Sports video automatic editing method and device

Abstract

The invention relates to a motion video automatic editing method and device, and belongs to the technical field of video editing, and the method comprises the steps: obtaining video data shot by a motion camera, and motion data transmitted based on the motion camera; wherein the motion data is data detected by a sensor installed on the motion camera, or data detected by an external sensor in communication connection with the motion camera; performing time alignment on the video data and the motion data; determining a highlight event of the user based on the motion data; wherein the highlight event is determined when the motion data meets a set threshold condition; the highlight event comprises time information; and automatically editing the motion video based on the highlight event and the video data matched with the time information of the highlight event, and generating an edited target motion video. Through the mode, automatic, efficient and accurate motion video editing is realized, the user experience can be remarkably improved, and the editing quality and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of video editing, and in particular to a method and a device for automatically editing a motion video. Background Art

[0002] Action cameras are small, durable and waterproof cameras designed for capturing extreme sports and outdoor activities. They are usually waterproof, shockproof, drop-resistant and can capture images and videos in complex environments.

[0003] Currently, more and more users use sports cameras to record their sports videos, and they are more looking forward to or paying more attention to recording the highlights in sports videos (such as ski jumping, cycling sprints, climbing, etc.). However, most users lack editing skills and can only capture the highlights through automatic editing technology.

[0004] However, after research, it was found that when performing automatic editing for sports cameras, the current method is to use image recognition technology to determine the highlight moments for automatic editing, such as analyzing the video content frame by frame to identify the highlight moments for automatic editing. This method involves image recognition and requires analysis of each frame of video content, involving a large number of complex calculations, slow computing speed, and difficult to meet the real-time requirements of users. In addition, the accuracy of image recognition is affected by the algorithm model and data quality, and it is easy to misjudge and miss the highlight moments. Summary of the invention

[0005] In order to solve the above-mentioned problems in the prior art, the present invention provides a method and device for automatically editing motion videos.

[0006] In a first aspect, the present application provides a method for automatically editing motion videos, comprising: acquiring video data captured by a motion camera, and motion data transmitted by the motion camera; wherein the motion data is data detected by a sensor installed on the motion camera itself, or data detected by an external sensor connected to the motion camera in communication; wherein both the video data and the motion data contain a timestamp; time-aligning the video data with the motion data based on the timestamp; determining a highlight event of a user based on the motion data; wherein the highlight event is determined when the motion data meets a set threshold condition; the highlight event includes time information; and automatically editing the motion video based on the highlight event and the video data matching the time information of the highlight event to generate an edited target motion video.

[0007] Optionally, the sensor installed on the sports camera itself includes at least one of a positioning sensor, an altimeter, and a pressure gauge; the external sensor communicatively connected to the sports camera includes at least one of a speedometer, a cadence meter, a power meter, and a heart rate meter.

[0008] Optionally, the automatic editing of motion video based on the highlight event and the video data matching the time information of the highlight event to generate the edited target motion video includes: determining the marked event in the video data in response to the marked node in the video data; wherein, during the use of the motion camera, the user clicks a button of the motion camera to trigger the generation of the marked node; the marked event represents a user-defined highlight event; and the automatic editing of motion video based on the marked event, the highlight event and the video data matching the time information of the highlight event to generate the edited target motion video.

[0009] Optionally, the automatic editing of motion video based on the highlight event and the video data matching the time information of the highlight event to generate an edited target motion video includes: determining the video data matching the time information of the highlight event; synthesizing the motion data corresponding to the highlight event into the video data matching the time information of the highlight event to generate the target motion video; wherein the motion data corresponding to the highlight event is visually displayed in the target motion video.

[0010] Optionally, after generating the edited target motion video, the method further includes: performing clarity identification on key frames in the target motion video; wherein the key frames are video frames in the target motion video corresponding to the highlight events; if the clarity of the key frames is lower than a preset threshold, searching for a target frame that is closest to the key frame and has a clarity higher than the preset threshold within a preset range before and after the key frame; and replacing the key frame with the target frame.

[0011] Optionally, before determining the highlight event of the user based on the motion data, the method further includes: receiving a motion scene clicked by the user; wherein different motion scenes trigger different highlight event determination logics.

