技术领域Technical field
本申请属于通信技术领域，具体涉及一种视频推送方法、装置、服务器设备及可读存储介质。This application belongs to the field of communication technology, and specifically relates to a video pushing method, device, server equipment and readable storage medium.
背景技术Background technique
现有技术中，雪车/雪橇等比赛的运动影像主要是基于固定的摄像机采集现场比赛画面后进行转播。但是，固定的摄像机无法实时跟踪运动员的运动过程，导致观众只能看到几个位置的固定画面和场景，从而造成观众的观看体验较差。In the existing technology, sports images of snowmobile/sledding and other competitions are mainly based on fixed cameras that collect live competition images and then broadcast them. However, fixed cameras cannot track the movement of athletes in real time, resulting in the audience only seeing fixed images and scenes in several positions, resulting in a poor viewing experience for the audience.
发明内容Contents of the invention
本申请实施例的目的是提供一种视频推送方法、装置、服务器设备及可读存储介质，以解决目前赛事转播造成的观众的观看体验较差的问题。The purpose of the embodiments of this application is to provide a video pushing method, device, server equipment and readable storage medium to solve the problem of poor viewing experience for viewers caused by current event broadcasts.
为了解决上述技术问题，本申请是这样实现的：In order to solve the above technical problems, this application is implemented as follows:
第一方面，提供了一种视频推送方法，包括：The first aspect provides a video push method, including:
根据运动员在比赛过程中的实时位置数据，确定所述运动员的运动轨迹；Determine the movement trajectory of the athlete based on the athlete's real-time position data during the game;
根据所述运动轨迹对预先建立的模型进行渲染，获得渲染结果，所述预先建立的模型为比赛相关对象的三维模型；Render a pre-established model according to the motion trajectory to obtain a rendering result. The pre-established model is a three-dimensional model of game-related objects;
将所述渲染结果转换为目标视频流，并推送所述目标视频流。Convert the rendering result into a target video stream, and push the target video stream.
可选的，所述根据运动员在比赛过程中的实时位置数据，确定所述运动员的运动轨迹，包括：Optionally, determining the athlete's movement trajectory based on the athlete's real-time position data during the game includes:
获取所述运动员在当前赛道区域的实时位置数据；Obtain the real-time location data of the athlete in the current track area;
根据所述实时位置数据修正第一运动轨迹，获得所述运动员在当前赛道区域的运动轨迹；其中，所述第一运动轨迹是基于所述运动员在所述当前赛道区域的上一段赛道区域的实时位置数据，预测得到的所述运动员在当前赛道区域的运动轨迹。Correct the first movement trajectory according to the real-time position data to obtain the movement trajectory of the athlete in the current track area; wherein the first movement trajectory is based on the previous track section of the athlete in the current track area. The real-time location data of the area predicts the movement trajectory of the athlete in the current track area.
可选的，所述根据所述运动轨迹对预先建立的模型进行渲染，获得渲染结果之前，所述方法还包括：Optionally, before rendering a pre-established model according to the motion trajectory and obtaining the rendering result, the method further includes:
确定所述运动员在比赛过程中的目标视角；Determine the target perspective of said athlete during competition;
所述根据所述运动轨迹对预先建立的模型进行渲染，获得渲染结果，包括：Rendering the pre-established model according to the motion trajectory and obtaining the rendering result includes:
根据所述运动轨迹以及所述目标视角对所述预先建立的模型进行渲染，获得所述渲染结果。The pre-established model is rendered according to the motion trajectory and the target perspective to obtain the rendering result.
可选的，所述确定所述运动员在比赛过程中的目标视角，包括以下任一项：Optionally, determining the athlete's target perspective during the game includes any of the following:
确定所述运动员在比赛过程中的真实视角；Determine the true perspective of said athlete during the game;
在所述运动员出现目标动作的情况下，根据所述运动员在超出摄像范围前的角速度和角加速度，确定所述目标视角。When the athlete performs a target action, the target angle of view is determined based on the angular velocity and angular acceleration of the athlete before exceeding the camera range.
可选的，所述确定所述运动员在比赛过程中的真实视角之后，当所述真实视角大于预设视角阈值时，所述确定所述运动员在比赛过程中的目标视角，还包括：Optionally, after determining the athlete's true perspective during the game, when the true perspective is greater than a preset perspective threshold, determining the athlete's target perspective during the game further includes:
利用所述预设视角阈值修正所述真实视角，获得所述目标视角。The real viewing angle is corrected using the preset viewing angle threshold to obtain the target viewing angle.
可选的，所述利用所述预设视角阈值修正所述真实视角，获得所述目标视角，包括：采用如下公式，计算得到所述目标视角β：Optionally, using the preset viewing angle threshold to correct the real viewing angle and obtain the target viewing angle includes: using the following formula to calculate the target viewing angle β:
其中，f表示所述预设视角阈值，θ表示所述真实视角。Where, f represents the preset viewing angle threshold, and θ represents the real viewing angle.
可选的，所述推送所述目标视频流，包括：Optionally, pushing the target video stream includes:
将所述目标视频流和其他视频流混流后推送至客户端，所述其他视频流为摄像头采集的所述运动员的比赛视频流。The target video stream and other video streams are mixed and pushed to the client. The other video streams are the athlete's game video streams collected by the camera.
可选的，所述预先建立的模型包括以下至少一项：赛道的三维模型、运动器具的三维模型和所述运动员的三维模型。Optionally, the pre-established model includes at least one of the following: a three-dimensional model of the track, a three-dimensional model of sports equipment, and a three-dimensional model of the athlete.
第二方面，提供了一种视频推送装置，包括：In the second aspect, a video push device is provided, including:
第一确定模块，用于根据运动员在比赛过程中的实时位置数据，确定所述运动员的运动轨迹；The first determination module is used to determine the movement trajectory of the athlete based on the real-time position data of the athlete during the game;
渲染模块，用于根据所述运动轨迹对预先建立的模型进行渲染，获得渲染结果，所述预先建立的模型为比赛相关对象的三维模型；A rendering module, configured to render a pre-established model according to the motion trajectory and obtain a rendering result, where the pre-established model is a three-dimensional model of competition-related objects;
推送模块，用于将所述渲染结果转换为目标视频流，并推送所述目标视频流。A push module, configured to convert the rendering result into a target video stream and push the target video stream.
第三方面，提供了一种服务器设备，包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。In a third aspect, a server device is provided, including a processor, a memory, and a program or instructions stored on the memory and executable on the processor. The program or instructions are implemented when executed by the processor. The steps of the method as described in the first aspect.
第四方面，提供了一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤。In a fourth aspect, a readable storage medium is provided. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the method described in the first aspect are implemented.
在本申请实施例中，可以根据运动员在比赛过程中的实时位置数据，确定运动员的运动轨迹，并根据所述运动轨迹对预先建立的模型进行渲染，获得渲染结果，所述预先建立的模型为比赛相关对象的三维模型，将所述渲染结果转换为目标视频流，并推送所述目标视频流，所述目标视频流为基于运动员视角的比赛视频流。由此，可以基于虚拟现实技术在赛事转播中展现运动员视角的比赛实况，从而缩小观众和运动员之间的距离，提高观众的代入感，提升观众的观看体验。In the embodiment of this application, the movement trajectory of the athlete can be determined based on the real-time position data of the athlete during the game, and the pre-established model can be rendered according to the movement trajectory to obtain the rendering result. The pre-established model is The three-dimensional model of the game-related objects is converted into a target video stream, and the target video stream is pushed. The target video stream is a game video stream based on the athlete's perspective. As a result, virtual reality technology can be used to show the live game from the perspective of the athletes in the event broadcast, thereby reducing the distance between the audience and the athletes, improving the audience's sense of immersion, and improving the audience's viewing experience.
附图说明Description of the drawings
图1是本申请实施例提供的一种视频推送方法的流程图；Figure 1 is a flow chart of a video pushing method provided by an embodiment of the present application;
图2是本申请实施例中运动员视角的示意图；Figure 2 is a schematic diagram of an athlete's perspective in an embodiment of the present application;
图3是本申请实施例提供的一种视频推送装置的结构示意图；Figure 3 is a schematic structural diagram of a video push device provided by an embodiment of the present application;
图4是本申请实施例提供的一种服务器设备的结构示意图。Figure 4 is a schematic structural diagram of a server device provided by an embodiment of the present application.
具体实施方式Detailed ways
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象，而不用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，说明书以及权利要求中“和/或”表示所连接对象的至少其中之一，字符“/”，一般表示前后关联对象是一种“或”的关系。The terms "first", "second", etc. in the description and claims of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It is to be understood that data so used are interchangeable under appropriate circumstances so that embodiments of the present application can be practiced in sequences other than those illustrated or described herein. In addition, "and/or" in the description and claims indicates at least one of the connected objects, and the character "/" generally indicates that the related objects are in an "or" relationship.
可选的，本申请实施例适用的场景包括但不限于雪车/雪橇等比赛场景。Optionally, applicable scenarios for the embodiments of the present application include but are not limited to snowmobile/sledding and other competition scenarios.
下面结合附图，通过具体的实施例及其应用场景对本申请实施例提供的视频推送方法、装置、服务器设备及可读存储介质进行详细地说明。The video pushing method, device, server device and readable storage medium provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios.
请参见图1，图1是本申请实施例提供的一种视频推送方法的流程图，该方法应用于服务器设备，如图1所示，该方法包括如下步骤：Please refer to Figure 1. Figure 1 is a flow chart of a video pushing method provided by an embodiment of the present application. The method is applied to a server device. As shown in Figure 1, the method includes the following steps:
步骤11：根据运动员在比赛过程中的实时位置数据，确定运动员的运动轨迹。Step 11: Determine the athlete's movement trajectory based on the athlete's real-time position data during the game.
本实施例中，可以通过在赛道中布置若干个超声波装置，来确定运动员在比赛过程中的实时位置数据。例如，每组超声波装置为3个，基于超声波的定位与跟踪，发射端(即超声波装置)发射声波信号，并同时通过射频信号通知接收端(如运动员所在位置的接收器)开始计时，当接收端接收到声波时结束计时，则此发射端和接收端之间的距离为声速*t。依次计算三个发射端和接收端之间的距离，设此时接收端的坐标为(x，y，z)，通过结构定义已知三个发射端的坐标以及各自和接收端之间的距离，则根据两点间距离公式(x-x')2+(y-y')2+(z-z')2＝d，可以获得三个一次方程，组成方程组即可求解坐标值，获得运动员在比赛过程中的实时位置数据。In this embodiment, the real-time position data of athletes during the competition can be determined by arranging several ultrasonic devices on the track. For example, there are three ultrasonic devices in each group. Based on ultrasonic positioning and tracking, the transmitter (i.e., the ultrasonic device) emits an acoustic signal, and at the same time notifies the receiving end (such as the receiver at the athlete's location) through a radio frequency signal to start timing. The timing ends when the end receives the sound wave, then the distance between the transmitting end and the receiving end is the speed of sound * t. Calculate the distance between the three transmitting ends and the receiving end in turn. Assume that the coordinates of the receiving end at this time are (x, y, z). The coordinates of the three transmitting ends and the distance between each of them and the receiving end are known through the structure definition, then According to the distance formula between two points (x-x')2+(y-y')2+(z-z')2=d, three linear equations can be obtained. By forming a system of equations, the coordinate values can be solved and the athletes can be obtained Real-time location data during matches.
一些实施例中，可以在赛道中布置的超声波装置上设置摄像头比如高速黑白摄像头，用于捕捉运动员的动作影像数据。In some embodiments, cameras, such as high-speed black and white cameras, can be installed on the ultrasonic devices arranged in the track to capture the athletes' action image data.
步骤12：根据所述运动轨迹对预先建立的模型进行渲染，获得渲染结果。Step 12: Render the pre-established model according to the motion trajectory to obtain the rendering result.
可选的，上述预先建立的模型为比赛相关对象的三维模型，可以包括但不限于以下至少一项：赛道的三维模型、运动器具的三维模型和运动员的三维模型。例如，以雪车/雪橇比赛场景为例，由于雪车/雪橇在运动赛事中共用赛道，仅出发点不同，并且赛道固定，可以通过激光雷达，构建点云数据，采用激光雷达里程计和实时建图(LOAM-SLAM)方法构建地图，得到一个赛道的三维(3D)模型。对于运动器具和运动员的3D模型，可以事先取得运动员的身体和器具数据，主要包括运动员的上下肢身高、体重、头盔、眼睛在脸部所处的高度等数据，以及雪车/雪橇的长度、宽度、重量、离地高度等数据，并使用这些数据进行3D建模，获得运动器具和运动员的3D模型。此外，可以根据眼睛的所在高度设定建模的视角，并根据运动员的头部倾斜角度微调视角，以达到反馈真实运动员视角的赛道场景的目的。Optionally, the above-mentioned pre-established model is a three-dimensional model of a competition-related object, which may include but is not limited to at least one of the following: a three-dimensional model of a track, a three-dimensional model of sports equipment, and a three-dimensional model of athletes. For example, take the snowmobile/sled competition scene as an example. Since the snowmobile/sled share the track in sports events, only the starting point is different, and the track is fixed, point cloud data can be constructed through lidar, using lidar odometry and The real-time mapping (LOAM-SLAM) method constructs a map and obtains a three-dimensional (3D) model of the track. For 3D models of sports equipment and athletes, the athlete's body and equipment data can be obtained in advance, including the athlete's upper and lower limb height, weight, helmet, eye height on the face and other data, as well as the length of the snowmobile/sled, Width, weight, ground clearance and other data, and use these data for 3D modeling to obtain 3D models of sports equipment and athletes. In addition, the modeling angle of view can be set according to the height of the eyes, and the angle of view can be fine-tuned according to the tilt angle of the athlete's head to achieve the purpose of feeding back the track scene from the real athlete's perspective.
需指出的，上述比赛相关对象的三维模型的建模方式可以采用现有方式，比如多边形建模(Polygon Modeling)、参数化建模(Parametric Modeling)、逆向建模(ReverseModeling)、曲面建模(NURBS Modeling)等方式，对此不作限定。It should be pointed out that the three-dimensional models of the above competition-related objects can be modeled using existing methods, such as polygon modeling (Polygon Modeling), parametric modeling (Parametric Modeling), reverse modeling (Reverse Modeling), surface modeling ( NURBS Modeling) and other methods, there is no limit to this.
一些实施例中，上述渲染可以使用UE或Unity等实时3D渲染工具。在获取运动员的运动轨迹和目标视角之后，一个逼近真实赛况的运动员视角影像就可以通过3D渲染工具进行渲染，并将渲染后的结果转为视频流实时输出到实况转播端。In some embodiments, the above rendering may use real-time 3D rendering tools such as UE or Unity. After obtaining the athlete's movement trajectory and target perspective, an athlete's perspective image that is close to the real game situation can be rendered through a 3D rendering tool, and the rendered result is converted into a video stream and output to the live broadcast terminal in real time.
步骤13：将所述渲染结果转换为目标视频流，并推送所述目标视频流。Step 13: Convert the rendering result into a target video stream, and push the target video stream.
本实施例中，由于在确定运动员的运动轨迹后，运动员的可视范围就基本确定，因此根据运动员的运动轨迹对比赛相关对象的三维模型进行渲染，并将渲染结果转换为目标视频流，可以得到基于运动员视角的比赛视频流。所述目标视频流为基于运动员视角的比赛视频流。In this embodiment, since the visual range of the athlete is basically determined after the athlete's movement trajectory is determined, the three-dimensional model of the game-related objects is rendered according to the athlete's movement trajectory, and the rendering result is converted into a target video stream. Get a video stream of the game based on the player's perspective. The target video stream is a game video stream based on an athlete's perspective.
可选的，在推送目标视频流时，可以将目标视频流和其他视频流混流后推送至客户端，所述其他视频流为摄像头采集的运动员的比赛视频流，以方便观众从多个角度观看比赛视频。Optionally, when pushing the target video stream, the target video stream can be mixed with other video streams and then pushed to the client. The other video streams are athletes' game video streams collected by cameras to facilitate viewers to watch from multiple angles. Competition video.
一些实施例中，可以将目标视频流作为实况的一个摄像机位的视频流，并通过混流和其他实况的摄像机位的视频流合为一个视频流展示给观众。基于运动员视角的目标视频流可以在视频小窗中播放，也可以作为一路直播流来展示给观众。对于混流的视频，观众可以通过切流的方式，观看实时运算得到的目标视频流。In some embodiments, the target video stream may be used as a video stream of one live camera position, and mixed with video streams of other live camera positions to be combined into one video stream and displayed to the audience. The target video stream based on the athlete's perspective can be played in a small video window or displayed to the audience as a live stream. For mixed-stream videos, viewers can switch streams to watch the target video stream obtained by real-time calculations.
本申请实施例的视频推送方法，可以根据运动员在比赛过程中的实时位置数据，确定运动员的运动轨迹，并根据所述运动轨迹对预先建立的模型进行渲染，获得渲染结果，将所述渲染结果转换为目标视频流，并推送所述目标视频流，所述目标视频流为基于运动员视角的比赛视频流。由此，可以基于虚拟现实技术在赛事转播中展现运动员视角的比赛实况，从而缩小观众和运动员之间的距离，提高观众的代入感，提升观众的观看体验。The video push method of the embodiment of the present application can determine the movement trajectory of the athlete based on the real-time position data of the athlete during the game, render the pre-established model based on the movement trajectory, obtain the rendering result, and convert the rendering result Convert to a target video stream, and push the target video stream, where the target video stream is a game video stream based on the athlete's perspective. As a result, virtual reality technology can be used to show the live game from the perspective of the athletes in the event broadcast, thereby reducing the distance between the audience and the athletes, improving the audience's sense of immersion, and improving the audience's viewing experience.
进一步的，本申请实施例的视频推送方法，不需要在运动员身上安装摄像机，也不依赖外部的摄像机，可以通过运算得到近乎真实的运动比赛视频，降低外设对运动员的影响，还可以连续的观看到整个比赛过程，无需依赖摄像机位片段。Furthermore, the video push method of the embodiment of the present application does not need to install cameras on athletes, nor does it rely on external cameras. It can obtain nearly real sports competition videos through calculations, reduce the impact of peripherals on athletes, and can also continuously Watch the entire game without relying on camera footage.
可选的，为了获得运动员的合理运动轨迹，上述确定运动员的运动轨迹的过程可以包括：首先，获取运动员在当前赛道区域的实时位置数据，比如可以基于在赛道中布置的超声波装置获取运动员的实时位置数据；然后，根据所述实时位置数据修正第一运动轨迹，获得运动员在当前赛道区域的运动轨迹；其中，所述第一运动轨迹是基于运动员在当前赛道区域的上一段赛道区域的实时位置数据，预测得到的所述运动员在当前赛道区域的运动轨迹。这样借助预测以及修正的过程，可以连续计算出运动员的运动轨迹，不仅可以给后续渲染提供足够时间，还可以获得运动员的合理运动轨迹。Optionally, in order to obtain the athlete's reasonable movement trajectory, the above-mentioned process of determining the athlete's movement trajectory may include: first, obtaining the athlete's real-time position data in the current track area. For example, the athlete's position data may be obtained based on an ultrasonic device arranged in the track. Real-time location data; then, correct the first movement trajectory according to the real-time location data to obtain the athlete's movement trajectory in the current track area; wherein the first movement trajectory is based on the athlete's previous section of the track in the current track area The real-time location data of the area predicts the movement trajectory of the athlete in the current track area. In this way, with the help of the prediction and correction process, the athlete's movement trajectory can be continuously calculated, which not only provides enough time for subsequent rendering, but also obtains the athlete's reasonable movement trajectory.
一些实施例中，上述对运动轨迹的预测可以使用半监督学习生成对抗网络(Semi-Supervised Generative Adversarial Network，SGAN)模型，即生成对抗网络GAN模型的优化，可以在原有GAN模型的生成结构中新增生成潜码分布的模块，以提升预测的准确性。In some embodiments, the above-mentioned prediction of motion trajectories can use a Semi-Supervised Generative Adversarial Network (SGAN) model, that is, the optimization of the Generative Adversarial Network (GAN) model can be added to the generation structure of the original GAN model. Add a module that generates latent code distribution to improve prediction accuracy.
例如，以雪橇比赛场景为例，雪橇比赛的运动员平均时速约90KM/H，赛道长度约1.5至2公里，大约有15至20个不同角度、倾斜度各异的弯道，通过若干的超声波的位置计算，可以得到运动员在每个直线与弯道的位置和运动轨迹，在运动员经过下一段区域前，通过事先训练的预测模型提前计算出下一段区域的运动轨迹，并在运动员到达下一段区域后，通过超声波设备采集的关键点，对预测的关键点轨迹进行提前量修正，达到在转播摄像头拍摄到运动员前，先得到合理运动轨迹的目的，给渲染提供足够时间。For example, take the sled racing scene as an example. The average speed of athletes in the sled racing is about 90KM/H, the track length is about 1.5 to 2 kilometers, and there are about 15 to 20 curves with different angles and inclinations. Through a number of ultrasonic waves By calculating the position, the position and movement trajectory of the athlete in each straight line and curve can be obtained. Before the athlete passes through the next section, the movement trajectory of the next section is calculated in advance through the pre-trained prediction model, and the movement trajectory of the next section is calculated when the athlete reaches the next section. After entering the area, the predicted key point trajectory is corrected in advance through the key points collected by the ultrasonic equipment, so as to obtain a reasonable movement trajectory before the athletes are captured by the broadcast camera and provide enough time for rendering.
本申请实施例中，在确定运动员的运动轨迹之后，运动员的可视范围就基本确定，但是，此可视范围为运动员的平视范围，通常与运动员的实际视角具有较大差异。因此为了获得较真实的基于运动员视角的比赛视频流，可以在根据运动员的运动轨迹对比赛相关对象的三维模型进行渲染时，利用运动员在比赛过程中的视角对渲染过程进行修正。In the embodiment of the present application, after the athlete's movement trajectory is determined, the athlete's visual range is basically determined. However, this visual range is the athlete's head-up range, which is usually quite different from the athlete's actual perspective. Therefore, in order to obtain a more realistic game video stream based on the athlete's perspective, when rendering the three-dimensional model of game-related objects based on the athlete's movement trajectory, the player's perspective during the game can be used to correct the rendering process.
可选的，上述根据运动员的运动轨迹对预先建立的模型进行渲染之前，可以先确定运动员在比赛过程中的目标视角；然后，根据所述运动轨迹以及所述目标视角对预先建立的模型进行渲染，获得渲染结果，并将所述渲染结果转换为目标视频流，并推送所述目标视频流。由此，在渲染过程中考虑运动员在比赛过程中的目标视角，而不默认运动员平视，可以获得较真实的基于运动员视角的比赛视频流。Optionally, before rendering the pre-established model based on the athlete's movement trajectory, the athlete's target perspective during the game can be determined first; then, the pre-established model is rendered based on the movement trajectory and the target perspective. , obtain the rendering result, convert the rendering result into a target video stream, and push the target video stream. Therefore, by considering the athlete's target perspective during the game during the rendering process, instead of defaulting to the athlete looking straight up, a more realistic game video stream based on the athlete's perspective can be obtained.
可选的，上述确定运动员在比赛过程中的目标视角可以包括：确定运动员在比赛过程中的真实视角。由此，可以根据运动员在比赛过程中的真实视角来生成比赛视频流，从而提高观众的代入感。Optionally, the above-mentioned determining the target perspective of the athlete during the competition may include: determining the true perspective of the athlete during the competition. As a result, the game video stream can be generated based on the athletes' real perspectives during the game, thereby improving the audience's sense of immersion.
实际运动中，运动员通常处于一个快速观察的过程中，如果将捕获到的运动员视角的比赛画面完全展现给用户，该比赛画面会快速变化，给观众的观感很差，因此，可以引入一个预设视角阈值f，当运动员的真实视角大于预设视角阈值时，对运动员的真实视角进行修正，并基于修正后的视角来生成比赛视频流，从而避免影响观众的观感。In actual sports, athletes are usually in the process of rapid observation. If the captured game picture from the athlete's perspective is fully displayed to the user, the game picture will change rapidly, giving the audience a poor impression. Therefore, a preset can be introduced. Viewing angle threshold f, when the athlete's true viewing angle is greater than the preset viewing angle threshold, the athlete's true viewing angle is corrected, and the game video stream is generated based on the corrected viewing angle, so as to avoid affecting the audience's perception.
可选的，当运动员的真实视角大于预设视角阈值时，上述确定运动员在比赛过程中的目标视角可以包括：利用预设视角阈值修正运动员的真实视角，获得运动员在比赛过程中的目标视角。之后，可以利用所述目标视角生成比赛视频流，从而避免影响观众的观感。Optionally, when the athlete's true perspective is greater than the preset perspective threshold, the above determination of the athlete's target perspective during the competition may include: using the preset perspective threshold to correct the athlete's true perspective to obtain the athlete's target perspective during the competition. Afterwards, the target perspective can be used to generate a game video stream to avoid affecting the audience's perception.
一些实施例中，在利用预设视角阈值f修正运动员的真实视角θ时，可以采用如下公式，计算得到目标视角β：In some embodiments, when using the preset visual angle threshold f to correct the athlete's true visual angle θ, the following formula can be used to calculate the target visual angle β:
一些实施例中，以雪橇比赛场景为例，在得到预测的运动员的轨迹后，运动员的可视范围就基本确定，但是实际视角还与当时运动员的抬头高度与转向有关。雪橇运动中运动员会佩戴头盔，并且高速运动，无法非常清晰的获得运动员的面部数据去计算视角，但是雪橇运动头盔有特定的规范，在头盔头部中间存在黑色的固定位，头盔、双眼以及鼻梁的数据可以预先采集到。如图2所示，可以以头盔头部中间的固定位为中心，替代鼻梁的所在位置，人双眼的中心距离设为a，固定位延长线与双眼中心的夹角设为b，固定位与双眼中心交点相对于双眼中点的偏移记为c，则：当b＝0，c＝0时，运动员视角θ＝f(a，0，0)＝0，即人处于平视，用以计算视角的偏移，通过高速黑白摄像头锁定深色位置(即固定位与眼球)，将该固定位在整个头盔中的投影位置设为d(由于头盔为圆形，通过圆形圆转即可以得到d)，用于修正θ，以消除头盔的偏移影响的视角，此时θ＝f(a，b，c)+d，比如计算得出θ等于15°，但是头盔又旋转了5°，那实际人眼偏移就是20°；为了辅助高速下无法精准捕捉面部导致的视角飘逸，可以使用FaceNet事先训练的数据，预先生成面部数据以提升计算速度，可以在运动员出现在高速摄像头后快速得出面部状态数据，得到运动员视角后，由于运动员是在运动中，最终加上雪橇的投影角度e，则运动员的真实视角θ＝f(a，b，c)+d+e，如果雪橇的钢轨长度为1时的投影角度为180°，长度为0时的投影角度为0°，则在画面中雪橇的钢轨长度从0到1顺序变化时，可以线性得到相应投影角度，如雪橇的钢轨长度为0.5时，对应投影角度为90°。通过上述视角与转角数据，可以将数据转为建模数据后修正运动轨迹预测得到的视角，以得出真实视角范围。In some embodiments, taking the sled racing scene as an example, after obtaining the predicted trajectory of the athlete, the athlete's visual range is basically determined, but the actual viewing angle is also related to the athlete's head height and steering at that time. In sledding sports, athletes wear helmets and move at high speeds. It is impossible to obtain very clear facial data of athletes to calculate the angle of view. However, sledding sports helmets have specific specifications. There is a black fixed position in the middle of the head of the helmet, the helmet, the eyes and the bridge of the nose. The data can be collected in advance. As shown in Figure 2, the fixed position in the middle of the helmet head can be used as the center to replace the position of the bridge of the nose. The distance between the centers of the human eyes is set to a. The angle between the extension line of the fixed position and the center of the eyes is set to b. The fixed position and The offset of the center intersection of the eyes relative to the midpoint of the eyes is recorded as c. Then: when b=0, c=0, the athlete’s angle of view θ=f(a,0,0)=0, that is, the person is looking straight up, which is used for calculation For the shift of the viewing angle, the dark position (i.e. the fixed position and the eyeball) is locked through the high-speed black and white camera, and the projection position of the fixed position in the entire helmet is set to d (since the helmet is round, it can be obtained by circular rotation d), used to correct θ to eliminate the angle of view affected by the offset of the helmet. At this time, θ = f (a, b, c) + d. For example, the calculated value θ is equal to 15°, but the helmet is rotated by 5°. The actual human eye offset is 20°; in order to assist with the drifting angle of view caused by the inability to accurately capture faces at high speeds, you can use FaceNet's pre-trained data to pre-generate facial data to improve calculation speed, which can be quickly obtained after athletes appear in high-speed cameras. After extracting the facial status data and obtaining the athlete's perspective, since the athlete is in motion, and finally adding the projection angle e of the sled, the athlete's true perspective θ = f (a, b, c) + d + e, if the rails of the sled When the length is 1, the projection angle is 180°, and when the length is 0, the projection angle is 0°. When the length of the sled's rails changes sequentially from 0 to 1 in the picture, the corresponding projection angle can be obtained linearly, such as the length of the sled's rails. When it is 0.5, the corresponding projection angle is 90°. Through the above viewing angle and angle data, the data can be converted into modeling data and then the viewing angle predicted by the motion trajectory can be corrected to obtain the true viewing angle range.
可选的，为了应对各种异常比赛状态，上述确定运动员在比赛过程中的目标视角可以包括：在运动员出现目标动作的情况下，根据所述运动员在超出摄像范围前的角速度和角加速度，确定所述目标视角。其中所述目标动作比如为运动员偏离赛道等。需指出的，真实比赛中存在各种异常状态，因此需要加入运动员异常的场景检测，当运动员出现失误的情况(比如雪橇比赛时，检测到运动员身体脱离雪橇或者雪橇偏离赛道等情况)下，此时为了给观众更强的视觉冲击，需要解除预设视角阈值f的限制，以真实视角的剧烈晃动来表现比赛画面。由于这种情况下的运动员可能也在剧烈晃动，无法实时完整捕获面部，可以将运动员在异常前的预设时间(比如1s)内的视角θ进行采样，比如以每0.02s作为间隔采样50次，然后计算相应的角速度ω＝dθ/dt，以及角加速度β＝dω/dt，并在运动员处于无法被摄像机观察到的位置时，以超出摄像范围前的最终角速度ω和加速度β，代替实际的运动员偏移视角，直到运动员下一次出现到比赛画面。下一次运动员超出摄像范围时，可以重复上述过程确定运动员视角，直到运动员稳定下来。Optionally, in order to cope with various abnormal competition conditions, the above-mentioned determination of the athlete's target perspective during the competition may include: in the case of the athlete's target action, determining based on the angular velocity and angular acceleration of the athlete before exceeding the camera range. The target perspective. The target action is, for example, an athlete deviating from the track, etc. It should be pointed out that there are various abnormal conditions in real competitions, so it is necessary to add abnormal scene detection for athletes. When an athlete makes a mistake (for example, during a sled race, it is detected that the athlete's body leaves the sled or the sled deviates from the track), At this time, in order to give the audience a stronger visual impact, it is necessary to lift the restriction of the preset viewing angle threshold f and display the game screen with violent shaking of the real viewing angle. Since the athlete in this case may also be shaking violently and the face cannot be completely captured in real time, the athlete's angle of view θ within the preset time (such as 1s) before the abnormality can be sampled, for example, 50 times at an interval of 0.02s. , and then calculate the corresponding angular velocity ω = dθ/dt, and angular acceleration β = dω/dt, and when the athlete is in a position that cannot be observed by the camera, the final angular velocity ω and acceleration β before exceeding the camera range are used instead of the actual The player shifts the perspective until the next time the player appears on the game screen. The next time the athlete goes beyond the camera range, the above process can be repeated to determine the athlete's perspective until the athlete stabilizes.
需要说明的是，本申请实施例提供的视频推送方法，执行主体可以为视频推送装置，或者该视频推送装置中的用于执行视频推送方法的控制模块。本申请实施例中以视频推送装置执行视频推送方法为例，说明本申请实施例提供的视频推送装置。It should be noted that, for the video push method provided by the embodiments of the present application, the execution subject may be a video push device, or a control module in the video push device for executing the video push method. In the embodiment of the present application, a video push device performing a video push method is used as an example to illustrate the video push device provided by the embodiment of the present application.
请参见图3，图3是本申请实施例提供的一种视频推送装置的结构示意图，该装置应用于服务器设备，如图3所示，视频推送装置30包括：Please refer to Figure 3. Figure 3 is a schematic structural diagram of a video push device provided by an embodiment of the present application. The device is applied to server equipment. As shown in Figure 3, the video push device 30 includes:
第一确定模块31，用于根据运动员在比赛过程中的实时位置数据，确定所述运动员的运动轨迹；The first determination module 31 is used to determine the movement trajectory of the athlete based on the real-time position data of the athlete during the game;
渲染模块32，用于根据所述运动轨迹对预先建立的模型进行渲染，获得渲染结果，所述预先建立的模型为比赛相关对象的三维模型；The rendering module 32 is used to render a pre-established model according to the motion trajectory and obtain a rendering result. The pre-established model is a three-dimensional model of competition-related objects;
推送模块33，用于将所述渲染结果转换为目标视频流，并推送所述目标视频流，所述目标视频流为基于所述运动员的视角的比赛视频流。The push module 33 is configured to convert the rendering result into a target video stream and push the target video stream. The target video stream is a game video stream based on the perspective of the athlete.
可选的，所述预先建立的模型包括以下至少一项：赛道的三维模型、运动器具的三维模型和所述运动员的三维模型。Optionally, the pre-established model includes at least one of the following: a three-dimensional model of the track, a three-dimensional model of sports equipment, and a three-dimensional model of the athlete.
可选的，所述第一确定模块31具体用于：获取所述运动员在当前赛道区域的实时位置数据；根据所述实时位置数据修正第一运动轨迹，获得所述运动员在当前赛道区域的运动轨迹；其中，所述第一运动轨迹是基于所述运动员在所述当前赛道区域的上一段赛道区域的实时位置数据，预测得到的所述运动员在当前赛道区域的运动轨迹。Optionally, the first determination module 31 is specifically configured to: obtain the real-time position data of the athlete in the current track area; correct the first motion trajectory according to the real-time position data to obtain the athlete's position in the current track area. The movement trajectory; wherein, the first movement trajectory is the movement trajectory of the athlete in the current track area predicted based on the real-time position data of the athlete in the previous track area of the current track area.
可选的，视频推送装置30还包括：Optionally, the video push device 30 also includes:
第二确定模块，用于确定所述运动员在比赛过程中的目标视角；a second determination module, used to determine the target perspective of the athlete during the game;
所述渲染模块32具体用于：根据所述运动轨迹以及所述目标视角对所述预先建立的模型进行渲染，获得所述渲染结果。The rendering module 32 is specifically configured to render the pre-established model according to the motion trajectory and the target perspective to obtain the rendering result.
可选的，所述第二确定模块具体用于：确定所述运动员在比赛过程中的真实视角。Optionally, the second determination module is specifically used to determine the true perspective of the athlete during the game.
可选的，所述第二确定模块具体用于：当所述真实视角大于预设视角阈值时，利用所述预设视角阈值修正所述真实视角，获得所述目标视角。Optionally, the second determination module is specifically configured to: when the real viewing angle is greater than a preset viewing angle threshold, use the preset viewing angle threshold to correct the real viewing angle to obtain the target viewing angle.
可选的，所述第二确定模块具体用于：采用如下公式，计算得到所述目标视角β：Optionally, the second determination module is specifically configured to calculate the target viewing angle β using the following formula:
其中，f表示所述预设视角阈值，θ表示所述真实视角。Where, f represents the preset viewing angle threshold, and θ represents the real viewing angle.
可选的，所述第二确定模块具体用于：在所述运动员出现目标动作的情况下，根据所述运动员在超出摄像范围前的角速度和角加速度，确定所述目标视角。Optionally, the second determination module is specifically configured to determine the target angle of view based on the angular velocity and angular acceleration of the athlete before exceeding the camera range when the athlete performs a target action.
可选的，所述推送模块34具体用于：将所述目标视频流和其他视频流混流后推送至客户端，所述其他视频流为摄像头采集的运动员的比赛视频流。Optionally, the push module 34 is specifically configured to: mix the target video stream and other video streams and push them to the client. The other video streams are the athletes' game video streams collected by the camera.
本申请实施例的视频推送装置30，可以实现上述图1所示的方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。The video push device 30 of the embodiment of the present application can implement each process of the above-mentioned method embodiment shown in Figure 1 and can achieve the same technical effect. To avoid duplication, the details will not be described here.
可选的，如图4所示，本申请实施例还提供一种服务器设备40，包括处理器41，存储器42，存储在存储器42上并可在所述处理器41上运行的程序或指令，该程序或指令被处理器41执行时实现上述视频推送方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。Optionally, as shown in Figure 4, this embodiment of the present application also provides a server device 40, including a processor 41, a memory 42, and programs or instructions stored on the memory 42 and executable on the processor 41. When the program or instruction is executed by the processor 41, each process of the above video pushing method embodiment is implemented, and the same technical effect can be achieved. To avoid duplication, the details will not be described here.
本申请实施例还提供了一种可读存储介质，其上存储有程序或指令，所述程序或指令被处理器执行时可实现上述图1所示方法实施例的各个过程且能达到相同的技术效果，为避免重复，这里不再赘述。Embodiments of the present application also provide a readable storage medium on which programs or instructions are stored. When executed by a processor, the programs or instructions can implement the various processes of the method embodiment shown in Figure 1 and achieve the same results. To avoid repetition, the technical effects will not be repeated here.
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体,可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。Computer-readable media includes permanent and non-permanent, removable and non-removable media, and can be used for information storage by any method or technology. Information may be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), and read-only memory. (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cassettes, tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium can be used to store information that can be accessed by a computing device. As defined in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。It should be noted that, in this document, the terms "comprising", "comprises" or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device that includes a series of elements not only includes those elements, It also includes other elements not expressly listed or inherent in the process, method, article or apparatus. Without further limitation, an element defined by the statement "comprises a..." does not exclude the presence of additional identical elements in a process, method, article or apparatus that includes that element.
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。The above serial numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台服务分类设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. implementation. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence or that contributes to the existing technology. The computer software product is stored in a storage medium (such as ROM/RAM, disk, CD), including several instructions to cause a service classification device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in various embodiments of the present application.
以上所述仅是本申请的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本申请原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本申请的保护范围。The above are only the preferred embodiments of the present application. It should be pointed out that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications can also be made. should be regarded as the scope of protection of this application.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210555431.9ACN114979708B (en) | 2022-05-20 | 2022-05-20 | Video push method, device, server equipment and readable storage medium |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210555431.9ACN114979708B (en) | 2022-05-20 | 2022-05-20 | Video push method, device, server equipment and readable storage medium |
| Publication Number | Publication Date |
|---|---|
| CN114979708A CN114979708A (en) | 2022-08-30 |
| CN114979708Btrue CN114979708B (en) | 2023-10-17 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210555431.9AActiveCN114979708B (en) | 2022-05-20 | 2022-05-20 | Video push method, device, server equipment and readable storage medium |
| Country | Link |
|---|---|
| CN (1) | CN114979708B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116233584A (en)* | 2022-12-30 | 2023-06-06 | 清华大学 | Control method and device for virtual reality camera equipment |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106454401A (en)* | 2016-10-26 | 2017-02-22 | 乐视网信息技术（北京）股份有限公司 | Method and device for playing video |
| CN108379809A (en)* | 2018-03-05 | 2018-08-10 | 宋彦震 | Skifield virtual track guiding based on AR and Training Control method |
| US10325410B1 (en)* | 2016-11-07 | 2019-06-18 | Vulcan Inc. | Augmented reality for enhancing sporting events |
| WO2019128787A1 (en)* | 2017-12-26 | 2019-07-04 | 阿里巴巴集团控股有限公司 | Network video live broadcast method and apparatus, and electronic device |
| CN112184920A (en)* | 2020-10-12 | 2021-01-05 | 中国联合网络通信集团有限公司 | AR-based skiing blind area display method and device and storage medium |
| JP2021074277A (en)* | 2019-11-08 | 2021-05-20 | 株式会社コナミデジタルエンタテインメント | Game program, information processing device and method |
| CN113971693A (en)* | 2021-10-29 | 2022-01-25 | 咪咕文化科技有限公司 | Live screen generation method, system, device and electronic device |
| CN113992974A (en)* | 2021-10-14 | 2022-01-28 | 咪咕视讯科技有限公司 | Method and device for simulating competition, computing equipment and computer-readable storage medium |
| CN114268827A (en)* | 2021-12-22 | 2022-04-01 | 咪咕互动娱乐有限公司 | Game viewing interaction method, device, equipment and computer readable storage medium |
| CN114359343A (en)* | 2021-12-31 | 2022-04-15 | 北京市商汤科技开发有限公司 | Motion trail management method, device and equipment and computer readable storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3869469A1 (en)* | 2014-07-28 | 2021-08-25 | Panasonic Intellectual Property Management Co., Ltd. | Augmented reality display system, terminal device and augmented reality display method |
| EP3307407B1 (en)* | 2015-06-14 | 2020-09-09 | Sony Interactive Entertainment Inc. | Expanded field of view re-rendering for vr spectating |
| US10390082B2 (en)* | 2016-04-01 | 2019-08-20 | Oath Inc. | Computerized system and method for automatically detecting and rendering highlights from streaming videos |
| US9965900B2 (en)* | 2016-09-01 | 2018-05-08 | Avid Technology, Inc. | Personalized video-based augmented reality |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106454401A (en)* | 2016-10-26 | 2017-02-22 | 乐视网信息技术（北京）股份有限公司 | Method and device for playing video |
| US10325410B1 (en)* | 2016-11-07 | 2019-06-18 | Vulcan Inc. | Augmented reality for enhancing sporting events |
| WO2019128787A1 (en)* | 2017-12-26 | 2019-07-04 | 阿里巴巴集团控股有限公司 | Network video live broadcast method and apparatus, and electronic device |
| CN108379809A (en)* | 2018-03-05 | 2018-08-10 | 宋彦震 | Skifield virtual track guiding based on AR and Training Control method |
| JP2021074277A (en)* | 2019-11-08 | 2021-05-20 | 株式会社コナミデジタルエンタテインメント | Game program, information processing device and method |
| CN112184920A (en)* | 2020-10-12 | 2021-01-05 | 中国联合网络通信集团有限公司 | AR-based skiing blind area display method and device and storage medium |
| CN113992974A (en)* | 2021-10-14 | 2022-01-28 | 咪咕视讯科技有限公司 | Method and device for simulating competition, computing equipment and computer-readable storage medium |
| CN113971693A (en)* | 2021-10-29 | 2022-01-25 | 咪咕文化科技有限公司 | Live screen generation method, system, device and electronic device |
| CN114268827A (en)* | 2021-12-22 | 2022-04-01 | 咪咕互动娱乐有限公司 | Game viewing interaction method, device, equipment and computer readable storage medium |
| CN114359343A (en)* | 2021-12-31 | 2022-04-15 | 北京市商汤科技开发有限公司 | Motion trail management method, device and equipment and computer readable storage medium |
| Title |
|---|
| 基于体育迷观赛体验的VR和AR技术在冬季体育赛事中的应用研究;王艾莎;刘梅;周锐;牛鹤璇;徐妹妍;周宁;;新媒体研究(07);全文* |
| 运动目标三维轨迹可视化与关联分析方法;郭洋;马翠霞;滕东兴;杨;王宏安;;软件学报(第05期);全文* |
| Publication number | Publication date |
|---|---|
| CN114979708A (en) | 2022-08-30 |
| Publication | Publication Date | Title |
|---|---|---|
| US10810798B2 (en) | Systems and methods for generating 360 degree mixed reality environments | |
| US10819967B2 (en) | Methods and systems for creating a volumetric representation of a real-world event | |
| JP6894962B2 (en) | Image data capture method, device, and program for free-viewpoint video | |
| US10771760B2 (en) | Information processing device, control method of information processing device, and storage medium | |
| US12294744B2 (en) | Video stream processing method and apparatus, device, and medium | |
| CN106454401A (en) | Method and device for playing video | |
| CN107801045A (en) | The method, apparatus and system of autozoom when playing augmented reality scene | |
| US12154284B2 (en) | Methods and systems to track a moving sports object trajectory in 3D using multiple cameras | |
| US20210125349A1 (en) | Systems and methods for visualizing ball trajectory in real-time | |
| CN112714926A (en) | Method and device for generating a photo-realistic three-dimensional model of a recording environment | |
| CN109712247A (en) | Outdoor scene training system based on mixed reality technology | |
| US11978254B2 (en) | Systems and methods for providing video presentation and video analytics for live sporting events | |
| CN110270078B (en) | Football game special effect display system and method and computer device | |
| CN114979708B (en) | Video push method, device, server equipment and readable storage medium | |
| JP2022501748A (en) | 3D strike zone display method and equipment | |
| WO2017092432A1 (en) | Method, device, and system for virtual reality interaction | |
| KR20190019407A (en) | Server, method and user device for providing time slice video | |
| CN119090972B (en) | Technical and tactical capability monitoring and analyzing system and method for tennis-ball sports | |
| CN108475410A (en) | Three-dimensional watermark adding method, device and terminal | |
| KR101857104B1 (en) | Contents service system for pictures of playing space | |
| CN115550563B (en) | Video processing method, device, computer equipment and storage medium | |
| CN108965859B (en) | Projection mode identification method, video playing method and device and electronic equipment | |
| CN115396644B (en) | Video fusion method and device based on multi-section external reference data | |
| JP7456959B2 (en) | 3D model generation device, method and program | |
| US20250245898A1 (en) | Three-dimensional video highlight from a camera source |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |