the target based on the streaming media data collected by each camera and the location trajectory information of the target;

[0169] Filter out each wonderful clip from each video clip corresponding to each of the targets;

[0170] Constructing a wonderful video collection from each of the wonderful clips;

[0171] The wonderful video highlights are displayed on the user client.

[0172] Optionally, the detailed functions and extended functions of the program may refer to the description of the method for generating the highlights of the competition in the method embodiment.

[0173] The embodiment of the present application further provides a storage medium, which can store a program suitable for execution by a processor, and when the program is running, controls the device where the storage medium is located to execute the following method for generating a highlight collection of a match, including:

[0174] Monitor in real time whether there is a target entering the competition area, and monitor in real time each target entering the competition area to determine the location and trajectory information of each target in the competition area;

[0175] Acquire streaming media data collected by various cameras arranged in the competition area;

[0176] For each of the targets, determine each video segment corresponding to the target based on the streaming media data collected by each camera and the location trajectory information of the target;

[0177] Filter out each wonderful clip from each video clip corresponding to each of the targets;

[0178] Constructing a wonderful video collection from each of the wonderful clips;

[0179] The wonderful video highlights are displayed on the user client.

[0180] Specifically, the storage medium may be a computer-readable storage medium, and the computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk or a ROM.

[0181] Optionally, the detailed functions and extended functions of the program may refer to the description of the method for generating the highlights of the competition in the method embodiment.

[0182] In addition, the functional modules in the various embodiments of the present disclosure can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a live broadcast device, or a network device, etc.) to perform all or part of the steps of the methods of the various embodiments of the present disclosure.

[0183] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0184] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0185] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating a highlight collection of a competition, characterized in that: include: Monitor in real time whether there is a target entering the competition area, and monitor in real time each target entering the competition area to determine the location and trajectory information of each target in the competition area; Acquire streaming media data collected by various cameras arranged in the competition area; For each of the targets, determine each video segment corresponding to the target based on the streaming media data collected by each camera and the location trajectory information of the target; Filter out each wonderful clip from each video clip corresponding to each of the targets; Constructing a wonderful video collection from each of the wonderful clips; The wonderful video highlights are displayed on the user client.

2. The method according to claim 1, characterized in that: For each of the targets, determining each video segment corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target includes: The streaming media data collected by each camera is divided into first streaming media segments respectively; dividing the position trajectory information of the target into individual first position information; Determining the camera coverage area of ​​each camera within the event area; Based on the camera coverage area of ​​each camera and the first position information of the target, the first streaming media segments are screened to determine the video segments corresponding to the target.

3. The method according to claim 2, characterized in that The filtering, based on the camera coverage area of ​​each camera and the first position information of the target, from the first streaming media segments to determine the video segments corresponding to the target includes: For each piece of the first position information of the target, determine whether the first position information is located in a camera coverage area of ​​one or more cameras; If so, then each target camera corresponding to the target is used; Determine the entry timestamp and the exit timestamp of the target entering and exiting the camera coverage area of ​​each of the target cameras; The entry timestamp and the exit timestamp are matched with each of the first streaming media segments to determine each video segment.

4. The method according to claim 1, characterized in that The step of selecting the wonderful clips from the video clips corresponding to the targets includes: Determine the current event; Determine each highlight moment corresponding to the current event in a pre-established event highlight time table; According to each of the wonderful moments, determine each wonderful time stamp of the current event; Based on the respective wonderful timestamps, the respective wonderful clips are screened out from the respective video clips corresponding to the respective targets.

5. The method according to claim 4, characterized in that The step of selecting each of the wonderful clips from each of the video clips based on each of the wonderful timestamps includes: Determine a championship time stamp from each of the wonderful time stamps, and determine a championship goal from each of the goals; The video clip corresponding to the championship goal at the championship timestamp is used as a highlight clip; Determine the video clips corresponding to the championship goal at other respective wonderful time stamps as the wonderful clips.

6. The method according to any one of claims 1 to 5, characterized in that The wonderful video collection is constructed from the wonderful clips, including: Determining a winning clip from each of the highlight clips; Determine the time information corresponding to each of the wonderful clips except the championship-winning clip; Sorting the other wonderful clips according to the time information; splicing the various wonderful clips according to the sorting to form a first spliced ​​clip; The first spliced ​​segment is spliced ​​after the championship segment to obtain a wonderful video collection.

7. The method according to any one of claims 1 to 5, characterized in that Also includes: Sending a video segment selection window to the user client, so that the user can make a selection in the video segment selection window; According to the user's selection, determining one or more corresponding video segments as respective selected segments; The selected clips are used to form an intended video collection; The intended video highlights are displayed on the user client.

8. A device for generating a highlight collection of a competition, characterized in that: include: A real-time monitoring module is used to monitor in real time whether there is a target entering the competition area, and to monitor in real time each target entering the competition area to determine the position trajectory information of each target in the competition area; A streaming media data acquisition module, used to acquire streaming media data collected by various cameras arranged in the competition area; A video segment determination module, for determining, for each of the targets, each video segment corresponding to the target based on the streaming media data collected by each camera and the position trajectory information of the target; A highlight segment screening module, used for screening out each highlight segment from each video segment corresponding to each target; A wonderful video collection construction module, used for constructing a wonderful video collection from each of the wonderful clips; A display module is used to display the wonderful video highlights on the user client.

9. A device for generating a highlight collection of a competition, characterized in that: including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the method for generating a highlight reel of a match as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for generating a highlight reel of a match as described in any one of claims 1 to 7 is implemented.

Images