[0012] Optionally, when there are multiple highlight events, automatically editing the motion video based on the highlight events and the video data matching the time information of the highlight events to generate the edited target motion video includes: identifying the action type corresponding to each highlight event; automatically editing the motion video based on the action type of each highlight event and the video data matching the time information of each highlight event to generate the edited target motion video; Among them, in the target motion video, highlight events of different action types correspond to different video special effects.

[0013] Optionally, the target motion video is a plurality of motion videos of different editing versions, and the target motion videos are all compressed preview videos; the editing versions of the target motion video include at least two of the following: a full motion review, a collection of highlight events, and a highlight event clip; Correspondingly, the method further includes: in response to a user's click operation on at least one target motion video among the multiple target motion videos, outputting the target motion video to the user, and the target motion video is an uncompressed video.

[0014] Optionally, the time aligning the video data with the motion data based on the timestamp includes: performing preliminary time alignment on the video data and the motion data based on the time difference based on the timestamp; segmenting the video data and the motion data after the preliminary time alignment, and comparing the change characteristics of each segment of the two groups of data to perform local time alignment on each segment of the data.

[0015] In a second aspect, an embodiment of the present application provides a motion video automatic editing device, comprising: An acquisition module is used to acquire video data captured by a motion camera and motion data transmitted by the motion camera; wherein the motion data is data detected by a sensor installed on the motion camera itself, or data detected by an external sensor connected to the motion camera in communication; wherein both the video data and the motion data contain a timestamp; a time alignment module is used to time-align the video data with the motion data based on the timestamp; a determination module is used to determine a highlight event of a user based on the motion data; wherein the highlight event is determined when the motion data meets a set threshold condition; the highlight event includes time information; an automatic editing module is used to automatically edit the motion video based on the highlight event and the video data matching the time information of the highlight event, so as to generate an edited target motion video.

[0016] The beneficial effects of the present invention include: First, the embodiment of the present application provides a highlight event association method based on motion data, that is, determining the highlight moments in the video data through motion data, and automatically editing the video based on this. Compared with the traditional method of determining the highlight moments based on image recognition technology for automatic editing, this method does not need to analyze and identify the content of each frame of the video data, but only requires a simple threshold comparison of the motion data, which can greatly reduce the computing power of the device and improve the editing efficiency, so it is suitable for the rapid processing of a large number of motion videos.

[0017] Second, since motion data can directly and accurately infer the user's motion status, the embodiment of the present application determines highlight events through motion data, which can improve the accuracy of judging highlight events. This method does not need to be affected by the algorithm model based on image recognition and the quality of video data, and reduces the probability of misjudgment and missed judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of the steps of a method for automatically editing a motion video provided by an embodiment of the present invention; Figure 2 A diagram of the association relationship between a motion camera and a sensor provided by an embodiment of the present invention; Figure 3 A flowchart of another method for automatically editing motion videos provided by an embodiment of the present invention; Figure 4 A module block diagram of a motion video automatic editing device provided by an embodiment of the present invention; Figure 5 A module block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0020] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0021] Currently, more and more users use sports cameras to record their sports videos, and they are more looking forward to or paying more attention to recording the highlights in sports videos (such as ski jumping, cycling sprints, climbing, etc.). However, most users lack editing skills and can only capture the highlights through automatic editing technology.

[0022] However, after research, it was found that when performing automatic editing for sports cameras, the current method is to use image recognition technology to determine the highlight moments for automatic editing, such as analyzing the video content frame by frame to identify the highlight moments for automatic editing. This method involves image recognition and requires analysis of each frame of video content, involving a large number of complex calculations, slow computing speed, and difficult to meet the real-time requirements of users. In addition, the accuracy of image recognition is affected by the algorithm model and data quality, and it is easy to misjudge and miss the highlight moments.

[0023] In view of the above problems, the present application proposes the following embodiments to solve the above technical problems.

[0024] Embodiment 1: See also Figure 1 The embodiment of the present application provides a method for automatically editing motion videos, including: steps 101 to 104.

[0025] Step 101: Obtain video data captured by a motion camera and motion data transmitted by the motion camera.

[0026] The motion data is data detected by a sensor installed on the motion camera itself, or data detected by an external sensor connected to the motion camera for communication. Both the video data and the motion data include a timestamp.

[0027] It should be noted that the automatic motion video editing method provided in the embodiment of the present application can be applied to an electronic device, which can be a mobile phone or tablet computer configured with an application, or a server.

[0028] The electronic device can be connected to the motion camera for communication, and can receive or obtain data transmitted by the motion camera, where the data includes video data captured by the motion camera, and motion data collected by the motion camera itself or other external sensors.

[0029] In addition, it should be noted that the placement of the action camera can be determined according to the user's movement. If the user is riding, the action camera can be placed on the bicycle or worn on the user. If the user is running, the action camera can be worn on the user or held by the user.

[0030] Step 102: Time-align the video data with the motion data.

[0031] Specifically, the video data and the motion data are time-aligned based on the timestamp.

[0032] The time alignment here refers to the automatic time matching of video data and motion data by the software side, that is, synchronizing the time.

[0033] Step 103: Determine highlight events of the user based on the motion data.

[0034] Among them, the highlight event is determined when the motion data meets the set threshold condition; the highlight event includes time information.

[0035] Example 1: Assuming that the speed detected by the speedometer exceeds the set threshold, the motion data is determined to correspond to a highlight event (such as a user sprinting). The set threshold can be 20 meters per second, 30 meters per second, etc., which is not limited here.

[0036] Example 2: Assuming that the motion data is that the altimeter detects that the altitude change exceeds a set threshold, it is determined that the motion data corresponds to a highlight event (such as a user skiing and jumping). The set threshold can be 0.5 meters, 1 meter, etc., which is not limited here.

[0037] Step 104: Automatically edit the motion video based on the highlight event and the video data matching the time information of the highlight event to generate an edited target motion video.

[0038] That is, after determining the highlight event from the motion data, since the time matching of the video data and the motion data has been performed, the time period of the highlight event in the video data can be directly determined, that is, the corresponding highlight moment in the video data is filtered out through the motion data, and then the target motion video is automatically edited and synthesized.

[0039] In summary, the method for automatically editing motion videos provided in the embodiments of the present application has the following beneficial effects, including: First, the embodiment of the present application provides a highlight event association method based on motion data, that is, determining the highlight moments in the video data through motion data, and automatically editing the video based on this. Compared with the traditional method of determining the highlight moments based on image recognition technology for automatic editing, this method does not need to analyze and identify the content of each frame of the video data, but only requires a simple threshold comparison of the motion data, which can greatly reduce the computing power of the device and improve the editing efficiency, so it is suitable for the rapid processing of a large number of motion videos.

[0040] Second, since motion data can directly and accurately infer the user's motion status, the embodiment of the present application determines highlight events through motion data, which can improve the accuracy of judging highlight events. This method does not need to be affected by the algorithm model based on image recognition and the quality of video data, and reduces the probability of misjudgment and missed judgment.

[0041] It can be seen that the technical solution of the embodiment of the present application realizes automatic, efficient and accurate motion video editing by combining motion data and video data, which can significantly improve the user experience and improve the editing quality and efficiency.

[0042] Optionally, the sensor installed on the motion camera itself includes at least one of a positioning sensor, an altimeter, and a pressure gauge.

[0043] The external sensor connected to the sports camera for communication includes at least one of a speedometer, a cadence meter, a power meter, and a heart rate meter.

[0044] The positioning sensor may be used to obtain position information (such as longitude, latitude, altitude, etc.) The positioning sensor may be a GPS (Global Positioning System).

[0045] An altimeter can be used to measure an athlete's altitude changes.

[0046] The pressure gauge can be used to measure the ambient air pressure to assist in determining the user's exercise status in different environments.

[0047] The speedometer can be used to measure the user's speed, that is, it can provide the user's motion data.

[0048] A cadence meter can be used to measure the user's cadence during cycling, that is, the number of pedal strokes per minute, and can record the user's efficiency and rhythm during cycling.

[0049] A power meter can be used to measure the power output of a user during exercise. A power meter can help assess the intensity and load of a user during exercise.

[0050] It should be noted that the external sensor connected to the motion camera for communication may be specifically connected via a Bluetooth or ANT interface.

[0051] See also Figure 2 In one embodiment, the connection relationship of the sports camera may include the positioning sensor 201, altimeter 202 and pressure gauge 203 set by itself, and external sensors: speedometer 204, cadence meter 205, power meter 206, heart rate meter 207. The above sensors are all connected to the processing module 208 of the sports camera itself.

[0052] See also Figure 3 Optionally, in one embodiment, the above steps automatically edit the motion video based on the highlight event and the video data matching the time information of the highlight event to generate the edited target motion video, which may specifically include: step 301 to step 302.

[0053] Step 301: In response to a marked node in video data, determine a marked event in the video data.

[0054] In the process of using the motion camera, the user clicks a button of the motion camera to trigger the generation of a marking node; the marking event represents a highlight event defined by the user.

[0055] Exemplarily, the sports camera itself is configured with a button, and when the user is exercising, he can click the button to trigger the mark.

[0056] Optionally, the button can be configured to receive a click from the user, and the motion camera automatically marks a period of time forward and backward with the click time as the median value as a highlight event.

[0057] The period of time here can be customized, such as 10 seconds or 20 seconds, and this application does not limit it.

[0058] In addition, the duration of the marked event can be adjusted according to user needs during subsequent editing.

[0059] Optionally, the button is configured to receive two clicks from the user, and the two clicks correspond to a start mark node and an end mark node. The area between the start mark node and the end mark node corresponds to a user-defined highlight event.

[0060] For example, the current user is cycling and when encountering a hill climb, the user wants to record the climbing process, so the user can click the button on the sports camera once. When the climbing is over, the user clicks the button on the sports camera again to complete the generation of the marking node, thereby forming a marking event.

[0061] Step 302: Automatically edit the motion video based on the marked event, the highlight event, and the video data matching the time information of the highlight event to generate an edited target motion video.

[0062] That is, in the final automatically edited target motion video, in addition to the highlight events automatically identified by motion design, user-defined highlight events are also combined.

[0063] In addition, in one embodiment, when the marked event and the highlight event overlap, the following methods can be used to handle the overlap: first, the union of the marked event and the highlight event can be retained. Second, only the marked event can be retained.

[0064] In summary, the automatic editing method of motion videos provided in the embodiments of the present application also provides a method in which the user can actively trigger and customize highlight moments. This method can not only meet the personalized needs of users, but also accurately determine all highlight moments in the motion video, thereby meeting user needs and improving user experience.

[0065] Optionally, the above steps automatically edit motion videos based on the highlight event and the video data matching the time information of the highlight event to generate an edited target motion video, including: determining the video data matching the time information of the highlight event; synthesizing the motion data corresponding to the highlight event into the video data matching the time information of the highlight event to generate the target motion video.

[0066] Among them, the motion data corresponding to the highlight event is visually displayed in the target motion video.

[0067] That is, in the process of video synthesis, in addition to being able to automatically extract highlight events, the embodiments of the present application can also visualize the motion data corresponding to the current highlight event.

[0068] For example, in the highlight event of the user's riding, in the final synthesized target motion video, when the highlight event is determined to be climbing, the user's speed, power data, and cadence data when climbing are visually displayed in the corresponding video clip.

[0069] It can be seen that the synthesis method of the embodiment of the present application can automatically display the motion data in a visual manner in the video clip corresponding to the highlight event, which can more intuitively understand the user's motion performance, enhance interactivity and sense of participation, and provide users with more convenient motion analysis.

[0070] Optionally, after generating the edited target motion video, the method also includes: performing clarity identification on key frames in the target motion video; wherein the key frames are video frames corresponding to highlight events in the target motion video; if the clarity of the key frames is lower than a preset threshold, searching for a target frame that is closest to the key frame and has a clarity higher than a preset threshold within a preset range before and after the key frame; and replacing the key frame with the target frame.

[0071] In this embodiment, the recognition of clarity can be judged by judging the features such as image details, contrast or sharpness. Of course, it can also be evaluated by the rate of change of image brightness, deep learning network model and the like, which is not limited in this application. Accordingly, the setting of the preset threshold can be set according to different clarity recognition methods. In addition, the preset range can also be set according to demand, such as the preset range of 5 frames, 10 frames, 20 frames, etc.

