WO2015192585A1 - 视频中广告的播放方法和装置 - Google Patents

视频中广告的播放方法和装置 Download PDF

Info

Publication number
WO2015192585A1
WO2015192585A1 PCT/CN2014/090573 CN2014090573W WO2015192585A1 WO 2015192585 A1 WO2015192585 A1 WO 2015192585A1 CN 2014090573 W CN2014090573 W CN 2014090573W WO 2015192585 A1 WO2015192585 A1 WO 2015192585A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
advertisement
location
frame
planar structure
Prior art date
Application number
PCT/CN2014/090573
Other languages
English (en)
French (fr)
Inventor
李颖超
谢涛
Original Assignee
百度在线网络技术（北京）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 百度在线网络技术（北京）有限公司 filed Critical 百度在线网络技术（北京）有限公司
Publication of WO2015192585A1 publication Critical patent/WO2015192585A1/zh

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
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/458—Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations

Definitions

  • the present invention relates to the field of Internet communication technologies, and in particular, to a method and apparatus for playing advertisements in a video.
  • Network video is more and more popular among people.
  • Network video is an indispensable part of network application technology.
  • As a network video service provider it has become a mature mode to provide viewers with video program content by referring to the profit mode of TV programs, and at the same time, by broadcasting a certain number of online video advertisements to viewers.
  • online video advertisements are mainly delivered by using video buffer loading, playback pause, or drag and drop time intervals.
  • this method causes time waiting during video viewing, thereby damaging the user's viewing experience.
  • the present invention aims to solve at least one of the technical problems in the related art to some extent.
  • an object of the present invention is to provide a method for playing an advertisement in a video, which method can not affect the viewing experience of the user.
  • Another object of the present invention is to provide a playback apparatus for an advertisement in a video.
  • a third object of the present invention is to provide a storage medium.
  • a method for playing an advertisement in a video includes: acquiring a video to be played, and acquiring information of the advertisement, where the information of the advertisement includes: advertisement content and information of the first location, A location is the location of the advertisement in the video; the advertisement content is incorporated into the first location of the video and played such that the advertisement is located on an object having a planar structure of the video.
  • the method for playing an advertisement in a video by acquiring the information of the video and the advertisement to be played, integrating the advertisement content into the first position of the video, and playing, the advertisement can be integrated into the video.
  • the advertisement can be integrated into the video.
  • the user experience, and the present embodiment can improve the viewing experience of the user by making the advertisement located on the object having the planar structure of the video without affecting the normal presentation of the video content.
  • a playback device for an advertisement in a video includes: an acquisition module, configured to acquire a video to be played, and obtain information of an advertisement, where the advertisement information includes an advertisement content and a first location.
  • the first location is the location of the advertisement in the video;
  • the integration module is configured to integrate the advertisement content into the first position of the video and play it such that the advertisement is located on the object having the planar structure of the video.
  • the playback device for the advertisement in the video proposed by the embodiment of the second aspect of the present invention integrates the advertisement content into the first position of the video by playing the information of the video and the advertisement to be played, and plays the advertisement, thereby integrating the advertisement into the video.
  • the user does not need to wait while watching the video, and the user experience can be improved, and the present embodiment can prevent the video content from being affected by placing the advertisement on the object having the planar structure of the video. Normal presentation, improving the user's viewing experience.
  • a third aspect of the present invention provides a storage medium for storing an application for executing a playback method of an advertisement in a video as in the embodiment of the first aspect of the present invention at runtime.
  • FIG. 1 is a schematic flowchart of a method for playing an advertisement in a video according to an embodiment of the invention
  • FIG. 2 is a schematic flowchart of a method for playing an advertisement in a video according to another embodiment of the present invention
  • FIG. 3 is a schematic flowchart of offline processing of a video to obtain an advertisement bit according to an embodiment of the present invention
  • FIG. 4 is a schematic flow chart of acquiring a position of an object having a planar structure in a picture group according to an embodiment of the present invention
  • FIG. 5 is a schematic structural diagram of an apparatus for playing an advertisement in a video according to another embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of a device for playing an advertisement in a video according to another embodiment of the present invention.
  • FIG. 1 is a schematic flowchart of a method for playing an advertisement in a video according to an embodiment of the present invention, where the method includes:
  • S101 Acquire a video to be played, and obtain information of the advertisement, where the information of the advertisement includes: the advertisement content and the information of the first location.
  • the first location is the location of the advertisement on the video, for example, the location of the advertisement in each frame of the video, and specifically may be the location of the object having a planar structure in each scene in each frame of the image.
  • An advertisement is an advertisement inserted into a video, and the form in which the advertisement is presented in each frame of image includes, but is not limited to, a text, a pattern, and the like.
  • an advertisement slot suitable for placing an advertisement in a video to be played can be obtained by offline analysis and stored in a database, and then each time an advertisement needs to be placed in the video, the advertisement position in the database can be obtained.
  • the information selects the first location for ad serving.
  • S102 merging the advertisement content into the first position of the video, and playing, so that the advertisement is located on the object having the planar structure of the video.
  • the advertisement content may be incorporated into the first position of the video by an existing integration method, for example, by using 3D rendering, and played along with the video, so that the advertisement is located on the object having the planar structure of the video.
  • the advertisement content is integrated into the first position of the video, and played, the advertisement can be incorporated into the video, instead of displaying the advertisement in the video play interval, thereby eliminating the need for The user can wait for the video to be watched, and the user experience can be improved.
  • the advertisement by placing the advertisement on the object having the planar structure of the video, the normal presentation of the video content can be not affected, and the viewing experience of the user is improved.
  • FIG. 2 is a schematic flowchart of a method for playing an advertisement in a video according to another embodiment of the present invention.
  • the video that needs to be inserted into the advertisement may be processed offline and in real time. Processing, as shown in Figure 2, the method includes:
  • S201 Acquire a video to be played, and obtain information of the advertisement.
  • the video and the advertisement information to be played may be obtained from the server through a preset program such as a player, and the database for saving the video and the database for saving the advertisement may be included in the server, and the player may respectively correspond to
  • the database gets information about videos and ads.
  • the information of the advertisement includes the advertisement content and the information of the first location, where the first location is the location of the advertisement on the video, and the first location may be selected from the predetermined advertisement slots, and the specific selection principle may be set according to actual conditions.
  • the advertisement space is, for example, the space mapping information of the advertisement in each frame of the video, and the information of the video advertisement may further include the advertisement presentation time and the like.
  • the video to be played and the information obtained by the advertisement can be obtained online.
  • the video ad slot can be obtained offline.
  • the advertising space is the location of an object having a planar structure of the video.
  • the segment containing the non-critical flat region (such as a wall) in the video can be found by offline processing, and the segment is subjected to plane analysis and plane tracking to obtain the orientation information of the plane to obtain an appropriate advertising space.
  • the process of offline processing a video to obtain an advertisement slot may include:
  • S301 Decode the video to obtain a picture of each frame.
  • the video may be pre-processed, such as video decoding, etc., to obtain a picture of each frame.
  • S302 Perform down-sampling processing on each frame of the image to obtain a downsampled video.
  • each frame of the video may be downsampled to reduce the sampling frequency and resolution of each frame to reduce the complexity of subsequent calculations.
  • the downsampling process may be in the prior art, and there are multiple ways, and details are not described herein again.
  • S303 Perform scene segmentation on the downsampled video to obtain at least one group of pictures corresponding to each scene.
  • the processing can be independently and parallelly processed. Therefore, the downsampled video can be segmented, thereby improving the overall processing speed of the video and eliminating the error introduced by the multi-scene mixing processing. Instability.
  • the downsampled video can be divided into scene A and scene B, and then the two groups of pictures of the video frame picture of scene A and the video frame picture of scene B are obtained.
  • S304 In each group of pictures, obtain a position of an object having a planar structure in the picture group, and determine the position as an advertisement bit.
  • the position of an object having a planar structure in each group of pictures can be obtained by a technique such as planar structure object detection, image analysis, or the like.
  • the process of obtaining the position of an object having a planar structure in a picture group may include:
  • S401 Perform visual feature point extraction on each frame of the picture group.
  • the visual feature point may be a point where the ambient brightness changes sharply in the image or a point having a sufficiently large curvature on the image boundary curve.
  • S402 Extract a perspective rectangular plane structure in each frame of the picture by using a preset detection algorithm according to the extracted visual feature points.
  • the perspective rectangular planar structure includes a standard rectangular structure and a rectangular structure with a perspective projection deformation, such as a wall, a desktop, and a window. Wait.
  • the preset detection algorithm may be an existing image detection algorithm, or any algorithm that may appear in the future to implement the above detection function.
  • S403 performing homography information calculation on a perspective rectangular plane structure extracted in different frames, and determining whether the single-single is satisfied Sex.
  • the same plane satisfies the homography characteristics in the video planes under different viewing angles (The specific relationship between the projection maps from one plane to another), the visual feature points need to have scale invariance and illumination invariance, so the homoversal information can be calculated for the perspective rectangular plane structure extracted in different frames, and then The optimization method is used to solve the dominant homography matrix in the scene according to the extracted visual feature points and the calculated homography information, thereby judging whether the perspective rectangular planar structure satisfies the homography characteristic.
  • the homography characteristic if the homography characteristic is satisfied, information such as the plane position and direction of the perspective rectangular plane structure in the scene can be obtained, and then the position of the perspective rectangular plane structure extracted in different frames is checked and corrected, such as manual inspection and correction. To avoid misrecognition, and then determine the position of the perspective rectangular planar structure as the position of the object with a planar structure in the picture group in the corresponding frame.
  • the position of the object having the planar structure according to the extracted visual feature points can also be determined in other manners.
  • the extraction of visual feature points requires strict dependence on the texture features of the plane (texture features are an important visual feature for describing images)
  • texture features are an important visual feature for describing images
  • the stability of the visual feature points is also not guaranteed, and in view of the consideration of the rectangular planar structure in the scene, more information can be extracted in conjunction with image analysis techniques to determine the position of the object having the planar structure.
  • edge detection may be performed on different frame images first, and a straight line structure in the image is extracted by using a Hough transform to obtain a closed polygon region composed of straight lines, and the color and gray scale of the closed polygon region are analyzed.
  • the feature locates the real rectangular flat area, and finally calculates the position and orientation parameters of the plane in combination with multi-view geometry theory.
  • the information of the ad slot is stored in a database to select a first location from the ad slot.
  • the first location includes the location of the advertisement on each frame of the video.
  • S203 Integrate the obtained advertisement content into the first position of the decoded video, and play, so that the advertisement is located on an object having a planar structure of the video.
  • the video to be played may be decoded to obtain each frame of the video, and then the advertisement content is integrated into the corresponding position of each frame according to the information of the first position of the advertised advertisement space.
  • the fusion and presentation may be performed by an existing integration method, for example, by using 3D rendering; or the advertisement content may be incorporated into a corresponding position of each frame of the picture by any integration method that may occur in the future.
  • the video to be played is processed offline to obtain an advertisement slot, and the information of the advertisement slot is stored in a database, so as to select an appropriate first location to perform the advertisement. Delivery, through the detection algorithm and manual inspection, correction to determine the placement of the ad, the placement is more accurate.
  • the processing is divided into offline processing and real-time processing, which reduces the computational complexity and improves the processing efficiency. Make full use of the non-critical flat areas in the video, improve the efficiency of advertising, reduce the waiting during the video viewing process, does not affect the normal presentation of video content, and enhance the user experience.
  • the present invention also provides a playback apparatus for advertisements in video.
  • FIG. 5 is a schematic structural diagram of an apparatus for playing an advertisement in a video according to another embodiment of the present invention.
  • the device includes an acquisition module 100 and an integration module 200.
  • the obtaining module 100 is configured to acquire a video to be played, and obtain information of the advertisement, where the information of the advertisement includes the advertisement content and the information of the first location, where the first location is a location of the advertisement in the video.
  • the first location is the location of the advertisement on the video, for example, the location of the advertisement in each frame of the video, and specifically may be the location of the object having a planar structure in each scene in each frame of the image.
  • An advertisement is an advertisement inserted into a video, and the form in which the advertisement is presented in each frame of image includes, but is not limited to, a text, a pattern, and the like.
  • an advertisement slot suitable for placing an advertisement in a video to be played can be obtained by offline analysis and stored in a database, and then each time an advertisement needs to be placed in the video, the advertisement position in the database can be obtained.
  • the information selects the first location for ad serving.
  • the integration module 200 is configured to integrate the advertisement content into the first position of the video and play it such that the advertisement is located on an object having a planar structure of the video. More specifically, the integration module 200 can integrate the advertisement content into the first position of the video through an existing integration method, for example, by using 3D rendering, and play along with the video, so that the advertisement is located on the object having the planar structure of the video. .
  • the advertisement content is integrated into the first position of the video, and played, the advertisement can be incorporated into the video, instead of displaying the advertisement in the video play interval, thereby eliminating the need for The user can wait for the video to be watched, and the user experience can be improved.
  • the advertisement by placing the advertisement on the object having the planar structure of the video, the normal presentation of the video content can be not affected, and the viewing experience of the user is improved.
  • FIG. 6 is a schematic structural diagram of a device for playing an advertisement in a video according to another embodiment of the present invention.
  • the device includes: an obtaining module 100, an merging module 200, a processing sub-module 210, an merging sub-module 220, an offline processing module 300, a decoding sub-module 310, a down-sampling sub-module 320, a severing module 330, and obtaining Submodule 340, first extraction unit 341, second extraction unit 342, determination unit 343, determination unit 344, and storage Module 400.
  • the integration module 200 includes a processing sub-module 210 and an integration sub-module 220.
  • the offline processing module 300 includes a decoding sub-module 310, a down-sampling sub-module 320, a severing module 330, and an obtaining sub-module 340.
  • the obtaining sub-module 340 includes a first extraction.
  • the offline processing module 300 is configured to perform offline processing on the video to obtain an advertisement bit, where the advertisement bit is a position of an object having a planar structure of the video.
  • An ad slot is the location of an object with a planar structure of the video.
  • the offline processing module 300 can find a segment of the video containing a non-critical flat region (such as a wall) by offline processing, and perform plane analysis and plane tracking on the segment to obtain plane orientation information to obtain a suitable advertisement slot.
  • the offline processing module 300 can include:
  • the decoding sub-module 310 is configured to decode the video to obtain a picture of each frame. More specifically, the decoding sub-module 310 can pre-process the video, such as video decoding, etc., to obtain a picture of each frame.
  • the downsampling sub-module 320 is configured to perform down-sampling processing on each frame of the picture to obtain a downsampled video. More specifically, the downsampling sub-module 320 may perform down-sampling processing on each frame of the video to reduce the sampling frequency and resolution of each frame of the picture to reduce the complexity of subsequent calculations.
  • the downsampling process may be in the prior art, and there are multiple ways, and details are not described herein again.
  • the cut molecular module 330 is configured to perform scene segmentation on the downsampled video to obtain at least one set of picture groups respectively corresponding to each scene. Since the information difference between different scenes is large, the processing can be independently and parallelly processed in parallel. Therefore, the clipped molecular module 330 can perform scene segmentation on the downsampled video, thereby improving the overall processing speed of the video and eliminating multi-scene mixing. Handle introduced errors and instability. For example, the downsampled video can be divided into scene A and scene B, and then the two groups of pictures of the video frame picture of scene A and the video frame picture of scene B are obtained.
  • the obtaining sub-module 340 is configured to obtain, in each group of picture groups, a location of an object having a planar structure in the picture group, and determine the position as an advertisement bit. More specifically, the acquisition sub-module 340 can acquire the position of an object having a planar structure in each group of pictures by techniques such as planar structure object detection, image analysis, and the like.
  • the obtaining submodule 340 may further include:
  • the first extracting unit 341 is configured to perform visual feature point extraction on each frame of the picture group.
  • the visual feature point may be a point where the ambient brightness changes sharply in the image or a point having a sufficiently large curvature on the image boundary curve.
  • the second extracting unit 342 is configured to extract a perspective rectangular plane structure in each frame of the picture according to the extracted visual feature points. Since most of the rectangular structural objects in the video are not facing the lens in the normal direction, there are various perspective projection deformations, so the perspective rectangular planar structure includes a standard rectangular structure and a rectangular structure with a perspective projection deformation, such as a wall, a desktop, and a window. Wait.
  • the second extracting unit 342 can combine the multi-view geometry theory and the image analysis technology when extracting the perspective rectangular plane structure in each frame picture (the general use of the mathematical model and the image processing technology to analyze the underlying features and the upper structure, so that the extraction has certain Intelligent information) is implemented by a preset detection algorithm.
  • the preset detection algorithm can It is an existing image detection algorithm, and it can also be any algorithm that can appear in the future to implement the above detection function.
  • the judging unit 343 is configured to perform homography information calculation on the perspective rectangular plane structure extracted in different frames, and determine whether the homography characteristic is satisfied. More specifically, based on multi-view geometry theory (mainly studying three-dimensional reconstruction, that is, using geometric methods to recover three-dimensional objects through several two-dimensional images), the same plane satisfies the homography characteristics in the video planes under different viewing angles. (The specific relationship between the projection maps from one plane to another), the visual feature points need to have scale invariance and illumination invariance, so the homography information can be calculated for the perspective rectangular plane structure extracted in different frames. Then, the optimization method is used to solve the dominant homography matrix in the scene according to the extracted visual feature points and the calculated homography information, thereby judging whether the perspective rectangular planar structure satisfies the homography characteristic.
  • multi-view geometry theory mainly studying three-dimensional reconstruction, that is, using geometric methods to recover three-dimensional objects through several two-dimensional images
  • the same plane satisfies the homography characteristics in the video planes under different viewing angles
  • the determining unit 344 is configured to determine, when a single characteristic is satisfied, the position of the object having the planar structure in the group of pictures according to the position of the perspective rectangular plane structure extracted in the different frames. More specifically, if the homography characteristic is satisfied, the determining unit 344 can obtain information such as the plane position and direction of the perspective rectangular plane structure in the scene, and then check and correct the position of the perspective rectangular plane structure extracted in different frames, such as Manual inspection and correction to avoid misrecognition, and then determine the position of the perspective rectangular planar structure as the position of the object with a planar structure in the picture group in the corresponding frame.
  • the position of the object having the planar structure according to the extracted visual feature points can also be determined in other manners.
  • the extraction of visual feature points requires strict dependence on the texture features of the plane (texture features are an important visual feature for describing images)
  • texture features are an important visual feature for describing images
  • the stability of the visual feature points is also not guaranteed, and in view of the consideration of the rectangular planar structure in the scene, more information can be extracted in conjunction with image analysis techniques to determine the position of the object having the planar structure.
  • edge detection may be performed on different frame images first, and a straight line structure in the image is extracted by using a Hough transform to obtain a closed polygon region composed of straight lines, and the color and gray scale of the closed polygon region are analyzed.
  • the feature locates the real rectangular flat area, and finally calculates the position and orientation parameters of the plane in combination with multi-view geometry theory.
  • the storage module 400 After determining the ad slot, the storage module 400 stores the information of the ad slot into a database to select a first location from the ad slots.
  • the first location includes the location of the advertisement on each frame of the video. After storing the information of the advertisement slot in the database, whenever the server receives the advertisement request, the information of the advertisement slot in the video is obtained according to the video query database to be played, so that the first location is selected from the advertisement slot.
  • Ad serving the information of the advertisement slot in the video is obtained according to the video query database to be played, so that the first location is selected from the advertisement slot.
  • the integration module 200 includes:
  • the processing sub-module 210 is configured to decode the video to obtain a picture of each frame.
  • the integration sub-module 220 is configured to integrate the advertisement content into the corresponding position of each frame of the picture according to the information of the first location. At the office. The integration sub-module 220 can integrate the advertisement content into the corresponding position of each frame of the picture according to the information of the first position of the advertised advertisement space. In a specific embodiment of the present invention, the fusion and presentation may be performed by an existing integration method, for example, by using 3D rendering; or the advertisement content may be integrated into each frame by any integration method that may occur in the future. At the corresponding location.
  • the video to be played is processed offline to obtain an advertisement slot, and the information of the advertisement slot is stored in a database, so as to select an appropriate first location to perform the advertisement. Delivery, through the detection algorithm and manual inspection, correction to determine the placement of the ad, the placement is more accurate.
  • the processing is divided into offline processing and real-time processing, which reduces the computational complexity and improves the processing efficiency. Make full use of the non-critical flat areas in the video, improve the efficiency of advertising, reduce the waiting during the video viewing process, does not affect the normal presentation of video content, and enhance the user experience.
  • the present invention also proposes a storage medium.
  • the storage medium of the embodiment of the present invention is configured to store an application, and the application is used to execute a play method of an advertisement in a video according to an embodiment of the present invention at runtime.
  • portions of the invention may be implemented in hardware, software, firmware or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals. Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated module is It can be implemented in the form of hardware or in the form of a software function module.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

本发明提出一种视频中广告的播放方法和装置，该视频中广告的播放方法包括：获取要播放的视频，以及获取广告的信息，广告的信息包括：广告内容以及第一位置的信息，第一位置是广告在视频中的位置；将广告内容融入到视频的第一位置处，并进行播放，使得广告位于视频的具有平面结构的物体上。该方法能够降低数据量，并提高数据保密性。本发明提出的视频中广告的播放方法，通过使广告位于视频的具有平面结构的物体上，可以不影响视频内容的正常呈现，提高了用户的观看体验。

Description

视频中广告的播放方法和装置
相关申请的交叉引用
本申请要求百度在线网络技术(北京)有限公司于2014年06月16日提交的、发明名称为“视频中广告的播放方法和装置”的、中国专利申请号“201410268322.4”的优先权。
技术领域
本发明涉及互联网通信技术领域，尤其涉及一种视频中广告的播放方法和装置。
背景技术
随着视频点播直播技术的发展，网络视频越来越受到人们的青睐，网络视频是网络应用技术中不可或缺的重要组成部分。作为网络视频服务商，参照电视节目的盈利方式，为观众提供视频节目内容，同时通过向观众播放一定数量的网络视频广告，已经成为一种成熟的模式。
目前网络视频广告的投放方式主要是利用影片缓冲加载、播放暂停或拖拽时间间隙完成广告播放，但是，这种方式会造成视频观看过程中的时间等待，从而伤害了用户的观看体验。
发明内容
本发明旨在至少在一定程度上解决相关技术中的技术问题之一。
为此，本发明的一个目的在于提出一种视频中广告的播放方法，该方法可以不影响用户的观看体验。
本发明的另一个目的在于提出一种视频中广告的播放装置。
本发明的第三个目的在于提出一种存储介质。
为达到上述目的，本发明第一方面实施例提出的视频中广告的播放方法，包括：获取要播放的视频，以及获取广告的信息，广告的信息包括：广告内容以及第一位置的信息，第一位置是广告在视频中的位置；将广告内容融入到视频的第一位置处，并进行播放，使得广告位于视频的具有平面结构的物体上。
本发明第一方面实施例提出的视频中广告的播放方法，通过获取要播放的视频和广告的信息，将广告内容融入到视频的第一位置处，并进行播放，可以将广告融入到视频中，而不是在视频播放间隙展现广告，从而不需要用户观看视频过程中进行等待，可以提升用 户体验，并且，本实施例通过使广告位于视频的具有平面结构的物体上，可以不影响视频内容的正常呈现，提高了用户的观看体验。
为达到上述目的，本发明第二方面实施例提出的视频中广告的播放装置，包括：获取模块，用于获取要播放的视频，以及获取广告的信息，广告的信息包括广告内容以及第一位置的信息，第一位置是广告在视频中的位置；融入模块，用于将广告内容融入到视频的第一位置处，并进行播放，使得广告位于视频的具有平面结构的物体上。
本发明第二方面实施例提出的视频中广告的播放装置，通过获取要播放的视频和广告的信息，将广告内容融入到视频的第一位置处，并进行播放，可以将广告融入到视频中，而不是在视频播放间隙展现广告，从而不需要用户观看视频过程中进行等待，可以提升用户体验，并且，本实施例通过使广告位于视频的具有平面结构的物体上，可以不影响视频内容的正常呈现，提高了用户的观看体验。
本发明第三方面实施例提供了一种存储介质，用于存储应用程序，所述应用程序用于在运行时执行如本发明第一方面实施例的视频中广告的播放方法。
本发明附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。
附图说明
本发明上述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解，其中：
图1是根据本发明一实施例提出的视频中广告的播放方法的流程示意图；
图2是根据本发明另一实施例提出的视频中广告的播放方法的流程示意图；
图3是本发明一实施例的对视频进行离线处理获取广告位的流程示意图；
图4是本发明一实施例的获取图片组中具有平面结构的物体的位置的流程示意图；
图5是本发明另一实施例的视频中广告的播放装置的结构示意图；
图6是本发明另一实施例的视频中广告的播放装置的结构示意图。
具体实施方式
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本发明，而不能理解为对本发明的限制。相反，本发明的实施例包括落入所附加权利要求书的精神和内涵范围内的所有变化、修改和等同物。
下面参考附图描述根据本发明实施例的视频中广告的播放方法和装置。
图1是本发明一实施例提出的视频中广告的播放方法的流程示意图，该方法包括：
S101：获取要播放的视频，以及获取广告的信息，广告的信息包括：广告内容以及第一位置的信息。
其中，第一位置是广告在视频上的位置，例如，广告在视频中每帧图像中的位置，具体可以是每帧图像中每个场景中具有平面结构的物体所在的位置等。
广告是指插入到视频中的广告，广告呈现在每帧图像中的形式包括但不限于文字、图案等。
本发明实施例中，可通过离线分析获取要播放的视频中适于投放广告的广告位并存储到数据库中，之后在每次需要在该视频中投放广告时，即可根据数据库中的广告位信息选择第一位置进行广告投放。具体内容将在后续实施例中详细说明。
S102：将广告内容融入到视频的第一位置处，并进行播放，使得广告位于视频的具有平面结构的物体上。
具体地，可以通过现有的融入方法，例如采用3D渲染等方式将广告内容融入到视频的第一位置处，并随视频一起播放，使得广告位于视频的具有平面结构的物体上。
具体的融入方法还有多种，在此不再一一列举。
本实施例通过获取要播放的视频和广告的信息，将广告内容融入到视频的第一位置处，并进行播放，可以将广告融入到视频中，而不是在视频播放间隙展现广告，从而不需要用户观看视频过程中进行等待，可以提升用户体验，并且，本实施例通过使广告位于视频的具有平面结构的物体上，可以不影响视频内容的正常呈现，提高了用户的观看体验。
图2是根据本发明另一实施例提出的视频中广告的播放方法的流程示意图，为了进一步提升用户的观看体验，减少广告处理的复杂度，可对需要插入广告的视频分别进行离线处理和实时处理，如图2所示，该方法包括：
S201：获取要播放的视频，以及获取广告的信息。
在视频播放过程中，可通过预设的程序如播放器从服务端获取要播放的视频和广告的信息，在服务端中可以包括保存视频的数据库和保存广告的数据库，播放器可以分别从相应的数据库获取视频和广告的信息。其中，广告的信息包括广告内容，以及第一位置的信息，第一位置是广告在视频上的位置，第一位置可以从预先确定的广告位中选取，具体选取的原则可以根据实际情况设置。广告位例如广告在视频的每帧图像中的空间映射信息，另外，视频广告的信息还可以包括广告展现时间等。
具体的，获取要播放的视频，以及获取广告的信息可以采用在线方式获取。
其中，视频的广告位可以采用离线方式获取。
广告位是所述视频的具有平面结构的物体的位置。
具体地，可通过离线处理找到视频中含有非关键平坦区域(如墙体)的片段，并对该片段进行平面分析和平面跟踪，得出平面的方位信息，以获取合适的广告位。
参见图3，对视频进行离线处理获取广告位的过程可以包括：
S301：对视频进行解码，得到每一帧图片。
具体地，可以对视频进行预处理，例如视频解码等，以得到每一帧图片。
S302：对每一帧图片进行降采样处理，得到降采样后的视频。
具体地，可对视频的每一帧图片进行降采样处理，降低每一帧图片的采样频率和分辨率，以降低后续计算的复杂度。其中，降采样处理过程可以为现有技术，方式有多种，在此不再赘述。
S303：对降采样后的视频进行场景切分，得到至少一组的分别与每个场景对应的图片组。
由于不同场景之间的信息差异较大，在处理上完全可以独立并行处理，因此可以对降采样后的视频进行场景切分，从而提高视频整体处理速度，并消除多场景混合处理引入的误差和不稳定性。例如，可将降采样后的视频切分为场景A和场景B，然后获取场景A的视频帧图片以及场景B的视频帧图片这两组图片组。
S304：在每组图片组中，获取图片组中具有平面结构的物体的位置，并确定为广告位。
具体地，可通过平面结构物体检测、图像分析等技术获取每组图片组中具有平面结构的物体的位置。
参见图4，获取图片组中具有平面结构的物体的位置的过程可以包括：
S401：对图片组中的每帧图片进行视觉特征点提取。
其中，视觉特征点可以为图像中周围亮度变化剧烈的点或者图像边界曲线上具有足够大曲率的点。
S402：根据提取到的视觉特征点，通过预设的检测算法提取每帧图片中的透视矩形平面结构。
由于通常情况下视频中大部分的矩形结构物体并非正面朝向镜头，存在各种透视投影变形，因此透视矩形平面结构包括标准的矩形结构以及透视投影变形后的矩形结构，例如墙体、桌面、窗子等。
在提取每帧图片中的透视矩形平面结构时，可结合多视图几何理论和图像分析技术(一般利用数学模型并结合图像处理技术来分析底层特征和上层结构，从而提取具有一定智能性的信息)通过预设的检测算法来实现。其中，预设的检测算法可以是现有的图像检测算法，也可以是未来可能出现的任何能实现上述检测功能的算法。
S403：对不同帧中提取的透视矩形平面结构进行单应信息计算，判断是否满足单应特 性。
具体地，基于多视图几何理论(主要研究三维重构，即用几何的方法，通过若干幅二维图像，来恢复三维物体)，同一平面在不同视角下的视频面内若满足单应特性(从一个平面到另一个平面的投影映射之间的特定关系)，则视觉特征点需具有尺度不变性和光照不变性，因此可对不同帧中提取的透视矩形平面结构进行单应信息计算，然后利用最优化方法根据提取到的视觉特征点和计算得到的单应信息求解场景中的优势单应矩阵，从而判断该透视矩形平面结构是否满足单应特性。
S404：如果满足单应特性，根据不同帧中提取的透视矩形平面结构所在的位置确定图片组中具有平面结构的物体的位置。
具体地，如果满足单应特性，可求出场景中透视矩形平面结构的平面位置和方向等信息，然后对不同帧中提取的透视矩形平面结构所在的位置进行检查和校正，比如人工检查和校正，以避免误识别，然后将该透视矩形平面结构所在的位置确定为图片组中具有平面结构的物体在相应帧中的位置。
需要说明的是，本实施例以根据提取到的视觉特征点确定具有平面结构的物体的位置为例，可以理解的是，也可以采用其他方式确定具有平面结构的物体的位置。例如，由于视觉特征点的提取需要严格依赖平面的纹理特征(纹理特征是描述图像的一种重要的视觉特征)，在纹理特征信息不丰富的情况下，不能保证提取到足够数量的特征点，也不能保证视觉特征点的稳定性，且鉴于着重考虑场景中的矩形平面结构，可结合图像分析技术提取更多信息，以确定具有平面结构的物体的位置。在本发明的一个实施例中，可以首先对不同帧图像进行边缘检测，利用霍夫变换提取图像中的直线结构，获得直线所组成的封闭多边形区域，并通过分析封闭多边形区域的颜色和灰度特征定位真实的矩形平坦区域，最终结合多视图几何理论计算出平面的位置和方向参数。
在确定广告位后，将所述广告位的信息存储到数据库中，以便从广告位中选择第一位置。在本发明的一个实施例中，第一位置包括广告在视频的每一帧图片上的位置。将所述广告位的信息存储到数据库中之后，每当服务器接收到广告请求时，都会根据要播放的视频查询数据库，获取该视频中的广告位的信息，以便从广告位中选择第一位置进行广告投放。
S202：对获取的视频进行解码。
S203：将获取的广告内容融入到解码后的视频的第一位置处，并进行播放，使得广告位于视频的具有平面结构的物体上。
具体地，可对要播放的视频进行解码，得到该视频的每一帧图片，然后根据查询到的广告位的第一位置的信息，将广告内容融入到每一帧图片的相应位置处。在本发明的具体 实施例中，可以通过现有的融入方法，例如采用3D渲染等方式进行融合和展现；也可以通过未来可能出现的任何融入方法将所述广告内容融入到每一帧图片的相应位置处。
本实施例通过获取要播放的视频，以及获取视频广告的信息，对要播放的视频进行离线处理获取广告位，并将广告位的信息存储到数据库中，以选取合适的第一位置对广告进行投放，通过检测算法和人工检查、校正确定广告投放位置，投放位置更加准确。处理过程分为离线处理和实时处理，降低了计算复杂度，提高了处理效率。充分利用了视频中的非关键平坦区域，提高了广告投放效率，减少了视频观看过程中的等待，不影响视频内容的正常呈现，提升了用户体验。
为了实现上述实施例，本发明还提出一种视频中广告的播放装置。
图5是本发明另一实施例的视频中广告的播放装置的结构示意图。
如图5所示，该装置包括：获取模块100和融入模块200。
具体地，获取模块100用于获取要播放的视频，以及获取广告的信息，广告的信息包括广告内容以及第一位置的信息，第一位置是广告在视频中的位置。其中，第一位置是广告在视频上的位置，例如，广告在视频中每帧图像中的位置，具体可以是每帧图像中每个场景中具有平面结构的物体所在的位置等。广告是指插入到视频中的广告，广告呈现在每帧图像中的形式包括但不限于文字、图案等。
本发明实施例中，可通过离线分析获取要播放的视频中适于投放广告的广告位并存储到数据库中，之后在每次需要在该视频中投放广告时，即可根据数据库中的广告位信息选择第一位置进行广告投放。具体内容将在后续实施例中详细说明。
融入模块200用于将广告内容融入到视频的第一位置处，并进行播放，使得广告位于视频的具有平面结构的物体上。更具体地，融入模块200可以通过现有的融入方法，例如采用3D渲染等方式将广告内容融入到视频的第一位置处，并随视频一起播放，使得广告位于视频的具有平面结构的物体上。
具体的融入方法还有多种，在此不再一一列举。
本实施例通过获取要播放的视频和广告的信息，将广告内容融入到视频的第一位置处，并进行播放，可以将广告融入到视频中，而不是在视频播放间隙展现广告，从而不需要用户观看视频过程中进行等待，可以提升用户体验，并且，本实施例通过使广告位于视频的具有平面结构的物体上，可以不影响视频内容的正常呈现，提高了用户的观看体验。
图6是本发明另一实施例的视频中广告的播放装置的结构示意图。
如图6所示，该装置包括：获取模块100、融入模块200、处理子模块210、融入子模块220、离线处理模块300、解码子模块310、降采样子模块320、切分子模块330、获取子模块340、第一提取单元341、第二提取单元342、判断单元343、确定单元344和存储 模块400。其中，融入模块200包括处理子模块210和融入子模块220；离线处理模块300包括解码子模块310、降采样子模块320、切分子模块330和获取子模块340；获取子模块340包括第一提取单元341、第二提取单元342、判断单元343和确定单元344。
具体地，离线处理模块300用于对视频进行离线处理获取广告位，广告位是视频的具有平面结构的物体的位置。广告位是视频的具有平面结构的物体的位置。离线处理模块300可通过离线处理找到视频中含有非关键平坦区域(如墙体)的片段，并对该片段进行平面分析和平面跟踪，得出平面的方位信息，以获取合适的广告位。
进一步地，离线处理模块300可以包括：
解码子模块310用于对视频进行解码，得到每一帧图片。更具体地，解码子模块310可以对视频进行预处理，例如视频解码等，以得到每一帧图片。
降采样子模块320用于对每一帧图片进行降采样处理，得到降采样后的视频。更具体地，降采样子模块320可对视频的每一帧图片进行降采样处理，降低每一帧图片的采样频率和分辨率，以降低后续计算的复杂度。其中，降采样处理过程可以为现有技术，方式有多种，在此不再赘述。
切分子模块330用于对降采样后的视频进行场景切分，得到至少一组的分别与每个场景对应的图片组。由于不同场景之间的信息差异较大，在处理上完全可以独立并行处理，因此可以通过切分子模块330对降采样后的视频进行场景切分，从而提高视频整体处理速度，并消除多场景混合处理引入的误差和不稳定性。例如，可将降采样后的视频切分为场景A和场景B，然后获取场景A的视频帧图片以及场景B的视频帧图片这两组图片组。
获取子模块340用于在每组图片组中，获取图片组中具有平面结构的物体的位置，并确定为广告位。更具体地，获取子模块340可通过平面结构物体检测、图像分析等技术获取每组图片组中具有平面结构的物体的位置。
进一步地，获取子模块340还可以包括：
第一提取单元341用于对图片组中的每帧图片进行视觉特征点提取。其中，视觉特征点可以为图像中周围亮度变化剧烈的点或者图像边界曲线上具有足够大曲率的点。
第二提取单元342用于根据提取到的视觉特征点，提取每帧图片中的透视矩形平面结构。由于通常情况下视频中大部分的矩形结构物体并非正面朝向镜头，存在各种透视投影变形，因此透视矩形平面结构包括标准的矩形结构以及透视投影变形后的矩形结构，例如墙体、桌面、窗子等。
第二提取单元342在提取每帧图片中的透视矩形平面结构时，可结合多视图几何理论和图像分析技术(一般利用数学模型并结合图像处理技术来分析底层特征和上层结构，从而提取具有一定智能性的信息)通过预设的检测算法来实现。其中，预设的检测算法可以 是现有的图像检测算法，也可以是未来可能出现的任何能实现上述检测功能的算法。
判断单元343用于对不同帧中提取的透视矩形平面结构进行单应信息计算，判断是否满足单应特性。更具体地，基于多视图几何理论(主要研究三维重构，即用几何的方法，通过若干幅二维图像，来恢复三维物体)，同一平面在不同视角下的视频面内若满足单应特性(从一个平面到另一个平面的投影映射之间的特定关系)，则视觉特征点需具有尺度不变性和光照不变性，因此可对不同帧中提取的透视矩形平面结构进行单应信息计算，然后利用最优化方法根据提取到的视觉特征点和计算得到的单应信息求解场景中的优势单应矩阵，从而判断该透视矩形平面结构是否满足单应特性。
确定单元344用于在满足单一特性时，根据不同帧中提取的透视矩形平面结构所在的位置确定图片组中具有平面结构的物体的位置。更具体地，如果满足单应特性，确定单元344可求出场景中透视矩形平面结构的平面位置和方向等信息，然后对不同帧中提取的透视矩形平面结构所在的位置进行检查和校正，比如人工检查和校正，以避免误识别，然后将该透视矩形平面结构所在的位置确定为图片组中具有平面结构的物体在相应帧中的位置。
需要说明的是，本实施例以根据提取到的视觉特征点确定具有平面结构的物体的位置为例，可以理解的是，也可以采用其他方式确定具有平面结构的物体的位置。例如，由于视觉特征点的提取需要严格依赖平面的纹理特征(纹理特征是描述图像的一种重要的视觉特征)，在纹理特征信息不丰富的情况下，不能保证提取到足够数量的特征点，也不能保证视觉特征点的稳定性，且鉴于着重考虑场景中的矩形平面结构，可结合图像分析技术提取更多信息，以确定具有平面结构的物体的位置。在本发明的一个实施例中，可以首先对不同帧图像进行边缘检测，利用霍夫变换提取图像中的直线结构，获得直线所组成的封闭多边形区域，并通过分析封闭多边形区域的颜色和灰度特征定位真实的矩形平坦区域，最终结合多视图几何理论计算出平面的位置和方向参数。
在确定广告位后，存储模块400将所述广告位的信息存储到数据库中，以便从广告位中选择第一位置。
在本发明的一个实施例中，第一位置包括广告在视频的每一帧图片上的位置。将所述广告位的信息存储到数据库中之后，每当服务器接收到广告请求时，都会根据要播放的视频查询数据库，获取该视频中的广告位的信息，以便从广告位中选择第一位置进行广告投放。
进一步地，融入模块200包括：
处理子模块210用于对视频进行解码，得到每一帧图片。
融入子模块220用于根据第一位置的信息，将广告内容融入到每一帧图片的相应位置 处。融入子模块220可根据查询到的广告位的第一位置的信息，将广告内容融入到每一帧图片的相应位置处。在本发明的具体实施例中，可以通过现有的融入方法，例如采用3D渲染等方式进行融合和展现；也可以通过未来可能出现的任何融入方法将所述广告内容融入到每一帧图片的相应位置处。
本实施例通过获取要播放的视频，以及获取视频广告的信息，对要播放的视频进行离线处理获取广告位，并将广告位的信息存储到数据库中，以选取合适的第一位置对广告进行投放，通过检测算法和人工检查、校正确定广告投放位置，投放位置更加准确。处理过程分为离线处理和实时处理，降低了计算复杂度，提高了处理效率。充分利用了视频中的非关键平坦区域，提高了广告投放效率，减少了视频观看过程中的等待，不影响视频内容的正常呈现，提升了用户体验。
为了实现上述实施例，本发明还提出一种存储介质。
本发明实施例的存储介质，用于存储应用程序，所述应用程序用于在运行时执行如本发明实施例的视频中广告的播放方法。
需要说明的是，在本发明的描述中，术语“第一”、“第二”等仅用于描述目的，而不能理解为指示或暗示相对重要性。此外，在本发明的描述中，除非另有说明，“多个”的含义是两个或两个以上。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本发明的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本发明的实施例所属技术领域的技术人员所理解。
应当理解，本发明的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如，如果用硬件来实现，和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本发明各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既 可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。
上述提到的存储介质可以是只读存储器，磁盘或光盘等。
在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
尽管上面已经示出和描述了本发明的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本发明的限制，本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (15)

  1. 一种视频中广告的播放方法，其特征在于，包括：
    获取要播放的视频，以及获取广告的信息，所述广告的信息包括：广告内容以及第一位置的信息，所述第一位置是所述广告在所述视频中的位置；
    将所述广告内容融入到所述视频的第一位置处，并进行播放，使得所述广告位于所述视频的具有平面结构的物体上。
  2. 根据权利要求1所述的方法，其特征在于，还包括：
    对所述视频进行离线处理获取广告位，所述广告位是所述视频的具有平面结构的物体的位置；
    将所述广告位的信息存储到数据库中，以便从所述广告位中选择所述第一位置。
  3. 根据权利要求2所述的方法，其特征在于，所述对所述视频进行离线处理获取广告位，包括：
    对所述视频进行解码，得到每一帧图片；
    对所述每一帧图片进行降采样处理，得到降采样后的视频；
    对所述降采样后的视频进行场景切分，得到至少一组的分别与每个场景对应的图片组；
    在每组图片组中，获取所述图片组中具有平面结构的物体的位置，并确定为广告位。
  4. 根据权利要求3所述的方法，其特征在于，所述获取所述图片组中具有平面结构的物体的位置，包括：
    对所述图片组中的每帧图片进行视觉特征点提取；
    根据提取到的所述视觉特征点，提取每帧图片中的透视矩形平面结构；
    对不同帧中提取的透视矩形平面结构进行单应信息计算，判断是否满足单应特性；
    如果满足单一特性，根据不同帧中提取的透视矩形平面结构所在的位置确定所述图片组中具有平面结构的物体的位置。
  5. 根据权利要求4所述的方法，其特征在于，所述根据不同帧中提取的透视矩形平面结构所在的位置确定所述图片组中具有平面结构的物体的位置，包括：
    对所述不同帧中提取的透视矩形平面结构所在的位置进行检查和校正后，确定为所述图片组中具有平面结构的物体在相应帧中的位置。
  6. 根据权利要求1至5任一项所述的方法，其特征在于，所述第一位置包括所述广告在所述视频的每一帧图片上的位置，所述将所述广告内容融入到所述视频的第一位置处，包括：
    对所述视频进行解码，得到每一帧图片；
    根据所述第一位置的信息，将所述广告内容融入到每一帧图片的相应位置处。
  7. 根据权利要求6所述的方法，其特征在于，所述将所述广告内容融入到每一帧图片的相应位置处，包括：
    采用3D渲染的方式，将所述广告内容融入到每一帧图片的相应位置处。
  8. 一种视频中广告的播放装置，其特征在于，包括：
    获取模块，用于获取要播放的视频，以及获取广告的信息，所述广告的信息包括：广告内容以及第一位置的信息，所述第一位置是所述广告在所述视频中的位置；
    融入模块，用于将所述广告内容融入到所述视频的第一位置处，并进行播放，使得所述广告位于所述视频的具有平面结构的物体上。
  9. 根据权利要求8所述的装置，其特征在于，还包括：
    离线处理模块，用于对所述视频进行离线处理获取广告位，所述广告位是所述视频的具有平面结构的物体的位置；
    存储模块，用于将所述广告位的信息存储到数据库中，以便从所述广告位中选择所述第一位置。
  10. 根据权利要求9所述的装置，其特征在于，所述离线处理模块，包括：
    解码子模块，用于对所述视频进行解码，得到每一帧图片；
    降采样子模块，用于对所述每一帧图片进行降采样处理，得到降采样后的视频；
    切分子模块，用于对所述降采样后的视频进行场景切分，得到至少一组的分别与每个场景对应的图片组；
    获取子模块，用于在每组图片组中，获取所述图片组中具有平面结构的物体的位置，并确定为广告位。
  11. 根据权利要求10所述的装置，其特征在于，所述获取子模块，包括：
    第一提取单元，用于对所述图片组中的每帧图片进行视觉特征点提取；
    第二提取单元，用于根据提取到的所述视觉特征点，提取每帧图片中的透视矩形平面结构；
    判断单元，用于对不同帧中提取的透视矩形平面结构进行单应信息计算，判断是否满足单应特性；
    确定单元，用于在满足单一特性时，根据不同帧中提取的透视矩形平面结构所在的位置确定所述图片组中具有平面结构的物体的位置。
  12. 根据权利要求11所述的装置，其特征在于，所述确定单元还用于对所述不同帧中提取的透视矩形平面结构所在的位置进行检查和校正后，确定为所述图片组中具有平面结构的物体在相应帧中的位置。
  13. 根据权利要求8至12任一项所述的装置，其特征在于，所述第一位置包括所述广告在所述视频的每一帧图片上的位置，所述融入模块，包括：
    处理子模块，用于对所述视频进行解码，得到每一帧图片；
    融入子模块，用于根据所述第一位置的信息，将所述广告内容融入到每一帧图片的相应位置处。
  14. 根据权利要求13所述的装置，其特征在于，所述融入子模块还用于采用3D渲染的方式，将所述广告内容融入到每一帧图片的相应位置处。
  15. 一种存储介质，其特征在于，用于存储应用程序，所述应用程序用于在运行时执行如权利要求1-7任一项所述的视频中广告的播放方法。
PCT/CN2014/090573 2014-06-16 2014-11-07 视频中广告的播放方法和装置 WO2015192585A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410268322.4A CN104066003B (zh) 2014-06-16 2014-06-16 视频中广告的播放方法和装置
CN201410268322.4 2014-06-16

Publications (1)

Publication Number Publication Date
WO2015192585A1 true WO2015192585A1 (zh) 2015-12-23

Family

ID=51553497

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/090573 WO2015192585A1 (zh) 2014-06-16 2014-11-07 视频中广告的播放方法和装置

Country Status (2)

Country Link
CN (1) CN104066003B (zh)
WO (1) WO2015192585A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113438540A (zh) * 2021-06-24 2021-09-24 广州欢网科技有限责任公司 基于广告曝光率的广告预加载播放方法及装置
CN114900722A (zh) * 2022-05-06 2022-08-12 浙江工商大学 基于ar技术的个性化广告植入方法及系统

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104066003B (zh) * 2014-06-16 2017-05-10 百度在线网络技术（北京）有限公司 视频中广告的播放方法和装置
CN104754412A (zh) * 2015-03-04 2015-07-01 深圳市亮新光电显示技术有限公司 交互式广告置入方法及系统
CN104735466B (zh) * 2015-03-31 2018-04-10 北京奇艺世纪科技有限公司 一种更换视频中商标图案的方法及装置
CN104766229A (zh) * 2015-04-22 2015-07-08 合一信息技术（北京）有限公司 植入式广告投放方法
US9872049B1 (en) * 2016-06-30 2018-01-16 SnifferCat, Inc. Systems and methods for dynamic stitching of advertisements
US11272228B2 (en) 2016-06-30 2022-03-08 SnifferCat, Inc. Systems and methods for dynamic stitching of advertisements in live stream content
CN107347166B (zh) * 2016-08-19 2020-03-03 北京市商汤科技开发有限公司 视频图像的处理方法、装置和终端设备
CN106331745A (zh) * 2016-08-31 2017-01-11 杭州探索文化传媒有限公司 一种动态的视频广告植入方法
CN108040267A (zh) * 2017-12-07 2018-05-15 北京奇虎科技有限公司 一种在视频中融合推荐内容的方法和装置
CN108122198A (zh) * 2017-12-07 2018-06-05 北京奇虎科技有限公司 一种在视频中融合推荐内容的实现方法、装置和服务器
CN108040280A (zh) * 2017-12-08 2018-05-15 北京小米移动软件有限公司 内容项目显示方法及装置、存储介质
CN109523297B (zh) * 2018-10-17 2022-02-22 成都索贝数码科技股份有限公司 一种体育比赛中实现虚拟广告的方法
CN111586440B (zh) * 2019-02-15 2022-03-11 腾讯科技（深圳）有限公司 多媒体资源的投放方法、装置、服务器及存储介质
CN110708593A (zh) * 2019-09-06 2020-01-17 深圳平安通信科技有限公司 视频内容中嵌入广告的方法、装置及存储介质
CN111292280B (zh) * 2020-01-20 2023-08-29 北京百度网讯科技有限公司 用于输出信息的方法和装置
CN114051166B (zh) * 2020-07-24 2024-03-29 北京达佳互联信息技术有限公司 在视频中植入广告的方法、装置、电子设备和存储介质
CN113222662A (zh) * 2021-05-10 2021-08-06 刘川民 一种广告置换或添加的处理方法及系统及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060059514A1 (en) * 2004-09-10 2006-03-16 Eric Hsiao Method and apparatus for utilizing blank space on a high definition television screen
CN101621636A (zh) * 2008-06-30 2010-01-06 北京大学 基于视觉注意力模型的广告标志插入和变换方法及系统
CN102318358A (zh) * 2011-05-26 2012-01-11 华为技术有限公司 广告插入的方法、设备与系统
CN102404642A (zh) * 2011-12-06 2012-04-04 鄂文轩 一种移动终端中的广告发布方法和设备
CN103780944A (zh) * 2012-10-17 2014-05-07 三亚中兴软件有限责任公司 广告播放方法、装置、系统及匹配信息建立装置
CN104066003A (zh) * 2014-06-16 2014-09-24 百度在线网络技术（北京）有限公司 视频中广告的播放方法和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060059514A1 (en) * 2004-09-10 2006-03-16 Eric Hsiao Method and apparatus for utilizing blank space on a high definition television screen
CN101621636A (zh) * 2008-06-30 2010-01-06 北京大学 基于视觉注意力模型的广告标志插入和变换方法及系统
CN102318358A (zh) * 2011-05-26 2012-01-11 华为技术有限公司 广告插入的方法、设备与系统
CN102404642A (zh) * 2011-12-06 2012-04-04 鄂文轩 一种移动终端中的广告发布方法和设备
CN103780944A (zh) * 2012-10-17 2014-05-07 三亚中兴软件有限责任公司 广告播放方法、装置、系统及匹配信息建立装置
CN104066003A (zh) * 2014-06-16 2014-09-24 百度在线网络技术（北京）有限公司 视频中广告的播放方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113438540A (zh) * 2021-06-24 2021-09-24 广州欢网科技有限责任公司 基于广告曝光率的广告预加载播放方法及装置
CN114900722A (zh) * 2022-05-06 2022-08-12 浙江工商大学 基于ar技术的个性化广告植入方法及系统

Also Published As

Publication number Publication date
CN104066003A (zh) 2014-09-24
CN104066003B (zh) 2017-05-10

Similar Documents

Publication Publication Date Title
WO2015192585A1 (zh) 视频中广告的播放方法和装置
US11102525B2 (en) Injecting customized content into 360-degree videos
US20160050465A1 (en) Dynamically targeted ad augmentation in video
US11482192B2 (en) Automated object selection and placement for augmented reality
US10573039B2 (en) Techniques for incorporating a text-containing image into a digital image
US11830161B2 (en) Dynamically cropping digital content for display in any aspect ratio
US9846960B2 (en) Automated camera array calibration
US9047376B2 (en) Augmenting video with facial recognition
WO2018010653A1 (zh) 全景媒体文件推送方法及装置
EP3913924B1 (en) 360-degree panoramic video playing method, apparatus, and system
US20180192160A1 (en) Context based augmented advertisement
US20140043363A1 (en) Systems and methods for image or video personalization with selectable effects
US20120068996A1 (en) Safe mode transition in 3d content rendering
WO2017084306A1 (zh) 一种在移动设备浏览器中视频播放关键信息的方法及装置
CN107770602B (zh) 视频图像处理方法、装置和终端设备
WO2018148076A1 (en) System and method for automated positioning of augmented reality content
EP3716180A1 (en) System and method for dynamically creating and inserting immersive promotional content in a multimedia
CN111193961A (zh) 视频编辑设备和方法
US20130229490A1 (en) Digital signage system and method for displaying content on digital signage
US11436788B2 (en) File generation apparatus, image generation apparatus, file generation method, and storage medium
US20230298289A1 (en) Systems and methods to insert supplemental content into presentations of two-dimensional video content
US20230388563A1 (en) Inserting digital contents into a multi-view video
US20230042078A1 (en) Encoding and decoding views on volumetric image data
US11968410B1 (en) Systems and methods to insert supplemental content into presentations of two-dimensional video content based on intrinsic and extrinsic parameters of a camera
WO2022236842A1 (zh) 一种广告置换或添加的处理方法及系统及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14895134

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14895134

Country of ref document: EP

Kind code of ref document: A1