WO2013177910A1 - 一种媒体质量的评估方法及装置 - Google Patents

一种媒体质量的评估方法及装置 Download PDF

Info

Publication number
WO2013177910A1
WO2013177910A1 PCT/CN2012/085710 CN2012085710W WO2013177910A1 WO 2013177910 A1 WO2013177910 A1 WO 2013177910A1 CN 2012085710 W CN2012085710 W CN 2012085710W WO 2013177910 A1 WO2013177910 A1 WO 2013177910A1
Authority
WO
WIPO (PCT)
Prior art keywords
quality
media
pause
event
duration
Prior art date
Application number
PCT/CN2012/085710
Other languages
English (en)
French (fr)
Inventor
高山
孙李娜
谢清鹏
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP12878144.0A priority Critical patent/EP2830316B1/en
Priority to JP2015512994A priority patent/JP6099107B2/ja
Priority to SG11201406655UA priority patent/SG11201406655UA/en
Priority to BR112014029458-5A priority patent/BR112014029458B1/pt
Priority to KR1020147031766A priority patent/KR101693564B1/ko
Publication of WO2013177910A1 publication Critical patent/WO2013177910A1/zh
Priority to US14/518,164 priority patent/US9654770B2/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N17/00Diagnosis, testing or measuring for television systems or their details
    • H04N17/004Diagnosis, testing or measuring for television systems or their details for digital television systems
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N17/00Diagnosis, testing or measuring for television systems or their details
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N17/00Diagnosis, testing or measuring for television systems or their details
    • H04N17/02Diagnosis, testing or measuring for television systems or their details for colour television signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/85Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
    • H04N19/89Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving methods or arrangements for detection of transmission errors at the decoder
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/23418Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
    • 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
    • H04N21/44008Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream

Definitions

  • the invention belongs to the technical field of communications, and in particular relates to a method and a device for evaluating media quality. Background technique
  • Video quality assessment is an essential technology in video applications. Video quality is affected by many complex factors, including: the quality of service of the transport channel (such as bandwidth, packet loss, delay, jitter, etc.), and the adaptation of the video codec parameters to the transport channel (eg, coding, video resolution). Rate, video frame rate, error-resistant strength, whether the codec side buffer control strategy is appropriate, etc.). In addition to video loss due to loss of video data, such as channel loss, coding, etc., video delay or jitter caused by video delay and jitter can seriously affect the quality of the video.
  • the existing video quality assessment model takes into account the impact of coding quality, the effects of video stalls, and the effects of network packet loss:
  • the coding quality takes into account the effects of the code stream and the encoding format:
  • C. , c ⁇ p /L is a constant, different encoding formats can have different values.
  • the network packet loss quality is calculated by using the packet loss rate. First, the average packet loss rate in the sliding window is calculated.
  • PLR p PLR The default maximum packet loss rate, PLR p PLR, is considered to be the worst quality if the packet loss rate in the sliding window is greater than the PLR. If the packet loss rate is less than the PLR, the packet loss is considered to have no effect on the video quality:
  • the quality of the lost packet over a period of time is:
  • the effect of video pauses takes into account the effects of video pauses, re-buffering durations, and initial buffer duration over a period of time.
  • the model is as follows:
  • the purpose of the embodiments of the present invention is to provide a method for evaluating media quality, so as to solve the problem that the interaction between the multiple pause events and the impact of the media content in the video quality assessment in the prior art is not considered.
  • the impact of the initial quality of the media leads to problems that do not match the subjective perceptions of existing video quality assessments.
  • the embodiment of the present invention is implemented by the method for evaluating the quality of the media, wherein the method includes:
  • the parameter of the pause event distortion quality includes at least one of the following: the number of pause events, the pause event duration, the multiple pause event interaction influence parameters, and the media initial quality. And a media content complexity description factor.
  • a final quality of the media is determined based on the calculated media quality of each of the score segments.
  • the embodiment of the present invention further provides an apparatus for evaluating media quality, the apparatus comprising: an obtaining unit, configured to obtain a media reference quality and a distortion quality of a pause event; and a determining unit, configured to obtain a media reference quality according to the acquiring unit And the quality of the distortion of the pause event determines the final quality of the media;
  • the parameters of the stall event distortion quality include at least one of the following: the number of pause events, the duration of the pause event, the interaction impact parameter of the multiple pause events, the media initial quality, and the media content complexity description factor.
  • a device for evaluating media quality comprising:
  • a scoring segment dividing unit configured to divide the media file to be evaluated into a plurality of scoring segments; a reference quality and a staging event distortion quality, wherein the parameter of the scrambled event distortion quality of the scoring segment includes at least one of the following: a number of pause events, a pause event Duration, multiple pause events, interaction parameters, media initial quality, and media content complexity description factors; a determining unit, configured to calculate the media of each of the score segments according to the calculating unit Quality determines the final quality of the media.
  • the embodiment of the present invention considers the influence of multiple pause event interaction influence parameters, media initial quality, and media content complexity description factors on media quality when calculating media quality, thereby making media quality
  • the assessment results are more accurate and more consistent with people's subjective feelings.
  • FIG. 1 is a flowchart of implementing a media quality evaluation method according to Embodiment 1 of the present invention
  • FIG. 2 is a pause interval histogram according to Embodiment 1 of the present invention
  • FIG. 3 is a flowchart of an implementation of a media quality evaluation method according to Embodiment 2 of the present invention
  • FIG. 4 is a flowchart of an implementation of a media quality evaluation method according to Embodiment 3 of the present invention
  • FIG. 6 is a flowchart of an implementation of a media quality evaluation method according to Embodiment 5 of the present invention
  • FIG. 7 is a structural diagram of a media quality evaluation apparatus according to Embodiment 6 of the present invention
  • Figure 8 is a block diagram showing the structure of a media quality evaluation apparatus according to a seventh embodiment of the present invention.
  • the media reference quality is the distortion caused by media coding compression, which is the basic quality of encoding different media streams to different code rates under different coding types.
  • Packet loss is the damage of media frames (such as video frames and/or audio frames) caused by delay packets caused by loss or jitter of media stream packets transmitted in the network channel. Errors due to frame damage. Distortion and error propagation distortion, the degree of distortion and the magnitude of the distortion value depend on the underlying quality of the encoding.
  • the media content complexity description factor represents a description of the media content complexity of the media content in time, space or integrated time and space, for example: the faster the video sequence or the more detailed or richer the video sequence The video content complexity description factor is larger.
  • Stall event For a video sequence, the effect of the pause event is represented by repeatedly displaying the last displayed image or a continuous still image. For audio sequences, the effect of a pause event is manifested by repeating the audio of one frame/segment before playback or without sound. For audio and video sequences, the effect of the stall event is a combination of the two.
  • Embodiments of the present invention are applicable to video pauses, audio pauses, and evaluation of audio and video pause quality.
  • the media in the embodiment of the present invention includes video, audio or audio and video.
  • pause events and packet loss distortion can occur in the media simultaneously or separately.
  • the following description will be made by way of specific embodiments.
  • Embodiment 1 is a diagrammatic representation of Embodiment 1:
  • FIG. 1 is a flowchart showing an implementation process of a media quality assessment method according to Embodiment 1 of the present invention. The process is detailed as follows:
  • step S101 the media reference quality and the pause event distortion quality are obtained.
  • the media reference quality can be obtained by using the prior art, and details are not described herein again.
  • the parameters of the stall quality of the pause event include, but are not limited to, at least one of the following: the number of pause events, the pause event duration, the multiple pause event interaction influence parameters, the media initial quality, and the media content complexity description factor.
  • the parameters of the stalling event quality include, but are not limited to, at least one of the following: multiple pause event interaction influence parameters, media initial quality, and media content complexity description factor.
  • the parameter of the quality of the pause event distortion includes a media initial quality, a number of pause events, and a pause event duration
  • Q rebuf func (Video _ Quality, Rebuf _ Num, Rebuf _ Len).
  • the parameters of the quality of the pause event distortion include media initial quality, number of pause events, pause event duration, and multiple pause event interaction influence parameters
  • Q rebuf func ⁇ Video _ Quality, Rebuf _ Num, Rebuf _ Len, MultiRebuf _ Factor ⁇ .
  • Q rebuf indicates the distortion quality of the pause event
  • / indicates the initial quality of the media
  • Reb /_N indicates the number of pause events
  • Reb /_Le « indicates the duration of the pause event
  • M to'Reb /_ 3 ⁇ 4ctor indicates the interaction parameters of multiple pause events .
  • the specific calculation formula can be: ⁇ W Len t
  • Rebuf - Len , where w represents the occurrence of a pause event within the preset time
  • the total number of times, L indicates the duration of the first pause event in the preset time
  • indicates the weighting coefficient of the first pause event (can be an equal constant, or the weight set according to the pause duration, the longer the pause time , the greater the weight, the smaller the anyway)
  • Reb /_L represents the weighted average duration of the pause event within the preset time
  • the duration of the pause event is a ratio of the total duration of the pause event to the preset time in the preset time period, and the specific calculation formula may be:
  • Rebuf _ Len ⁇ -, where "represents the total number of pauses in the preset time period
  • the number, L represents the duration of the first pause event in the preset time
  • 7 me represents the preset time
  • Rebuf_Len represents the ratio of the total duration of the pause event in the preset time period to the preset time; Or the duration of the pause event is the total duration of the pause time in the preset time period, and the specific calculation formula may be:
  • Rebuf _ Len j Le ⁇ , where "represents the total number of pause events in the preset time period
  • the number, L represents the duration of the first pause event in the preset time
  • R e b / _ L represents the total duration of the pause time in the preset time.
  • the weighted average duration of the pause event time interval in the preset time is according to the preset time pause event and the front The time interval of a pause event and the weighting factor of the pause event are obtained.
  • the specific calculation formula can be:
  • MultiRebuf _ Factor ⁇ ⁇ , where; ⁇ represents the total number of pause events in the preset time, /w e rv represents the time interval between the first pause event and the previous pause event in the preset time, for example, the current pause The distance between the start time of the time and the end time of the previous pause event; the weighting coefficient indicating the first pause event (can be an equal constant, or the weight set according to the pause interval time. The longer the interval, the greater the weight, anyway The smaller the value, MultiRebuf—Factor represents the weighted average duration of the pause event interval within the preset time.
  • the weighting coefficient may also be set according to a preset rule, and the preset rule includes setting according to the length of the pause event time interval or according to the number of pauses occurring within the same pause interval time.
  • the horizontal axis t represents the length of the pause interval, that is, the distance between the start time of the current pause time and the end time of the previous pause event
  • the vertical axis N m represents the number of pauses occurring during the same pause interval ; It can be set according to N m, and the larger the N m is, the larger the weight is.
  • it may be the media reference quality or the media quality after packet loss distortion.
  • the higher ⁇ 0 _ ⁇ ⁇ ⁇ the greater the decrease.
  • the larger the Rebuf _ Num or Rebuf _ Len or MultiRebuf _ Factor the greater the impact of media quality and the more the media quality declines.
  • the quality of the pause event distortion may be obtained according to the initial quality of the media, the number of pause events, and the duration of the pause event, and the distortion quality of the pause event is b /_N m , Rebuf _ Len , MultiRebuf _ Factor linear, Nonlinear or a combination of linear and nonlinear, the specific calculation formula of the distortion quality of the pause event may be:
  • the pause event distortion quality is based on the initial quality of the media, the number of pause events, and the pause event
  • e b4 (Video_Quality-MOS vm )- ' Rebif _Nm b + - Rebif _Nm dl + ) ⁇
  • ⁇ ⁇ indicates the media minimum quality ( a constant greater than 0)
  • b M /_N represents the number of pause events in the score segment (the media sequence within a preset period of time)
  • Rebuf _ Len indicates the duration of the pause time within the score segment
  • MultiRebuf _ Factor indicates the preset
  • the weighted average duration of the time interval of pause events, ⁇ , ⁇ 2 , ⁇ » 2 is 1 $t.
  • the specific calculation formula for determining the final quality of the media according to the obtained media reference quality and the stall quality of the pause event may be:
  • Q v Q coding - Q rebuf , which represents the final quality of the media, ⁇ ⁇ represents the media reference quality, and represents the quality of the pause event distortion.
  • Embodiment 2 is a diagrammatic representation of Embodiment 1:
  • FIG. 3 is a flowchart showing an implementation process of a media quality assessment method according to Embodiment 2 of the present invention. The process is detailed as follows:
  • step S301 the media reference quality, the acquired packet distortion quality, and the stall event distortion quality are acquired.
  • the quality of the media reference and the quality of the packet loss can be obtained by using the prior art, and details are not described herein again.
  • the distortion quality of the pause event is obtained by the method of the first embodiment.
  • the parameters of the stall event distortion quality include at least one of the following: the number of pause events, the duration of the pause event, the interaction impact parameter of the multiple pause events, the media initial quality, and the media content complexity description factor.
  • the final media quality c (whi , ⁇ . 5 ⁇ , ;> is determined according to the acquired media reference quality, the packet loss distortion quality, and the stall event distortion quality.
  • the specific calculation formula for determining the final quality of the media according to the obtained media reference quality, packet loss distortion quality, and pause event distortion quality may be:
  • Q rebuf [Q codmg - MOS ⁇ ) - func (Rebuf_Num, Rebuf_Len, MultiRebuf_F actor) '
  • Q v denotes the final quality of the media, which indicates the quality of the media reference, which indicates the quality of the packet loss distortion, and indicates the quality of the distortion of the pause event.
  • the initial quality of the media is also calculated according to the obtained media reference quality and the quality of the packet loss distortion, and the quality of the suspended event is obtained according to the obtained event.
  • Q rebuf ⁇ Video _ Quality - MOS ⁇ ) ⁇ func [Rebuf_N urn, Rebuf_Len, MultiRebuf_F actor) and the calculated media initial quality to determine the final quality of the media.
  • Embodiment 3 is a diagrammatic representation of Embodiment 3
  • FIG. 4 is a flowchart showing an implementation process of a media quality assessment method according to Embodiment 3 of the present invention. The process is detailed as follows:
  • step S401 the media reference quality and the pause event distortion quality are obtained.
  • the parameter of the quality of the pause event includes the initial quality of the media, the number of pause events, the duration of the pause event, and the media content complexity description factor Q rebuf - func ⁇ Video Quality, Rebuf Num, Rebuf Lm, Complexity Factor ) or
  • the parameters of the stop event distortion quality include the number of pause events, the duration of the pause event And the media content is complex
  • Q rebuf func ⁇ Rebuf _ Num, Rebuf _ Len, Complxity - Factor); or the parameter of the pause event distortion quality includes the number of pause events, the duration of the pause event, the interaction effect of multiple pause events
  • Q rebuf func [Rebuf _ Num, Rebuf _ Len, MultiRebuf _ Factor, Complxity _ Factor).
  • the pause information in the first embodiment including Rebuf_Num, Rebuf_Len, Factor
  • media initial quality combined with the media content complexity description factor to calculate the stall event distortion quality.
  • the quality of the pause event distortion is obtained according to the initial quality of the media, the number of pause events, the duration of the pause event, and the media content complexity description factor, and the specific calculation formula may be:
  • the quality of the mediation of the pause event is obtained according to the initial quality of the media, the number of pause events, the duration of the pause event, the interaction parameter of the multiple pause event, and the media content complexity description factor, and the specific calculation formula may be :
  • Video _ Quality is the media initial quality
  • MO ⁇ n is the media minimum quality
  • Rebuf _ Num is the number of pause events in the preset time
  • R e b / _ L is the duration of the pause time in the preset time
  • MultiRebuf _ Factor Indicates the weighted average duration of the pause interval in the preset time.
  • CompZe; y _ 3 ⁇ 4ctor indicates the complexity of the media content in each preset time period, ⁇ , ⁇ is a constant.
  • FIG. 5 is a flowchart showing an implementation process of a media quality assessment method according to Embodiment 4 of the present invention. The process is detailed as follows:
  • step S501 the media reference quality, the lost packet distortion quality, and the stall event distortion quality are acquired.
  • the quality of the media reference and the quality of the packet loss can be obtained by using the prior art, and details are not described herein again.
  • the distortion quality of the pause event is obtained by the method of the third embodiment.
  • the parameters of the quality of the pause event include the media initial quality, the number of pause events, the duration of the pause event, and the media content complexity description factor.
  • the parameter of the stop event distortion quality includes media initial quality, number of pause events, pause event Duration, multiple pause event interaction influence parameters, and media content complexity description factor
  • Q rebuf (Video _ Quality - MOS ⁇ ) ⁇ func ⁇ Rebuf _ Lm, Rebuf _ Num, MultiRebuf _ Factor) ⁇ The said •fund ( Complexity _ Factor).
  • the quality of the pause event distortion can be obtained according to the initial quality of the media, the number of pause events, the duration of the pause event, and the media content complexity description factor;
  • the quality of the pause event distortion is obtained according to the initial quality of the media, the number of pause events, the duration of the pause event, the interaction impact parameter of the multiple pause events, and the media content complexity description factor;
  • the quality of the pause event distortion is obtained according to the number of pause events, the duration of the pause event, and the media content complexity description factor;
  • the pause event distortion quality is obtained according to the number of pause events, the pause event duration, the multiple pause event interaction influence parameters, and the media content complexity description factor.
  • Embodiment 5 is a diagrammatic representation of Embodiment 5:
  • FIG. 6 is a flowchart showing an implementation process of a media quality assessment method according to Embodiment 5 of the present invention. The process is detailed as follows:
  • step S601 the media file to be evaluated is divided into a plurality of scoring segments.
  • the media file to be evaluated is divided into a plurality of rating segments according to a pause event or a pause time.
  • step S602 the media reference quality and the pause event distortion quality of each of the score segments are obtained, and the parameters of the pause event distortion quality of the score segment include at least one of the following: the number of pause events, the pause event duration, and the multiple pause events. Interactions affect parameters, media initial quality, and media content complexity description factors.
  • step S603 the media quality of each of the score segments is calculated according to the acquired media reference quality and the stall event distortion quality of each of the score segments.
  • the media quality of each score segment can be obtained by using the media quality calculation method of the first, second, third or fourth embodiment to obtain 3 ⁇ 4, Q) f.
  • a weight is set for each score segment according to the pause duration of each score segment pause event, or a weight is set for each score segment according to each score segment pause quality score or a pause model impact factor;
  • the media quality of the N score segments is lower than the preset media quality, the lowest media quality of the N score segments or the average of the N score segment media qualities is used as the final quality of the media, where The N is greater than or equal to an integer of 1.
  • Fig. 7 is a view showing the configuration of a medium quality evaluation apparatus according to a sixth embodiment of the present invention. For the convenience of description, only parts related to the embodiment of the present invention are shown.
  • the media quality evaluation device can be applied to various information terminals (television, mobile phone, computer, personal digital assistant, etc.), and can be a software unit, a hardware unit or a combination of hardware and software running in these terminals, or As independent pendants integrated into these terminals or in the application system of these terminals.
  • the media quality evaluation device 7 includes an acquisition unit 71 and a determination unit 72. Among them, the specific functions of each unit are as follows:
  • the obtaining unit 71 is configured to obtain media reference quality and pause event distortion quality
  • a determining unit 72 configured to determine a media final quality according to the media reference quality acquired by the acquiring unit 71 and the quality of the stall event distortion;
  • the parameters of the pause event distortion quality include at least one of the following: the number of pause events, the pause event duration, the multiple pause event interaction influence parameters, the media initial quality, and the media content complexity. Description factor.
  • the acquiring unit 71 is further configured to acquire a packet loss distortion quality.
  • the determining unit 72 is further configured to determine a media final quality according to the media reference quality, the packet distortion quality, and the stall event distortion quality acquired by the acquiring unit 71.
  • the determining unit 72 is specifically configured to calculate a media initial quality according to the obtained media reference quality and packet loss distortion quality, and then determine a media final quality according to the obtained pause event distortion quality and the calculated media initial quality.
  • the quality of the pause event is obtained according to the initial quality of the media, the number of pause events, and the duration of the pause event; or the quality of the pause event is based on the initial quality of the media, the number of pause events, and the duration of the pause event.
  • the multiple pause event interaction affects the parameter obtaining; or, the pause event distortion quality is obtained according to the media initial quality, the number of pause events, the pause event duration, and the media content complexity description factor; or, the pause event distortion quality Obtaining according to the media initial quality, the number of pause events, the pause event duration, the multiple pause event interaction influence parameter, and the media content complexity description factor; or, the pause event distortion quality is based on the pause event number, the pause event duration And the media content complexity description factor is obtained; or, the pause event distortion quality is described according to the number of pause events, the duration of the pause event, the interaction parameter of the multiple pause events, and the complexity of the media content. Son get.
  • the duration of the pause event is a weighted average duration of the pause event in the preset time period, and the weighted average duration of the pause event in the preset time period is obtained according to the duration of the pause event in the preset time period and the weighting coefficient of the pause event; or
  • the duration of the pause event is the ratio of the total duration of the pause event to the preset time in the preset time; or the duration of the pause event is the total duration of the pause time in the preset time.
  • the multiple pause event interaction influence parameter is a weighted average duration of the pause event interval in the preset time, and the weighted average duration of the pause event interval in the preset time is based on the pause event and the previous time in the preset time
  • the time interval of the pause event and the weighting factor of the pause event are paid.
  • the weighting factor is set according to the length of the pause event time interval or according to the number of times of the same pause interval.
  • the media quality evaluation apparatus may use the foregoing corresponding media quality evaluation method.
  • the media quality evaluation apparatus may use the foregoing corresponding media quality evaluation method.
  • Fig. 8 is a view showing the configuration of a medium quality evaluation apparatus according to a seventh embodiment of the present invention. For the convenience of description, only parts related to the embodiment of the present invention are shown.
  • the media quality evaluation device can be applied to various information terminals (television, mobile phone, computer, personal digital assistant, etc.), and can be a software unit, a hardware unit or a combination of hardware and software running in these terminals, or As independent pendants integrated into these terminals or in the application system of these terminals.
  • the media quality evaluation apparatus 8 includes a scoring section dividing unit 81, an obtaining unit 82, a calculating unit 83, and a determining unit 84. Among them, the specific functions of each unit are as follows:
  • a scoring segment dividing unit 81 configured to divide the media file to be evaluated into a plurality of scoring segments; and an obtaining unit 82, configured to acquire media benchmark quality and pause of each of the scoring segments divided by the scoring segment dividing unit 81
  • the event distortion quality, the parameter of the stall event distortion quality of the score segment includes at least one of the following: a number of pause events, a pause event duration, a plurality of pause event interaction influence parameters, a media initial quality, and a media content complexity description factor;
  • the calculating unit 83 is configured to calculate, according to the media reference quality and the pause event distortion quality of each of the score segments acquired by the obtaining unit 82, the media quality of each of the score segments divided by the score segment dividing unit 81;
  • the determining unit 84 is configured to determine a final quality of the media according to the media quality of each of the score segments calculated by the calculating unit 83.
  • the score segment dividing unit 81 is specifically configured to divide the media file to be evaluated into multiple score segments according to the pause event or the pause time.
  • the determining unit 84 includes:
  • the weight setting module 841 is configured to set a weight for each score segment according to a pause duration of each score segment pause event, or set a weight for each score segment according to each score segment pause quality score or a pause model impact factor;
  • a determining module 842 configured to perform a weighting operation on a media quality of each scoring segment of the media according to the weight set by the weight setting module 841, and use a weighted average obtained by the weighting operation as a final of the media quality.
  • the determining unit 84 is configured to use the lowest media quality of the N score segments or the N score segment media qualities. Mean as the final quality of the media, wherein the N is greater than or equal to 1
  • the media quality evaluation apparatus provided in this embodiment may use the foregoing corresponding media quality evaluation method.
  • the media quality evaluation apparatus may use the foregoing corresponding media quality evaluation method.
  • each unit and module included in the foregoing embodiments 6 and 7 is only divided according to functional logic, but is not limited to the above division, as long as the corresponding functions can be implemented;
  • the specific names of the functional units and modules are also for convenience of distinguishing from each other and are not intended to limit the scope of the present invention.
  • the embodiment of the present invention considers the influence of multiple pause event interaction influence parameters, media initial quality, and media content complexity description factor on media quality when calculating media quality, so that the media quality evaluation result is more accurate. , more consistent with people's subjective feelings.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本发明适用于通信领域,提供了一种媒体质量的评估方法及装置,所述方法包括:获取媒体基准质量及停顿事件失真质量;根据所获取的媒体基准质量及停顿事件失真质量确定媒体最终质量;所述停顿事件失真质量的参数包括以下至少一个:停顿事件次数、停顿事件时长、多次停顿事件相互作用影响参数、媒体初始质量以及媒体内容复杂度描述因子。由于本发明在计算媒体质量时考虑了多次停顿事件相互作用影响参数、媒体初始质量以及媒体内容复杂度描述因子对媒体质量的影响,从而使得媒体质量的评估结果更准确,与人的主观感受更相符。

Description

说 明 书 一种媒体质量的评估方法及装置 技术领域
本发明属于通信技术领域, 尤其涉及一种媒体质量的评估方法及装置。 背景技术
视频质量评估是视频应用中必不可少的一项重要技术。 视频质量受到许多 复杂因素的影响, 包括: 传输信道的服务质量(例如带宽、 丟包、 时延、 抖动 等) 、 以及视频编解码端参数与传输信道的适配情况(例如编码方式、 视频分 辨率、 视频帧率、 抗误码强度、 编解码端緩沖控制策略是否合适等)。 除了信 道丟包、 编码方式等引起视频数据丟失导致视频质量下降之外, 信道时延和抖 动引起视频停顿或卡顿也会严重影响视频的质量。
现有的视频质量评估模型考虑了编码质量的影响、 视频停顿的影响以及网 络丟包的影响:
= f匿 {Q , Q , Q腿1 pl )
其中, 编码质量考虑了码流和编码格式的影响:
QuaLcoding = c0 - c1 - e- -x
C。,c^p /L为常量, 不同编码格式可以有不同的值。
网络丟包质量利用丟包率进行计算, 首先计算滑动窗内的平均丟包率
Figure imgf000002_0001
预设最大丟包率 PLR p PLR, , 如果滑动窗内的丟包率大于 PLR„, 则认为是 最差质量, 如果丟包率小于 PLR, , 则认为此次丟包对视频质量没有影响:
PLRt = min ( PLRj, PLRu ), and PLRt = max ( PLRj, PLRt ) 在一段时间内丟包的质量为:
Qualpl = const
Figure imgf000003_0001
_ 1)· + 1
, ― PLR - PLR Π < < 1
_ PLRu - PLRt
视频停顿的影响考虑了一段时间内视频停顿的次数、 re-buffering时长和 初始 buffer时长的影响, 模型如下:
Qualbuff =C0+C INIT _ PERC + C2 BUF_ PERC + C3 BUF_ FRQ 最终视频质量为:
TOT _ MOSpred = Qualpl - Qualbuff 现有技术在视频质量评估时, 没有考虑一段时间内多次停顿事件之间的相 互作用影响参数、 视频内容的影响以及视频初始质量的影响, 导致现有视频质 量评估结果不够准确, 与人的主观感受存在差距。 技术问题
本发明实施例的目的在于提供一种媒体质量的评估方法, 以解决现有技术 在视频质量评估时, 没有考虑一段时间内多次停顿事件之间的相互作用影响参 数、 媒体内容的影响以及始媒体初始质量的影响, 导致现有视频质量评估结果 与人的主观感受不相符的问题。 技术解决方案
本发明实施例是这样实现的, 一种媒体质量的评估方法, 其特征在于, 所 述方法包括:
获取媒体基准质量及停顿事件失真质量;
根据所获取的媒体基准质量及停顿事件失真质量确定媒体最终质量; 所述停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事 件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度 描述因子。 一种媒体质量的评估方法, 所述方法包括:
将待评估的媒体划分为多个评分段;
获取每个所述评分段的媒体基准质量及停顿事件失真质量, 所述评分段的 停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事件时长、 多次停顿事件相互作用影响参数、媒体初始质量以及媒体内容复杂度描述因子; 根据所获取的每个所述评分段的媒体基准质量及停顿事件失真质量计算每 个所述评分段的媒体质量;
根据计算得到的所述每个所述评分段的媒体质量确定所述媒体的最终质 量。
本发明实施例还提供了一种媒体质量的评估装置, 所述装置包括: 获取单元, 用于获取媒体基准质量及停顿事件失真质量; 确定单元, 用于 根据所述获取单元获取的媒体基准质量及停顿事件失真质量确定媒体最终质 量;
所述停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事 件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度 描述因子。
一种媒体质量的评估装置, 所述装置包括:
评分段划分单元, 用于将待评估的媒体文件划分为多个评分段; 基准质量及停顿事件失真质量, 所述评分段的停顿事件失真质量的参数包括以 下至少一个: 停顿事件次数、停顿事件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度描述因子;
Figure imgf000004_0001
确定单元, 用于根据所述计算单元计算得到的所述每个所述评分段的媒体 质量确定所述媒体的最终质量。 有益效果
从上述技术方案中可以看出, 本发明实施例在计算媒体质量时考虑了多次 停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度描述因子对媒 体质量的影响,从而使得媒体质量的评估结果更准确, 与人的主观感受更相符。 附图说明
为了更清楚地说明本发明实施例中的技术方案, 下面将对实施例或现有技 术描述中所需要使用的附图作筒单地介绍, 显而易见地, 下面描述中的附图仅 仅是本发明的一些实施例, 对于本领域普通技术人员来讲, 在不付出创造性劳 动性的前提下, 还可以根据这些附图获得其他的附图。
图 1是本发明实施例一提供的媒体质量的评估方法的实现流程图; 图 2是本发明实施例一提供的停顿间隔直方图;
图 3是本发明实施例二提供的媒体质量的评估方法的实现流程图; 图 4是本发明实施例三提供的媒体质量的评估方法的实现流程图; 图 5是本发明实施例四提供的媒体质量的评估方法的实现流程图; 图 6是本发明实施例五提供的媒体质量的评估方法的实现流程图; 图 7是本发明实施例六提供的媒体质量的评估装置的组成结构图; 图 8是本发明实施例七提供的媒体质量的评估装置的组成结构图。 本发明的实施方式
为了使本发明的目的、 技术方案及优点更加清楚明白, 以下结合附图及实 施例, 对本发明进行进一步详细说明。 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。
为了更好的理解本发明实施例, 下面对本发明实施例中出现的一些概念进 行下说明:
媒体基准质量是由于媒体编码压缩造成的失真, 是在不同的编码类型下不 同媒体流编码为不同码率的基础质量。
丟包失真是在网络信道中传输的媒体流数据包由于丟失或抖动造成的时延 丟包而引起媒体帧(例如: 视频帧和 /或音频帧)的损伤, 由于帧的损伤造成的 误码失真和误码传播失真, 失真的程度和失真值大小依赖于编码的基础质量。
媒体内容复杂度描述因子表示媒体内容在时间上、 空间上或者综合时间和 空间上的媒体内容复杂度的描述, 例如: 运动越快的视频序列或者内容细节越 多或色彩越丰富的的视频序列, 视频内容复杂度描述因子越大。
停顿事件: 对于视频序列, 停顿事件的影响具体表现为重复显示上一幅显 示的图像或者连续静止图像。 对于音频序列, 停顿事件的影响具体表现为重复 播放之前一帧 /段时间的音频或者静止没有声音。 对于音视频序列, 停顿事件的 影响是上述两者的组合。
本发明实施例可应用于视频停顿、 音频停顿、 音视频停顿质量的评估。 本 发明实施例所述媒体包括视频、 音频或者音视频。
在实际应用中, 停顿事件和丟包失真可以同时或者单独出现在媒体中。 为了说明本发明所述的技术方案, 下面通过具体实施例来进行说明。
实施例一:
图 1示出了本发明实施例一提供的媒体质量评估方法的实现流程, 该方法 过程详述如下:
在步骤 S101中, 获取媒体基准质量及停顿事件失真质量。
在本实施例中, 媒体基准质量可以采用现有技术获取, 在此不再赘述。 停 顿事件失真质量的参数包括但不局限于以下至少一个: 停顿事件次数、 停顿事 件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度 描述因子。 或者停顿事件失真质量的参数包括但不局限于以下至少一个: 多次 停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度描述因子。 具体的, 所述停顿事件失真质量的参数包括媒体初始质量、 停顿事件次数 以及停顿事件时长, Qrebuf = func (Video _ Quality, Rebuf _ Num, Rebuf _ Len)。 或者所述 停顿事件失真质量的参数包括媒体初始质量、 停顿事件次数、 停顿事件时长以 及 多 次 停 顿 事 件 相 互 作 用 影 响 参 数 , Qrebuf = func {Video _ Quality, Rebuf _ Num, Rebuf _ Len, MultiRebuf _ Factor^。其中, Qrebuf表 示停顿事件失真质量, / 表示媒体初始质量, Reb /_N画表示停顿事 件次数, Reb /_Le«表示停顿事件时长, M to'Reb /_ ¾ctor表示多次停顿事件相 互作用影响参数。
其中, Rebuf _ _ Num = n ·> n表示预设时间内停顿事件发生的总次数; 当所述停顿事件时长为预设时间内停顿事件的加权平均时长, 所述预设时 间内停顿事件的加权平均时长根据预设时间内停顿事件持续的时长以及停顿事 件的加权系数获得, 其具体计算公式可以为: ^W Lent
Rebuf - Len = ,其中 w表示所述预设时间内停顿事件发生的
i=l
总次数, L ;表示所述预设时间内第 次停顿事件持续的时长, ^表示第 次停 顿事件的加权系数(可以是相等的常数, 也可以是根据停顿时长设置的权重, 停顿时间越长, 权重越大, 反正越小), Reb /_L 表示预设时间内停顿事件的 加权平均时长;
或者, 所述停顿事件时长为预设时间内停顿事件持续的总时长与所述预设 时间的比值, 其具体计算公式可以为:
Rebuf _ Len = ^——,其中"表示所述预设时间内停顿事件发生的总次
Time
数, L ;表示预设时间内第 次停顿事件持续的时长, 7 me表示所述预设时间,
Rebuf _ Len表示预设时间内停顿事件持续的总时长与所述预设时间的比值; 或者, 所述停顿事件时长为预设时间内停顿时间持续的总时长, 其具体计 算公式可以为:
Rebuf _ Len = j Le^ ,其中"表示所述预设时间内停顿事件发生的总次
!■ = 0
数, L ;表示预设时间内第 次停顿事件持续的时长, Reb / _ L 表示预设时间 内停顿时间持续的总时长。
当所述多次停顿事件相互作用影响参数为预设时间内停顿事件时间间隔的 加权平均时长, 所述预设时间内停顿事件时间间隔的加权平均时长根据所述预 设时间内停顿事件与其前一次停顿事件的时间间隔以及停顿事件的加权系数获 得, 其具体计算公式可以为:
^ . - Interval
MultiRebuf _ Factor = ^ ~~ ,其中; ^表示预设时间内停顿事件发 生的总次数, /werv 表示预设时间内的第 次停顿事件与其前一次停顿事件的 时间间隔, 例如为当前停顿时间开始时刻与前一次停顿事件结束时刻的间距, ;表示第 次停顿事件的加权系数(可以是相等的常数, 也可以是根据停顿间 隔时间设置的权重, 间隔时间越长, 权重越大, 反正越小), MultiRebuf— Factor 表示预设时间内停顿事件时间间隔的加权平均时长。
在本实施例中, 所述加权系数还可以根据预设规则设定, 所述预设规则包 括根据停顿事件时间间隔的长短设定或者根据相同停顿间隔时间内发生的停顿 次数设定。
图 2表示停顿间隔次数的直方图, 横轴 t表示停顿间隔长度, 即当前停顿 时间开始时刻与前一次停顿事件结束时刻的间距, 纵轴 N m表示相同停顿间隔 时间内发生的停顿次数, ;可以根据 N m设定, N m越大, 权重越大。
在本实施例中, 可以是媒体基准质量,也可以是丟包失真后的 媒体质量。 在相同停顿事件下, ν^0 _ βΜΩΖ 越高, 可下降幅度越大。 在相同 Video _ Quality下 , Rebuf _ Num或 Rebuf _ Len或 MultiRebuf _ Factor越大 ,媒体质量影 响越大, 媒体质量下降越多。
在本实施例中, 所述停顿事件失真质量可以根据所述媒体初始质量、 停顿 事件次数以及停顿事件时长获得, 所述停顿事件失真质量为 b /_N m、 Rebuf _ Len、 MultiRebuf _ Factor线性、 非线性或者线性与非线性的组合, 所述停 顿事件失真质量的具体计算公式可以为:
Rebuf _ Len | ( Rebuf _ Num
Quality—MO S 或者
Rebuf _ Len | ( Rebuf _ Num
1 +
a
Qrebuf = {Video _ Quality MOSmin )·(<¾· Rebuf _ Len1"1 + cx · Rebuf _ Num
或 者 ( 2 · Rebuf _ Len2 + c2 · Rebuf _
= [Video _ Quality - MOSn
Figure imgf000009_0001
, 或者
所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停顿事件
Q,ebuf =
Figure imgf000009_0002
, 或者
eb4=(Video_Quality-MOSvm)- ' Rebif _Nmb + - Rebif _Nmdl + )·
Figure imgf000009_0003
-\- -Rebif _Nwndl + )·
Figure imgf000009_0004
, 或者
Figure imgf000010_0001
(<¾ - Rebuf _Nwnl +q - Rebuf _Numl +e^-{^a1- Rebuf _Lsn +c2 -Rehf _Num2 + )·
(<¾ 'Re ff Jrtterm 3 + ■ Rebuf _Intervdds + ) ·(<¾ - MdtiRebf _Factor4 +c4 - AMtiRebuf _ Facto/4 +e4) 其中 为媒体初始质量, ΜΟ^η表示媒体最低质量(大于 0的常 数) , bM/_N画表示评分段(预设的一段时间内的媒体序列) 内的停顿事件 次数, Rebuf _ Len表示评分段内停顿时间持续的时长, MultiRebuf _ Factor表示预 设时间内停顿事件时间间隔的加权平均时长, αι2,α»21 $t。
在步骤 S102中,根据所获取的媒体基准质量及停顿事件失真质量确定媒体 最终质量 βν = func(Qmding,Qrebuf )。 在本实施例中, 所述根据所获取的媒体基准质量及停顿事件失真质量确定 媒体最终质量的具体计算公式可以为:
Qv = Qcoding - Qrebuf , 其中 表示媒体最终质量, β∞ώ 表示媒体基准 质量, 表示停顿事件失真质量。
实施例二:
图 3示出了本发明实施例二提供的媒体质量评估方法的实现流程, 该方法 过程详述如下:
在步骤 S301中,获取媒体基准质量、获取丟包失真质量及停顿事件失真质 量。
在本实施例中, 媒体基准质量及丟包失真质量可以采用现有技术获取, 在 此不再赘述。 停顿事件失真质量采用实施例一的方法获取。
所述停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事 件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度 描述因子。
在步骤 S302中,根据所获取的媒体基准质量、丟包失真质量及停顿事件失 真质量确定媒体最终质量 = c ( „ , β^。 , ;>。 在本实施例中, 所述根据所获取的媒体基准质量、 丟包失真质量及停顿事 件 失真质 量确 定媒体最终质 量 的 具体计 算公式可 以 为 :
Q Q Q - Q re b uf , 其 中
Qrebuf = [Qcodmg - MOS^ ) - func (Rebuf_Num, Rebuf_Len, MultiRebuf_F actor) ' Qv表示媒体最终 质量, 表示媒体基准质量, 表示丟包失真质量, 表示停顿事件 失真质量。
优选的是, 还可以根据所获取的媒体基准质量和丟包失真质量计算媒体初 始 质 量 , 再 根 据 所 获 取 的 停 顿 事 件 失 真 质 量
Qrebuf = {Video _ Quality - MOS^ ) · func [Rebuf_N urn, Rebuf_Len, MultiRebuf_F actor)以及计算 得到的媒体初始质量确定媒体最终质量。 其中, 所述根据所获取的停顿事件失 真质量以及计算得到的媒体初始质量确定媒体最终质量的具体计算公式可以 为: βν = Video― Quality - Qrebuf , 其中 βν表示媒体最终质量 , Video _ Quality表示 媒体初始质量, 2refcM/表示停顿事件失真质量。
实施例三:
图 4示出了本发明实施例三提供的媒体质量评估方法的实现流程, 该方法 过程详述如下:
在步骤 S401中, 获取媒体基准质量及停顿事件失真质量。
当媒体基准质量相同时, 不同内容特性的媒体对于相同的停顿事件, 主观 质量是不一样的, 例如: 相比运动小的媒体, 停顿对运动大的媒体造成的影响 更大。 因此在本实施例中, 所述停顿事件失真质量的参数包括媒体初始质量、 停顿事件次数、 停顿事件时长以及媒体内 容复杂度描述因子 Qrebuf - func {Video Quality, Rebuf Num, Rebuf Lm, Complexity Factor) 或
Qrebuf = (Video _ Quality - MOS^n ) · func {Rebuf _ Len, Rebuf _ Num) · fund ( Complexity _ Factor); 或 者所述停顿事件失真质量的参数包括媒体初始质量、 停顿事件次数、 停顿事件 时长、 多次停顿事件相互作用影响参数以及媒体内容复杂度描述因子 Qrebuf = {Video _ Quality - MOS^n ) · func {Rebuf _ Len. Rebuf _ Num、 · fund ( Complexity _ Factor^ 或
Qrebuf = {Video _ Quality - MOS^ ) · func {Rebuf _ Len, Rebuf _ Num, MultiRebuf _ Factor) · 者所述 •fund ( Complexity _ Factor 停顿事件失真质量的参数包括停顿事件次数、 停顿事件时长以及媒体内容复杂 逸 千 Qrebuf = func {Rebuf _ Num, Rebuf _ Len, Complxity— Factor); 或者所述停顿事件失 真质量的参数包括停顿事件次数、 停顿事件时长、 多次停顿事件相互作用影响 参 数 以 及 媒 体 内 容 复 杂 度 描 述 因 子 Qrebuf = func [Rebuf _ Num, Rebuf _ Len, MultiRebuf _ Factor, Complxity _ Factor)。 在本实施例中, 除了使用实施例一中的停顿信息 ( 括 Rebuf _ Num、 Rebuf — Len、
Figure imgf000012_0001
Factor )和 /或媒体初始质量夕卜, 结合媒体内容复杂度描 述因子计算停顿事件失真质量。 媒体内容复杂度描述因子越大, 停顿事件失真 质量越大。
在本实施例中, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件 次数、 停顿事件时长以及媒体内容复杂度描述因子获得, 其具体的计算公式可 以为:
Rebvf—Len Rebvf—Num Conplodty _Factor
Rebvf—Num Conplodty _Factor
Figure imgf000012_0002
,或者所述所述停顿事件失真质量根据所述媒体初始质量、停顿事件次数、 停顿事件时长、 多次停顿事件相互作用影响参数以及媒体内容复杂度描述因子 获得获得, 其具体的计算公式可以为:
Figure imgf000012_0003
其中 Video _ Quality为媒体初始质量, MO^n表示媒体最低质量, Rebuf _ Num 表示预设时间内的停顿事件次数, Reb / _ L 表示预设时间内停顿时间持续的时 长, MultiRebuf _ Factor表示预设时间内停顿事件时间间隔的加权平均时长, CompZe; y _ ¾ctor表示每个预设时间段内媒体内容复杂度, ^^ ,^为常数。
在步骤 S402中,根据所获取的媒体基准质量及停顿事件失真质量确定媒体 最终质量 βν = func (Qcoding , Qrebuf )。 实施例四:
图 5示出了本发明实施例四提供的媒体质量评估方法的实现流程, 该方法 过程详述如下:
在步骤 S501中,获取媒体基准质量、获取丟包失真质量及停顿事件失真质 量。
在本实施例中, 媒体基准质量及丟包失真质量可以采用现有技术获取, 在 此不再赘述。 停顿事件失真质量采用实施例三的方法获取。
所述停顿事件失真质量的参数包括媒体初始质量、 停顿事件次数、 停顿事 件 时 长 以 及 媒 体 内 容 复 杂 度 描 述 因 子
Qrebuf - func {Video Quality, Rebuf Num, Rebuf Lm, Complexity Factor) 或
Qrebuf = {Video _ Quality - MOS^ ) · func {Rebuf _ Len, Rebuf _ Num) · func2 ( Complexity _ Factor); 或 者所述停顿事件失真质量的参数包括媒体初始质量、 停顿事件次数、 停顿事件 时长、 多次停顿事件相互作用影响参数以及媒体内容复杂度描述因子
Qrebuf = {Video _ Quality - MOS^ ) · func {Rebuf _ Len, Rebuf _ Num) · fund ( Complexity _ Factor) 或
Qrebuf = (Video _ Quality - MOS^ ) · func {Rebuf _ Lm, Rebuf _ Num, MultiRebuf _ Factor) · 者所述 •fund ( Complexity _ Factor 停顿事件失真质量的参数包括停顿事件次数、 停顿事件时长以及媒体内容复杂 度 4 述因子 = func [Rebuf _ Num, Rebuf _ Len, Complxity _ Factor); 或者所述停顿事件失 真质量的参数包括停顿事件次数、 停顿事件时长、 多次停顿事件相互作用影响 参 数 以 及 媒 体 内 容 复 杂 度 描 述 因 子 Qrebuf = func (Rebuf _ Num, Rebuf _ Len, MultiRebuf _ Factor, Complxity _ Factor)。
即所述停顿事件失真质量可以根据所述媒体初始质量、 停顿事件次数、 停 顿事件时长以及媒体内容复杂度描述因子获得;
或者, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停 顿事件时长、 多次停顿事件相互作用影响参数以及媒体内容复杂度描述因子获 付;
或者, 所述停顿事件失真质量根据所述停顿事件次数、 停顿事件时长以及 媒体内容复杂度描述因子获得;
或者, 所述停顿事件失真质量根据所述停顿事件次数、 停顿事件时长、 多 次停顿事件相互作用影响参数以及媒体内容复杂度描述因子获得。
在步骤 S502中,根据所获取的媒体基准质量、丟包失真质量及停顿事件失 真质量确定媒体最终质量 βν = func (Qencoding , QpktJost , Qrebuf )
实施例五:
图 6示出了本发明实施例五提供的媒体质量评估方法的实现流程, 该方法 过程详述如下:
在步骤 S601中, 将待评估的媒体文件划分为多个评分段。
优选的是, 将待评估的媒体文件根据停顿事件或者停顿时间划分为多个评 分段。
在步骤 S602 中, 获取每个所述评分段的媒体基准质量及停顿事件失真质 量,所述评分段的停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容 复杂度描述因子。
在步骤 S603中,根据所获取的每个所述评分段的媒体基准质量及停顿事件 失真质量计算每个所述评分段的媒体质量。
在本实施例中, 每个评分段的媒体质量可采用实施例一、 二、 三或四的媒 体质量计算方法获得 ¾ , Q ) f。 在步骤 S604中,根据计算得到的所述每个所述评分段的媒体质量确定所述 媒体的最终质量 β = 其中 β表示所述媒体的最终质量, β;表示每个评 分段(预设的一段时间内的媒体序列 ) 的媒体质量。
具体的, 根据每个评分段停顿事件的停顿时长为每个评分段设置权重, 或 者根据每个评分段停顿质量分数或者停顿模型影响因子为每个评分段设置权 重;
根据设置的所述权重,对所述媒体的每个评分段的媒体质量进行加权运算, 将加权运算后得到的加权平均值作为所述媒体的最终质量 (例如 β = βι Χ Ωι2 χΩ2 +〜 + βη Χ Ωη , Ω;表示第 i个评分段的权重) 。 或者,
当存在 N个评分段的媒体质量低于预设的媒体质量时,将所述 N个评分段 中最低的媒体质量或者所述 N个评分段媒体质量的均值作为所述媒体的最终质 量, 其中所述 N大于或等于 1的整数。
实施例六:
图 7示出了本发明实施例六提供的媒体质量的评估装置的组成结构, 为了 便于说明, 仅示出了与本发明实施例相关的部分。
该媒体质量的评估装置可以应用于各种信息终端(电视机、 手机、 计算机、 个人数字助理等) , 可以是运行于这些终端内的软件单元、 硬件单元或者软硬 件相结合的单元, 也可以作为独立的挂件集成到这些终端中或者运行于这些终 端的应用系统中。
该媒体质量的评估装置 7包括获取单元 71以及确定单元 72。 其中, 各单 元的具体功能如下:
获取单元 71 , 用于获取媒体基准质量及停顿事件失真质量;
确定单元 72, 用于根据所述获取单元 71获取的媒体基准质量及停顿事件 失真质量确定媒体最终质量;
所述停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事 件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度 描述因子。
进一步的, 所述获取单元 71还用于, 获取丟包失真质量。
所述确定单元 72还用于, 根据所述获取单元 71获取的媒体基准质量、 丟 包失真质量及停顿事件失真质量确定媒体最终质量。
进一步的,所述确定单元 72具体用于,根据所获取的媒体基准质量和丟包 失真质量计算媒体初始质量, 再根据所获取的停顿事件失真质量以及计算得到 的媒体初始质量确定媒体最终质量。
在本实施例中, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件 次数以及停顿事件时长获得; 或者, 所述停顿事件失真质量根据所述媒体初始 质量、停顿事件次数、停顿事件时长以及多次停顿事件相互作用影响参数获得; 或者, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停顿事 件时长以及媒体内容复杂度描述因子获得; 或者, 所述停顿事件失真质量根据 所述媒体初始质量、 停顿事件次数、 停顿事件时长、 多次停顿事件相互作用影 响参数以及媒体内容复杂度描述因子获得; 或者, 所述停顿事件失真质量根据 所述停顿事件次数、 停顿事件时长以及媒体内容复杂度描述因子获得; 或者, 所述停顿事件失真质量根据所述停顿事件次数、 停顿事件时长、 多次停顿事件 相互作用影响参数以及媒体内容复杂度描述因子获得。
所述停顿事件时长为预设时间内停顿事件的加权平均时长, 所述预设时间 内停顿事件的加权平均时长根据预设时间内停顿事件持续的时长以及停顿事件 的加权系数获得; 或者, 所述停顿事件时长为预设时间内停顿事件持续的总时 长与所述预设时间的比值; 或者, 所述停顿事件时长为预设时间内停顿时间持 续的总时长。
所述多次停顿事件相互作用影响参数为预设时间内停顿事件时间间隔的加 权平均时长, 所述预设时间内停顿事件时间间隔的加权平均时长根据所述预设 时间内停顿事件与其前一次停顿事件的时间间隔以及停顿事件的加权系数获 付。 所述加权系数根据停顿事件时间间隔的长短设定或者根据相同停顿间隔的 次数设定。
本实施例提供的媒体质量的评估装置可以使用在前述对应的媒体质量的评 估方法, 详情参见上述媒体质量的评估方法实施例一、 二、 三、 四的相关描述, 在此不再赘述。
实施例七:
图 8示出了本发明实施例七提供的媒体质量的评估装置的组成结构, 为了 便于说明, 仅示出了与本发明实施例相关的部分。
该媒体质量的评估装置可以应用于各种信息终端(电视机、 手机、 计算机、 个人数字助理等) , 可以是运行于这些终端内的软件单元、 硬件单元或者软硬 件相结合的单元, 也可以作为独立的挂件集成到这些终端中或者运行于这些终 端的应用系统中。
该媒体质量的评估装置 8包括评分段划分单元 81、获取单元 82、计算单元 83以及确定单元 84。 其中, 各单元的具体功能如下:
评分段划分单元 81 , 用于将待评估的媒体文件划分为多个评分段; 获取单元 82, 用于获取所述评分段划分单元 81划分后的每个所述评分段 的媒体基准质量及停顿事件失真质量, 所述评分段的停顿事件失真质量的参数 包括以下至少一个: 停顿事件次数、 停顿事件时长、 多次停顿事件相互作用影 响参数、 媒体初始质量以及媒体内容复杂度描述因子;
计算单元 83 , 用于根据所述获取单元 82获取的每个所述评分段的媒体基 准质量及停顿事件失真质量计算所述评分段划分单元 81 划分后的每个所述评 分段的媒体质量;
确定单元 84, 用于根据所述计算单元 83计算得到的所述每个所述评分段 的媒体质量确定所述媒体的最终质量。
进一步的,所述评分段划分单元 81具体用于,将待评估的媒体文件根据停 顿事件或者停顿时间划分为多个评分段。 所述确定单元 84包括:
权重设置模块 841 , 用于根据每个评分段停顿事件的停顿时长为每个评分 段设置权重, 或者根据每个评分段停顿质量分数或者停顿模型影响因子为每个 评分段设置权重;
确定模块 842, 用于根据所述权重设置模块 841设置的所述权重, 对所述 媒体的每个评分段的媒体质量进行加权运算, 将加权运算后得到的加权平均值 作为所述媒体的最终质量。
优选的是, 当存在 N个评分段的媒体质量低于预设的媒体质量时, 所述确 定单元 84用于将所述 N个评分段中最低的媒体质量或者所述 N个评分段媒体 质量的均值作为所述媒体的最终质量, 其中所述 N大于或等于 1
本实施例提供的媒体质量的评估装置可以使用在前述对应的媒体质量的评 估方法, 详情参见上述媒体质量的评估方法实施例五的相关描述, 在此不再赘 述。
本领域普通技术人员可以理解为上述实施例六和七所包括的各个单元和模 块只是按照功能逻辑进行划分的, 但并不局限于上述的划分, 只要能够实现相 应的功能即可; 另外,各功能单元和模块的具体名称也只是为了便于相互区分, 并不用于限制本发明的保护范围。
综上所述, 本发明实施例在计算媒体质量时考虑了多次停顿事件相互作用 影响参数、 媒体初始质量以及媒体内容复杂度描述因子对媒体质量的影响, 从 而使得媒体质量的评估结果更准确, 与人的主观感受更相符。
本领域普通技术人员可以理解, 实现上述实施例方法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, 所述的程序可以在存储于一计算机 可读取存储介质中, 所述的存储介质, 包括 ROM/RAM、 磁盘、 光盘等。
以上所述仅为本发明的较佳实施例而已, 并不用以限制本发明, 凡在本发 明的精神和原则之内所作的任何修改、 等同替换和改进等, 均应包含在本发明 的保护范围之内。

Claims

权 利 要 求 书
1、 一种媒体质量的评估方法, 其特征在于, 所述方法包括:
获取媒体基准质量及停顿事件失真质量;
根据所获取的媒体基准质量及停顿事件失真质量确定媒体最终质量; 所述停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事 件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度 描述因子。
2、 如权利要求 1所述的方法, 其特征在于, 在所述根据所获取的媒体基准 质量及停顿事件失真质量确定媒体最终质量之前, 所述方法还包括:
获取丟包失真质量。
3、 如权利要求 2所述的方法, 其特征在于, 所述根据所获取的媒体基准质 量及停顿事件失真质量确定媒体最终质量包括:
根据所获取的媒体基准质量、 丟包失真质量及停顿事件失真质量确定媒体 最终质量。
4、 如权利要求 1至 3任一项所述的方法, 其特征在于, 所述停顿事件失真 质量根据所述媒体初始质量、 停顿事件次数以及停顿事件时长获得;
或者, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停 顿事件时长以及多次停顿事件相互作用影响参数获得;
或者, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停 顿事件时长以及媒体内容复杂度描述因子获得;
或者, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停 顿事件时长、 多次停顿事件相互作用影响参数以及媒体内容复杂度描述因子获 付;
或者, 所述停顿事件失真质量根据所述停顿事件次数、 停顿事件时长以及 媒体内容复杂度描述因子获得; 或者, 所述停顿事件失真质量根据所述停顿事件次数、 停顿事件时长、 多 次停顿事件相互作用影响参数以及媒体内容复杂度描述因子获得。
5、 如权利要求 4所述的方法, 其特征在于, 所述停顿事件时长为预设时间 内停顿事件的加权平均时长, 所述预设时间内停顿事件的加权平均时长根据预 设时间内停顿事件持续的时长以及停顿事件的加权系数获得;
或者, 所述停顿事件时长为预设时间内停顿事件持续的总时长与所述预设 时间的比值;
或者, 所述停顿事件时长为预设时间内停顿时间持续的总时长。
6、 如权利要求 4所述的方法, 其特征在于, 所述多次停顿事件相互作用影 响参数为预设时间内停顿事件时间间隔的加权平均时长, 所述预设时间内停顿 事件时间间隔的加权平均时长根据所述预设时间内停顿事件与其前一次停顿事 件的时间间隔以及停顿事件的加权系数获得。
7、 如权利要求 5或 6所述的方法, 其特征在于, 所述加权系数根据停顿事 件时间间隔的长短设定或者根据相同停顿间隔的次数设定。
8、 如权利要求 3至 7任一项所述的方法, 其特征在于, 所述根据所获取的 媒体基准质量、 丟包失真质量及停顿事件失真质量确定媒体最终质量包括: 根据所获取的媒体基准质量和丟包失真质量计算媒体初始质量, 再根据所 获取的停顿事件失真质量以及计算得到的媒体初始质量确定媒体最终质量。
9、 一种媒体质量的评估方法, 其特征在于, 所述方法包括:
将待评估的媒体文件划分为多个评分段;
获取每个所述评分段的媒体基准质量及停顿事件失真质量, 所述评分段的 停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事件时长、 多次停顿事件相互作用影响参数、媒体初始质量以及媒体内容复杂度描述因子; 根据所获取的每个所述评分段的媒体基准质量及停顿事件失真质量计算每 个所述评分段的媒体质量;
根据计算得到的所述每个所述评分段的媒体质量确定所述媒体的最终质 量。
10、 如权利要求 9所述的方法, 其特征在于, 所述将待评估的媒体文件划 分为多个评分段具体包括:
将待评估的媒体文件根据停顿事件或者停顿时间划分为多个评分段。
11、 如权利要求 9或 10所述的方法, 其特征在于, 所述根据计算得到的每 个评分段的媒体质量确定所述媒体的最终质量具体包括:
根据每个评分段停顿事件的停顿时长为每个评分段设置权重, 或者根据每 个评分段停顿质量分数或者停顿模型影响因子为每个评分段设置权重;
根据设置的所述权重,对所述媒体的每个评分段的媒体质量进行加权运算, 将加权运算后得到的加权平均值作为所述媒体的最终质量。
12、 如权利要求 9或 10所述的方法, 其特征在于, 所述根据计算得到的每 个评分段的媒体质量确定所述媒体的最终质量具体包括:
当存在 N个评分段的媒体质量低于预设的媒体质量时,将所述 N个评分段 中最低的媒体质量或者所述 N个评分段媒体质量的均值作为所述媒体的最终质 量, 其中所述 N大于或等于 1。
13、 一种媒体质量的评估装置, 其特征在于, 所述装置包括:
获取单元, 用于获取媒体基准质量及停顿事件失真质量;
确定单元, 用于根据所述获取单元获取的媒体基准质量及停顿事件失真质 量确定媒体最终质量;
所述停顿事件失真质量的参数包括以下至少一个: 停顿事件次数、 停顿事 件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度 描述因子。
14、 如权利要求 12所述的装置, 其特征在于, 所述获取单元还用于, 获取 丟包失真质量。
15、 如权利要求 14所述的装置, 其特征在于, 所述确定单元还用于, 根据 所述获取单元获取的媒体基准质量、 丟包失真质量及停顿事件失真质量确定媒 体最终质量。
16、 如权利要求 13至 15任一项所述的装置, 其特征在于, 所述停顿事件 失真质量根据所述媒体初始质量、 停顿事件次数以及停顿事件时长获得;
或者, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停 顿事件时长以及多次停顿事件相互作用影响参数获得;
或者, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停 顿事件时长以及媒体内容复杂度描述因子获得;
或者, 所述停顿事件失真质量根据所述媒体初始质量、 停顿事件次数、 停 顿事件时长、 多次停顿事件相互作用影响参数以及媒体内容复杂度描述因子获 付;
或者, 所述停顿事件失真质量根据所述停顿事件次数、 停顿事件时长以及 媒体内容复杂度描述因子获得;
或者, 所述停顿事件失真质量根据所述停顿事件次数、 停顿事件时长、 多 次停顿事件相互作用影响参数以及媒体内容复杂度描述因子获得。
17、 如权利要求 16所述的装置, 其特征在于, 所述停顿事件时长为预设时 间内停顿事件的加权平均时长, 所述预设时间内停顿事件的加权平均时长根据 预设时间内停顿事件持续的时长以及停顿事件的加权系数获得;
或者, 所述停顿事件时长为预设时间内停顿事件持续的总时长与所述预设 时间的比值;
或者, 所述停顿事件时长为预设时间内停顿时间持续的总时长。
18、 如权利要求 16所述的装置, 其特征在于, 所述多次停顿事件相互作用 影响参数为预设时间内停顿事件时间间隔的加权平均时长, 所述预设时间内停 顿事件时间间隔的加权平均时长根据所述预设时间内停顿事件与其前一次停顿 事件的时间间隔以及停顿事件的加权系数获得。
19、 如权利要求 17或 18所述的装置, 其特征在于, 所述加权系数根据停 顿事件时间间隔的长短设定或者根据相同停顿间隔的次数设定。
20、 如权利要求 15至 19任一项所述的装置, 其特征在于, 所述确定单元 具体用于, 根据所获取的媒体基准质量和丟包失真质量计算媒体初始质量, 再 根据所获取的停顿事件失真质量以及计算得到的媒体初始质量确定媒体最终质
21、 一种媒体质量的评估装置, 其特征在于, 所述装置包括:
评分段划分单元, 用于将待评估的媒体文件划分为多个评分段; 基准质量及停顿事件失真质量, 所述评分段的停顿事件失真质量的参数包括以 下至少一个: 停顿事件次数、停顿事件时长、 多次停顿事件相互作用影响参数、 媒体初始质量以及媒体内容复杂度描述因子; 及停顿事件失真质量计算每个所述评分段的媒体质量;
确定单元, 用于根据所述计算单元计算得到的所述每个所述评分段的媒体 质量确定所述媒体的最终质量。
22、 如权利要求 21所述的装置, 其特征在于, 所述评分段划分单元具体用 于, 将待评估的媒体文件根据停顿事件或者停顿时间划分为多个评分段。
23、 如权利要求 21或 22所述的装置, 其特征在于, 所述确定单元包括: 权重设置模块, 用于根据每个评分段停顿事件的停顿时长为每个评分段设 置权重, 或者根据每个评分段停顿质量分数或者停顿模型影响因子为每个评分 段设置权重;
确定模块, 用于根据所述权重设置模块设置的所述权重, 对所述媒体的每 个评分段的媒体质量进行加权运算, 将加权运算后得到的加权平均值作为所述 媒体的最终质量。
24、 如权利要求 21或 22所述的装置, 其特征在于, 当存在 N个评分段的 媒体质量低于预设的媒体质量时, 所述确定单元用于将所述 N个评分段中最低 的媒体质量或者所述 N个评分段媒体质量的均值作为所述媒体的最终质量, 其 中所述 N大于或等于 1。
PCT/CN2012/085710 2012-05-28 2012-12-02 一种媒体质量的评估方法及装置 WO2013177910A1 (zh)

Priority Applications (6)

Application Number Priority Date Filing Date Title
EP12878144.0A EP2830316B1 (en) 2012-05-28 2012-12-02 Method and device for evaluating media quality
JP2015512994A JP6099107B2 (ja) 2012-05-28 2012-12-02 メディア品質を評価するための方法および装置
SG11201406655UA SG11201406655UA (en) 2012-05-28 2012-12-02 Method and apparatus for evaluating media quality
BR112014029458-5A BR112014029458B1 (pt) 2012-05-28 2012-12-02 Método e aparelho para avaliar qualidade de mídia
KR1020147031766A KR101693564B1 (ko) 2012-05-28 2012-12-02 미디어 품질 평가 방법 및 장치
US14/518,164 US9654770B2 (en) 2012-05-28 2014-10-20 Method and apparatus for evaluating media quality

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210168687.0A CN103458264B (zh) 2012-05-28 2012-05-28 一种媒体质量的评估方法及装置
CN201210168687.0 2012-05-28

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14/518,164 Continuation US9654770B2 (en) 2012-05-28 2014-10-20 Method and apparatus for evaluating media quality

Publications (1)

Publication Number Publication Date
WO2013177910A1 true WO2013177910A1 (zh) 2013-12-05

Family

ID=49672346

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2012/085710 WO2013177910A1 (zh) 2012-05-28 2012-12-02 一种媒体质量的评估方法及装置

Country Status (9)

Country Link
US (1) US9654770B2 (zh)
EP (1) EP2830316B1 (zh)
JP (1) JP6099107B2 (zh)
KR (1) KR101693564B1 (zh)
CN (1) CN103458264B (zh)
BR (1) BR112014029458B1 (zh)
HK (1) HK1190844A1 (zh)
SG (1) SG11201406655UA (zh)
WO (1) WO2013177910A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114640884A (zh) * 2022-03-21 2022-06-17 武汉庆实广告传媒有限公司 一种在线视频播放质量分析方法、系统及计算机存储介质

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104052991A (zh) * 2014-06-17 2014-09-17 德科仕通信(上海)有限公司 检测has视频卡顿的方法及系统
US10271112B2 (en) * 2015-03-26 2019-04-23 Carnegie Mellon University System and method for dynamic adaptive video streaming using model predictive control
CN106911927B (zh) * 2015-12-23 2020-05-01 中国移动通信集团公司 评估网络视频用户体验质量的方法、装置和dpi设备
CN107105224A (zh) * 2017-03-24 2017-08-29 深圳信息职业技术学院 一种视频体验质量评估的方法、装置与系统
CN108376147B (zh) * 2018-01-24 2021-09-28 北京一览科技有限公司 一种用于获得视频的评价结果信息的方法和装置
CN108389592B (zh) * 2018-02-27 2021-10-08 上海讯飞瑞元信息技术有限公司 一种语音质量评价方法及装置
CN109600508B (zh) * 2018-04-10 2019-08-30 利辛县雨若信息科技有限公司 手机播放故障自查方法
CN108650407B (zh) * 2018-04-10 2019-04-26 新昌县智创机械有限公司 手机播放故障自查平台
CN109729433B (zh) * 2019-01-22 2021-05-07 北京奇艺世纪科技有限公司 一种视频播放评估方法及装置
CN112689200B (zh) * 2020-12-15 2022-11-11 万兴科技集团股份有限公司 视频编辑方法、电子设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090244289A1 (en) * 2008-03-28 2009-10-01 Deutsche Telekom Ag Audio-visual quality estimation
CN101635846A (zh) * 2008-07-21 2010-01-27 华为技术有限公司 一种视频质量评估方法、系统及装置
CN101998137A (zh) * 2009-08-21 2011-03-30 华为技术有限公司 视频质量参数获取方法和装置及电子设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7099282B1 (en) * 1998-12-24 2006-08-29 Mci, Inc. Determining the effects of new types of impairments on perceived quality of a voice service
WO2003041055A1 (en) * 2001-11-02 2003-05-15 The Regents Of The University Of California End-to-end distortion estimation for streaming of pre-compressed video
KR100587972B1 (ko) * 2004-09-14 2006-06-08 한국전자통신연구원 인터넷 멀티미디어 서비스 품질 평가 방법
ES2313323T3 (es) * 2005-04-11 2009-03-01 Telefonaktiebolaget Lm Ericsson (Publ) Tecnica para controlar transmisiones de paquetes de datos de velocidad binaria variable.
JP4965659B2 (ja) * 2006-10-19 2012-07-04 テレフオンアクチーボラゲット エル エム エリクソン(パブル) ビデオ画質の決定方法
CN103379360B (zh) * 2012-04-23 2015-05-27 华为技术有限公司 一种视频质量评估方法和装置
CN103634577B (zh) * 2012-08-22 2014-12-31 华为技术有限公司 多媒体质量的监控方法和设备
US9578074B2 (en) * 2013-11-11 2017-02-21 Amazon Technologies, Inc. Adaptive content transmission

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090244289A1 (en) * 2008-03-28 2009-10-01 Deutsche Telekom Ag Audio-visual quality estimation
CN101635846A (zh) * 2008-07-21 2010-01-27 华为技术有限公司 一种视频质量评估方法、系统及装置
CN101998137A (zh) * 2009-08-21 2011-03-30 华为技术有限公司 视频质量参数获取方法和装置及电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP2830316A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114640884A (zh) * 2022-03-21 2022-06-17 武汉庆实广告传媒有限公司 一种在线视频播放质量分析方法、系统及计算机存储介质
CN114640884B (zh) * 2022-03-21 2023-01-31 广东易教优培教育科技有限公司 一种在线视频播放质量分析方法、系统及计算机存储介质

Also Published As

Publication number Publication date
EP2830316A1 (en) 2015-01-28
CN103458264B (zh) 2015-02-25
BR112014029458A8 (pt) 2021-06-15
EP2830316B1 (en) 2016-04-27
BR112014029458B1 (pt) 2022-06-14
KR101693564B1 (ko) 2017-01-06
CN103458264A (zh) 2013-12-18
US9654770B2 (en) 2017-05-16
HK1190844A1 (zh) 2014-07-11
SG11201406655UA (en) 2014-12-30
JP6099107B2 (ja) 2017-03-22
JP2015523774A (ja) 2015-08-13
EP2830316A4 (en) 2015-03-11
KR20150003316A (ko) 2015-01-08
US20150035996A1 (en) 2015-02-05
BR112014029458A2 (pt) 2017-06-27

Similar Documents

Publication Publication Date Title
WO2013177910A1 (zh) 一种媒体质量的评估方法及装置
CN108476317B (zh) 音频视频质量推测装置、音频视频质量推测方法以及程序
US7873727B2 (en) System and method for evaluating streaming multimedia quality
WO2013159502A1 (zh) 一种视频质量评估方法和装置
JP5427238B2 (ja) ビデオストリームの品質値を判定する方法及びシステム
WO2010009637A1 (zh) 一种视频质量评估方法、系统及装置
WO2012139467A1 (zh) 一种视频数据质量评估方法和装置
WO2014029315A1 (zh) 一种获得视频编码压缩质量的方法及装置
WO2013159487A1 (zh) 评估多媒体质量的方法和装置
WO2012119363A1 (zh) 一种度量用户体验质量QoE的方法及装置
WO2013097783A1 (zh) 媒体传输质量的评估方法和装置
WO2010003338A1 (zh) 一种视频码流的质量评估方法、装置及系统
EP3282698B1 (en) Method and apparatus for evaluating video quality
US20110063504A1 (en) Audio and video communications apparatus and communications method thereof
JP6162596B2 (ja) 品質推定装置、方法及びプログラム
CN107087210B (zh) 基于缓存时间判断视频播放状态的方法及终端
US20220109910A1 (en) Engagement estimation apparatus, engagement estimation method and program
US20130262293A1 (en) Variable charging of audience member temporal viewing of a live video chat performance
JP5107971B2 (ja) ユーザ体感品質推定システムおよび方法
JP5405915B2 (ja) 映像品質推定装置、映像品質推定方法および映像品質推定装置の制御プログラム
JP2011009919A (ja) ユーザ体感品質推定システムおよび方法
JP6146471B2 (ja) 符号化装置、符号化方法、および符号化プログラム
JP2009194610A (ja) 映像品質推定装置、方法、およびプログラム
JP7215209B2 (ja) エンゲージメント推定装置、エンゲージメント推定方法及びプログラム
JP2013168814A (ja) メディアプレイヤパラメタ推定装置及び方法及びプログラム

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: 12878144

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2012878144

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 20147031766

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2015512994

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112014029458

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 112014029458

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20141126