[0072] It should be noted that highlight events in the video may include some quick turns, jumps, sudden movements, etc. These moments often contain fast-moving images, which may cause the image to appear blurred or out of focus. Therefore, the embodiment of the present application proposes to improve the quality of the final automatically synthesized video by replacing the target frame that is closest to the key frame with lower clarity of the highlight event. That is, this implementation method can automatically identify the clarity of the key frame. If the clarity of the key frame is lower than the preset threshold, another frame with a clarity higher than the preset threshold is found within the range of multiple frames before and after, and replaced. In this way, the final presentation is still a smooth and clear video picture, which improves the user viewing experience.

[0073] In addition, the above preset threshold can be subdivided into a first preset threshold and a second preset threshold, wherein the second preset threshold is higher than the first preset threshold. Specifically, the clarity of the key frame can be judged by the first preset threshold, while the clarity of the target frame needs to be judged by the second preset threshold. Thus, this method can replace a higher-definition image frame.

[0074] Optionally, before determining the highlight event of the user based on the motion data, the method further includes: receiving a motion scene clicked by the user; wherein different motion scenes trigger different highlight event determination logics.

[0075] Among them, sports scenes may include cycling, skiing, running, etc. The embodiment of the present application may trigger different highlight event determination logics according to different sports scenes, and the highlight event determination logic here may be understood to match different set threshold conditions for different sports scenes.

[0076] For example, when the sports scene is cycling, the threshold condition is set to include a first speed threshold. When the sports scene is skiing, the threshold condition is set to include a second speed threshold and a height threshold. The first speed threshold and the second speed threshold are different.

[0077] It can be seen that this method adapts to different scene editing requirements according to the user's motion scenes, and then can output different corresponding highlight event videos according to different motion scenes, meet the user's shooting and editing needs in various motion scenes, and improve the user experience.

[0078] Optionally, when there are multiple highlight events, the above steps automatically edit the motion video based on the highlight events and the video data matching the time information of the highlight events to generate a edited target motion video, including: identifying the action type corresponding to each highlight event; automatically editing the motion video based on the action type of each highlight event and the video data matching the time information of each highlight event to generate a edited target motion video; wherein, in the target motion video, highlight events of different action types correspond to different video effects.

[0079] The action type may include but is not limited to sprinting, jumping, spinning, and the like.

[0080] In this embodiment, different action types correspond to different video effects during video synthesis.

[0081] For example, when the action type is recognized as a cycling sprint, the corresponding video special effect is a line special effect, which is used to enhance the sense of speed of the picture.

[0082] For example, when the action type is identified as a ski jump, the corresponding video feature is an upward glare to simulate the action of the jump.

[0083] It can be seen that this implementation method can add exclusive special effects for different action types of highlight events, making the synthesized target motion video richer and more interesting. It can also make each highlight event more distinctive and meet the personalized needs of users through the combination of action type and special effects.

[0084] Optionally, the target motion video is a plurality of motion videos with different editing versions, and the target motion videos are all compressed preview videos; the editing versions of the target motion video include at least two of the following: a full motion review, a collection of highlight events, and a highlight event clip; Correspondingly, the method further includes: in response to a user's click operation on at least one target motion video among the multiple target motion videos, outputting the target motion video to the user, and the target motion video is an uncompressed video.

[0085] That is, the embodiment of the present application provides a method for outputting a target motion video, which can provide multiple editing versions and uncompressed preview videos for users to choose from (which may include a full review of the motion, a collection of highlight events, highlight event clips, etc.), and then, after the user selects the specific required video, the uncompressed complete video of the editing version is output to the user.

[0086] It should be noted that compressing preview videos can reduce storage usage and transmission bandwidth, providing users with a fast preview experience. When users require a certain version of the clip, a high-quality uncompressed version is provided to the user. This method can provide users with a variety of clip versions to choose from, and it also takes into account efficiency and quality. It not only meets the needs of efficient preview, but also provides the high-definition and complete version required by users.

[0087] Optionally, the above steps time-align the video data with the motion data based on the timestamp, including: performing preliminary time alignment on the video data and the motion data based on the time difference based on the timestamp; segmenting the video data and the motion data after the preliminary time alignment, and comparing the change characteristics of each segment of the two sets of data to perform local time alignment on each segment of the data.

[0088] In this step, preliminary time alignment based on time difference can convert the two data sources into the same format, calculate the time difference, and then align them. Then, the video data and motion data after preliminary time alignment are segmented, such as 1 second segment, 3 second segment, or 5 second segment, and each segment of data is tested for synchronization. This process can determine whether the two sets of data are synchronized by comparing the change characteristics of the two sets of data (such as the optical flow change of the video frame and the acceleration fluctuation of the motion data), thereby achieving local synchronization.

[0089] That is, the embodiment of the present application provides a global and local time alignment method, which can ensure the synchronization of data from two data sources so that accurate highlight video can be output subsequently.

[0090] In addition, the automatic motion video editing method provided in the embodiment of the present application can also be applied to the live broadcast field.

[0091] Specifically, the SDK (Software Development Kit) of a third-party live broadcast platform can be integrated into the APP (Application) of the sports camera, and then, after authorization verification through the user account, the clipped target motion video generated by the above method can be directly pushed to the live broadcast room of the user's account registered on the live broadcast platform. That is, in the live broadcast room, the automatically clipped target motion video is presented to other users watching the live broadcast.

[0092] In other words, when a user wants to broadcast his or her exercise process in real time on a live broadcast platform, the sports camera in the embodiment of the present application can simultaneously display various data of the exercise process on the screen while pushing the real-time picture to the live broadcast platform, making the live broadcast effect of the exercise more appealing. That is, a live interactive method of real-time picture plus real-time exercise data is provided.

[0093] For example, user A is a cycling enthusiast who likes to live broadcast his cycling process. His live broadcast room screen not only has his own cycling screen from the main perspective, but also real-time sports data, such as the climbing slope and sports power of user A. The audience watching the live broadcast are amazed that user A can maintain such an amazing power output at a slope of 10°, and they all give him thumbs up.

[0094] Embodiment 2: See also Figure 4 Based on the same inventive concept, the embodiment of the present application also provides a motion video automatic editing device 400, including: an acquisition module 401, used to acquire video data captured by a motion camera, and motion data transmitted based on the motion camera; wherein the motion data is data detected by a sensor installed on the motion camera itself, or data detected by an external sensor connected to the motion camera in communication; wherein both the video data and the motion data contain a timestamp; a time alignment module 402, used to time-align the video data with the motion data based on the timestamp; a determination module 403, used to determine a user's highlight event based on the motion data; wherein the highlight event is determined when the motion data meets a set threshold condition; the highlight event includes time information; an automatic editing module 404, used to automatically edit the motion video based on the highlight event and the video data matching the time information of the highlight event, to generate an edited target motion video.

[0095] Embodiment three: See also Figure 5 Based on the same inventive concept, the present application embodiment provides a module frame of an electronic device 500 that applies the above method. The electronic device 500 includes: at least one processor 501 ( Figure 5 Only one is shown in the figure), a memory 502, a computer program 503 stored in the memory 502 and executable on at least one processor 501, and when the processor 501 executes the computer program 503, the steps of the method in any of the foregoing embodiments are implemented.

[0096] The electronic device 500 may be a server, a personal computer, a notebook computer, etc.

[0097] Those skilled in the art will understand that Figure 5 The electronic device 500 is merely an example and does not constitute a limitation on the electronic device 500 , and may include more or less components than those shown in the figure, or may combine certain components, or may include different components.

[0098] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0099] In some embodiments, the memory 502 may be an internal storage unit of the electronic device 500, such as a hard disk or memory of the electronic device 500. In other embodiments, the memory 502 may also be an external storage device of the electronic device 500, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 500. Furthermore, the memory 502 may also include both an internal storage unit of the electronic device 500 and an external storage device.

[0100] It should be noted that the above-mentioned systems, devices, etc. are based on the same concept as the method embodiments of the present application. The modules designed for the systems, the steps performed by the devices, and the technical effects brought about can all be found in the method embodiment section and will not be repeated here.

[0101] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0102] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0103] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electrical carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0105] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0107] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for automatically editing a motion video, characterized in that: include: Acquire video data captured by a motion camera, and motion data transmitted by the motion camera; wherein the motion data is data detected by a sensor installed on the motion camera itself, or data detected by an external sensor connected to the motion camera in communication; wherein both the video data and the motion data include a timestamp; time-aligning the video data with the motion data based on a timestamp; Based on the motion data, determining a highlight event of the user; wherein the highlight event is determined when the motion data meets a set threshold condition; and the highlight event includes time information; Based on the highlight event and the video data matching the time information of the highlight event, the motion video is automatically edited to generate an edited target motion video.

2. The method for automatically editing motion videos according to claim 1, characterized in that: The sensor installed in the motion camera itself includes at least one of a positioning sensor, an altimeter, and a pressure gauge; The external sensor connected to the sports camera for communication includes at least one of a speedometer, a cadence meter, a power meter, and a heart rate meter.

3. The method for automatically editing motion videos according to claim 1, characterized in that: The step of automatically editing the motion video based on the highlight event and the video data matching the time information of the highlight event to generate the edited target motion video includes: In response to the marked node in the video data, determining a marked event in the video data; wherein, during the use of the motion camera, the user clicks a button of the motion camera to trigger the generation of the marked node; the marked event represents a user-defined highlight event; Based on the marked event, the highlight event and the video data matching the time information of the highlight event, the motion video is automatically edited to generate an edited target motion video.

4. The method for automatically editing motion videos according to claim 1, characterized in that: The step of automatically editing the motion video based on the highlight event and the video data matching the time information of the highlight event to generate the edited target motion video includes: Determining video data matching the time information of the highlight event; synthesizing the motion data corresponding to the highlight event into the video data matching the time information of the highlight event to generate the target motion video; Wherein, the motion data corresponding to the highlight event is visually displayed in the target motion video.

5. The method for automatically editing motion videos according to claim 1, characterized in that: After generating the clipped target motion video, the method further includes: Performing clarity recognition on key frames in the target motion video; wherein the key frames are video frames in the target motion video corresponding to the highlight event; If the definition of the key frame is lower than a preset threshold, searching for a target frame closest to the key frame and having a definition higher than the preset threshold within a preset range around the key frame; The key frame is replaced by the target frame.

6. The method for automatically editing motion videos according to claim 1, characterized in that: Before determining the highlight event of the user based on the motion data, the method further includes: Receive the motion scene clicked by the user; Among them, different motion scenes trigger different highlight event determination logics.

7. The method for automatically editing motion videos according to claim 1, characterized in that: When there are multiple highlight events, the automatic motion video editing based on the highlight events and the video data matching the time information of the highlight events to generate the edited target motion video includes: Identify the action type corresponding to each highlight event; Based on the action type of each highlight event and the video data matching the time information of each highlight event, the motion video is automatically edited to generate an edited target motion video; Among them, in the target motion video, highlight events of different action types correspond to different video special effects.

8. The method for automatically editing motion videos according to claim 1, characterized in that: The target motion videos are motion videos of multiple different edited versions, and the target motion videos are all compressed preview videos; The edited version of the target sports video includes at least two of the following: a full review of the sports, a collection of highlight events, and a clip of highlight events; Accordingly, the method further includes: In response to a user's click operation on at least one target motion video among a plurality of target motion videos, the target motion video is output to the user, and the target motion video is an uncompressed video.

9. The method for automatically editing motion videos according to claim 1, characterized in that: The step of temporally aligning the video data with the motion data based on the timestamp comprises: Preliminarily time-aligning the video data and the motion data based on a time difference based on the timestamp; The video data and motion data after preliminary time alignment are segmented, and the change characteristics of each segment of the two sets of data are compared to perform local time alignment of each segment of the data.

10. A motion video automatic editing device, characterized in that: include: An acquisition module, used for acquiring video data captured by a motion camera and motion data transmitted by the motion camera; wherein the motion data is data detected by a sensor installed on the motion camera itself, or data detected by an external sensor connected to the motion camera in communication; wherein the video data and the motion data both contain a timestamp; A time alignment module, configured to perform time alignment on the video data and the motion data based on a timestamp; A determination module, configured to determine a highlight event of the user based on the motion data; wherein the highlight event is determined when the motion data meets a set threshold condition; and the highlight event includes time information; The automatic editing module is used to automatically edit the motion video based on the highlight event and the video data matching the time information of the highlight event to generate an edited target motion video.

Images