WO2016101256A1 - 视频匹配方法和装置 - Google Patents

视频匹配方法和装置 Download PDF

Info

Publication number
WO2016101256A1
WO2016101256A1 PCT/CN2014/095112 CN2014095112W WO2016101256A1 WO 2016101256 A1 WO2016101256 A1 WO 2016101256A1 CN 2014095112 W CN2014095112 W CN 2014095112W WO 2016101256 A1 WO2016101256 A1 WO 2016101256A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
frame data
matched
compared
encoding
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2014/095112
Other languages
English (en)
French (fr)
Inventor
王甜甜
江中央
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen TCL Digital Technology Co Ltd
Original Assignee
Shenzhen TCL Digital Technology Co Ltd
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 Shenzhen TCL Digital Technology Co Ltd filed Critical Shenzhen TCL Digital Technology Co Ltd
Publication of WO2016101256A1 publication Critical patent/WO2016101256A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • 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 or synchronising decoder's clock; Client middleware
    • H04N21/44Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs

Definitions

  • the present invention relates to the field of video technologies, and in particular, to a video matching method and apparatus.
  • a video is a collection of a series of frames that are continuous in time. It is a comprehensive media information that integrates images, sounds, and texts.
  • the traditional video matching scheme mainly matches the content of the video, and needs to browse all the video files. Different users extract different video content according to their different angles, analyze the extracted video content, and perform video matching according to the extracted video content. , judging whether the video content is the same by the matching result.
  • the traditional video matching needs to browse all the video files, and needs to extract different video content at all time points according to different user angles, and in the process of matching, the extracted video content needs to be matched with all the video files. Therefore, the matching time is long and the amount of calculation is large, and the video content at different time points has a certain error in the matching process.
  • the main object of the present invention is to provide a video matching method and apparatus, aiming at solving the technical problems of video matching efficiency and low precision.
  • the present invention provides a video matching method, where the video matching method includes the following steps:
  • Extracting a coded identifier of the to-be-matched video determining, according to the coded identifier, whether an encoding type of the to-be-matched video is the same;
  • the step of extracting the coding parameters of the to-be-matched video includes:
  • the encoding parameters of the audio stream and/or the image stream are extracted when the audio stream and/or the image stream are extracted.
  • the video matching method further includes:
  • the step of acquiring image parameters corresponding to each I frame data includes:
  • the extracted face information and color information are used as image parameters corresponding to the I frame data.
  • the present invention further provides a video matching apparatus, where the video matching apparatus includes:
  • An extraction module configured to extract a coded identifier of the video to be compared
  • a determining module configured to determine, according to the encoding identifier, whether an encoding type of the to-be-matched video is the same;
  • the extracting module is further configured to: when the encoding type of the to-be-compared video is the same, extract the encoding parameter of the to-be-matched video;
  • the comparison module is configured to compare the encoding parameters of the comparison video
  • a processing module configured to determine that the to-be-matched video matches when the encoding parameters of the to-be-matched video match.
  • the extracting module is further configured to: when the encoding type of the to-be-compared video is the same, extract the audio stream and the image stream in the to-be-matched video, and when extracting the audio stream and/or the image stream And extracting coding parameters of the audio code stream and/or the image code stream.
  • the extracting module is further configured to: when the encoding type of the to-be-compared video is different, extract I frame data of the same time point in the video to be compared;
  • the video matching device further includes an acquiring module, configured to acquire each An image parameter corresponding to the I frame data;
  • the comparison module is further configured to compare the image parameters corresponding to the I frame data at the same time point in the video;
  • the processing module is further used to compare When the image parameters corresponding to the I frame data at the same time point in the video match, it is determined that the to-be-matched video matches.
  • the obtaining module comprises:
  • An obtaining unit configured to acquire face information and color information in the I frame data
  • a processing unit configured to use the extracted face information and color information as image parameters corresponding to the I frame data.
  • the video matching method and device provided by the present invention determine whether the to-be-matched video matches directly by using the encoding parameters of the to-be-compared video directly when the encoding type of the to-be-compared video is the same, without extracting too much content data for comparison, and efficiency Higher and more accurate.
  • FIG. 1 is a schematic flowchart of a first embodiment of a video matching method according to the present invention
  • FIG. 2 is a schematic flowchart of a second embodiment of a video matching method according to the present invention.
  • FIG. 3 is a schematic diagram of functional modules of a first embodiment of a video matching apparatus according to the present invention.
  • FIG. 4 is a schematic diagram of functional modules of a second embodiment of a video matching apparatus according to the present invention.
  • the invention provides a video matching method.
  • FIG. 1 is a schematic flowchart diagram of a first embodiment of a video matching method according to the present invention.
  • This embodiment provides a video matching method, where the video matching method includes the following steps:
  • Step S10 Extract an encoding identifier of the to-be-matched video, and determine, according to the encoding identifier, whether the encoding type of the to-be-matched video is the same;
  • Step S20 When the coding types of the to-be-compared video are the same, extract coding parameters of the to-be-matched video;
  • the encoding parameters may include the Width, Height, Frame_rate, Bit_depth, Bit_rate, Block_align, Audio_rate, Channel (Video) of the video.
  • Parameter information such as the number of audio channels, Extra_data (video file header information), Extradata_size (the size of bytes occupied by Extra_data), and Metadata (video source data).
  • the parameter values corresponding to the respective parameter information may be obtained when the coding parameters are extracted. It can be understood by those skilled in the art that the parameter information included in the coding parameters corresponding to the video of different coding types is different due to the difference in coding types.
  • Step S10 includes:
  • the encoding parameters of the audio stream and/or the image stream are extracted when the audio stream and/or the image stream are extracted.
  • Step S30 comparing the encoding parameters of the comparison video
  • step S40 when the coding parameters of the to-be-matched video match, it is determined that the to-be-matched video matches.
  • Step S20 further includes the steps of: determining whether the to-be-matched video matches or does not match when the encoding parameters of the to-be-matched video match, and outputting the output of the to-be-compared video after determining whether the to-be-matched video matches or does not match.
  • the person skilled in the art can understand that when the number of to-be-matched videos is greater than three, information of the matched videos in the plurality of to-be-matched videos and the unmatched videos can be displayed.
  • the coding parameters of the to-be-compared video are directly determined whether the to-be-matched video matches, and the content data is not extracted, and the efficiency is compared. High and accurate.
  • the video matching method further includes:
  • Step S50 When the coding types of the to-be-matched videos are different, extract I-frame data at the same time point in the to-be-matched video;
  • Video data includes I frames, P frames, and B frames.
  • I frames are basic frames, usually for each GOP (MPEG).
  • MPEG MPEG
  • the I frame data at the same time point refers to the I frame data whose time difference between the same time point is less than a preset threshold.
  • the I frame data is I frame data at a certain time point in the same time period as the video to be compared.
  • the to-be-matched video includes the source 1 and the source 2, and the recording time of the source 1 is 10:00-12. :00, and the recording time of the source 2 is 11:00-12:00, then the same time period from the source 1 to the source 2 is 11:00-12:00, then 11:30 is taken as the source one.
  • the I frame data is I frame data at a plurality of time points in the same period of time to be compared to the video.
  • the to-be-matched video includes the source 1 and the source 2, and the recording time of the source 1 is 10:00. -12:00, and the recording time of the source 2 is 11:00-12:00, then the same time period from the source 1 to the source 2 is 11:00-12:00, then 11:00, 11 :10, 11:20, 11:30, 11:40, 11:50, 12:00 are the same time points of the source and the source 2. If the image parameters corresponding to the I frame data at any time point do not match, it is determined that the to-be-matched video does not match.
  • Step S60 acquiring image parameters corresponding to each of the I frame data
  • the image parameters corresponding to the I frame data may include face information, color information, and the like, that is, the step S40 includes the steps of: acquiring face information and color information in the I frame data; The face information and the color information are used as image parameters corresponding to the I frame data.
  • the face information may include a face feature (such as a shape, etc.), a face texture, and color information, and the face feature may be calculated by an Adaboost algorithm, and the face texture may be calculated by a Gabor algorithm, the Adaboost algorithm and Gabor.
  • the algorithm is an existing algorithm, and the specific calculation process will not be described here.
  • the calculation method of the color information is also a prior art, and will not be described here.
  • Step S70 comparing image parameters corresponding to the I frame data at the same time point in the to-be-matched video
  • step S80 when the image parameters corresponding to the I frame data at the same time point in the video are matched, it is determined that the to-be-matched video matches.
  • the to-be-matched video may not be directly considered to be mismatched.
  • the comparison of the I-frame data at the same time point makes the comparison of the to-be-compared videos more accurate.
  • the invention further provides a video matching device.
  • FIG. 3 is a schematic diagram of functional modules of a first embodiment of a video matching apparatus according to the present invention.
  • the functional module diagram shown in FIG. 3 is merely an exemplary diagram of a preferred embodiment, and those skilled in the art can surround the functional modules of the video matching apparatus shown in FIG. It is easy to add a new function module; the name of each function module is a custom name, which is only used to assist in understanding the various program function blocks of the video matching device, and is not used to limit the technical solution of the present invention, and the core of the technical solution of the present invention is , the function to be achieved by the function module of each name.
  • This embodiment provides a video matching apparatus, where the video matching apparatus includes:
  • the extracting module 10 is configured to extract a coded identifier of the video to be compared
  • a determining module 20 configured to determine, according to the encoding identifier, whether an encoding type of the to-be-matched video is the same;
  • the extracting module 10 is further configured to: when encoding types of the to-be-compared video are the same, extract encoding parameters of the to-be-matched video;
  • the encoding parameters may include the Width, Height, Frame_rate, Bit_depth, Bit_rate, Block_align, Audio_rate, Channel (Video) of the video.
  • Parameter information such as the number of audio channels, Extra_data (video file header information), Extradata_size (the size of bytes occupied by Extra_data), and Metadata (video source data).
  • the parameter values corresponding to the respective parameter information may be obtained when the coding parameters are extracted. It can be understood by those skilled in the art that the parameter information included in the coding parameters corresponding to the video of different coding types is different due to the difference in coding types.
  • the audio code stream and/or the image code stream are included in the video, and the audio code stream and the image code stream corresponding to the coding parameters are different, and the extraction module 10 is further configured to compare the video. Extracting the audio stream and the image stream in the to-be-matched video when the encoding types are the same, and extracting the encoding of the audio stream and/or the image stream when the audio stream and/or the image stream are extracted parameter.
  • the comparison module 30 is configured to compare the encoding parameters of the comparison video
  • the processing module 40 is configured to determine that the to-be-matched video matches when the encoding parameters of the to-be-matched video match.
  • the parameter values corresponding to the respective parameter information in the coding parameters may be respectively compared, and the matching of the coding parameters of the comparison video refers to the corresponding parameter information of the coding parameters of the video to be compared.
  • the parameter values are all equal.
  • the processing module 30 is further configured to determine that the to-be-matched video matches or does not match when the encoding parameters of the to-be-matched video match, and output the output of the to-be-compared video after determining whether the to-be-matched video matches or does not match.
  • the person skilled in the art can understand that when the number of to-be-matched videos is greater than three, information of the matched videos in the plurality of to-be-matched videos and the unmatched videos can be displayed.
  • the video matching apparatus of the present embodiment directly determines whether the to-be-matched video matches by the coding parameters of the to-be-compared video, and does not need to extract too much content data for comparison. High and accurate.
  • the extraction module 10 is further used to compare When the encoding type of the video is different, the I frame data of the same time point in the video is compared;
  • the video matching device further includes an obtaining module 50, configured to acquire image parameters corresponding to each of the I frame data;
  • the module is further configured to compare the image parameters corresponding to the I frame data at the same time point in the video;
  • the processing module 40 is further configured to: at the same time point in the video to be compared When the image parameters corresponding to the data match, it is determined that the to-be-matched video matches.
  • Video data includes I frames, P frames, and B frames.
  • I frames are usually every GOP (MPEG).
  • MPEG MPEG
  • the I frame data at the same time point refers to the I frame data whose time difference between the same time point is less than a preset threshold.
  • the I frame data is I frame data at a certain time point in the same time period as the video to be compared.
  • the to-be-matched video includes the source 1 and the source 2, and the recording time of the source 1 is 10:00-12. :00, and the recording time of the source 2 is 11:00-12:00, then the same time period from the source 1 to the source 2 is 11:00-12:00, then 11:30 is taken as the source one.
  • the I frame data is I frame data at a plurality of time points in the same period of time to be compared to the video.
  • the to-be-matched video includes the source 1 and the source 2, and the recording time of the source 1 is 10:00. -12:00, and the recording time of the source 2 is 11:00-12:00, then the same time period from the source 1 to the source 2 is 11:00-12:00, then 11:00, 11 :10, 11:20, 11:30, 11:40, 11:50, 12:00 are the same time points of the source and the source 2. If the image parameters corresponding to the I frame data at any time point do not match, it is determined that the to-be-matched video does not match.
  • the image parameters corresponding to the I frame data may include face information, color information, and the like, that is, the obtaining module 50 includes: an acquiring unit, configured to acquire face information and color information in the I frame data; And a processing unit, configured to use the extracted face information and color information as image parameters corresponding to the I frame data.
  • the face information may include a face feature (such as a shape, etc.), a face texture, and color information, and the face feature may be calculated by an Adaboost algorithm, and the face texture may be calculated by a Gabor algorithm, the Adaboost algorithm and Gabor.
  • the algorithm is an existing algorithm, and the specific calculation process will not be described here.
  • the calculation method of the color information is also a prior art, and will not be described here.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better.
  • Implementation Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a cell phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)

Abstract

本发明公开了一种视频匹配方法,所述视频匹配方法包括以下步骤:提取待比对视频的编码标识,基于所述编码标识确定所述待比对视频的编码类型是否相同;在待比对视频的编码类型相同时,提取待比对视频的编码参数;比对待比对视频的编码参数;在待比对视频的编码参数匹配时,确定待比对视频匹配。本发明还公开了一种视频匹配装置。本发明提高了视频匹配的效率较以及准确度。

Description

视频匹配方法和装置
技术领域
本发明涉及视频技术领域,尤其涉及视频匹配方法和装置。
背景技术
随着计算机、数字媒体技术的不断提高,视频匹配技术越来越重要。视频是在时间上连续的一系列帧的集合,是集图像、声音、文本为一体的综合性媒体信息。传统视频匹配方案主要基于视频的内容进行匹配,需要浏览所有的视频文件,不同的用户根据他们的不同角度提取不同的视频内容,并对提取的视频内容进行分析,根据提取的视频内容进行视频匹配,由匹配的结果判断视频内容是否相同。但是传统的视频匹配需要浏览所有的视频文件,并且需要根据不同的用户角度提取所有时间点的不同的视频内容,且在进行匹配过程中,需要将提取的视频内容与所有的视频文件进行匹配,因此匹配的时间较长且运算量较大,并且不同时间点的视频内容在匹配过程中具有一定的误差。
发明内容
本发明的主要目的在于提出一种视频匹配方法和装置,旨在解决视频匹配效率以及精度低的技术问题。
为实现上述目的,本发明提供的一种视频匹配方法,所述视频匹配方法包括以下步骤:
提取待比对视频的编码标识,基于所述编码标识确定所述待比对视频的编码类型是否相同;
在待比对视频的编码类型相同时,提取待比对视频的编码参数;
比对待比对视频的编码参数;
在待比对视频的编码参数匹配时,确定待比对视频匹配。
优选地,所述在待比对视频的编码类型相同时,提取待比对视频的编码参数的步骤包括:
在待比对视频的编码类型相同时,提取待比对视频中的音频码流和图像码流;
在提取到音频码流及/或图像码流时,提取所述音频码流及/或图像码流的编码参数。
优选地,所述视频匹配方法还包括:
在待比对视频的编码类型不同时,提取待比对视频中同一时间点的I帧数据;
获取各个所述I帧数据对应的图像参数;
比对待比对视频中同一时间点的所述I帧数据所对应的图像参数;
在待比对视频中同一时间点的所述I帧数据所对应的图像参数匹配时,确定待比对视频匹配。
优选地,所述获取各个I帧数据对应的图像参数的步骤包括:
获取所述I帧数据中的人脸信息以及颜色信息;
将提取到的人脸信息以及颜色信息作为所述I帧数据对应的图像参数。
此外,为实现上述目的,本发明还提出一种视频匹配装置,所述视频匹配装置包括:
提取模块,用于提取待比对视频的编码标识;
确定模块,用于基于所述编码标识确定所述待比对视频的编码类型是否相同;
提取模块,还用于在待比对视频的编码类型相同时,提取待比对视频的编码参数;
比对模块,用于比对待比对视频的编码参数;
处理模块,用于在待比对视频的编码参数匹配时,确定待比对视频匹配。
优选地,所述提取模块还用于在待比对视频的编码类型相同时,提取待比对视频中的音频码流和图像码流,以及在提取到音频码流及/或图像码流时,提取所述音频码流及/或图像码流的编码参数。
优选地,所述提取模块还用于在待比对视频的编码类型不同时,提取待比对视频中同一时间点的I帧数据;所述视频匹配装置还包括获取模块,用于获取各个所述I帧数据对应的图像参数;所述比对模块,还用于比对待比对视频中同一时间点的所述I帧数据所对应的图像参数;所述处理模块,还用于在待比对视频中同一时间点的所述I帧数据所对应的图像参数匹配时,确定待比对视频匹配。
优选地,所述获取模块包括:
获取单元,用于获取I帧数据中的人脸信息以及颜色信息;
处理单元,用于将提取到的人脸信息以及颜色信息作为所述I帧数据对应的图像参数。
本发明提出的视频匹配方法和装置,在待比对视频的编码类型相同时,直接通过待比对视频的编码参数确定待比对视频是否匹配,不用提取过多的内容数据进行比对,效率较高且准确度高。
附图说明
图1为本发明视频匹配方法第一实施例的流程示意图;
图2为本发明视频匹配方法第二实施例的流程示意图;
图3为本发明视频匹配装置第一实施例的功能模块示意图;
图4为本发明视频匹配装置第二实施例的功能模块示意图。
本发明目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
本发明提供一种视频匹配方法。
参照图1,图1为本发明视频匹配方法第一实施例的流程示意图。
本实施例提出一种视频匹配方法,所述视频匹配方法包括步骤:
步骤S10,提取待比对视频的编码标识,基于所述编码标识确定所述待比对视频的编码类型是否相同;
步骤S20,在待比对视频的编码类型相同时,提取待比对视频的编码参数;
编码参数可包括视频的Width(宽)、Height(高)、Frame_rate(帧率)、Bit_depth(位深度)、Bit_rate(码率)、Block_align(音频对齐方式)、Sample_rate(音频采样率)、Channel(音频通道数)、Extra_data(视频文件头信息)、Extradata_size(Extra_data所占字节的大小)、Metadata(视频源数据)等参数信息。在提取编码参数时可获取各个参数信息对应的参数值。本领域技术人员可以理解的是,由于编码类型的差别,不同编码类型的视频对应的编码参数中包含的参数信息不同。
本领域技术人员可以理解得是,视频中包含音频码流及/或图像码流,而音频码流以及图像码流对应的编码参数不同,则步骤S10包括:
在待比对视频的编码类型相同时,提取待比对视频中的音频码流和图像码流;
在提取到音频码流及/或图像码流时,提取所述音频码流及/或图像码流的编码参数。
步骤S30,比对待比对视频的编码参数;
步骤S40,在待比对视频的编码参数匹配时,确定待比对视频匹配。
在比对待比对视频的编码参数时,可分别比对编码参数中各个参数信息对应的参数值,待比对视频的编码参数匹配是指待比对视频的编码参数中各个参数信息对应的参数值均相等。步骤S20还包括步骤:在待比对视频的编码参数匹配时,确定待比对视频匹配或者不匹配,并在确定待比对视频匹配或者不匹配之后,可输出待比对视频的输出结果。本领技术人员可以理解的是,在待比对视频的数量大于三个时,可显示多个待比对视频中匹配的视频以及不匹配的视频的信息。
本实施例提出的视频匹配方法,在待比对视频的编码类型相同时,直接通过待比对视频的编码参数确定待比对视频是否匹配,不用提取过多的内容数据进行比对,效率较高且准确度高。
进一步地,为提高视频比对的准确性,参照图2,基于第一实施例提出本发明视频比对方法第二实施例,在本实施例中,所述视频匹配方法还包括:
步骤S50,在所述待比对视频的编码类型不同时,提取所述待比对视频中同一时间点的I帧数据;
视频数据包括I帧、P帧以及B帧, I 帧是基础帧,通常是每个 GOP(MPEG 所使用的一种视频压缩技术)的第一个帧,经过适度地压缩,作为随机访问的参考点,可以当成图像。
在本实施例中,同一时间点的I帧数据是指与同一时间点之间的时间差小于预设阈值的I帧数据。该I帧数据为待比对视频相同的时间段内某一时间点的I帧数据,例如,待比对视频包括片源一和片源二,片源一的录制时间为10:00-12:00,而片源二的录制时间为11:00-12:00,则片源一和片源二中相同的时间段为11:00-12:00,则可取11:30为片源一和片源二的同一时间点。或者,该I帧数据为待比对视频相同的时间段内多个时间点的I帧数据,例如,待比对视频包括片源一和片源二,片源一的录制时间为10:00-12:00,而片源二的录制时间为11:00-12:00,则片源一和片源二中相同的时间段为11:00-12:00,则可取11:00、11:10、11:20、11:30、11:40、11:50、12:00为片源一和片源二的同一时间点。则有任一时间点的I帧数据对应的图像参数不匹配时,确定待比对视频不匹配。
步骤S60,获取各个所述I帧数据对应的图像参数;
本实施例中,所述I帧数据对应的图像参数可包括人脸信息以及颜色信息等,即所述步骤S40包括步骤:获取所述I帧数据中的人脸信息以及颜色信息;将提取到的人脸信息以及颜色信息作为所述I帧数据对应的图像参数。
所述人脸信息可包括人脸特征(如形状等)、人脸纹理以及颜色信息,该人脸特征可通过Adaboost算法计算得到,而人脸纹理可通过Gabor算法计算得到,该Adaboost算法以及Gabor算法为现有的算法,具体计算过程在此不做赘述。而颜色信息的计算方式也为现有技术,在此不做赘述。
步骤S70,比对所述待比对视频中同一时间点的所述I帧数据所对应的图像参数;
步骤S80,在待比对视频中同一时间点的所述I帧数据所对应的图像参数匹配时,确定待比对视频匹配。
本领域技术人员可以理解的是,在所述待比对视频的编码类型不同时,还可直接认为待比对视频不匹配。
在待比对视频的编码类型不同时,通过同一时间点I帧数据的比对,使得待比对视频的比对更加准确。
本发明进一步提供一种视频匹配装置。
参照图3,图3为本发明视频匹配装置第一实施例的功能模块示意图。
需要强调的是,对本领域的技术人员来说,图3所示功能模块图仅仅是一个较佳实施例的示例图,本领域的技术人员围绕图3所示的视频匹配装置的功能模块,可轻易进行新的功能模块的补充;各功能模块的名称是自定义名称,仅用于辅助理解该视频匹配装置的各个程序功能块,不用于限定本发明的技术方案,本发明技术方案的核心是,各自定义名称的功能模块所要达成的功能。
本实施例提出一种视频匹配装置,所述视频匹配装置包括:
提取模块10,用于提取待比对视频的编码标识;
确定模块20,用于基于所述编码标识确定所述待比对视频的编码类型是否相同;
所述提取模块10,还用于在待比对视频的编码类型相同时,提取待比对视频的编码参数;
编码参数可包括视频的Width(宽)、Height(高)、Frame_rate(帧率)、Bit_depth(位深度)、Bit_rate(码率)、Block_align(音频对齐方式)、Sample_rate(音频采样率)、Channel(音频通道数)、Extra_data(视频文件头信息)、Extradata_size(Extra_data所占字节的大小)、Metadata(视频源数据)等参数信息。在提取编码参数时可获取各个参数信息对应的参数值。本领域技术人员可以理解的是,由于编码类型的差别,不同编码类型的视频对应的编码参数中包含的参数信息不同。
本领域技术人员可以理解得是,视频中包含音频码流及/或图像码流,而音频码流以及图像码流对应的编码参数不同,则所述提取模块10还用于在待比对视频的编码类型相同时,提取待比对视频中的音频码流和图像码流,以及在提取到音频码流及/或图像码流时,提取所述音频码流及/或图像码流的编码参数。
比对模块30,用于比对待比对视频的编码参数;
处理模块40,用于在待比对视频的编码参数匹配时,确定待比对视频匹配。
在比对待比对视频的编码参数时,可分别比对编码参数中各个参数信息对应的参数值,待比对视频的编码参数匹配是指,待比对视频的编码参数中各个参数信息对应的参数值均相等。处理模块30还用于在待比对视频的编码参数匹配时,确定待比对视频匹配或者不匹配,并在确定待比对视频匹配或者不匹配之后,可输出待比对视频的输出结果。本领技术人员可以理解的是,在待比对视频的数量大于三个时,可显示多个待比对视频中匹配的视频以及不匹配的视频的信息。
本实施例提出的视频匹配装置,在待比对视频的编码类型相同时,直接通过待比对视频的编码参数确定待比对视频是否匹配,不用提取过多的内容数据进行比对,效率较高且准确度高。
进一步地,为提高视频比对的准确性,参照图4,基于第一实施例提出本发明视频比对系统第二实施例,在本实施例中,所述提取模块10还用于在待比对视频的编码类型不同时,提取待比对视频中同一时间点的I帧数据;所述视频匹配装置还包括获取模块50,用于获取各个所述I帧数据对应的图像参数;所述比对模块,还用于比对待比对视频中同一时间点的所述I帧数据所对应的图像参数;所述处理模块40,还用于在待比对视频中同一时间点的所述I帧数据所对应的图像参数匹配时,确定待比对视频匹配。
视频数据包括I帧、P帧以及B帧, I 帧通常是每个 GOP(MPEG 所使用的一种视频压缩技术)的第一个帧,经过适度地压缩,作为随机访问的参考点,可以当成图像。
在本实施例中,同一时间点的I帧数据是指与同一时间点之间的时间差小于预设阈值的I帧数据。该I帧数据为待比对视频相同的时间段内某一时间点的I帧数据,例如,待比对视频包括片源一和片源二,片源一的录制时间为10:00-12:00,而片源二的录制时间为11:00-12:00,则片源一和片源二中相同的时间段为11:00-12:00,则可取11:30为片源一和片源二的同一时间点。或者,该I帧数据为待比对视频相同的时间段内多个时间点的I帧数据,例如,待比对视频包括片源一和片源二,片源一的录制时间为10:00-12:00,而片源二的录制时间为11:00-12:00,则片源一和片源二中相同的时间段为11:00-12:00,则可取11:00、11:10、11:20、11:30、11:40、11:50、12:00为片源一和片源二的同一时间点。则有任一时间点的I帧数据对应的图像参数不匹配时,确定待比对视频不匹配。
本实施例中,所述I帧数据对应的图像参数可包括人脸信息以及颜色信息等,即所述获取模块50包括:获取单元,用于获取I帧数据中的人脸信息以及颜色信息;处理单元,用于将提取到的人脸信息以及颜色信息作为所述I帧数据对应的图像参数。所述人脸信息可包括人脸特征(如形状等)、人脸纹理以及颜色信息,该人脸特征可通过Adaboost算法计算得到,而人脸纹理可通过Gabor算法计算得到,该Adaboost算法以及Gabor算法为现有的算法,具体计算过程在此不做赘述。而颜色信息的计算方式也为现有技术,在此不做赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本发明各个实施例所述的方法。
以上仅为本发明的优选实施例,并非因此限制本发明的专利范围,凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本发明的专利保护范围内。

Claims (12)

  1. 一种视频匹配方法,其特征在于,所述视频匹配方法包括以下步骤:
    提取待比对视频的编码标识,基于所述编码标识确定所述待比对视频的编码类型是否相同;
    在待比对视频的编码类型相同时,提取待比对视频的编码参数;
    比对待比对视频的编码参数;
    在待比对视频的编码参数匹配时,确定待比对视频匹配。
  2. 如权利要求1所述的视频匹配方法,其特征在于,所述在待比对视频的编码类型相同时,提取待比对视频的编码参数的步骤包括:
    在待比对视频的编码类型相同时,提取待比对视频中的音频码流和图像码流;
    在提取到音频码流及/或图像码流时,提取所述音频码流及/或图像码流的编码参数。
  3. 如权利要求1所述的视频匹配方法,其特征在于,所述视频匹配方法还包括:
    在待比对视频的编码类型不同时,提取待比对视频中同一时间点的I帧数据;
    获取各个所述I帧数据对应的图像参数;
    比对待比对视频中同一时间点的所述I帧数据所对应的图像参数;
    在待比对视频中同一时间点的所述I帧数据所对应的图像参数匹配时,确定待比对视频匹配。
  4. 如权利要求2所述的视频匹配方法,其特征在于,所述视频匹配方法还包括:
    在待比对视频的编码类型不同时,提取待比对视频中同一时间点的I帧数据;
    获取各个所述I帧数据对应的图像参数;
    比对待比对视频中同一时间点的所述I帧数据所对应的图像参数;
    在待比对视频中同一时间点的所述I帧数据所对应的图像参数匹配时,确定待比对视频匹配。
  5. 如权利要求3所述的视频匹配方法,其特征在于,所述获取各个I帧数据对应的图像参数的步骤包括:
    获取所述I帧数据中的人脸信息以及颜色信息;
    将提取到的人脸信息以及颜色信息作为所述I帧数据对应的图像参数。
  6. 如权利要求4所述的视频匹配方法,其特征在于,所述获取各个I帧数据对应的图像参数的步骤包括:
    获取所述I帧数据中的人脸信息以及颜色信息;
    将提取到的人脸信息以及颜色信息作为所述I帧数据对应的图像参数。
  7. 一种视频匹配装置,其特征在于,所述视频匹配装置包括:
    提取模块,用于提取待比对视频的编码标识;
    确定模块,用于基于所述编码标识确定所述待比对视频的编码类型是否相同;
    提取模块,还用于在待比对视频的编码类型相同时,提取待比对视频的编码参数;
    比对模块,用于比对待比对视频的编码参数;
    处理模块,用于在待比对视频的编码参数匹配时,确定待比对视频匹配。
  8. 如权利要求7所述的视频匹配装置,其特征在于,所述提取模块还用于在待比对视频的编码类型相同时,提取待比对视频中的音频码流和图像码流,以及在提取到音频码流及/或图像码流时,提取所述音频码流及/或图像码流的编码参数。
  9. 如权利要求7所述的视频匹配装置,其特征在于,所述提取模块还用于在待比对视频的编码类型不同时,提取待比对视频中同一时间点的I帧数据;所述视频匹配装置还包括获取模块,用于获取各个所述I帧数据对应的图像参数;所述比对模块,还用于比对待比对视频中同一时间点的所述I帧数据所对应的图像参数;所述处理模块,还用于在待比对视频中同一时间点的所述I帧数据所对应的图像参数匹配时,确定待比对视频匹配。
  10. 如权利要求8所述的视频匹配装置,其特征在于,所述提取模块还用于在待比对视频的编码类型不同时,提取待比对视频中同一时间点的I帧数据;所述视频匹配装置还包括获取模块,用于获取各个所述I帧数据对应的图像参数;所述比对模块,还用于比对待比对视频中同一时间点的所述I帧数据所对应的图像参数;所述处理模块,还用于在待比对视频中同一时间点的所述I帧数据所对应的图像参数匹配时,确定待比对视频匹配。
  11. 如权利要求9所述的视频匹配装置,其特征在于,所述获取模块包括:
    获取单元,用于获取I帧数据中的人脸信息以及颜色信息;
    处理单元,用于将提取到的人脸信息以及颜色信息作为所述I帧数据对应的图像参数。
  12. 如权利要求10所述的视频匹配装置,其特征在于,所述获取模块包括:
    获取单元,用于获取I帧数据中的人脸信息以及颜色信息;
    处理单元,用于将提取到的人脸信息以及颜色信息作为所述I帧数据对应的图像参数。
PCT/CN2014/095112 2014-12-24 2014-12-26 视频匹配方法和装置 Ceased WO2016101256A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410814202.X 2014-12-24
CN201410814202.XA CN105791974B (zh) 2014-12-24 2014-12-24 视频匹配方法和装置

Publications (1)

Publication Number Publication Date
WO2016101256A1 true WO2016101256A1 (zh) 2016-06-30

Family

ID=56148984

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/095112 Ceased WO2016101256A1 (zh) 2014-12-24 2014-12-26 视频匹配方法和装置

Country Status (2)

Country Link
CN (1) CN105791974B (zh)
WO (1) WO2016101256A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101478684A (zh) * 2008-12-31 2009-07-08 杭州华三通信技术有限公司 检测存储视频数据完整性的方法和系统
CN102222103A (zh) * 2011-06-22 2011-10-19 央视国际网络有限公司 视频内容的匹配关系的处理方法及装置
CN102281471A (zh) * 2011-05-24 2011-12-14 深圳Tcl新技术有限公司 一种电视节目自动提醒装置及方法
CN102802138A (zh) * 2011-05-25 2012-11-28 腾讯科技(深圳)有限公司 一种视频文件的处理方法和系统、视频代理系统

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8442117B2 (en) * 2006-03-27 2013-05-14 Chang Gung University Method of block matching-based motion estimation in video coding
CN102938840A (zh) * 2012-11-26 2013-02-20 南京邮电大学 应用于多视点视频编码系统的关键帧量化参数选择方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101478684A (zh) * 2008-12-31 2009-07-08 杭州华三通信技术有限公司 检测存储视频数据完整性的方法和系统
CN102281471A (zh) * 2011-05-24 2011-12-14 深圳Tcl新技术有限公司 一种电视节目自动提醒装置及方法
CN102802138A (zh) * 2011-05-25 2012-11-28 腾讯科技(深圳)有限公司 一种视频文件的处理方法和系统、视频代理系统
CN102222103A (zh) * 2011-06-22 2011-10-19 央视国际网络有限公司 视频内容的匹配关系的处理方法及装置

Also Published As

Publication number Publication date
CN105791974A (zh) 2016-07-20
CN105791974B (zh) 2018-11-02

Similar Documents

Publication Publication Date Title
WO2015085765A1 (zh) 推送资讯信息的方法和智能终端
WO2017101266A1 (zh) 语音控制方法及系统
US12254604B2 (en) Systems and methods for media privacy
WO2018027549A1 (zh) 一种虚拟试衣的系统及方法
WO2017201913A1 (zh) 一种精准语音控制方法及装置
WO2020168606A1 (zh) 广告视频优化方法、装置、设备及计算机可读存储介质
WO2015137666A1 (ko) 오브젝트 인식 장치 및 그 제어 방법
WO2020000621A1 (zh) 空调控制方法、空调控制装置、空调设备及存储介质
WO2016029596A1 (zh) 音视频信号同步方法和装置
WO2019214039A1 (zh) 一种扫地机器人控制方法、设备、扫地机器人及存储介质
WO2016090652A1 (zh) 视频压缩方法及装置
WO2018032693A1 (zh) 电视显示内容的处理方法、装置及系统
WO2017142143A1 (en) Method and apparatus for providing summary information of a video
WO2017036209A1 (zh) 基于智能电视的音频数据播放方法、智能电视及系统
WO2017036218A1 (zh) 多媒体文件读取方法及装置
WO2019000462A1 (zh) 人脸图像处理方法、装置、存储介质及电子设备
WO2019119624A1 (zh) 基于Excel表的计算方法、装置、设备及存储介质
CN111712818B (zh) 认证数字记录
WO2019090981A1 (zh) 保险应用系统的监控方法及装置
WO2016175564A1 (ko) 오디오 컨텐츠 인식 방법 및 장치
WO2017092267A1 (zh) 频道处理方法及装置
WO2018053964A1 (zh) 基于安卓系统的语音输入标点符号的方法及装置
WO2020114333A1 (zh) 基于视频的ar教育方法、智能电视、存储介质及设备
WO2021157880A1 (ko) 전자 장치 및 데이터 처리 방법
WO2017012419A1 (zh) 流媒体解密方法及装置

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: 14908824

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 03/11/17)

122 Ep: pct application non-entry in european phase

Ref document number: 14908824

Country of ref document: EP

Kind code of ref document: A1