CN107241645B - Method for automatically extracting goal wonderful moment through caption recognition of video - Google Patents
Method for automatically extracting goal wonderful moment through caption recognition of videoDownload PDFInfo
- Publication number
- CN107241645B CN107241645BCN201710434108.5ACN201710434108ACN107241645BCN 107241645 BCN107241645 BCN 107241645BCN 201710434108 ACN201710434108 ACN 201710434108ACN 107241645 BCN107241645 BCN 107241645B
- Authority
- CN
- China
- Prior art keywords
- shot
- score
- picture
- goal
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47217—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for controlling playback functions for recorded or on-demand content, e.g. using progress bars, mode or play-point indicators or bookmarks
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Studio Devices (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及视频提取技术，具体涉及一种通过对视频的字幕识别自动提取进球精彩瞬间的方法。The invention relates to a video extraction technology, in particular to a method for automatically extracting the wonderful moments of a goal by recognizing the subtitles of the video.
背景技术Background technique
就目前而言，融合媒体时代，广电媒体和互联网媒体齐头并进，相辅相成。广电媒体拥有丰富的资源，比如，有大量的专业体育赛事信号可以为互联网媒体提供内容支撑，而体育赛事也是人们生活中常常津津乐道的话题，拥有大量的受众；互联网媒体具有传播速度快、散播面广、信息碎片化等特点，能够持续保持热度，一方面，能够推动广电媒体的生产，另一方面，也对广电媒体现有制作系统提出了内容和效率的要求。For now, in the era of convergent media, radio and television media and Internet media go hand in hand and complement each other. Radio and television media have rich resources. For example, there are a large number of professional sports event signals that can provide content support for Internet media, and sports events are also a topic that people often talk about in their lives and have a large audience. The characteristics of wide dissemination and fragmentation of information can continue to maintain popularity. On the one hand, it can promote the production of radio and television media, and on the other hand, it also puts forward content and efficiency requirements for the existing production system of radio and television media.
现有的制作系统中，主要存在以下两个问题：In the existing production system, there are mainly the following two problems:
内容问题，一场比赛一般有一两个小时，内容的时间长度不利于在互联网、社交媒体传播，互联网和融合媒体的发展，使得越来越多的人适应和需求“碎片化”的信息。因此，就内容来说，一般采取提取比赛精彩镜头再针对互联网发布的方式。The content issue, a game usually lasts for one or two hours. The length of the content is not conducive to the spread of the Internet and social media. The development of the Internet and converged media makes more and more people adapt and demand "fragmented" information. Therefore, in terms of content, the method of extracting the highlights of the game and publishing it on the Internet is generally adopted.
效率问题，现有的提取比赛精彩镜头的方法基本上是在视频收录完成之后进行手动打点、人工剪切，显然这样的方法不仅消耗大量的人力和时间，而且效率很低，也不能满足时效性的需求。Efficiency problem, the existing method of extracting the highlights of the game basically is to manually check and cut the video after the video recording is completed. Obviously, this method not only consumes a lot of manpower and time, but also has low efficiency and cannot meet the timeliness. demand.
发明内容SUMMARY OF THE INVENTION
本发明的目的在于克服现有技术的不足，提供一种通过对视频的字幕识别自动提取进球精彩瞬间的方法，应用比分变化前有得分镜头的原理对视频进行字幕识别提取比赛进球镜头，该方法改善了现有技术中手动打点剪切精彩镜头的缺陷，能够提高效率。The purpose of the present invention is to overcome the deficiencies of the prior art, and to provide a method for automatically extracting the wonderful moment of a goal by recognizing the subtitles of the video, and applying the principle of scoring shots before the score changes to perform subtitle recognition on the video to extract the game goal shots, The method improves the defect of manual dot-cutting and cutting of wonderful shots in the prior art, and can improve the efficiency.
本发明的目的是通过以下技术方案来实现的：The purpose of this invention is to realize through the following technical solutions:
一种通过对视频的字幕识别自动提取进球精彩瞬间的方法，包括以下步骤：A method for automatically extracting the wonderful moments of goals by recognizing the subtitles of the video, including the following steps:
S1:确定比分字幕位置，按比分牌的特征对视频画面中的比分字幕板进行识别；S1: determine the score subtitle position, and identify the score subtitle board in the video picture by the feature of the score board;
S2监控比分，连续间隔的获取当前比分所对应的画面，并将当前比分与前一次比分进行比较，若相同则忽略，若不同则表示此处有进球的精彩瞬间的镜头；S2 monitors the score, obtains the screen corresponding to the current score at continuous intervals, and compares the current score with the previous score. If it is the same, ignore it;
S3:提取精彩镜头，从比分变化的帧开始往前寻找标记好的最近的远景，在识别出远镜头后，以远镜头结束帧为基准，在其前后截取一定数量的连续的视频帧，作为进球镜头。S3: Extract the wonderful shots, and start from the frame where the score changes to find the nearest marked distant view. After identifying the far shot, take the end frame of the far shot as the benchmark, and intercept a certain number of continuous video frames before and after it, as Goal shot.
进一步的，所述的步骤S1确定比分板的位置具体包括以下子步骤：Further, the step S1 to determine the position of the scoreboard specifically includes the following sub-steps:
S11：全屏搜索文字字幕，分区域识别出字幕文字；S11: Search for text subtitles in full screen, and identify subtitle text by region;
S12：将识别出的字幕文字与比分牌特征进行对比，若能对比上则为比分字幕板的位置。S12: Compare the recognized subtitle text with the score board feature, and if it can be compared, it is the position of the score subtitle board.
进一步的，所述的比分牌特征是队1名称队1比分：队2比分队2名称或者队1名称队1比分 - 队2比分队2名称，即识别字幕中的字符“：”或者“-”。Further, the score board feature is the name of team 1, the score of team 1: the name of team 2 is the name of team 2 or the name of team 1 is the score of team 1- the name of team 2 is the name of team 2, that is, the characters ":" or "-" in the subtitle are identified. ".
进一步的，所述的步骤S2计算监控比分具体包括以下子步骤：Further, the step S2 to calculate the monitoring score specifically includes the following sub-steps:
S21：按设置的时间间隔获取比分所在位置的画面；S21: Acquire the picture of the location of the score according to the set time interval;
S22：通过字幕识别方法识别比分；S22: Recognize the score by the subtitle recognition method;
S23：将本次识别的比分与上一次的比分对比，首次识别的比分除外，若相同则忽略，若不同则表示此处有进球的精彩瞬间的镜头。S23: Compare the score recognized this time with the previous score, except for the score recognized for the first time. If they are the same, ignore them. If they are different, it means that there is a scene of the wonderful moment of the goal.
进一步的，所述的步骤S3提取精彩镜头具体包括以下子步骤：Further, the step S3 extracting the highlights specifically includes the following sub-steps:
S31：以帧为单位，识别每一帧画面；S31: In units of frames, identify each frame of the picture;
S32：根据人头数目标注近景、中景、远景或根据镜头内帧对比方式标注远景、非远景；S32: Mark the close-range, medium-range, and long-range according to the number of heads, or mark the long-range and non-far-range according to the frame comparison method in the shot;
S33：在识别出远镜头后，以远镜头结束帧为基准，在其前后截取一定数量的连续的视频帧，作为进球镜头。S33: After identifying the far-lens, taking the ending frame of the far-lens as a benchmark, intercept a certain number of continuous video frames before and after it as the goal shot.
进一步的，所述的根据人头数目判断帧画面具体是指利用人工神经网络训练出识别人头数的模型，通过人头识别技术判断画面中人头的数目，若人头数小于等于1，则该画面为近景画面；若人头数在2和设定的值x之间，则该画面为中景；若人头数大于x，则为远景画面。Further, the described judging the frame picture according to the number of heads specifically refers to using an artificial neural network to train a model for recognizing the number of heads, and judging the number of heads in the picture through the head recognition technology, if the number of heads is less than or equal to 1, then the picture is a close-up view. Picture; if the number of heads is between 2 and the set value x, the picture is a medium shot; if the number of heads is greater than x, it is a long shot.
进一步的，所述的镜头内帧对比方式是指识别转场镜头，两个转场镜头间为一个自然镜头，对每个自然镜头进行内部帧对比观察其波动情况，波动幅度小的为远景，波动幅度大的为非远景，剪切视频时主要用到远景，因此不用详细区分近景和中景。Further, the method of comparing frames within a shot refers to identifying a transition shot, and between two transition shots is a natural shot. Comparing the internal frames of each natural shot to observe its fluctuations, the smaller the fluctuation range is the distant view, Those with a large fluctuation range are not distant scenes. When cutting videos, the distant scenes are mainly used, so there is no need to distinguish between close and medium scenes in detail.
进一步的，所述的近景、中景、远景定义如下：Further, the close-up, mid-range and long-range views are defined as follows:
近景：指进球或出界发生后对球员、教练的个人技艺、表情的特写，是一个人的镜头；Close-up: refers to the close-up of the personal skills and expressions of the players and coaches after the goal or out of bounds, which is a shot of a person;
中景：指对抢球、犯规等事件发生过程的局部特写，是2-5人的镜头；Medium shot: refers to a partial close-up of the process of grabbing the ball, fouls, etc., which is a shot of 2-5 people;
远景：是对整个球场的活动的镜头，以球的运动为线索进行拍摄，是多人的镜头，其人数大于中景中的人数。Long shot: It is a shot of the entire stadium activity, shot with the movement of the ball as a clue, and it is a shot of many people, the number of which is larger than the number of people in the medium shot.
本发明的有益效果是：本发明通过识别字幕中比分变化情况，再结合镜头近景、中景、远景的分析，综合计算找出进球瞬间的精彩视频，该方法操作简单可靠，能有效提取体育比赛视频中的精彩进球画面。The beneficial effects of the present invention are as follows: the present invention finds the wonderful video at the moment of scoring a goal through comprehensive calculation by identifying the change of the score in the subtitles, combined with the analysis of the close-range, medium-range and long-range shots of the lens, the method is simple and reliable in operation, and can effectively extract sports Great goal footage from the match video.
附图说明Description of drawings
图1是本发明的流程图。Figure 1 is a flow chart of the present invention.
具体实施方式Detailed ways
下面结合附图1进一步详细描述本发明的技术方案，但本发明的保护范围不局限于以下所述。The technical solution of the present invention is further described in detail below with reference to FIG. 1, but the protection scope of the present invention is not limited to the following.
原理介绍：Principle introduction:
1、我们把球赛中的各种镜头分类，分别为近景镜头、中景镜头和远景镜头。通过分析，我们发现进球镜头都是发生在远镜头中1. We classify various shots in the game into close-up shots, medium shots and long-range shots. Through analysis, we found that the goal shots all happened in the long shot
1）近景镜头：通常指进球、出界等事件发生后对球员、教练的个人技艺、表情的特写，基本是一个人的镜头，这种镜头一般都发生在比赛中断期间。1) Close-up shot: usually refers to the close-up of the personal skills and expressions of the players and coaches after events such as goals and out of bounds.
2）中景镜头：通常指对抢球、犯规等事件发生过程的局部特写，一般是三五个人的镜头。这种镜头一般出现在中场或者边场，球门前不会出现这种镜头。2) Medium shot: usually refers to a partial close-up of the process of grabbing the ball, fouls, etc., usually three or five people. This kind of lens usually appears in the midfield or sidefield, and it does not appear in front of the goal.
3）远景镜头：通常是对整个球场的活动的镜头，一般以球的运动为线索进行拍摄。球到球门前，一般都会切换到这种镜头，进球的过程发生在这类镜头中。3) Long-range shot: It is usually a shot of the activity of the entire stadium, and it is generally shot with the movement of the ball as a clue. When the ball reaches the goal, it is generally switched to this kind of shot, and the process of scoring a goal takes place in this kind of shot.
2、一场比赛中，比分板的位置不会改变。2. During a game, the position of the scoreboard will not change.
3、比分的变化标志着此处前有一个进球瞬间，一场比赛中进球瞬间是观众最关心的关键点，可以提取离比分变化最近的远景镜头作为精彩镜头发布到互联网媒体。3. The change of the score indicates that there is a scoring moment before here. The scoring moment in a game is the key point that the audience cares most about. The long-range shot closest to the score change can be extracted and released to the Internet media as a wonderful shot.
【实施例一】[Example 1]
一种通过对视频的字幕识别自动提取进球精彩瞬间的方法，应用于足球比赛，包括以下步骤；A method for automatically extracting the wonderful moments of scoring goals by recognizing subtitles of videos, applied to football games, includes the following steps;
S1：确定比分字幕位置S1: Determine the score subtitle position
全屏搜索文字字幕，分区域识别出字幕文字，将识别出的字幕文字与比分牌特征进行对比，若能对比上则为比分字幕板的位置；比分模板特征为：队1名称 队1比分：队2比分 队2名称，例如中国00：00韩国；Full-screen search for text subtitles, subtitles are identified by region, and the identified subtitles are compared with the score board features. If they can be compared, it is the position of the score subtitle board; the score template features are: team 1 name, team 1 score: team 2-point team 2 name, such as China 00:00 Korea;
S2：监控比分S2: Monitor the score
按设置的时间间隔获取比分所在位置的画面，通过字幕识别方法识别比分，将本次识别的比分与上一次的比分对比（首次识别的比分除外），若相同则忽略，若不同则表示此处有进球的精彩瞬间的镜头，进行下一步。Obtain the picture of the score at the set time interval, identify the score through the subtitle recognition method, and compare the score recognized this time with the previous score (except the score recognized for the first time). If they are the same, they will be ignored. With footage of the best moments of the goal, move on to the next step.
S3：提取精彩镜头S3: Extract Highlights
从比分变化的帧开始往前寻找标记好的最近的远景，画面类型的判断是与比分监控同时进行的，画面的判断包括以下步骤：Starting from the frame where the score changes, look forward to the nearest marked vision. The judgment of the picture type is carried out at the same time as the score monitoring. The judgment of the picture includes the following steps:
以帧为单位，识别每一帧画面，根据人头数目标注近景、中景、远景或根据镜头内帧对比方式标注远景、非远景。Take the frame as a unit, identify each frame of the picture, and mark the close-range, medium-range, and long-range according to the number of heads, or mark the long-range and non-long-range according to the frame comparison method in the lens.
通过人头数目判定：Judging by the number of heads:
利用人工神经网络训练出识别人头数的模型，通过该模型可以用于人头识别，通过人头识别技术判断画面中人头的数目，若人头数为小于等于1，则该画面为近景画面；若人头数在2和设定的值X之间，则该画面为中景；若人头数大于X，则为远景画面，其中X可根据具体的视频对应设置。The artificial neural network is used to train a model for recognizing the number of heads. This model can be used for head recognition, and the number of heads in the picture can be judged by the head recognition technology. If the number of heads is less than or equal to 1, the picture is a close-up picture; Between 2 and the set value X, the picture is a medium shot; if the number of heads is greater than X, it is a long-range picture, where X can be set according to the specific video.
镜头内帧对比方法判定：Intra-shot frame comparison method to determine:
识别转场镜头，两个转场镜头间为一个自然镜头，对每个自然镜头进行内部帧对比观察其波动情况，波动幅度小的为远景，波动幅度大的为非远景，剪切视频时主要用到远景，因此不用详细区分近景和中景。Identify the transition shots. There is a natural shot between the two transition shots. Compare the internal frame of each natural shot to observe its fluctuation. The fluctuation range is small, and the fluctuation range is non-telephoto. When cutting the video, the main The long shot is used, so there is no need to distinguish between close and medium shots in detail.
选取进球镜头Pick a goal shot
在识别出远镜头后，以远镜头结束帧为基准，在其前后截取一定数量的连续的视频帧，比如前面截取15秒，后面切取5秒，作为进球镜头。After recognizing the telephoto, take the end frame of the telephoto as the benchmark, and capture a certain number of continuous video frames before and after it, for example, 15 seconds in the front and 5 seconds in the back, as the goal shot.
【实施例二】[Example 2]
一种通过对视频的字幕识别自动提取进球精彩瞬间的方法，应用于篮球比赛；A method for automatically extracting the wonderful moments of scoring goals through subtitle recognition of videos, which is applied to basketball games;
S1：确定比分字幕位置S1: Determine the score subtitle position
全屏搜索文字字幕，分区域识别出字幕文字，将识别出的字幕文字与比分牌特征进行对比，若能对比上则为比分字幕板的位置；比分模板特征为：队1名称 队1比分-队2比分 队2名称，例如公牛00-00火箭；Search for text subtitles on the full screen, identify subtitle text by area, and compare the recognized subtitle text with the score board features. If they can be compared, it is the position of the score subtitle board; the score template features are: team 1 name team 1 score - team 2-point team 2 name, such as Bulls 00-00 Rockets;
S2：监控比分S2: Monitor the score
按设置的时间间隔获取比分所在位置的画面，通过字幕识别方法识别比分，将本次识别的比分与上一次的比分对比（首次识别的比分除外），若相同则忽略，若相差3分表示此处有进球的精彩瞬间的镜头（篮球比赛中3分球一般都是精彩镜头），进行下一步。Obtain the picture of the score at the set time interval, identify the score through the subtitle recognition method, and compare the score recognized this time with the previous score (except the score recognized for the first time). If they are the same, they will be ignored. There is a shot of the wonderful moment of the goal (the 3-point shot in a basketball game is usually a wonderful shot), and go to the next step.
S3：提取精彩镜头S3: Extract Highlights
从比分变化的帧开始往前寻找标记好的最近的远景，画面类型的判断是与比分监控同时进行的，画面的判断包括以下步骤：Starting from the frame where the score changes, look forward to the nearest marked vision. The judgment of the picture type is carried out at the same time as the score monitoring. The judgment of the picture includes the following steps:
以帧为单位，识别每一帧画面，根据人头数目和镜头内帧对比等方式综合判断帧画面的类型，并标注：近景、中景、远景或远景、非远景。Take the frame as a unit, identify each frame of picture, comprehensively judge the type of frame picture according to the number of heads and the comparison of frames in the lens, and mark: close-up, medium-range, long-range or long-range, non-long-range.
通过人头数目判定：Judging by the number of heads:
利用人工神经网络训练出识别人头数的模型，通过该模型可以用于人头识别，通过人头识别技术判断画面中人头的数目，若人头数为小于等于1，则该画面为近景画面；若人头数在2和设定的值X之间，则该画面为中景；若人头数大于X，则为远景画面，其中X可根据具体的视频对应设置。The artificial neural network is used to train a model for recognizing the number of heads. This model can be used for head recognition, and the number of heads in the picture can be judged by the head recognition technology. If the number of heads is less than or equal to 1, the picture is a close-up picture; Between 2 and the set value X, the picture is a medium shot; if the number of heads is greater than X, it is a long-range picture, where X can be set according to the specific video.
镜头内帧对比方法判定：Intra-shot frame comparison method to determine:
识别转场镜头，两个转场镜头间为一个自然镜头，对每个自然镜头进行内部帧对比观察其波动情况，波动幅度小的为远景，波动幅度大的为非远景，剪切视频时主要用到远景，因此不用详细区分近景和中景。Identify the transition shots. There is a natural shot between the two transition shots. Compare the internal frame of each natural shot to observe its fluctuation. The fluctuation range is small, and the fluctuation range is non-telephoto. When cutting the video, the main The long shot is used, so there is no need to distinguish between close and medium shots in detail.
选取进球镜头Pick a goal shot
在识别出远镜头后，以远镜头结束帧为基准，在其前后截取一定数量的连续的视频帧，比如前面截取15秒，后面切取5秒，作为进球镜头。After recognizing the telephoto, take the end frame of the telephoto as the benchmark, and capture a certain number of continuous video frames before and after it, for example, 15 seconds in the front and 5 seconds in the back, as the goal shot.
本发明不仅仅局限于篮球或足球比赛中，同样适用于其他计分制体育比赛，可以根据不同比赛计分机制制定精彩镜头的分值变化标准，从而提取相应的精彩镜头。The invention is not only limited to basketball or football games, but is also applicable to other scoring system sports games, and can formulate the score change standard of highlight shots according to different game scoring mechanisms, so as to extract corresponding highlight shots.
以上所述仅是本发明的优选实施方式，应当理解本发明并非局限于本文所披露的形式，不应看作是对其他实施例的排除，而可用于各种其他组合、修改和环境，并能够在本文所述构想范围内，通过上述教导或相关领域的技术或知识进行改动。而本领域人员所进行的改动和变化不脱离本发明的精神和范围，则都应在本发明所附权利要求的保护范围内。The foregoing are only preferred embodiments of the present invention, and it should be understood that the present invention is not limited to the forms disclosed herein, and should not be construed as an exclusion of other embodiments, but may be used in various other combinations, modifications, and environments, and Modifications can be made within the scope of the concepts described herein, from the above teachings or from skill or knowledge in the relevant field. However, modifications and changes made by those skilled in the art do not depart from the spirit and scope of the present invention, and should all fall within the protection scope of the appended claims of the present invention.
Claims (3)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710434108.5ACN107241645B (en) | 2017-06-09 | 2017-06-09 | Method for automatically extracting goal wonderful moment through caption recognition of video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710434108.5ACN107241645B (en) | 2017-06-09 | 2017-06-09 | Method for automatically extracting goal wonderful moment through caption recognition of video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107241645A CN107241645A (en) | 2017-10-10 |
| CN107241645Btrue CN107241645B (en) | 2020-07-24 |
Family
ID=59986153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710434108.5AActiveCN107241645B (en) | 2017-06-09 | 2017-06-09 | Method for automatically extracting goal wonderful moment through caption recognition of video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107241645B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107801106B (en)* | 2017-10-24 | 2019-10-15 | 维沃移动通信有限公司 | A video clip interception method and electronic equipment |
| CN109344292B (en)* | 2018-09-28 | 2022-04-22 | 百度在线网络技术（北京）有限公司 | Method, device, server and storage medium for generating event score segments |
| CN109635707A (en)* | 2018-12-06 | 2019-04-16 | 安徽海豚新媒体产业发展有限公司 | A kind of video lens extracting method based on feature identification |
| CN110267116A (en)* | 2019-05-22 | 2019-09-20 | 北京奇艺世纪科技有限公司 | Video generation method, device, electronic equipment and computer-readable medium |
| CN110339566A (en)* | 2019-05-29 | 2019-10-18 | 努比亚技术有限公司 | A kind of game Wonderful time recognition methods, terminal and computer readable storage medium |
| CN111031384A (en)* | 2019-12-24 | 2020-04-17 | 北京多格科技有限公司 | Video content display method and device |
| CN111340837A (en)* | 2020-02-18 | 2020-06-26 | 上海眼控科技股份有限公司 | Image processing method, device, equipment and storage medium |
| CN111488847B (en)* | 2020-04-17 | 2024-02-02 | 上海媒智科技有限公司 | Sports game video ball-feeding segment acquisition system, method and terminal |
| CN111988670B (en)* | 2020-08-18 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Video playing method and device, electronic equipment and computer readable storage medium |
| CN113537052B (en)* | 2021-07-14 | 2023-07-28 | 北京百度网讯科技有限公司 | Video clip extraction method, device, equipment and storage medium |
| CN113490049B (en)* | 2021-08-10 | 2023-04-21 | 深圳市前海动竞体育科技有限公司 | Sports event video editing method and system based on artificial intelligence |
| CN117132925B (en)* | 2023-10-26 | 2024-02-06 | 成都索贝数码科技股份有限公司 | An intelligent recording method and device for sports events |
| CN119169497A (en)* | 2024-08-22 | 2024-12-20 | 广东省新一代通信与网络创新研究院 | A method, system and device for capturing optimal shots |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1460835A1 (en)* | 2003-03-19 | 2004-09-22 | Thomson Licensing S.A. | Method for identification of tokens in video sequences |
| CN101211460A (en)* | 2006-12-30 | 2008-07-02 | 中国科学院计算技术研究所 | Method and device for automatically segmenting and classifying sports video shots |
| CN101604325A (en)* | 2009-07-17 | 2009-12-16 | 北京邮电大学 | Method for classifying sports video based on key frame of main scene lens |
| CN102254160A (en)* | 2011-07-12 | 2011-11-23 | 央视国际网络有限公司 | Video score detecting and recognizing method and device |
| CN102263907A (en)* | 2011-08-04 | 2011-11-30 | 央视国际网络有限公司 | Play control method of competition video, and generation method and device for clip information of competition video |
| CN102393909A (en)* | 2011-06-29 | 2012-03-28 | 西安电子科技大学 | Method for detecting goal events in soccer video based on hidden markov model |
| CN103049787A (en)* | 2011-10-11 | 2013-04-17 | 汉王科技股份有限公司 | People counting method and system based on head and shoulder features |
| CN105955708A (en)* | 2016-05-09 | 2016-09-21 | 西安北升信息科技有限公司 | Sports video lens classification method based on deep convolutional neural networks |
- 2017
- 2017-06-09CNCN201710434108.5Apatent/CN107241645B/enactiveActive
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1460835A1 (en)* | 2003-03-19 | 2004-09-22 | Thomson Licensing S.A. | Method for identification of tokens in video sequences |
| CN101211460A (en)* | 2006-12-30 | 2008-07-02 | 中国科学院计算技术研究所 | Method and device for automatically segmenting and classifying sports video shots |
| CN101604325A (en)* | 2009-07-17 | 2009-12-16 | 北京邮电大学 | Method for classifying sports video based on key frame of main scene lens |
| CN102393909A (en)* | 2011-06-29 | 2012-03-28 | 西安电子科技大学 | Method for detecting goal events in soccer video based on hidden markov model |
| CN102254160A (en)* | 2011-07-12 | 2011-11-23 | 央视国际网络有限公司 | Video score detecting and recognizing method and device |
| CN102263907A (en)* | 2011-08-04 | 2011-11-30 | 央视国际网络有限公司 | Play control method of competition video, and generation method and device for clip information of competition video |
| CN103049787A (en)* | 2011-10-11 | 2013-04-17 | 汉王科技股份有限公司 | People counting method and system based on head and shoulder features |
| CN105955708A (en)* | 2016-05-09 | 2016-09-21 | 西安北升信息科技有限公司 | Sports video lens classification method based on deep convolutional neural networks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107241645A (en) | 2017-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107241645B (en) | Method for automatically extracting goal wonderful moment through caption recognition of video | |
| US10758807B2 (en) | Smart court system | |
| CN105183849B (en) | A kind of match Video Events detection of Snooker and semanteme marking method | |
| US10616663B2 (en) | Computer-implemented capture of live sporting event data | |
| US8611723B2 (en) | System for relating scoreboard information with event video | |
| CN100531352C (en) | A method for detecting wonderful section of football match video | |
| US7006945B2 (en) | Processing of video content | |
| CN106131469B (en) | Ball intelligent robot coach and judgment system based on machine vision | |
| US20030182620A1 (en) | Synchronization of video and data | |
| US20080269924A1 (en) | Method of summarizing sports video and apparatus thereof | |
| CN109672899A (en) | The Wonderful time of object game live scene identifies and prerecording method in real time | |
| CN107454437B (en) | Video annotation method and device and server | |
| CN112533003B (en) | Video processing system, device and method | |
| CN107172487A (en) | A kind of method that Highlight is extracted by camera lens playback feature | |
| JP6307892B2 (en) | Extraction program, method, and apparatus, and baseball video meta information creation apparatus, method, and program | |
| CN101202842A (en) | Method for marking refined striking segments in video of baseball game | |
| JP2015139017A (en) | Information processing program, method, device, and baseball video meta information generating device, method and program | |
| Lee et al. | Highlight-video generation system for baseball games | |
| US10200764B2 (en) | Determination method and device | |
| CN101090453A (en) | How to search for highlights in videos of tennis matches | |
| CN114463664B (en) | A new puck tracking method for ice hockey | |
| Dai et al. | Replay scene classification in soccer video using web broadcast text | |
| CN110969133B (en) | Intelligent data acquisition method for table tennis game video | |
| CN112827154A (en) | A sports intelligent scorer system | |
| Ke | Application of artificial intelligence in large-scale international wushu (taolu) events |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |