CN106254925A - Target object extraction method, target object extraction equipment and target object extraction system based on video identification - Google Patents

Target object extraction method, target object extraction equipment and target object extraction system based on video identification Download PDF

Info

Publication number
CN106254925A
CN106254925A CN201610621286.4A CN201610621286A CN106254925A CN 106254925 A CN106254925 A CN 106254925A CN 201610621286 A CN201610621286 A CN 201610621286A CN 106254925 A CN106254925 A CN 106254925A
Authority
CN
China
Prior art keywords
video
target object
data
hyperlink
video data
Prior art date
Application number
CN201610621286.4A
Other languages
Chinese (zh)
Inventor
闫磊
Original Assignee
乐视控股(北京)有限公司
乐视致新电子科技(天津)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 乐视控股(北京)有限公司, 乐视致新电子科技(天津)有限公司 filed Critical 乐视控股(北京)有限公司
Priority to CN201610621286.4A priority Critical patent/CN106254925A/en
Publication of CN106254925A publication Critical patent/CN106254925A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
    • G06K9/00711Recognising video content, e.g. extracting audiovisual features from movies, extracting representative key-frames, discriminating news vs. sport content
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network, synchronizing decoder's clock; Client middleware
    • H04N21/431Generation of visual interfaces for content selection or interaction; Content or additional data rendering
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/478Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/47815Electronic shopping
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/478Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4782Web browsing, e.g. WebTV
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/85Assembly of content; Generation of multimedia applications
    • H04N21/858Linking data to content, e.g. by linking an URL to a video object, by creating a hotspot
    • H04N21/8586Linking data to content, e.g. by linking an URL to a video object, by creating a hotspot by using a URL

Abstract

Embodiments of the invention provide a target object extraction method, target object extraction equipment and a target object extraction system based on video identification, which belong to the technical field of video processing. The method comprises the following steps: receiving video data and identity data from a video identification device, wherein the identity data includes a target object of interest to users identified from the video data; getting a hyperlink corresponding to relevant information of the target object of interest to users according to the identity data; and adding the identity data and the hyperlink to a video playing page to display the identity data and the hyperlink together with the video data. According to the embodiments of the invention, while a video is being played, the relevant information and the hyperlink of the target object of interest to users in the video can be displayed, users can further understand the target object of interest, choose to buy something or the like conveniently and quickly by clicking on the hyperlink, and therefore, time is saved for users while user needs are met.

Description

基于视频识别的目标对象提取方法、设备以及系统 Extraction methods, devices and systems based on the identified video audiences

技术领域 FIELD

[0001 ]本发明实施例涉及视频处理技术领域,具体地,涉及一种基于视频识别的目标对象提取方法、一种基于视频识别的目标对象提取设备、以及一种基于视频识别的目标对象提取系统。 [0001] Audience extraction system embodiment relates to video processing technology of the present invention, in particular, to a method of extracting a target object based on the identified video, the video extracting device based on the identified target object, and a video based on the identified .

背景技术 Background technique

[0002]随着网络的快速发展,越来越多的用户选择通过收看各种视频作为了解第一手资讯的手段,例如通过视频了解时事新闻、各地文化、剧情等。 [0002] With the rapid development of the network, more and more users choose as a means to understand first-hand information, such as video news about current events, local culture, and so on through the story to watch a variety of videos. 很多时候,用户观看视频后可能会对其中一些视频内容(例如衣服、背包等)感兴趣,并希望了解或购买。 In many cases, users after watching the video might be interested in some of which the video content (such as clothing, backpacks, etc.) and want to learn or purchase.

[0003]在实施现有技术的上述过程中,发明人发现用户一般是先观看了视频再去查找想要了解视频中的感兴趣的目标对象,而不能直接在观看视频的同时就对其感兴趣的目标对象进行了解或购买,耗时且不够便捷。 [0003] In the process of implementation of the prior art, the inventors found that users generally the first to go to watch the video to find audiences want to know are interested in video, but not directly on their sense while watching the video interested audience to understand or purchase, time-consuming and is not convenient. 即本申请发明人在实现本发明实施例的过程中发现,现有技术的上述方案具有不能对视频中出现的对象建立链接的缺陷。 Namely, the present inventors in the process of implementing the present embodiments of the invention found that the above-described prior art solutions have drawbacks can not establish a link to an object appearing in the video.

发明内容 SUMMARY

[0004]针对现有技术中存在的缺少能够对视频中出现的用户感兴趣的目标对象建立链接的方法的技术问题,本发明提供了一种基于视频识别的目标对象提取方法,该方法包括:接收来自视频识别装置的视频数据以及标识数据,其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象;根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接;以及将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示。 [0004] The technical problem for the user is missing the target object appearing in the video can be of interest to establish a link in the prior art method, the present invention provides a method of extracting a target object based on the identified video, the method comprising: receiving video data from the video data and the identification recognition means, wherein said identification data comprises a target object of interest to the user identified from the video data; obtaining related information of said target object of interest corresponding to the user according to the identification data hyperlinks; and the identification data added to the hyperlink and the video player page is displayed together with the video data.

[0005] 可选地,所述用户感兴趣的目标对象包括能够购买到的商品。 [0005] Alternatively, the target objects of interest to the user comprises the product can be purchased.

[0006]可选地,所述视频数据为直播购物视频数据。 [0006] Alternatively, the video data is live video data cart.

[0007] 可选地,该方法还包括:按照所述视频的播放时间滚动显示所述标识数据和所述超链接。 [0007] Optionally, the method further comprising: according to playback time of the video data and the identification scroll display the hyperlink.

[0008]相应地,本发明实施例还提供了一种基于视频识别的目标对象提取设备,该设备包括:接收模块,用于接收来自视频识别装置的视频数据以及标识数据,其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象;超链接生成模块,用于根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接;以及超链接添加模块,用于将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示。 [0008] Accordingly, embodiments of the present invention further provides a video based on the identified target object extracting apparatus, the apparatus comprising: a receiving module, configured to receive video data from the video data and the identification recognition means, wherein said identification data including the target object of interest to the user identified from the video data; hyperlink generating module, for obtaining information about the target object of interest corresponding to the user based on the identification data hyperlinks; hyperlinks adding module, It means for adding the identification data and the video playback hyperlink to a page displayed together with the video data.

[0009]可选地,所述用户感兴趣的目标对象包括能够购买到的商品。 [0009] Alternatively, the target objects of interest to the user comprises the product can be purchased.

[0010]可选地,所述视频数据为直播购物视频数据。 [0010] Alternatively, the video data is live video data cart.

[0011]可选地,所述超链接添加模块还用于:按照所述视频的播放时间滚动显示所述标识数据和所述超链接。 [0011] Alternatively, the hyperlink adding module further configured to: according to the playback time of the video data and the identification scroll display the hyperlink.

[0012]可选地,所述基于视频识别的目标对象提取设备为乐视超级电视。 [0012] Alternatively, the video based on the identified target object extracting apparatus as music as Super TV.

[0013]另外,本发明实施例还提供了一种基于视频识别的目标对象提取系统,该系统包括:本发明实施例提供的的基于视频识别的目标对象提取设备;以及用户设备,所述用户设备与所述基于视频识别的目标对象提取设备通过网络通信,所述基于视频识别的目标对象提取设备将所述视频播放页面传送到所述用户设备进行显示。 [0013] Further, embodiments of the present invention further provides a video based on the identified target object extraction system, the system comprising: extracting recognition target object based on the video device according to an embodiment of the present invention; and a user device, the user apparatus and the target object is identified based video extracting device via a network communication based on the identified target object extracting video device, the video player page to be displayed to the user equipment.

[0014]可选地,所述基于视频识别的目标对象提取设备为服务器。 [0014] Alternatively, the video based on the identified target object extracting device is a server.

[0015] 可选地,所述用户设备为乐视超级电视。 [0015] Alternatively, the user device is a music as Super TV.

[0016]采用本发明实施例提供的基于视频识别的目标对象提取方法,通过接收来自视频识别装置的视频数据以及标识数据(其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象),之后根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接,以及将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示,能够实现在视频播放同时显示其中用户感兴趣的目标对象的相关信息和超链接,通过点击该超链接用户可以方便地、快速地对感兴趣的目标对象进行进一步地了解或者选择购物等,在满足用户需求的同时节约了用户的时间,提供了一种便捷的认知或购物方式。 [0016] The embodiments of the present invention provides a method of extracting the target object based on the identified video, by receiving the video data, and identification data (identification wherein the user data comprises identifying an object of interest from the video data from the video identification means Object), after obtaining said target object of interest based on the user identification information corresponding to the data related to the hyperlink, and adding the identification data and the video playback hyperlink to a page displayed together with the video data can be achieved simultaneously display information about the target object in which the user is interested in video playback and hyperlinks can be easily and quickly to the target object of interest for further understanding of the user by clicking on the hyperlink or choose shopping in to meet customer needs while saving users time, provides a convenient way to shop or cognition.

[0017]以及,采用本发明实施例提供的基于视频识别的目标对象提取设备,通过接收模块接收来自视频识别装置的视频数据以及标识数据(其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象),之后超链接生成模块根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接,以及超链接添加模块将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示,能够实现在视频播放同时显示其中用户感兴趣的目标对象的相关信息和超链接,通过点击该超链接用户可以方便地、快速地对感兴趣的目标对象进行进一步地了解或者选择购物等,在满足用户需求的同时节约了用户的时间,提供了一种更省时、便捷的认知或购物方式。 [0017] and, using the embodiment of the present invention is based on the user identification provided by the target object extracting video device, video data, and receiving identification data (identification data wherein said identification means comprises a video from a module identified by receiving from the video data target object of interest), then the hyperlink generation module obtaining the target object of interest to the user based on the identification information corresponding to data associated hyperlink, the hyperlink and adding module adding the identification data and the hyperlink the video playback pages are displayed together with the video data can be achieved simultaneously display information about the target object in which the user is interested in video playback and hyperlinks, by clicking on the hyperlink that users can easily and quickly be interested in further understanding of the target audience or choose shopping, etc., to meet the needs of users saving the user time, provides a time-saving and convenient way to shop or cognitive.

[0018]另外,包括本发明实施例提供的基于视频识别的目标对象提取设备的基于视频识别的目标对象提取系统,也同样可以实现上述技术效果,在此不再赘述。 [0018] Further, embodiments of the present invention including the target object based on the extracted video identification system of video recognition target object based on the extraction device, also be provided to achieve the above technical effect, and are not repeated here.

[0019]本发明实施例的其它特征和优点将在随后的具体实施方式部分予以详细说明。 [0019] Other features and advantages of embodiments of the present invention will be described in detail in a subsequent section of the particular embodiment.

附图说明 BRIEF DESCRIPTION

[0020]附图是用来提供对本发明实施例的进一步理解,并且构成说明书的一部分,与下面的具体实施方式一起用于解释本发明实施例,但并不构成对本发明实施例的限制。 [0020] The drawings are provided for further understanding of embodiments of the present invention, and constitute a part of this specification, the following specific embodiments serve to explain embodiments of the present invention, but not limiting embodiments of the present invention. 在附图中: In the drawings:

[0021]图1是根据本发明实施例的基于视频识别的目标对象提取设备的结构示意图; [0021] FIG. 1 is a schematic structure extraction device based on the identified video audiences embodiment of the present invention embodiment;

[0022]图2是根据本发明实施例的基于视频识别的目标对象提取系统的结构示意图;以及 [0022] FIG. 2 is a schematic structural diagram of a video based on the identified target object extraction system in accordance with an embodiment of the present invention; and

[0023]图3是根据本发明实施例的基于视频识别的目标对象提取方法的示例流程图。 [0023] FIG. 3 is a flowchart of an example method based on the target object extracting video recognition according to an embodiment of the present invention.

[0024]附图标记说明 [0024] REFERENCE NUMERALS

[0025] 10接收模块 20超链接生成模块 [0025] The receiving module 10 module 20 generates a hyperlink

[0026] 30超链接添加模块100基于视频识别的目标对象提取设备 [0026] 30 hyperlinks adding module 100 extracts a target object based on the identified video

[0027] 200用户设备 300视频识别装置 [0027] The user equipment 200 300 a video identification means

具体实施方式 Detailed ways

[0028]以下结合附图对本发明实施例的具体实施方式进行详细说明。 [0028] The following detailed description in conjunction with the accompanying drawings DETAILED DESCRIPTION Embodiments of the present invention. 应当理解的是,此处所描述的具体实施方式仅用于说明和解释本发明实施例,并不用于限制本发明实施例。 It should be understood that the specific embodiments described herein are only used to illustrate and explain the embodiments of the invention, the invention is not intended to limit the present embodiment.

[0029]为了更加清楚地说明本发明实施例的思想,本发明实施例考虑了多种实施例,下面将一一进行详细地说明。 [0029] In order to more clearly illustrate the idea of ​​an embodiment of the present invention, the present invention embodiments contemplate various embodiments will be described in detail below eleven.

[0030] 实施例1 [0030] Example 1

[0031]图1是根据本发明实施例的基于视频识别的目标对象提取设备100的结构示意图,该设备可以包括:接收模块10,用于接收来自视频识别装置的视频数据以及标识数据,其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象;超链接生成模块20,用于根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接;以及超链接添加模块30,用于将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示。 [0031] FIG. 1 is an embodiment of the present invention is based on the video recognition target object extraction structure schematic view of apparatus 100, the apparatus may include: a receiving module 10, configured to receive video data from the video data and the identification recognition means, wherein said identification data comprises a target object of interest to the user identified from the video data; hyperlink generation module 20, for obtaining related information corresponding to the hyperlink target object of interest to the user based on the identification data; and super link Add module 30 for adding the identification data and the video playback hyperlink to a page displayed together with the video data.

[0032]具体来说,为了实现本发明实施例的功能,首先需要提供视频源,该视频源可以是直播视频数据,也可以是点播视频数据。 [0032] Specifically, in order to realize functions of the embodiment of the present invention, first, a need to provide a video source, the video source may be a live video data, may be video on demand data. 采用现有技术中的视频识别装置来进行视频的拍摄和识别(具体识别过程与现有技术相同,为了不混淆本发明实施例的保护范围,在此不再赘述),生成视频数据以及标识数据,其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象。 Using video recognition apparatus in the prior art and to identify a video shooting (the specific recognition process the same as the prior art, in order not to obscure the scope of embodiments of the present invention, are not repeated here), generates video data and identification data wherein said identification data of interest comprises identifying the user from the video data of the target object.

[0033]具体来说,一个视频中用户感兴趣的目标对象可以包括能够购买到的商品、商品品牌、商品价格、商品名称、商品介绍,或者地点名称、地点介绍、人物名称、以及人物介绍等等。 [0033] Specifically, the target object of interest in the video the user may include the ability to purchase goods, commodities brand, product price, product name, product description, name or location, location description, character name and character introductions Wait. 例如,在一个视频中,帧A示出了一本书、帧B示出了一个人物、帧C示出了一处景点等等,这些信息可以是用户感兴趣的目标对象,因此视频识别装置都可以将他们提取出来,其中视频识别装置可以为现有技术中任何适当的具有视频识别功能的设备,为了不混淆本发明实施例的保护范围,在此不再赘述。 For example, in a video, frame A shows a book, a frame B is shown figure, frame C show an attraction, etc., which information may be the target of interest to the user, so the video identification means they can be extracted, wherein the video identification means may be any suitable prior art device with video recognition function, in order not to obscure the scope of embodiments of the present invention, it is not repeated here.

[0034]之后,基于视频识别的目标对象提取设备100的接收模块10可以接收来自视频识别装置的视频数据以及标识数据。 After [0034], video recognition target object extracting apparatus 100 based on the receiving module 10 may receive video data from the video data and the identification recognition means. 接着,超链接生成模块20可以根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接。 Subsequently, the hyperlink generation module 20 may obtain relevant information of the target object of interest corresponding to the user identification data according to the hyperlinks. 基于视频识别的目标对象提取设备100中可以存储多个超链接,每个超链接可以与一种用户感兴趣的目标对象对应。 Video recognition target object extracting apparatus 100 may store a plurality of hyperlinks, the target object may be of interest to each hyperlink corresponds to one based on the user. 举例来说,超链接生成模块20可以根据标识数据“X商品”可以获得“X商品”对应的超链接,例如该商品的介绍页面,或者购买页面。 For example, module 20 may generate a hyperlink "X product" may obtain the corresponding hyperlink "X Goods" The identification data, for example, introduction page of the product or purchase page. 或者,超链接生成模块20可以根据标识数据“X地点”可以获得“X地点”对应的超链接,例如该X地点的介绍页面,或者门票购买页面等。 Alternatively, module 20 may generate a hyperlink "X location" available "X location" hyperlink corresponding to the identification data according to, for example, introduction page of the site X, and the like or ticket purchase page.

[0035]之后,超链接添加模块30可以将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示。 After [0035], adding hyperlinks module 30 may add the identification data and the video playback hyperlink to a page displayed together with the video data. 举例来说,将“X商品”的文字(“X商品”)添加到视频播放页面的一个区域中(例如视频播放区域的左边栏或者右边栏等),将“X地点”的文字(“X地点”)添加到视频播放页面的一个区域中。 For example, the "X product" of the text ( "X product") to add a video playing area of ​​the page (for example, video playback area on the left column or right column, etc.), the "X place," the text ( "X place ") added to one area of ​​the video playback page. 可选地,超链接添加模块30还可以按照所述视频的播放时间滚动显示所述标识数据和所述超链接。 Alternatively, the hyperlink adding module 30 also follow the playback time of the video data and the identification scroll display the hyperlink. 例如,在视频播放区域的左边栏或者右边栏进行滚动显示。 For example, to scroll the display in the video playback area on the left column or the right column.

[0036]这样,用户观看视频过程中可以通过点击在视频播放页面上的特定区域中所列出的用户感兴趣的目标对象而超链接到与该信息相关的页面,进一步了解该信息。 [0036] In this way, the user can watch the video by clicking on the course of the target object the user is interested in a specific area on the video playback page listed and hyperlinks to related information page to learn more about the information.

[0037]应当理解的是,在上述实施例中以视频的每一帧仅提取一个用户感兴趣的对象(即帧A示出的一本书、帧B示出的一个人物、帧C示出的一处景点)作为示例阐明,但实际上,也可以从一帧视频中提取多个用户感兴趣的目标对象(例如帧A示出的一本书、一个人物、以及一处景点),这样的示例的超链接获得和添加过程与上述实施例是相似的,即本发明实施例的思想并不局限于上述实施例。 [0037] It should be appreciated that each frame of video to extract the object of interest only a user in the above embodiments (i.e., frame A shows a book, a frame B shown in figure, frame C shown the one of interest) set forth as an example, but in fact, the target object may be of interest to extract a plurality of users (e.g., frame a shows a book, a figure, and an interest) from a video, so hyperlinks addition process and to obtain the above-described exemplary embodiments are similar, i.e. idea of ​​an embodiment of the present invention is not limited to the above embodiments.

[0038]采用这样的实施例1,可以实现用户在观看视频同时在视频播放页面中还显示出当前播放的视频内容中出现的用户感兴趣的目标对象,以供用户进一步了解。 [0038] With such an embodiment, the user also may be implemented in the video player displays a page showing the target object the user is interested in playing the video content currently appearing in the video viewing for the user to learn more. 例如,在观看购物节目视频时,视频中出现一件商品时,视频播放页面中就会出现该商品的超链接,用户如果感兴趣想要进一步了解或购买,就可以直接点击该超链接,进入到相应页面,方便快捷。 For example, when watching video shopping program, a commodity appear in the video, the video playback page will appear in the hyperlink of the goods, if users want to learn more about or are interested in buying, you can click the hyperlink, enter to the appropriate page, and convenient.

[0039] 实施例2 [0039] Example 2

[0040]在该实施例2中,考虑到网络的快速发展,越来越多的用户参考视频进行购物,因此在该实施例2中提供一种新型的购物方式一直播购物。 [0040] In this embodiment 2, considering the rapid development of the network, more and more users reference video shop, so that the Example 2 to provide a novel way of a live shopping cart. 直播购物是指买手通过携带视频识别装置进行在特定地点进行视频直播,用户直接通过观看该视频来购买其中想要的商品。 Live shopping refers to the buyers by carrying the video identification means live video in a particular place, the user directly to where you want to purchase goods by watching the video. 这样的购物方式,与传统的看图片购物相比更加直观,并且买手的介绍、购买过程均在线直播,避免了以次充好,以假换真的不良买卖。 Such a way of shopping, look at the pictures and the traditional shopping more intuitive compared to, and buyers, the purchase process are live online, to avoid shoddy, fake change really bad deal.

[0041 ]想要实现这种购物方式,需要将用户感兴趣的目标对象和对应的超链接显示在视频播放页面当中,因此基于视频识别的目标对象提取设备100可以应用于这种购物方式中。 [0041] want to achieve this way of shopping, the target object and the corresponding hyperlink to interested users need to display the video playback pages of them, so the identification of the target object based video extracting device 100 may be applied in such a way to shop. 在这种情况中,所述用户感兴趣的目标对象可以包括能够购买到的商品,例如商场中出售的任何物品。 In this case, the target object of interest to the user may include the product can be purchased, for example, any article sold in shopping malls. 买手在开始一次直播购物前,可以提前列出可以购买的物品列表,并发送给直播购物的服务提供方,服务提供方可以预先在基于视频识别的目标对象提取设备100中存储好列表中的物品的超链接。 Buyers before the start of a live shopping list in advance a list of items can be purchased and sent to live shopping service provider, the service provider can pre-extraction equipment in good list of stores 100 based on the video identified the target object hyperlinks items. 之后,买手可以开始使用视频识别装置进行视频的拍摄和识另Ij,基于视频识别的目标对象提取设备100的接收模块10可以接收来自视频识别装置的视频数据以及标识数据,其中所述视频数据为直播购物视频数据,所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象(即能够购买到的商品)。 Thereafter, the buyers can start using the video identification means for identifying another shooting video and Ij, 10 may receive video data from the video data and the identification means of identifying a target object extracting video recognition apparatus 100 based on the receiving module, wherein the video data Shopping is live video data, the identification data including the target object (i.e., able to purchase the product) of interest to the user identified from the video data.

[0042]之后,超链接生成模块20可以根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接,例如根据标识数据“X商品”可以获得“X商品”对应的超链接,例如该商品的介绍页面,或者购买页面。 After [0042], the hyperlink target generation module 20 may obtain the object of interest based on the user identification information corresponding to the data related to the hyperlink, for example "X Goods" available "X product" according to the identification data corresponding to the super link, such as the product description page, or purchase page. 然后,超链接添加模块30可以将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示,将“X商品”的文字(“X商品”)添加到视频播放页面的一个区域中(例如视频播放区域的左边栏或者右边栏等)。 Then, adding hyperlinks module 30 may add the identification data and hyperlinks to the video player page is displayed together with the video data, the "X goods" character ( "X Goods") added to the video player page in a region (such as video playback area on the left column or right column, etc.). 可选地,超链接添加模块30还可以按照所述视频的播放时间滚动显示所述标识数据和所述超链接。 Alternatively, the hyperlink adding module 30 also follow the playback time of the video data and the identification scroll display the hyperlink. 例如,在视频播放区域的左边栏或者右边栏进行滚动显示。 For example, to scroll the display in the video playback area on the left column or the right column. 这样,用户观看直播的视频中可以通过点击在视频播放页面上的特定区域中所列出的用户感兴趣的目标对象而超链接到与该信息相关的页面,进一步了解该信息,例如点击“X商品”进入到其购买页面进行购买,实现直播购物。 This allows the user to view the target object of interest to the user can be listed by clicking on the video playback page in a specific area in live video and hyperlinks to pages related to the information, learn more about the information, for example, click the "X goods "into its purchase page to make a purchase, implement live shopping.

[0043]本发明实施例所提供的基于视频识别的目标对象提取设备可以以硬件或软件(例如应用程序)的形式实现,本发明实施例对此不进行限定。 [0043] The embodiment of the present invention (e.g., an application) implemented in the form of hardware or software, video recognition target object extracting apparatus based on examples provided, embodiments of the present invention which is not limited. 并且,该基于视频识别的目标对象提取设备可以为具有上述功能的任何适当的设备,例如,基于视频识别的目标对象提取设备可以为能够实现上述功能的用户设备。 Then, the recognition target object based on video extraction device may, for example, video recognition target object based on the extracted user equipment device may be capable of realizing the functions of any suitable device having the above function.

[0044]由于乐视超级电视的硬件方面的极佳性能,因此所述基于视频识别的目标对象提取设备也可以为乐视超级电视,即乐视超级电视可以被配置成实现上述本发明实施例所提供的上述功能。 [0044] Since the excellent performance of the hardware aspects of music, as the super television, so the target object based video identification extraction device may be to implement an embodiment of the present invention provides for the music, as the Couch, i.e. music as Super TV may be configured the above functions. 通过观看乐视超级电视,用户可以选择进入“直播购物”的页面并通过如上所述的实施例进行购物,足不出户即可以享受购物带来的乐趣,十分便捷。 By viewing music as a super TV, users can choose to enter "live shopping" page and make purchases through the embodiments described above, staying at home can enjoy the fun of shopping that is brought about, very convenient.

[0045] 实施例3 [0045] Example 3

[0046]在实施例3中,与实施例2不同之处在于,基于视频识别的目标对象提取设备100也可以为能够实现上述功能的服务器,所述用户设备200可以为乐视超级电视,也可以为手机、平板电脑等设备。 [0046] In Example 3, Example 2 except that the extraction device 100 may be capable of achieving the above functions of the server-based video recognition target object, the user device 200 may be a music as Couch, may be for mobile phones, tablet PCs and other devices. 在这种情况中,用户需要通过用户设备来与服务器互通,以实现实施例2的上述功能。 In this case, the user needs to communicate with the server by a user equipment, in order to achieve the above-described functions of the embodiment of Example 2.

[0047]举例来说,图2是根据本发明实施例的基于视频识别的目标对象提取系统的结构示意图,如图2所示,该系统包括:本发明实施例提供的基于视频识别的目标对象提取设备100;以及用户设备200,所述用户设备200与所述基于视频识别的目标对象提取设备100通过网络通信。 [0047] For example, FIG. 2 is a schematic structural diagram of a video based on the identified target object extraction system in accordance with an embodiment of the present invention, shown in Figure 2, the system comprising: a video-based recognition of the target object according to an embodiment of the present invention extraction device 100; and a user device 200, the user device 200 extracts the recognition target object based on the video device 100 via the communication network.

[0048]在这种情况中,所述用户感兴趣的目标对象可以包括能够购买到的商品,例如商场中出售的任何物品。 [0048] In this case, the target object of interest to the user may include the product can be purchased, for example, any article sold in shopping malls. 买手在开始一次直播购物前,可以提前列出可以购买的物品列表,并发送给直播购物的服务提供方,服务提供方可以预先在基于视频识别的目标对象提取设备100中存储好列表中的物品的超链接。 Buyers before the start of a live shopping list in advance a list of items can be purchased and sent to live shopping service provider, the service provider can pre-extraction equipment in good list of stores 100 based on the video identified the target object hyperlinks items. 之后,买手可以开始使用视频识别装置300进行视频的拍摄和识别,基于视频识别的目标对象提取设备100的接收模块10可以接收来自视频识别装置300的视频数据以及标识数据,即步骤Sll,其中所述视频数据为直播购物视频数据,所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象(即能够购买到的商品)。 Thereafter, the buyers can start using video recognition apparatus 300 imaging and identifying video 10 may receive video data and identification data from the video identification means 300 of the video identified target object extracting receiving module apparatus 100 based on, i.e. step Sll, wherein the video data is live video data shopping, the identification data including the target object (i.e., able to purchase the product) of interest to the user identified from the video data.

[0049]之后,超链接生成模块20可以根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接,例如根据标识数据“X商品”可以获得“X商品”对应的超链接,例如该商品的介绍页面,或者购买页面。 After [0049], the hyperlink target generation module 20 may obtain the object of interest based on the user identification information corresponding to the data related to the hyperlink, for example "X Goods" available "X product" according to the identification data corresponding to the super link, such as the product description page, or purchase page. 然后,超链接添加模块30可以将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示,将“X商品”的文字(“X商品”)添加到视频播放页面的一个区域中(例如视频播放区域的左边栏或者右边栏等)。 Then, adding hyperlinks module 30 may add the identification data and hyperlinks to the video player page is displayed together with the video data, the "X goods" character ( "X Goods") added to the video player page in a region (such as video playback area on the left column or right column, etc.). 可选地,超链接添加模块30还可以按照所述视频的播放时间滚动显示所述标识数据和所述超链接。 Alternatively, the hyperlink adding module 30 also follow the playback time of the video data and the identification scroll display the hyperlink. 例如,在视频播放区域的左边栏或者右边栏进行滚动显示。 For example, to scroll the display in the video playback area on the left column or the right column. 之后,基于视频识别的目标对象提取设备100可以将所述视频播放页面传送到所述用户设备200进行显示,即步骤S12。 Thereafter, the video recognition target object extracting device 100 may be based on the video player page is transmitted to the user equipment 200 for display, i.e., step S12.

[0050]采用这样的实施例3,用户观看直播的视频中可以通过点击在视频播放页面上的特定区域中所列出的用户感兴趣的目标对象而超链接到与该信息相关的页面,进一步了解该信息,例如点击“X商品”进入到其购买页面进行购买,实现直播购物,在享受便捷购物的同时,减少用户设备的负荷、复杂性、或成本。 [0050] The target object of interest using such an embodiment, the user 3, the user can watch live video listed by clicking on a specific area on the video player and the page associated with the hyperlink to a page of information, further understand the information, for example, click the "X product" to enter its purchase page to make a purchase, implement live shopping, enjoy the convenience of shopping at the same time, reduce the load on the user equipment, complexity, or cost.

[0051]图3是根据本发明实施例的基于视频识别的目标对象提取方法的示例流程图,如图3所示,该方法可以包括以下步骤: [0051] FIG. 3 is an example of the extraction method based video recognition target object of the present invention, an embodiment of the flowchart shown in Figure 3, the method may comprise the steps of:

[0052]步骤1001,接收来自视频识别装置的视频数据以及标识数据,其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象; [0052] Step 1001 receives the video data from the video data and the identification recognition means, wherein said identification data comprises a target object of interest to the user identified from the video data;

[0053]步骤1002,根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接;以及 [0053] Step 1002, the target object of interest to obtain the user data according to the identification information corresponding hyperlink; and

[0054]步骤1003,将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示。 [0054] Step 1003, adding the identification data and the video playback hyperlink to a page displayed together with the video data.

[0055] 可选地,所述用户感兴趣的目标对象包括能够购买到的商品。 [0055] Alternatively, the target objects of interest to the user comprises the product can be purchased.

[0056]可选地,所述视频数据为直播购物视频数据。 [0056] Alternatively, the video data is live video data cart.

[0057] 可选地,该方法还包括:按照所述视频的播放时间滚动显示所述标识数据和所述超链接。 [0057] Optionally, the method further comprising: according to playback time of the video data and the identification scroll display the hyperlink.

[0058]应当理解的是,上述基于视频识别的目标对象提取方法的各个具体实施例,均已在示例基于视频识别的目标对象提取设备以及系统的实施例中做了详细地说明(如上所述),在此不再赘述。 [0058] It should be appreciated that the above-described embodiments based on various specific extraction method of video recognition target object, based on the video have been identified target object extracting embodiment of the apparatus and system made in the example described in detail (as described above ), not discussed here. 并且,本领域技术人员可以根据本发明实施例的公开选择上述各种实施例中的任一者,或者选择上述各种实施例的组合来配置基于视频识别的目标对象提取设备以及系统,并且其他的替换实施例也落入本发明实施例的保护范围。 Further, the skilled artisan may be selected in accordance with the disclosure of the above-described embodiment of the invention in various embodiments any one embodiment or example of selecting the combinations of the various embodiments to configure the extraction devices and systems based on the identified video audiences, and other alternative embodiments are also within the scope of embodiments of the present invention.

[0059]本发明实施例提供的基于视频识别的目标对象提取方法、设备以及系统可以以硬件或软件的形式应用于需要对视频进行目标对象提取的任何适当的场景中,例如电视机、手机、平板电脑等,在视频播放同时显示其中用户感兴趣的目标对象的相关信息和超链接,通过点击该超链接用户可以方便地、快速地对感兴趣的目标对象进行进一步地了解或者选择购物等,在满足用户需求的同时大大节约了用户的时间,提供了一种更省时、便捷的认知或购物方式。 [0059] The embodiments of the present invention provides a video recognition target object extraction method, apparatus and system may be applied in the form of hardware or software required for any suitable video scene extraction target object, for example a television, a mobile phone based on tablet PC, etc., and displays information and hyperlinks target object in which the user is interested in video player, you can easily and quickly to the target object of interest for further understanding of the user by clicking on the hyperlink or select shopping, at the same time meet the needs of users, it saves users time, provides a time-saving and convenient way to shop or cognitive.

[0060]以上结合附图详细描述了本发明例的优选实施方式,但是,本发明实施例并不限于上述实施方式中的具体细节,在本发明实施例的技术构思范围内,可以对本发明实施例的技术方案进行多种简单变型,这些简单变型均属于本发明实施例的保护范围。 [0060] The above detailed description of preferred embodiments of the present invention, the drawings embodiment, however, embodiments of the present invention is not limited to the specific details of the above embodiment, the technical concept of the scope of the embodiments in the present invention, embodiments of the present invention various technical solutions of simple modifications, these simple modifications belong to the scope of embodiments of the present invention.

[0061]另外需要说明的是,在上述具体实施方式中所描述的各个具体技术特征,在不矛盾的情况下,可以通过任何合适的方式进行组合。 [0061] Further to be noted that, in various specific features of the above-described specific embodiment described, without conflict, may be combined in any suitable manner. 为了避免不必要的重复,本发明实施例对各种可能的组合方式不再另行说明。 To avoid unnecessary repetition, embodiments of the present invention to various possible combinations detailed description is omitted.

[0062]本领域技术人员可以理解实现上述实施例方法、设备、系统中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序存储在一个存储介质中,包括若干指令用以使得一个(可以是单片机,芯片等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。 [0062] Those skilled in the art may understand that the above-described embodiments of the method, apparatus, system or part of the steps may all be relevant hardware instructed by a program, the program is stored in a storage medium and includes several instructions to such that one (may be a single-chip, chips, etc.) or (processor) to perform all or a part of steps of the various embodiments of the methods described in the present application. 而前述的存储介质包括:U盘、移动硬盘、只读存储器(R0M,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。 The storage medium includes: U disk, mobile hard disk, a read-only memory (R0M, Read-Only Memory), a random access various memories (RAM, Random Access Memory), a magnetic disk, or an optical medium can store program codes .

[0063]此外,本发明实施例的各种不同的实施方式之间也可以进行任意组合,只要其不违背本发明实施例的思想,其同样应当视为本发明实施例所公开的内容。 [0063] Further, among various embodiments of the present invention by way of example may be arbitrarily combined as long as it is not contrary to the idea of ​​the embodiment of the present invention, which should also be considered as embodiments of the present invention, the contents disclosed embodiments.

Claims (10)

1.一种基于视频识别的目标对象提取方法,其特征在于,该方法包括: 接收来自视频识别装置的视频数据以及标识数据,其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象; 根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接;以及将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示。 CLAIMS 1. A video-based extraction method of identifying a target object, characterized in that, the method comprising: receiving video data from the video data and the identification recognition means, wherein said identification data includes a user identified from the video data of interest audience; obtaining said target object of interest based on the user identification information corresponding to data associated hyperlink; and the identification data added to the hyperlink and the video player page is displayed together with the video data.
2.根据权利要求1所述的方法,其特征在于,所述用户感兴趣的目标对象包括能够购买到的商品。 2. The method according to claim 1, characterized in that the target object of interest to the user comprises the product can be purchased.
3.根据权利要求2所述的方法,其特征在于,所述视频数据为直播购物视频数据。 3. The method according to claim 2, wherein said video data is live video data cart.
4.根据权利要求3所述的方法,其特征在于,该方法还包括:按照所述视频的播放时间滚动显示所述标识数据和所述超链接。 4. The method according to claim 3, characterized in that, the method further comprising: according to playback time of the video data and the identification scroll display the hyperlink.
5.一种基于视频识别的目标对象提取设备,其特征在于,该设备包括: 接收模块,用于接收来自视频识别装置的视频数据以及标识数据,其中所述标识数据包括从视频数据中识别出的用户感兴趣的目标对象; 超链接生成模块,用于根据所述标识数据获得所述用户感兴趣的目标对象的相关信息对应的超链接;以及超链接添加模块,用于将所述标识数据和所述超链接添加到视频播放页面中与所述视频数据一起显示。 A video recognition based on the extracted target object, characterized in that, the apparatus comprising: a receiving module, configured to receive video data from the video data and the identification recognition means, wherein said identifying comprises identifying data from the video data audience interest to the user; generation module hyperlink, the hyperlink for obtaining related information corresponding to said target object of interest according to the user identification data; and adding hyperlinks module, the identification data for and add the hyperlink to the video playback page displayed together with the video data.
6.根据权利要求5所述的设备,其特征在于,所述用户感兴趣的目标对象包括能够购买到的商品。 6. The apparatus as claimed in claim 5, wherein said target object of interest to a user to purchase merchandise comprises.
7.根据权利要求6所述的设备,其特征在于,所述视频数据为直播购物视频数据。 7. The apparatus according to claim 6, wherein said video data is live video data cart.
8.根据权利要求7所述的设备,其特征在于,所述超链接添加模块还用于:按照所述视频的播放时间滚动显示所述标识数据和所述超链接。 8. The apparatus of claim 7, wherein said module is further used for adding hyperlinks: Following the play time of the video data and the identification scroll display the hyperlink.
9.根据权利要求8所述的设备,其特征在于,所述基于视频识别的目标对象提取设备为乐视超级电视。 9. The apparatus of claim 8, wherein the video recognition target object based on the extracted music as Super TV equipment.
10.一种基于视频识别的目标对象提取系统,其特征在于,该系统包括:根据权利要求5-8中任一项权利要求所述的基于视频识别的目标对象提取设备;以及用户设备,所述用户设备与所述基于视频识别的目标对象提取设备通过网络通信,所述基于视频识别的目标对象提取设备将所述视频播放页面传送到所述用户设备进行显示。 A video recognition target object based extraction system, characterized in that the system comprising: according to any one of claims 5-8 claims claim extracting video recognition target object based on the device; and a user equipment, the said user equipment and the target object based on the identified video extracting device via a network communication based on the identified target object extracting video device, the video player page to be displayed to the user equipment.
CN201610621286.4A 2016-08-01 2016-08-01 Target object extraction method, target object extraction equipment and target object extraction system based on video identification CN106254925A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610621286.4A CN106254925A (en) 2016-08-01 2016-08-01 Target object extraction method, target object extraction equipment and target object extraction system based on video identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610621286.4A CN106254925A (en) 2016-08-01 2016-08-01 Target object extraction method, target object extraction equipment and target object extraction system based on video identification

Publications (1)

Publication Number Publication Date
CN106254925A true CN106254925A (en) 2016-12-21

Family

ID=57606788

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610621286.4A CN106254925A (en) 2016-08-01 2016-08-01 Target object extraction method, target object extraction equipment and target object extraction system based on video identification

Country Status (1)

Country Link
CN (1) CN106254925A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106937172A (en) * 2017-03-23 2017-07-07 百度在线网络技术(北京)有限公司 Interaction method and device based on artificial intelligence in video playing process

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101753913A (en) * 2008-12-17 2010-06-23 华为技术有限公司 Method and device for inserting hyperlinks in video, and processor
US20110258057A1 (en) * 2000-11-06 2011-10-20 Boncyk Wayne C Image Capture and Identification System and Process
CN102855273A (en) * 2012-07-16 2013-01-02 宇龙计算机通信科技(深圳)有限公司 Terminal and information acquisition method
CN102855298A (en) * 2012-08-16 2013-01-02 熊兵 Image retrieval method and system
CN103297840A (en) * 2012-03-01 2013-09-11 阿里巴巴集团控股有限公司 Additional information display method and system based on video moving focus

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110258057A1 (en) * 2000-11-06 2011-10-20 Boncyk Wayne C Image Capture and Identification System and Process
CN101753913A (en) * 2008-12-17 2010-06-23 华为技术有限公司 Method and device for inserting hyperlinks in video, and processor
CN103297840A (en) * 2012-03-01 2013-09-11 阿里巴巴集团控股有限公司 Additional information display method and system based on video moving focus
CN102855273A (en) * 2012-07-16 2013-01-02 宇龙计算机通信科技(深圳)有限公司 Terminal and information acquisition method
CN102855298A (en) * 2012-08-16 2013-01-02 熊兵 Image retrieval method and system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106937172A (en) * 2017-03-23 2017-07-07 百度在线网络技术(北京)有限公司 Interaction method and device based on artificial intelligence in video playing process

Similar Documents

Publication Publication Date Title
Johnson Branding television
JP4501209B2 (en) The information processing apparatus, information processing method and remote control commander
US9280515B2 (en) Provision of alternate content in response to QR code
CN103997691B (en) Method and system for interactive video
KR101478275B1 (en) System and/or method for distributing media content
US8209223B2 (en) Video object tag creation and processing
JP3633452B2 (en) 3D advertisement system and method and recording medium in motion in the three-dimensional virtual space
US20110125582A1 (en) Maintaining Advertisements
US9008491B2 (en) Snapshot feature for tagged video
US8560405B1 (en) Method, system, and computer readable medium for displaying items for sale in uploaded video content
EP2045730A1 (en) Methods and apparatuses for an engine that pairs advertisements with video files
US20080052750A1 (en) Direct-point on-demand information exchanges
KR101432457B1 (en) Content capture device and methods for automatically tagging content
US20080288600A1 (en) Apparatus and method for providing access to associated data related to primary media data via email
CN102244807B (en) Adaptive video zoom
US20080089551A1 (en) Interactive TV data track synchronization system and method
JP2014524062A (en) Extension of the live view
KR20140108494A (en) Remote device for a multimedia commerce service and method for the same
EP2462494A1 (en) Ecosystem for smart content tagging and interaction
US20130282532A1 (en) Systems and methods for presentation and analysis of media content
KR20140004750A (en) Creation of video bookmarks via scripted interactivity in advanced digital television
CN103402118B (en) A media program interaction method and system
CN102598109A (en) Multiple-screen interactive screen architecture
US20140236726A1 (en) Transference of data associated with a product and/or product package
KR20140121400A (en) Method and system for providing a graphical representation on a second screen of social messages related to content on a first screen

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination