WO2010009637A1 - 一种视频质量评估方法、系统及装置 - Google Patents
一种视频质量评估方法、系统及装置 Download PDFInfo
- Publication number
- WO2010009637A1 WO2010009637A1 PCT/CN2009/071633 CN2009071633W WO2010009637A1 WO 2010009637 A1 WO2010009637 A1 WO 2010009637A1 CN 2009071633 W CN2009071633 W CN 2009071633W WO 2010009637 A1 WO2010009637 A1 WO 2010009637A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- video
- parameter
- quality
- video frame
- frame
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
- H04N19/89—Methods 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/004—Diagnosis, testing or measuring for television systems or their details for digital television systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/103—Selection of coding mode or of prediction mode
- H04N19/109—Selection of coding mode or of prediction mode among a plurality of temporal predictive coding modes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/132—Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/146—Data rate or code amount at the encoder output
- H04N19/152—Data rate or code amount at the encoder output by measuring the fullness of the transmission buffer
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/164—Feedback from the receiver or from the transmission channel
- H04N19/166—Feedback from the receiver or from the transmission channel concerning the amount of transmission errors, e.g. bit error rate [BER]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/172—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/179—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a scene or a shot
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/44—Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/65—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using error resilience
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
- H04N19/86—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving reduction of coding artifacts, e.g. of blockiness
Definitions
- the present invention relates to the field of communications technologies, and in particular, to a video quality assessment method, system, and apparatus.
- Video on-demand, Internet TV and videophone will all adopt the data transmission method of network video.
- the development of services such as video on demand, Internet TV and videophone has also promoted the rapid development of network video.
- a method for evaluating a video quality in the prior art is to detect a video quality by using a Peak Signal to Noise Ratio (PSNR) method.
- the method of the method generally includes: acquiring an original reference video and a terminal video;
- the video quality is determined based on the specific value of the PSNR.
- the inventors have found that the prior art has the following disadvantages:
- the PSNR value reflects only the signal-to-noise ratio between the terminal video signal and the original reference video signal.
- the signal-to-noise ratio does not intuitively reflect the user's perception of the network video when watching the network video. Therefore, in the prior art, The results obtained by the video quality assessment method are not accurate. Summary of the invention
- Embodiments of the present invention provide a video quality assessment method, system, and apparatus, which can improve the accuracy of video quality assessment.
- the method for evaluating a video quality according to the embodiment of the present invention includes: acquiring transmission video information; parsing a video frame parameter according to the transmission video information, where the video frame parameter includes a compression distortion parameter and/or a packet loss video quality distortion parameter; Calculating the video frame quality according to the video frame parameter, the video quality evaluation method provided by the embodiment of the present invention includes: acquiring transmission video information, where the video frame information includes at least a duration of the video frame; and parsing according to the transmission video information Obtaining a video frame parameter; calculating a video frame quality parameter according to the video frame parameter; weighting the video frame quality parameter and the duration to obtain a video sequence quality parameter.
- the video quality evaluation apparatus includes: a video frame acquiring unit, configured to acquire transmission video information; and a video frame parameter calculation unit, configured to parse and obtain a video frame parameter according to the transmission video information acquired by the video frame acquiring unit,
- the video frame parameter includes a compression distortion parameter and/or a packet loss video quality distortion parameter.
- the video frame quality parameter calculation unit is configured to calculate a video frame quality parameter according to the video frame parameter calculated by the video frame parameter calculation unit.
- the video quality evaluation system includes: a video quality evaluation apparatus, configured to acquire transmission video information, and parse a video frame parameter according to the transmission video information, where the video frame parameter includes compression distortion parameters and/or data. a packet loss video quality distortion parameter, calculating a video frame quality parameter according to the video frame parameter; and a sending device, configured to acquire the video quality evaluation device And setting the generated video frame quality parameter, and sending the video frame quality parameter.
- the embodiments of the present invention have the following advantages:
- the compression distortion parameter and/or the packet loss video quality distortion parameter may be calculated according to the transmission video information, and then the video quality may be lost according to the compression distortion parameter and/or the data packet.
- the distortion parameter calculates the video frame quality parameter. Therefore, in the embodiment of the present invention, only the quality of the video frame can be calculated according to the transmission video information of the terminal side, and the original reference video does not need to be acquired, thereby saving network resources;
- the video frame quality parameter in the embodiment of the present invention is related to the compression distortion parameter and/or the packet loss video quality distortion parameter, that is, the compression distortion parameter is an index for evaluating the quality of the video frame, and the compression distortion parameter and/or data
- the compression distortion parameter and/or data There is a linear relationship between the packet loss video quality distortion parameter and the video frame quality. Therefore, using the compression distortion parameter and/or the packet loss video quality distortion parameter to evaluate the video frame quality can more intuitively reflect the user's perception of the network video when watching the network video. , thereby improving the accuracy of video quality assessment.
- FIG. 1 is a schematic diagram of a first embodiment of a video quality evaluation method according to an embodiment of the present invention
- FIG. 2 is a linear relationship between subjective quality score and compression distortion according to an embodiment of the present invention
- FIG. 3 is a video quality evaluation according to an embodiment of the present invention
- FIG. 4 is a schematic diagram of an embodiment of a video quality evaluation apparatus according to an embodiment of the present invention
- FIG. 5 is a schematic diagram of an embodiment of a video quality assessment system according to an embodiment of the present invention.
- Embodiments of the present invention provide a video quality assessment method, system, and apparatus for improving the accuracy of video quality assessment.
- the process of detecting video quality is completed on the terminal side, that is, the video quality evaluation apparatus may be part of the terminal, or exist independently, and only need to acquire the transmission video information of the terminal side to perform video quality evaluation without acquiring The original reference video was used as the basis for evaluation.
- the transmission video information in this embodiment may include a code rate, a quantization factor of the video coding, or may also include information such as the duration of the video frame. It can be understood that, in practical applications, in addition to the above information, other similar transmission video information can be obtained.
- the video frame parameter includes a compression distortion parameter and/or a packet loss video quality distortion parameter
- the video frame parameters obtained by the above steps can be parsed to obtain video frame parameters, and the video frame parameters may include compression distortion parameters and/or packet loss video quality distortion parameters.
- the compression distortion parameter refers to quality information when there is only compression distortion of the video frame, and there is no other type of loss
- the packet loss video quality distortion parameter refers to when the video frame only has packet loss and there is no coding compression. Loss.
- the video frame parameters in this embodiment may also include other types of parameters, and the specific parameter types are not limited herein.
- the video frame parameters in this embodiment include a compression distortion parameter and/or a packet loss video quality distortion parameter, so the process of calculating a video frame quality parameter is related to a specific video frame parameter, and the calculated video frame quality parameter is video quality. Basis for evaluation.
- the video information may be calculated according to the transmitted video information. Obtaining a compression distortion parameter and/or a packet loss video quality distortion parameter, and then calculating a video frame quality parameter according to the compression distortion parameter and/or the packet loss video quality distortion parameter, so in the embodiment of the present invention, only the terminal side is required.
- the transmission of video information can calculate the quality of the video frame without the need to obtain the original reference video, thereby saving network resources;
- the video frame quality parameter in this embodiment is related to the compression distortion parameter and/or the packet loss video quality distortion parameter, that is, the compression distortion parameter and/or the packet loss video quality distortion parameter are indicators for evaluating the quality of the video frame.
- the compression distortion parameter and/or the packet loss video quality distortion parameter are indicators for evaluating the quality of the video frame.
- there is a linear relationship between the compression distortion parameter and/or the packet loss video quality distortion parameter and the video frame quality so using the compression distortion parameter and/or the packet loss video quality distortion parameter to evaluate the video frame quality can more intuitively reflect the user. The feeling of online video when watching online video, and thus improve the accuracy of video quality assessment.
- the compression distortion parameter as a video frame parameter:
- the video quality loss of the data packet may not be caused, that is, the factor of loss of the video data packet is not considered.
- the network video is encoded and compressed due to the limitation of the network bandwidth. In this embodiment, only the compression distortion parameter is used as the reference basis for the video quality.
- the first embodiment of the video quality evaluation method in the embodiment of the present invention includes: 101: Acquire transmission video information;
- the process of detecting video quality is completed on the terminal side, that is, the video quality evaluation apparatus may be part of the terminal, or exist independently, and only need to acquire the transmission video information of the terminal side to perform video quality evaluation without acquiring
- the original reference video is used as the evaluation basis.
- the solution is not limited to the terminal side, and the solution can be applied to any node of the network that can obtain video information.
- the transmission video information in this embodiment may include a code rate, a quantization factor of video coding (the quantization factor mentioned herein may be a so-called quantization parameter QP (quantization) Parameter) can also be Qstep (quantization step) quantization step size and other parameters to control different degrees of quantization, the following examples are represented by the quantization parameter QP, but the parameters for controlling the quantization degree such as the quantization step size Qstep are also applicable) Or it may also include information such as the duration of the video frame. It can be understood that, in practical applications, in addition to the above information, other similar transmission video information can be obtained.
- QP quantization parameter
- Qstep quantization step quantization step size and other parameters to control different degrees of quantization
- the compression distortion parameter can be calculated according to the transmission information, and the specific process is:
- the R is the code rate
- the QP is the quantization factor.
- the R and the QP are calculated according to the transmission video. The specific calculation process is a prior art, which is not limited herein.
- Cl ' C2 ' c - c is the above space complexity parameter and the time domain activity parameter is calculated based on QP and R.
- the calculation of the spatial complexity parameter and the calculation of the time domain activity parameter are respectively obtained by the above formula (2) for different video frames, and the video frame encoded by the intra mode reflects the spatial complexity of the video frame.
- ⁇ reflects the time domain activity of the video frame.
- the spatial complexity refers to the complexity of the video space content, such as the elements contained in a certain frame. Generally speaking, the more complex the elements, the higher the spatial complexity of the video;
- the above-mentioned time domain activity indicates the motion characteristics of the video time domain, such as the duration of a certain frame, or the degree of alternation between video frames. Generally speaking, the higher the degree of alternation, the higher the time domain activity of the video. .
- the spatial complexity of the nth video frame, the time domain activity of the nth video frame, the code rate of the nth video frame, ⁇ ⁇ is the average of the nth video frame Quantization factor.
- the time domain activity is predicted according to the time domain activity of the adjacent video frame encoded by the inter mode; for the video frame encoded by the inter mode
- the spatial complexity is predicted based on the spatial complexity of the adjacent video frames encoded by the intra mode.
- the code rate, the quantization factor, the spatial complexity parameter and the time domain activity parameter of the video frame are calculated, and the video frame quality parameter can be calculated according to the parameter.
- Video compression is lossy compression, and the quantization process in video coding is caused by video compression distortion. root cause. Since network video applications are usually able to correctly receive and decode most of the frames, for video frames without errors, measuring quantization distortion based on the user's visual characteristics is the key to evaluating video quality.
- the subjective quality of the video frame has an approximate linear relationship with QP or quantization step size, as shown in Figure 2.
- Curve 201 and video 202 represent two different video sequences, respectively.
- Figure 2 shows the relationship between video quality and QP for different video sequences in the case of considering only compression distortion. It can be seen from Fig. 2 that the linear relationship between the subjective quality of different video sequences and QP has different characteristics (such as different intercepts and slopes), thereby reflecting the content characteristics of the video, that is, the spatial complexity of the video and In the case of time domain activity, when a video frame considers only compression distortion, its quality parameter is related to the spatial complexity parameter, time domain activity parameter, code rate and quantization factor of the video frame.
- the compression distortion caused by the video encoder is caused by the quantization of the DCT coefficients, so the quantization factor is directly related to the compression distortion of the video.
- the subjective quality of the video frame has an approximate linear relationship with QP, ie
- n also known as the video frame quality base
- a and b are constants, all obtained through subjective experiments.
- the process of obtaining a, b is not limited here.
- the quality parameter of the video frame can be obtained by the above formula (5). Note that since it is determined by the size of Qp, the formula actually represents the relationship between video quality and code rate R, and QP. This quality parameter is a video frame quality parameter considering only compression distortion.
- the quality parameter of the video sequence can be calculated according to the quality parameter of the video frame, but the rate control algorithm of the video encoder often causes the video frame rate of the decoder to change with time.
- the quality of the entire video sequence is not a simple superposition or average of the quality of each frame.
- the quality evaluation of the video sequence also needs to consider the video playback frame rate, playback pause and other factors.
- the quality parameter of the video sequence is calculated in a manner of "contribution of video frame to video sequence score".
- the “contribution of video frame to video sequence score” indicates the effect of each video frame on the overall video quality when displaying the entire video sequence, which is related to the quality of the video frame and the duration of the video frame.
- the durations in this embodiment and subsequent embodiments all refer to the interval time between video frames, which may be the display time interval between two consecutive frames having different display contents, such as after frame a is displayed.
- the frame b is displayed after the end of the buffer. At this time, the duration between frame a and frame b must include the buffer time.
- the time includes this case: There are several frames missing after frame a cannot be decoded and cannot be displayed. The real content, until the frame b can be decoded and correctly displayed, then after the end of the a frame display, there will be different processing and display strategies according to different error masking methods.
- the usual processing method is to use a for each subsequent lost frame. The content of the frame is displayed, and then the b frame is displayed again.
- the time interval referred to herein is the difference between the display time of the first a frame and the b frame.
- the contribution of the nth video frame to the video sequence score is related to the quality parameter of the video frame ⁇ , and the time domain activity parameter of the video frame, and the duration of the video frame.
- the quality parameters of the entire video sequence can be obtained by time domain weighting.
- At least the compression distortion parameter may be calculated according to the transmission video information, and then the video frame quality parameter may be calculated according to the compression distortion parameter, so in the embodiment of the present invention, only the terminal side is required.
- the transmission of video information can calculate the quality of the video frame without the need to obtain the original reference video, thereby saving network resources;
- the video frame quality parameter in this embodiment is at least related to the compression distortion parameter, that is, the compression distortion parameter is an index for evaluating the quality of the video frame, and the compression distortion parameter has a linear relationship with the video frame quality, so compression distortion is used.
- the parameter evaluation video frame quality can more intuitively reflect the user's perception of the network video when watching the network video, thereby improving the accuracy of the video quality assessment.
- the packet loss may be caused by the video quality distortion, that is, the factor of the video frame loss needs to be considered when calculating the video frame quality parameter.
- the network video is encoded and compressed due to the limitation of the network bandwidth. Therefore, in this embodiment, the compression distortion parameter and the packet loss video quality distortion parameter are used as the reference basis for the video quality.
- a second embodiment of the video quality evaluation method in the embodiment of the present invention includes: 301: Acquire transmission video information;
- the process of detecting video quality is performed on the terminal side as an example, that is, the video quality evaluation apparatus may be part of the terminal, or exist independently, and only needs to acquire the transmission video information of the terminal side to perform video quality evaluation. There is no need to obtain the original reference video as the evaluation basis.
- the solution is not limited to the terminal side, and the solution can be applied to any node of the network that can obtain video information.
- the transmission video information in this embodiment may include a code rate, a quantization factor of the video coding, or Information such as the duration of the video frame may also be included. It can be understood that, in practical applications, in addition to the above information, other similar transmission video information can be obtained.
- the process of calculating the compression distortion parameter according to the transmission video information in this embodiment is the same as the process of calculating the compression distortion parameter in the foregoing first embodiment, and details are not described herein again.
- a packet loss video quality distortion parameter can also be calculated.
- errors in the reference video frame and loss of the reference video frame can cause error propagation.
- the delay of network packets and the impact of jitter on video terminals are reflected in data loss.
- the packet loss video quality distortion parameter in this embodiment represents the effect of data loss on the quality of the video frame.
- the "slice” is the smallest unit of decoding by the decoder.
- the decoder will cover the error, and the quality of the video after the error is concealed is closely related to the content of the video. Therefore, the spatial domain time correlation of video, that is, the spatial complexity and time domain activity of video frames, is a key factor affecting the error concealment effect.
- the quality of video frames is also a key factor in the absence of data loss.
- the parameters in the embodiment include two aspects, one is ", indicating the degree of degradation of the video frame caused by data loss directly; the other is ", indicating the degree of degradation of the video frame caused by the error propagation.
- the current frame is completely lost, because the calculation parameters cannot be obtained, it can be predicted according to the decoding error concealment method, for example. If the time domain masking method is used in the previous frame, the current frame may be predicted by the previous frame parameter, and the distortion of the video frame is caused by the loss of the entire frame.
- the quality parameters of the video frame are:
- a video frame quality parameter indicating complete error-free, A is the distortion caused by the error propagation, that is, ".
- the interframe prediction mode coding may be used instead of the previous frame.
- step of calculating the video frame quality parameter in the case of no packet loss is the result calculated in step 203 in the first embodiment, and the specific calculation process is not described herein again.
- the packet loss video quality distortion parameter is obtained in step 302.
- step 303 the video frame quality parameter in the case of no packet loss is obtained, and the difference between the video frame quality parameter and the packet loss video quality distortion parameter in the case of no packet loss may be obtained.
- the value is used as the video frame quality parameter.
- the quality parameter of the video sequence can be calculated according to the quality parameter of the video frame, but the rate control algorithm of the video encoder often causes the video frame rate of the decoder to change with time.
- the quality of the entire video sequence is not a simple superposition or average of the quality of each frame.
- the quality evaluation of the video sequence also needs to consider the video playback frame rate, playback pause and other factors.
- the quality parameter of the video sequence is calculated in a manner of "contribution of video frame to video sequence score".
- the "contribution of video frame to video sequence score” indicates the effect of each video frame on the overall video quality when displaying the entire video sequence, which is related to the quality of the video frame and the duration of the video frame.
- the contribution of the nth video frame to the video sequence score is related to the quality parameter of the video frame ⁇ , and the time domain activity parameter of the video frame, and the duration of the video frame.
- the quality parameters of the entire video sequence can be obtained by time domain weighting.
- At least the compression distortion parameter may be calculated according to the transmission video information, and then the video frame quality parameter may be calculated according to the compression distortion parameter, so in the embodiment of the present invention, only the terminal side is required.
- the transmission of video information can calculate the quality of the video frame without the need to obtain the original reference video, thereby saving network resources;
- the video frame quality parameter in this embodiment is at least related to the compression distortion parameter, that is, the compression distortion parameter is an index for evaluating the quality of the video frame, and the compression distortion parameter has a linear relationship with the video frame quality, so compression distortion is used.
- the parameter evaluation video frame quality can more intuitively reflect the user's perception of the network video when watching the network video, thereby improving the accuracy of the video quality assessment.
- the packet loss video quality distortion parameter is used as the video frame parameter:
- the playback quality of the video needs to be as much as the original quality, it may not be The ratio of compression or compression of the video is small, and some applications do not consider video compression damage only considering network impairments.
- only the video frame parameters including the packet loss video quality distortion parameters may be considered, and then Consider further the case of including compression distortion.
- the manner of calculating the packet loss video quality distortion parameter in this embodiment is similar to the manner of calculating the packet loss video quality distortion parameter in the second embodiment described above.
- the initial quality parameter of the video frame may be calculated according to a preset manner, that is, the video packet loss is not included (the specific manner may be the calculation method in the prior art or other similar computing video).
- the specific manner may be the calculation method in the prior art or other similar computing video.
- the method of frame quality, and the direct assumption, etc.) the difference between the video frame initial quality parameter and the packet loss video quality distortion parameter is taken as the video frame quality parameter.
- the video sequence quality may be calculated in the manner of the foregoing embodiment, and the manner is similar, and details are not described herein again.
- the quality of the video sequence can be obtained by performing weighting operation according to the video frame quality parameter and the duration of the video frame. It can be understood that in practical applications.
- the present invention can be applied to the obtained video frame quality parameter, regardless of the manner in which it is calculated (including the manner provided by the embodiment of the present invention or other calculation methods using the prior art).
- the manner of the embodiment is to calculate the quality of the entire video sequence, and the specific manner is similar to the manner in the foregoing embodiment, which is not limited herein.
- the video quality evaluation apparatus in the embodiment of the present invention includes:
- a video frame obtaining unit 401 configured to acquire transmission video information
- the video frame parameter calculation unit 402 is configured to parse the video frame parameter according to the transmission video information acquired by the video frame acquiring unit 401, where the video frame parameter includes at least a compression distortion parameter or a data packet loss parameter;
- the video frame quality parameter calculation unit 404 is configured to calculate a video frame quality parameter according to the video frame parameter calculated by the video frame parameter calculation unit 402.
- the present embodiment can be divided into three cases according to the content included in the video frame parameters:
- the video frame parameters only contain compression distortion parameters:
- the video quality evaluation apparatus in this embodiment includes:
- a video frame obtaining unit 401 configured to acquire transmission video information
- the video frame parameter calculation unit 402 is configured to parse the video frame parameter according to the transmission video information acquired by the video frame acquiring unit 401, where the video frame parameter includes at least a compression distortion parameter.
- a compression distortion calculation unit 4021 configured to calculate a compression distortion parameter according to the transmission video information acquired by the video frame acquisition unit 401;
- a video frame quality parameter calculation unit 404 configured to calculate according to the compression distortion calculation unit 4021.
- the resulting compression distortion parameter calculates a video frame quality parameter.
- the video sequence quality calculation unit 405 is configured to acquire a duration of the video frame, perform a weighting operation on the video frame quality parameter and the duration to obtain a video sequence quality calculation unit.
- the video frame parameters only contain the packet loss distortion parameters:
- the video quality evaluation apparatus in this embodiment includes:
- a video frame obtaining unit 401 configured to acquire transmission video information
- the video frame parameter calculation unit 402 is configured to parse the video frame parameter according to the transmission video information acquired by the video frame acquiring unit 401, where the video frame parameter includes at least a packet loss video quality distortion parameter;
- the video frame parameter calculation unit 402 in this embodiment includes a data packet loss calculation unit 4022, configured to calculate a data packet loss video quality distortion parameter according to the transmission video information acquired by the video frame acquisition unit 401;
- the video frame quality parameter calculation unit 404 is configured to calculate a video frame quality parameter according to the packet loss video quality distortion parameter calculated by the packet loss calculation unit 4022.
- the video sequence quality calculation unit 405 is configured to acquire a duration of the video frame, perform a weighting operation on the video frame quality parameter and the duration to obtain a video sequence quality calculation unit.
- the specific calculation manner is the same as the calculation method in the foregoing method embodiment, and details are not described herein again.
- the video frame parameter includes a compression distortion parameter and a packet loss video quality distortion parameter.
- the video quality evaluation apparatus in this embodiment includes:
- a video frame obtaining unit 401 configured to acquire transmission video information
- the video frame parameter calculation unit 402 is configured to parse the video frame parameter according to the transmission video information acquired by the video frame acquiring unit 401, where the video frame parameter includes a compression distortion parameter and a data packet loss video quality distortion parameter;
- the video frame parameter calculation unit 402 in this embodiment includes a compression distortion calculation unit 4021 and a packet loss calculation unit 4022;
- the compression distortion calculation unit 4021 is configured to calculate a compression distortion parameter according to the transmission video information acquired by the video frame acquisition unit 401;
- the data packet loss calculation unit 4022 is configured to calculate a data packet loss video quality distortion parameter according to the transmission video information acquired by the video frame acquisition unit 401;
- the lossless code parameter calculation unit 403 is configured to calculate a video frame parameter in the case of no packet loss according to the compression distortion parameter calculated by the compression distortion calculation unit 4021;
- the video frame quality parameter calculation unit 404 is configured to calculate a video frame quality parameter according to the video frame parameter in the case of no packet loss calculated by the lossless code parameter calculation unit 403 and the packet loss video quality distortion parameter calculated by the packet loss calculation unit 4022. .
- the video sequence quality calculation unit 405 is configured to acquire a duration of the video frame, perform a weighting operation on the video frame quality parameter and the duration to obtain a video sequence quality calculation unit.
- the specific calculation manner is the same as the calculation method in the foregoing method embodiment, and details are not described herein again.
- at least the compression distortion parameter may be calculated according to the transmission video information, and then the video frame quality parameter may be calculated according to the compression distortion parameter, so in the embodiment of the present invention, only the terminal side is required.
- the transmission of video information can calculate the quality of the video frame without the need to obtain the original reference video, thereby saving network resources;
- the video frame quality parameter in this embodiment is at least related to the compression distortion parameter, that is, the compression distortion parameter is an index for evaluating the quality of the video frame, and the compression distortion parameter has a linear relationship with the video frame quality, so compression distortion is used.
- the parameter evaluation video frame quality can more intuitively reflect the user's perception of the network video when watching the network video, thereby improving the accuracy of the video quality assessment.
- the video quality evaluation system in the embodiment of the present invention is described below. Referring to FIG. 5, the present invention is implemented.
- the video quality assessment system in the example includes:
- the video quality evaluation apparatus 501 is configured to acquire transmission video information, and parse the video frame parameter according to the transmission video information, where the video frame parameter includes a compression distortion parameter and/or a packet loss video quality distortion parameter; according to the video frame The parameter calculates a video frame quality parameter;
- the sending device 502 is configured to acquire a video frame quality parameter generated by the video quality evaluating device 501, and send the video frame quality parameter.
- the display device 503 is configured to receive a video frame quality parameter sent by the sending device 502, and display the video frame quality parameter to a user.
- the storage device 504 is configured to store a video frame quality parameter sent by the sending device 502. It can be understood that the specific structure of the video quality evaluating apparatus 501 in this embodiment may adopt the structure of the video quality evaluating apparatus shown in FIG. 4, the working mode of the video quality evaluating apparatus 501, and the data processing flow and the foregoing figure. The working mode and data processing flow in 4 are similar, and will not be described here.
- the video frame parameter includes a compression distortion parameter and/or a packet loss video quality distortion parameter
- a video frame quality parameter is calculated based on the video frame parameters.
- the above-mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.
- the storage medium may be a magnetic disk, an optical disk, or a read-only storage memory.
- ROM Read-Only Memory
- RAM Random Access Memory
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Description
一种视频质量评估方法、 系统及装置
技术领域
本发明涉及通讯技术领域, 尤其涉及一种视频质量评估方法、 系统及装 置。
背景技术
随着网络技术的发展, 影视点播、 网络电视、 可视电话等已成为宽带网 络的主要业务, 并且这些业务也将成为第三代 (3G, the 3rd Generation) 无 线网络的主要业务。
影视点播, 网络电视以及可视电话都会采用网络视频的数据传输方式, 影视点播、 网络电视、 可视电话等业务的发展同时也带动了网络视频的迅速 发展。
在网络视频迅速发展的背景下, 如何对网络视频的质量进行便捷、 有效 的评估, 便成为网络视频应用中一个迫切需要解决的重要问题。 为了保证网 络视频的服务质量, 必须对网络视频的质量进行监控, 以便及时采取相应的 措施进行调节和保持, 以保证网络视频的正常运行。 网络视频的质量受到许 多复杂因素的影响, 首先需要考虑传输信道的服务质量 (例如带宽、 丢包、 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、 分辨率、 抗误码强度、 以及编解码端缓冲控制策略是否合适等) 。 另 夕卜, 信道丢包、 时延等引起视频数据丢失的位置不同, 对于视频主观质量的 影响也大不相同; 信道时延、 抖动等引起视频停顿或抖动也严重影响着视频 的主观质量。
现有技术中一种视频质量评估方法是采用计算峰值信噪比 (PSNR, Peak Signal to Noise Ratio) 的方式检测视频质量, 其方法流程大致包括: 获取原始参考视频以及终端视频;
对原始参考视频以及终端视频进行对比计算 PSNR;
根据 PSNR的具体数值确定视频质量。
但是, 发明人在实现本发明的过程中, 发现现有技术有如下缺点:
( 1 ) 对于网络视频来说, 由于带宽的限制, 获取原始参考视频需要大 量的带宽以及传输时间, 造成网络资源的浪费;
(2 ) PSNR数值体现的仅是终端视频信号与原始参考视频信号之间的 信噪比, 该信噪比并不能直观的体现用户观看网络视频时对网络视频的感 受, 因此现有技术中的视频质量评估方法所得到的检测结果并不准确。 发明内容
本发明实施例提供了一种视频质量评估方法、 系统及装置, 能够提高视 频质量评估的准确性。
本发明实施例提供的视频质量评估方法, 包括: 获取传输视频信息; 根 据所述传输视频信息解析得到视频帧参数, 所述视频帧参数包括压缩失真参 数和 /或数据包丢失视频质量失真参数; 根据所述视频帧参数计算视频帧质 本发明实施例提供的视频质量评估方法, 包括: 获取传输视频信息, 所 述视频帧信息至少包括所述视频帧的持续时间; 根据所述传输视频信息解析 得到视频帧参数; 根据所述视频帧参数计算视频帧质量参数; 对所述视频帧 质量参数以及所述持续时间进行加权运算得到视频序列质量参数。
本发明实施例提供的视频质量评估装置, 包括: 视频帧获取单元, 用于 获取传输视频信息; 视频帧参数计算单元, 用于根据视频帧获取单元获取到 的传输视频信息解析得到视频帧参数, 所述视频帧参数包括压缩失真参数和 /或数据包丢失视频质量失真参数; 视频帧质量参数计算单元, 用于根据视 频帧参数计算单元计算得到的视频帧参数计算视频帧质量参数。
本发明实施例提供的视频质量评估系统, 包括: 视频质量评估装置, 用 于获取传输视频信息, 根据所述传输视频信息解析得到视频帧参数, 所述视 频帧参数包括压缩失真参数和 /或数据包丢失视频质量失真参数, 根据所述 视频帧参数计算视频帧质量参数; 发送装置, 用于获取所述视频质量评估装
置生成的视频帧质量参数, 发送所述视频帧质量参数。
从以上技术方案可以看出, 本发明实施例具有以下优点:
本发明实施例中, 获取到传输视频信息之后, 可以根据该传输视频信息 计算得到压缩失真参数和 /或数据包丢失视频质量失真参数, 之后可以根据 该压缩失真参数和 /或数据包丢失视频质量失真参数计算视频帧质量参数, 所以本发明实施例中只需要根据终端侧的传输视频信息即可计算视频帧的质 量, 无需获取原始参考视频, 因此能够节省网络资源;
其次, 由于本发明实施例中的视频帧质量参数与压缩失真参数和 /或数 据包丢失视频质量失真参数相关, 即压缩失真参数是评价视频帧质量的指 标, 而该压缩失真参数和 /或数据包丢失视频质量失真参数与视频帧质量之 间存在线性关系, 所以使用压缩失真参数和 /或数据包丢失视频质量失真参 数评价视频帧质量可以更加直观地体现用户观看网络视频时对网络视频的感 受, 进而提高视频质量评估的准确性。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案, 下面将对实 施例或现有技术描述中所需要使用的附图作简单地介绍, 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为本发明实施例中视频质量评估方法第一实施例示意图; 图 2为本发明实施例中主观质量评分与压缩失真之间的线性关系图; 图 3为本发明实施例中视频质量评估方法第二实施例示意图; 图 4为本发明实施例中视频质量评估装置实施例示意图;
图 5为本发明实施例中视频质量评估系统实施例示意图。
具体实施方式
下面将结合本发明实施例中的附图, 对本发明实施例中的技术方案进行 清楚、 完整地描述, 显然, 所描述的实施例仅仅是本发明一部分实施例, 而
不是全部的实施例。 基于本发明中的实施例, 本领域普通技术人员在没有作 出创造性劳动前提下所获得的所有其他实施例, 都属于本发明保护的范围。
本发明实施例提供了一种视频质量评估方法、 系统及装置, 用于提高视 频质量评估的准确性。
本发明实施例中视频质量评估方法包括:
1 ) 获取传输视频信息;
本实施例中, 检测视频质量的过程在终端侧完成, 即视频质量评估装置 可以作为终端的一部分, 或独立存在, 其只需获取终端侧的传输视频信息即 可进行视频质量评估, 而无需获取原始参考视频作为评价依据。
本实施例中的传输视频信息可以包括码率, 视频编码的量化因子, 或者 还可以包括视频帧的持续时间等信息。 可以理解的是, 在实际应用中, 除了 上述信息之外, 还可以获取其他类似的传输视频信息。
2) 根据所述传输视频信息解析得到视频帧参数, 所述视频帧参数包括 压缩失真参数和 /或数据包丢失视频质量失真参数;
本实施例中根据上述步骤获取到的传输视频信息即可解析得到视频帧参 数, 该视频帧参数中可以包含压缩失真参数和 /或数据包丢失视频质量失真 参数。 该压缩失真参数指当该视频帧仅存在压缩失真, 而不存在其他类型的 损耗时的质量信息, 该数据包丢失视频质量失真参数是指当该视频帧仅存在 丢包而不存在编码压缩时的损耗。
在实际应用中, 本实施例中的视频帧参数还可以包括其他类型的参数, 具体参数类型此处不做限定。
3) 根据所述视频帧参数计算视频帧质量参数。
本实施例中的视频帧参数包括压缩失真参数和 /或数据包丢失视频质量 失真参数, 因此计算视频帧质量参数的过程与具体的视频帧参数相关, 该计 算得到的视频帧质量参数为视频质量的评价依据。
本实施例中, 获取到传输视频信息之后, 可以根据该传输视频信息计算
得到压缩失真参数和 /或数据包丢失视频质量失真参数, 之后可以至少根据 该压缩失真参数和 /或数据包丢失视频质量失真参数计算视频帧质量参数, 所以本发明实施例中只需要根据终端侧的传输视频信息即可计算视频帧的质 量, 无需获取原始参考视频, 因此能够节省网络资源;
其次, 由于本实施例中的视频帧质量参数与压缩失真参数和 /或数据包 丢失视频质量失真参数相关, 即压缩失真参数和 /或数据包丢失视频质量失 真参数是评价视频帧质量的指标, 而该压缩失真参数和 /或数据包丢失视频 质量失真参数与视频帧质量之间存在线性关系, 所以使用压缩失真参数和 / 或数据包丢失视频质量失真参数评价视频帧质量可以更加直观地体现用户观 看网络视频时对网络视频的感受, 进而提高视频质量评估的准确性。
本发明实施例中的视频质量评估方式按照具体的视频帧参数的不同可以 分为三种情况:
一、 以压缩失真参数作为视频帧参数的情况:
本实施例中, 若该视频的传输信道质量比较高, 则可能不会造成数据包 丢失视频质量失真, 即不考虑视频数据包丢失的因素。 但从目前的技术来 看, 网络视频由于网络带宽的限制, 都会对视频进行编码压缩, 则本实施例 中仅以压缩失真参数作为视频质量的参考依据。
请参阅图 1, 本发明实施例中视频质量评估方法第一实施例包括: 101、 获取传输视频信息;
本实施例中, 检测视频质量的过程在终端侧完成, 即视频质量评估装置 可以作为终端的一部分, 或独立存在, 其只需获取终端侧的传输视频信息即 可进行视频质量评估, 而无需获取原始参考视频作为评价依据, 当然本方案 并不局限于终端侧, 本方案可以运用于只要能获取视频信息的网络的任意节 点。
本实施例中的传输视频信息可以包括码率, 视频编码的量化因子 (本文 所提到的量化因子可以是通常所说的量化参数 QP ( quantization
parameter) , 也可以是 Qstep (quantization step) 量化步长等控制不同量化 程度的参数, 以下的实例内容中都以量化参数 QP表示, 但对于量化步长 Qstep等控制量化程度的参数同样适用) , 或者还可以包括视频帧的持续时 间等信息。 可以理解的是, 在实际应用中, 除了上述信息之外, 还可以获取 其他类似的传输视频信息。
102、 根据所述传输视频信息计算压缩失真参数;
本实施例中, 获取到传 ^τί言息之后, 即可根据该传^ 「息计算 压缩失真参数, 具体过程为:
根据视频压缩的率失真公式
其中, "为拉普拉斯分布的 采用平方失真测度, D =QIA。 因 ? In 4
此, 可以得到 ― ^。
特别地, 对于视频序列, 为视频的区域方差。
上述 R为码率, QP为量化因子, 根据传输视频即可计算得到 R以及 QP, 具体的计算过程为现有技术, 此处不做限定。
由上述公式可以得到: a = Cl - QP - e^R (2) 对于固定的 QP, = ci ' eC2R , 通常情况下, R的取值范围较小 (小于 0.3 ) 而对于较小的 R, 与 R近似为线性关系, 即可以由上式 (2)计算得到 视频帧的空域复杂度参数以及时域活动度参数: 空域复杂度参数 ^ = + ; 时域活动度参数 = + C4R
上述^ , 为常数, 可以通过实验确定, 且每个 Qp都对应有固定的
Cl'C2'c-c 即上述空间复杂度参数以及时域活动度参数是依据 QP以及 R计 算得到。
其中, 空域复杂度参数的计算以及时域活动度参数的计算分别是上述式 (2)针对不同的视频帧所得到的, 采用帧内模式编码的视频帧, 反映了视 频帧的空域复杂度, 对于采用帧间模式编码的视频帧, σ反映了视频帧的时 域活动度。
上述空域复杂度表示视频空间内容的复杂度, 例如某一帧所包含的元素 等, 一般来说, 元素越多越复杂, 则该视频的空域复杂度越高;
上述时域活动度表示视频时域的运动特性, 例如某一帧所持续的时间, 或视频帧之间的交替程度, 一般来说, 交替程度越高, 则该视频的时域活动 度越高。
作为通用项, ,"为第 η个视频帧的空域复杂度, 为第 η个视频帧 的时域活动度, 为第 η个视频帧的码率, βρ "为第 η个视频帧的平均量化 因子。
需要说明的是, 对于采用帧内模式编码的视频帧, 其时域活动度根据其 相邻的采用帧间模式编码的视频帧的时域活动度预测得到; 对于采用帧间模 式编码的视频帧, 其空域复杂度根据其相邻的采用帧内模式编码的视频帧的 空域复杂度预测得到。
103、 根据压缩失真参数计算视频帧质量参数。
上述步骤 102中计算得到了视频帧的码率, 量化因子, 空域复杂度参数 以及时域活动度参数, 则可以根据参数计算视频帧质量参数。
在根据压缩失真参数计算视频帧质量参数之前, 首先需要说明一下视频 压缩与视频质量之间的关系:
视频压缩属于有损压缩, 视频编码中的量化过程是引起视频压缩失真的
根本原因。 由于网络视频应用通常能够对大部分帧进行正确接收和解码, 因 此对于没有出错的视频帧来说, 根据用户的视觉特性衡量量化失真就是评价 视频质量的关键。
通过主观实验得到, 视频帧的主观质量与 QP或者量化步长有近似的线 性关系, 如图 2所示。 其中曲线 201以及视频 202分别表示两个不同的视频 序列, 图 2展示的是不同的视频序列在只考虑压缩失真的情况的视频质量与 QP之间的曲线关系。 由图 2可以看出, 不同的视频序列的主观质量与 QP 之间的线性关系具有不同的特性 (例如不同的截距、 斜率) , 由此反映视频 的内容特性, 即视频的空域复杂度和时域活动度, 则某视频帧在只考虑压缩 失真的情况下, 其质量参数与该视频帧的空域复杂度参数, 时域活动度参 数, 码率以及量化因子有关。
其中, '表示视频帧 n的主观质量, 也称为视频帧质量基数, a以及 b 为常数, 均通过主观实验得到, 获取 a, b的过程此处不做限定。
由上式 (5)即可得到该视频帧的质量参数, 注意由于 , 是由 Qp的 大小决定, 所以实际上该公式表示的是视频质量和码率 R, 以及 QP之间的 关系。 该质量参数是只考虑压缩失真情况下的视频帧质量参数。
本实施例中, 计算得到视频帧的质量参数之后, 即可根据该视频帧的质 量参数计算视频序列的质量参数, 但是由于视频编码器的速率控制算法往往 导致解码端视频帧率随时间变化。
另外, 由于网络带宽的变化, 视频的播放过程往往会出现短暂的停顿。 因此, 整个视频序列的质量不是每一帧质量的简单叠加或平均, 对视频序列 进行质量评估还需要考虑视频播放帧率、 播放停顿等因素。
因此, 本实施例中采用 "视频帧对视频序列评分的贡献" 的方式计算视 频序列的质量参数。 其中, "视频帧对视频序列评分的贡献"表示当显示整 个视频序列时, 每个视频帧对整个视频质量的影响, 它与视频帧的质量和视 频帧的持续时间有关。 本实施例以及后续各个实施例中的持续时间均指视频 帧之间的间隔时间, 该时间间隔可以是连续的两个具有不同显示内容的帧之 间的显示时间间隔, 比如帧 a显示后出现了缓存情况, 缓存结束后才开始显 示帧 b, 这时帧 a和帧 b间的持续时间就必须包括缓存时间; 同时该时间还 包括这种情况: 帧 a后面有若干帧丢失无法解码不能显示其真实内容, 直到 帧 b才能解码并正确显示, 这时 a帧显示结束后, 根据不同的错误掩盖方法 会有不同的处理和显示策略, 通常的处理方法是, 后面每一丢失帧都使用 a 帧的内容来显示, 然后 b帧再显示, 这时本文所指的时间间隔就是第一个 a 帧和 b帧显示时间的差值。
具体地, 第 n个视频帧对视频序列评分的贡献 与视频帧 η的质量参 数有关, 且该视频帧的时域活动度参数, 以及该视频帧的持续时间有关。
计算得到各视频帧对视频序列评分的贡献之后, 可以通过时域加权的方 式得到整个视频序列的质量参数。
本实施例中, 获取到传输视频信息之后, 可以根据该传输视频信息至少 计算得到压缩失真参数, 之后可以至少根据该压缩失真参数计算视频帧质量 参数, 所以本发明实施例中只需要根据终端侧的传输视频信息即可计算视频 帧的质量, 无需获取原始参考视频, 因此能够节省网络资源;
其次, 由于本实施例中的视频帧质量参数至少与压缩失真参数相关, 即 压缩失真参数是评价视频帧质量的指标, 而该压缩失真参数与视频帧质量之 间存在线性关系, 所以使用压缩失真参数评价视频帧质量可以更加直观的体 现用户观看网络视频时对网络视频的感受, 进而提高视频质量评估的准确 性。
二、 以压缩失真参数以及数据包丢失视频质量失真参数作为视频帧参数 的情况:
本实施例中, 若该视频的传输信道质量不高, 则可能会造成数据包丢失 视频质量失真, 即在计算视频帧质量参数时需要考虑视频帧丢失的因素。 而 从目前的技术来看, 网络视频由于网络带宽的限制, 都会对视频进行编码压 缩, 所以本实施例中同时以压缩失真参数以及数据包丢失视频质量失真参数 作为视频质量的参考依据。
请参阅图 3, 本发明实施例中视频质量评估方法第二实施例包括: 301、 获取传输视频信息;
本实施例中, 以检测视频质量的过程在终端侧完成为例, 即视频质量评 估装置可以作为终端的一部分, 或独立存在, 其只需获取终端侧的传输视频 信息即可进行视频质量评估, 而无需获取原始参考视频作为评价依据, 当然 本方案并不局限于终端侧, 本方案可以运用于只要能获取视频信息的网络的 任意节点。
本实施例中的传输视频信息可以包括码率, 视频编码的量化因子, 或者
还可以包括视频帧的持续时间等信息。 可以理解的是, 在实际应用中, 除了 上述信息之外, 还可以获取其他类似的传输视频信息。
302、 根据所述传输视频信息计算压缩失真参数以及数据包丢失视频质 量失真参数;
本实施例中根据传输视频信息计算压缩失真参数的过程与前述第一实施 例中计算压缩失真参数的过程相同, 此处不再赘述。
此外, 本实施例中还可以计算数据包丢失视频质量失真参数, 对于网络 视频, 数据包丢失视频质量失真时影响视频质量的一个关键因素。 视频数据 的丢失会使解码器无法正常恢复相关的视频帧区域, 造成恢复视频的失真。 对于采用帧间预测模式编码的视频, 参考视频帧的错误以及参考视频帧的丢 失都会引起错误传播。 另外, 对于实时视频流, 网络数据包的时延、 抖动对 视频终端的影响都体现为数据丢失。
本实施例中的数据包丢失视频质量失真参数 表示数据丢失对视频帧 质量的影响。 需要说明的是, "片"是解码器解码的最小单位, 对于 "片" 的丢失, 解码器会进行误码掩盖, 误码掩盖后视频的质量与视频的内容密切 相关。 因此, 视频的空域时域相关性, 即视频帧的空域复杂度和时域活动度 是影响误码掩盖效果的关键因素。 另外, 没有数据丢失时视频帧的质量也是 影响 的一个关键因素。
因此, 本实施例中的 包括两个方面的参数, 一个为 ", 表示直接遭 受数据丢失引起视频帧质量下降的程度; 另一个为 ", 表示误码传播引起 视频帧质量下降的程度。
首先说明 "的计算过程:
其中, 由于视频数据丢失越多, 该视频帧受误码引起的失真就越大, 所 以包含有误码的视频帧的质量参数为:
of =o - 其中, "" 表示为该帧接收到的有效包数 (该数据包可以是实时传输 协议包或者其他视频传输协议数据包, 这里以实时传输协议为例, RTP, Real Time Protocol, ) , "M 为该帧所有的 RTP包数, ^表示完全无误码 的视频帧质量参数, 当当前帧完全丢失时, 由于计算参数无法获取, 可 以根据解码端错误掩盖方法, 通过预测得到, 例如如果采用前一帧进行时域 掩盖的方法, 可以通过前一帧参数来预测当前帧, 为整帧丢失引起该视 频帧的失真, 其中,
Dn = Qn R
a3
上述式 (8)中 以及 均为常数, 可以通过实现得到, 具体的获得方式此 处不做限定。
其次说明 "的计算方式:
其中, 以及 ¾均为常数, 可以通过实验得到。 上述介绍了计算 以及 ,"的过程, 将上述两个参数直接相加即可得到 d", 即数据包丢失视频质量失真参数。
303、 根据压缩失真参数计算无丢包情况下视频帧质量参数;
本实施例中, 具体计算无丢包情况下视频帧质量参数的步骤即为第一实 施例中步骤 203计算得到的结果, 具体计算过程此处不再赘述。
304、 根据无丢包情况下视频帧质量参数以及数据包丢失视频质量失真 参数计算视频帧质量参数。
步骤 302中获得了数据包丢失视频质量失真参数, 步骤 303中获得了无 丢包情况下视频帧质量参数, 则可将无丢包情况下视频帧质量参数与数据包 丢失视频质量失真参数的差值作为视频帧质量参数。
本实施例中, 计算得到视频帧的质量参数之后, 即可根据该视频帧的质 量参数计算视频序列的质量参数, 但是由于视频编码器的速率控制算法往往 导致解码端视频帧率随时间变化。
另外, 由于网络带宽的变化, 视频的播放过程往往会出现短暂的停顿。 因此, 整个视频序列的质量不是每一帧质量的简单叠加或平均, 对视频序列 进行质量评估还需要考虑视频播放帧率、 播放停顿等因素。
因此, 本实施例中采用 "视频帧对视频序列评分的贡献" 的方式计算视 频序列的质量参数。 其中, "视频帧对视频序列评分的贡献"表示当显示整 个视频序列时, 每个视频帧对整个视频质量的影响, 它与视频帧的质量和视 频帧的持续时间有关。
具体地, 第 n个视频帧对视频序列评分的贡献 与视频帧 η的质量参 数有关, 且该视频帧的时域活动度参数, 以及该视频帧的持续时间有关。
计算得到各视频帧对视频序列评分的贡献之后, 可以通过时域加权的方 式得到整个视频序列的质量参数。
本实施例中, 获取到传输视频信息之后, 可以根据该传输视频信息至少 计算得到压缩失真参数, 之后可以至少根据该压缩失真参数计算视频帧质量 参数, 所以本发明实施例中只需要根据终端侧的传输视频信息即可计算视频 帧的质量, 无需获取原始参考视频, 因此能够节省网络资源;
其次, 由于本实施例中的视频帧质量参数至少与压缩失真参数相关, 即 压缩失真参数是评价视频帧质量的指标, 而该压缩失真参数与视频帧质量之 间存在线性关系, 所以使用压缩失真参数评价视频帧质量可以更加直观的体 现用户观看网络视频时对网络视频的感受, 进而提高视频质量评估的准确 性。
三、 以数据包丢失视频质量失真参数作为视频帧参数的情况: 本实施例中, 对于某些有特殊要求的视频, 例如要求视频的播放质量需 要尽可能的和原始质量相同, 则可能不会对视频进行压缩或者压缩的比例很 小, 同时有些应用不考虑视频压缩损伤仅仅考虑网络损伤, 在这种情况下, 则可以只考虑视频帧参数包括数据包丢失视频质量失真参数的情况, 之后可 能再考虑进一步包括压缩失真的情况。
本实施例中计算数据包丢失视频质量失真参数的方式与上述第二实施例 中计算数据包丢失视频质量失真参数的方式类似。
计算得到数据包丢失视频质量失真参数之后, 可以按照预置的方式计算 视频帧初始质量参数即不包括视频数据包丢失影响 (具体的方式可以采用现 有技术中的计算方式或其他类似的计算视频帧质量的方式, 以及直接假定等 方式) , 将视频帧初始质量参数与数据包丢失视频质量失真参数的差值作为 视频帧质量参数。
同样的, 在计算得到视频帧质量参数之后, 可以按照前述实施例中的方 式计算视频序列质量, 方式类似, 此处不再赘述。
需要说明的是, 上述三个实施例中在计算得到视频帧质量参数之后同样 可以根据视频帧质量参数以及该视频帧的持续时间进行加权运算得到视频序 列的质量, 可以理解的是, 在实际应用中, 对于已经获取到的视频帧质量参 数而言, 无论其采用何种方式计算得到 (包括采用本发明实施例提供的方 式, 或采用现有技术的其他计算方式) 之后, 均可采用本发明实施例中的方 式计算整个视频序列的质量, 具体方式与前述实施例中的方式类似, 此处不 作限定。
下面介绍本发明实施例中的视频质量评估装置, 请参阅图 4, 本发明实 施例中的视频质量评估装置包括:
视频帧获取单元 401, 用于获取传输视频信息;
视频帧参数计算单元 402, 用于根据视频帧获取单元 401获取到的传输 视频信息解析得到视频帧参数, 所述视频帧参数至少包括压缩失真参数或者 数据包丢失参数;
视频帧质量参数计算单元 404, 用于根据视频帧参数计算单元 402计算 得到的视频帧参数计算视频帧质量参数。
本实施例中, 按照视频帧参数所包含的内容可以将本实施例分为三种情 况:
一、 视频帧参数仅包含压缩失真参数:
此种情况下, 本实施例中的视频质量评估装置包括:
视频帧获取单元 401, 用于获取传输视频信息;
视频帧参数计算单元 402, 用于根据视频帧获取单元 401获取到的传输 视频信息解析得到视频帧参数, 所述视频帧参数至少包括压缩失真参数; 本实施例中的视频帧参数计算单元 402 中包含压缩失真计算单元 4021, 用于根据视频帧获取单元 401获取到的传输视频信息计算压缩失真参 数;
视频帧质量参数计算单元 404, 用于根据压缩失真计算单元 4021计算
得到的压缩失真参数计算视频帧质量参数。
视频序列质量计算单元 405, 用于获取所述视频帧的持续时间, 对所述 视频帧质量参数以及所述持续时间进行加权运算得到视频序列质量计算单 元。
具体的计算方式与前述方法实施例中的计算方式一致, 此处不再赘述。 二、 视频帧参数仅包含数据包丢失失真参数:
此种情况下, 本实施例中的视频质量评估装置包括:
视频帧获取单元 401, 用于获取传输视频信息;
视频帧参数计算单元 402, 用于根据视频帧获取单元 401获取到的传输 视频信息解析得到视频帧参数, 所述视频帧参数至少包括数据包丢失视频质 量失真参数;
本实施例中的视频帧参数计算单元 402 中包含数据包丢失计算单元 4022, 用于根据视频帧获取单元 401获取到的传输视频信息计算数据包丢失 视频质量失真参数;
视频帧质量参数计算单元 404, 用于根据数据包丢失计算单元 4022计 算得到的数据包丢失视频质量失真参数计算视频帧质量参数。
视频序列质量计算单元 405, 用于获取所述视频帧的持续时间, 对所述 视频帧质量参数以及所述持续时间进行加权运算得到视频序列质量计算单 元。
具体的计算方式与前述方法实施例中的计算方式一致, 此处不再赘述。 三、 视频帧参数包含压缩失真参数以及数据包丢失视频质量失真参数: 此种情况下, 本实施例中的视频质量评估装置包括:
视频帧获取单元 401, 用于获取传输视频信息;
视频帧参数计算单元 402, 用于根据视频帧获取单元 401获取到的传输 视频信息解析得到视频帧参数, 所述视频帧参数包括压缩失真参数以及数据 包丢失视频质量失真参数;
本实施例中的视频帧参数计算单元 402中包含压缩失真计算单元 4021 以及数据包丢失计算单元 4022;
其中压缩失真计算单元 4021用于根据视频帧获取单元 401获取到的传 输视频信息计算压缩失真参数;
其中数据包丢失计算单元 4022用于根据视频帧获取单元 401获取到的 传输视频信息计算数据包丢失视频质量失真参数;
本实施例中的视频质量评估装置还包括:
无损码参数计算单元 403, 用于根据压缩失真计算单元 4021计算得到 的压缩失真参数计算无丢包情况下视频帧参数;
视频帧质量参数计算单元 404, 用于根据无损码参数计算单元 403计算 得到的无丢包情况下视频帧参数以及数据包丢失计算单元 4022计算得到的 数据包丢失视频质量失真参数计算视频帧质量参数。
视频序列质量计算单元 405, 用于获取所述视频帧的持续时间, 对所述 视频帧质量参数以及所述持续时间进行加权运算得到视频序列质量计算单 元。
具体的计算方式与前述方法实施例中的计算方式一致, 此处不再赘述。 本实施例中, 获取到传输视频信息之后, 可以根据该传输视频信息至少 计算得到压缩失真参数, 之后可以至少根据该压缩失真参数计算视频帧质量 参数, 所以本发明实施例中只需要根据终端侧的传输视频信息即可计算视频 帧的质量, 无需获取原始参考视频, 因此能够节省网络资源;
其次, 由于本实施例中的视频帧质量参数至少与压缩失真参数相关, 即 压缩失真参数是评价视频帧质量的指标, 而该压缩失真参数与视频帧质量之 间存在线性关系, 所以使用压缩失真参数评价视频帧质量可以更加直观的体 现用户观看网络视频时对网络视频的感受, 进而提高视频质量评估的准确 性。
下面介绍本发明实施例中的视频质量评估系统, 请参阅图 5, 本发明实
施例中的视频质量评估系统包括:
视频质量评估装置 501, 用于获取传输视频信息; 根据所述传输视频信 息解析得到视频帧参数, 所述视频帧参数包括压缩失真参数和 /或数据包丢 失视频质量失真参数; 根据所述视频帧参数计算视频帧质量参数;
发送装置 502, 用于获取所述视频质量评估装置 501生成的视频帧质量 参数, 发送所述视频帧质量参数。
本实施例中的视频质量评估系统还可以进一步包括:
显示装置 503, 用于接收所述发送装置 502发送的视频帧质量参数, 向 用户展示所述视频帧质量参数。
本实施例中的视频质量评估系统还可以进一步包括:
存储装置 504, 用于存储所述发送装置 502发送的视频帧质量参数。 可以理解的是, 本实施例中的视频质量评估装置 501的具体结构可采用 前述图 4中所示的视频质量评估装置的结构, 该视频质量评估装置 501的工 作方式以及数据处理流程与前述图 4中的工作方式以及数据处理流程类似, 此处不再赘述。
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完成, 所述的程序可以存储于一种计算机 可读存储介质中, 该程序在执行时, 包括如下步骤:
获取传输视频信息;
根据所述传输视频信息解析得到视频帧参数, 所述视频帧参数包括压缩 失真参数和 /或数据包丢失视频质量失真参数;
根据所述视频帧参数计算视频帧质量参数。
上述提到的存储介质可以是只读存储器, 磁盘或光盘等。
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流 程, 是可以通过计算机程序来指令相关的硬件来完成, 所述的程序可存储于 一计算机可读取存储介质中, 该程序在执行时, 可包括如上述各方法的实施
例的流程。 其中, 所述的存储介质可为磁碟、 光盘、 只读存储记忆体
(ROM, Read-Only Memory) 或随机存储记忆体 (RAM, Random Access Memory) 等。
以上对本发明所提供的一种视频质量评估方法及装置进行了详细介绍, 对于本领域的一般技术人员, 依据本发明实施例的思想, 在具体实施方式及 应用范围上均会有改变之处, 综上所述, 本说明书内容不应理解为对本发明 的限制。
Claims
1、 一种视频质量评估方法, 其特征在于, 包括:
获取传输视频信息;
根据所述传输视频信息解析得到视频帧参数, 所述视频帧参数包括压缩 失真参数和 /或数据包丢失视频质量失真参数;
根据所述视频帧参数计算视频帧质量参数。
2、 根据权利要求 1所述的方法, 其特征在于, 所述根据所述视频帧参 数计算视频帧质量参数的步骤包括:
根据所述压缩失真参数计算所述视频帧质量参数; 或者
根据所述数据包丢失视频质量失真参数计算所述视频帧质量参数; 或者 根据所述压缩失真参数和所述数据包丢失视频质量失真参数计算所述视 频帧质量参数。
3、 根据权利要求 1或 2所述的方法, 其特征在于, 所述获取的压缩失 真参数的过程中至少使用视频帧信息的码率以及量化因子。
4、 根据权利要求 3所述的方法, 其特征在于, 所述根据所述传输视频 信息解析得到视频帧参数中的压缩失真参数的步骤包括:
获取所述传输视频信息的码率以及量化因子;
根据所述码率以及量化因子计算所述视频帧对应的空域复杂度参数以及 时域活动度参数, 所述空域复杂度参数表示视频空间内容的复杂度, 所述时 域活动度参数表示视频时域的运动特性;
根据所述空域复杂度参数以及时域活动度参数计算所述压缩失真参数。
5、 根据权利要求 4所述的方法, 其特征在于, 所述根据视频帧参数中 的压缩失真参数计算视频帧质量参数的步骤包括:
根据所述量化因子计算得到视频质量基数;
根据所述视频空间复杂度参数和时域活动度参数对所述视频质量基数进 行掩盖修正获得视频帧质量参数。
6、 根据权利要求 2所述的方法, 其特征在于, 所述根据所述传输视频 信息解析得到视频帧参数中的数据包丢失视频质量失真参数的步骤包括: 根据所述传输视频信息计算第一视频质量失真参数以及第二视频质量失 真参数;
将所述第一视频质量失真参数以及第二视频质量失真参数之和作为所述 视频质量失真参数, 所述第一视频质量失真参数表示视频帧内丢失数据所造 成的视频帧质量下降的程度, 所述第二视频质量失真参数表示误码传播所造 成的视频帧质量下降的程度。
7、 根据权利要求 6所述的方法, 其特征在于, 所述根据所述传输视频 信息计算第一视频质量失真参数的步骤包括:
获取所述视频帧中有效数据包的数目以及所有数据包的数目; 将所述所有数据包的数目与所述有效数据包的数目的差与所述所有数据 包的数目进行除法运算得到所述视频帧中失效数据包所占的比例;
将所述比例与所述视频帧整帧丢失的失真参数之间的乘积作为所述第一 视频质量失真参数。
8、 根据权利要求 7所述的方法, 所述视频整帧丢失的失真参数的计算 步骤包括:
计算当前视频帧在没有误码时的视频质量;
根据当前帧没有误码时的视频时域活动度参数以及预制常数计算视频整 帧丢失的失真参数。
9、 根据权利要求 6所述的方法, 其特征在于, 所述根据所述传输视频 信息计算第二视频质量失真参数的步骤包括:
获取当前视频帧的参考帧的视频质量失真参数;
根据所述参考帧的视频质量失真参数、 时域活动度参数以及预置常数计 算第二视频质量失真参数。
10、 根据权利要求 2或 4或 6所述的方法, 其特征在于, 所述根据所述
压缩失真参数和所述数据包丢失视频质量失真参数计算所述视频帧质量参数 的步骤包括:
根据所述压缩失真参数计算无丢包情况下视频帧质量参数;
获取数据包丢失视频质量失真参数;
根据所述无丢包情况下视频帧质量参数以及数据包丢失视频质量失真参 数计算所述视频帧质量参数。
11、 根据权利要求 10所述的方法, 其特征在于, 所述根据所述无丢包 情况下视频帧质量参数以及数据包丢失视频质量失真参数计算所述视频帧质 量参数的步骤包括:
将所述无丢包情况下视频帧质量参数与所述数据包丢失视频质量失真参 数之间的差值作为所述视频帧质量参数。
12、 根据权利要求 1至 9中任一项所述的方法, 其特征在于, 所述根据 所述视频帧参数计算视频帧质量参数的步骤之后包括:
获取所述视频帧的持续时间;
根据所述视频帧质量参数以及所述持续时间计算视频序列质量参数。
13、 一种视频质量评估方法, 其特征在于, 包括:
获取传输视频信息, 所述视频帧信息至少包括所述视频帧的持续时间; 根据所述传输视频信息解析得到视频帧参数;
根据所述视频帧参数计算视频帧质量参数;
对所述视频帧质量参数以及所述持续时间进行加权运算得到视频序列质
14、 根据权利要求 13所述的方法, 其特征在于, 所述视频帧参数包 括: 压缩失真参数和 /或数据包丢失视频质量失真参数;
所述根据所述视频帧参数计算视频帧质量参数的步骤包括:
根据所述压缩失真参数计算所述视频帧质量参数; 或者
根据所述数据包丢失视频质量失真参数计算所述视频帧质量参数; 或者
根据所述压缩失真参数和所述数据包丢失视频质量失真参数计算所述视 频帧质量参数。
15、 根据权利要求 13或 14所述的方法, 其特征在于, 所述持续时间包 括视频帧之间的间隔时间。
16、 一种视频质量评估装置, 其特征在于, 包括:
视频帧获取单元, 用于获取传输视频信息;
视频帧参数计算单元, 用于根据视频帧获取单元获取到的传输视频信息 解析得到视频帧参数, 所述视频帧参数包括压缩失真参数和 /或数据包丢失 视频质量失真参数;
视频帧质量参数计算单元, 用于根据视频帧参数计算单元计算得到的视 频帧参数计算视频帧质量参数。
17、 根据权利要求 16所述的视频质量评估装置, 其特征在于, 所述视 频质量评估装置还包括:
视频序列质量计算单元, 用于获取所述视频帧的持续时间, 对所述视频 帧质量参数以及所述持续时间进行加权运算得到视频序列质量参数。
18、 根据权利要求 16或 17所述的视频质量评估装置, 其特征在于, 所 述视频帧参数计算单元包括:
压缩失真计算单元, 用于根据视频帧获取单元获取到的传输视频信息计 算压缩失真参数;
数据包丢失计算单元, 用于根据视频帧获取单元获取到的传输视频信息 计算数据包丢失视频质量失真参数。
19、 根据权利要求 18所述的视频质量评估装置, 其特征在于, 所述视 频质量评估装置还包括:
无损码参数计算单元, 用于根据压缩失真计算单元计算得到的压缩失真 参数计算无丢包情况下视频帧参数;
所述视频帧质量参数计算单元还用于根据无损码参数计算单元计算得到
的无丢包情况下视频帧参数以及数据包丢失计算单元计算得到的数据包丢失 视频质量失真参数计算视频帧质量参数。
20、 一种视频质量评估系统, 其特征在于, 包括:
视频质量评估装置, 用于获取传输视频信息, 根据所述传输视频信息解 析得到视频帧参数, 所述视频帧参数包括压缩失真参数和 /或数据包丢失视 频质量失真参数, 根据所述视频帧参数计算视频帧质量参数;
发送装置, 用于获取所述视频质量评估装置生成的视频帧质量参数, 发 送所述视频帧质量参数。
21、 根据权利要求 20所述的视频质量评估系统, 其特征在于, 所述视 频质量评估系统还包括:
显示装置, 用于接收所述发送装置发送的视频帧质量参数, 向用户展示 所述视频帧质量参数。
22、 根据权利要求 20或 21所述的视频质量评估系统, 其特征在于, 所 述视频质量评估系统还包括:
存储装置, 用于存储所述发送装置发送的视频帧质量参数。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP09799953A EP2296379A4 (en) | 2008-07-21 | 2009-05-05 | METHOD, SYSTEM AND DEVICE FOR EVALUATING A VIDEO QUALITY |
US12/976,319 US8917777B2 (en) | 2008-07-21 | 2010-12-22 | Method, system and apparatus for evaluating video quality |
US14/555,121 US9723332B2 (en) | 2008-07-21 | 2014-11-26 | Method, system and apparatus for evaluating video quality |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200810130787.8 | 2008-07-21 | ||
CN200810130787 | 2008-07-21 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/976,319 Continuation US8917777B2 (en) | 2008-07-21 | 2010-12-22 | Method, system and apparatus for evaluating video quality |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2010009637A1 true WO2010009637A1 (zh) | 2010-01-28 |
Family
ID=41570012
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2009/071633 WO2010009637A1 (zh) | 2008-07-21 | 2009-05-05 | 一种视频质量评估方法、系统及装置 |
Country Status (4)
Country | Link |
---|---|
US (2) | US8917777B2 (zh) |
EP (1) | EP2296379A4 (zh) |
CN (1) | CN101635846B (zh) |
WO (1) | WO2010009637A1 (zh) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103002285A (zh) * | 2012-12-06 | 2013-03-27 | 深圳广晟信源技术有限公司 | 视频单元的复杂度生成方法及装置 |
CN103002287A (zh) * | 2012-12-06 | 2013-03-27 | 深圳广晟信源技术有限公司 | 视频单元的复杂度生成方法及装置 |
US20140286441A1 (en) * | 2011-11-24 | 2014-09-25 | Fan Zhang | Video quality measurement |
Families Citing this family (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2296379A4 (en) | 2008-07-21 | 2011-07-20 | Huawei Tech Co Ltd | METHOD, SYSTEM AND DEVICE FOR EVALUATING A VIDEO QUALITY |
CN101827280B (zh) * | 2010-02-04 | 2012-03-21 | 深圳市同洲电子股份有限公司 | 视频输出质量的检测方法和装置 |
US9288071B2 (en) | 2010-04-30 | 2016-03-15 | Thomson Licensing | Method and apparatus for assessing quality of video stream |
JP2014504471A (ja) * | 2010-11-30 | 2014-02-20 | トムソン ライセンシング | フレーム損失パターンに基づいてビデオの品質を測定する方法および装置 |
CN102204265B (zh) * | 2010-12-31 | 2013-08-07 | 华为技术有限公司 | 视频质量的评估方法、终端、服务器及系统 |
CN104883563B (zh) | 2011-04-11 | 2017-04-12 | 华为技术有限公司 | 一种视频数据质量评估方法和装置 |
CN103039085B (zh) * | 2011-06-07 | 2015-03-11 | 华为技术有限公司 | 用于在数据网络中监视视频会话的监视装置和方法 |
CN102257831B (zh) * | 2011-06-09 | 2013-08-07 | 华为技术有限公司 | 一种视频质量评估的方法和网络节点 |
JP2014527778A (ja) * | 2011-08-29 | 2014-10-16 | アイ.シー.ブイ.ティー リミテッド | ビデオコンテンツシステムの制御 |
CN103188236B (zh) * | 2011-12-30 | 2015-12-16 | 华为技术有限公司 | 媒体传输质量的评估方法和装置 |
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 |
CN103379358B (zh) * | 2012-04-23 | 2015-03-18 | 华为技术有限公司 | 评估多媒体质量的方法和装置 |
CN103428523B (zh) * | 2012-05-22 | 2015-07-08 | 华为技术有限公司 | 评估视频质量的方法和装置 |
CN103458264B (zh) * | 2012-05-28 | 2015-02-25 | 华为技术有限公司 | 一种媒体质量的评估方法及装置 |
CN104780369B (zh) * | 2012-08-21 | 2018-04-17 | 华为技术有限公司 | 一种获得视频编码压缩质量的方法及装置 |
CN104539943B (zh) * | 2012-08-22 | 2017-01-04 | 华为技术有限公司 | 多媒体质量的监控方法和设备 |
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 |
KR20150052049A (ko) * | 2012-08-27 | 2015-05-13 | 톰슨 라이센싱 | 비디오 품질 평가를 위해 모션 균일성을 추정하기 위한 방법 및 장치 |
CN103813160B (zh) * | 2012-11-12 | 2016-03-02 | 中国电信股份有限公司 | 视频质量监控方法和装置 |
CN102984541B (zh) * | 2012-12-07 | 2015-01-14 | 浙江大学 | 一种基于像素域失真度估计的视频质量评价方法 |
CN103945213B (zh) * | 2013-01-22 | 2016-12-28 | 中兴通讯股份有限公司 | 一种视频流质量监测方法及装置 |
CN103747237B (zh) * | 2013-02-06 | 2015-04-29 | 华为技术有限公司 | 视频编码质量的评估方法及设备 |
AU2013377642A1 (en) | 2013-02-07 | 2015-07-23 | Thomson Licensing | Method and apparatus for context-based video quality assessment |
JP2016510568A (ja) | 2013-02-07 | 2016-04-07 | トムソン ライセンシングThomson Licensing | コンテキストベースのビデオ品質評価のための方法および装置 |
CN104935918B (zh) * | 2013-02-20 | 2017-04-05 | 华为技术有限公司 | 视频静止失真程度评估方法和装置 |
CN103347195B (zh) * | 2013-05-31 | 2016-04-06 | Tcl集团股份有限公司 | 一种监测评估视频质量的系统及方法 |
CN104427383B (zh) * | 2013-08-19 | 2018-08-10 | 联想(北京)有限公司 | 一种信息处理方法以及电子设备 |
CN103533367B (zh) * | 2013-10-23 | 2015-08-19 | 传线网络科技(上海)有限公司 | 一种无参考视频质量评价方法及装置 |
CN104486092B (zh) * | 2014-12-15 | 2018-04-06 | 北京国双科技有限公司 | 数据监控方法及装置 |
CN104581140B (zh) * | 2014-12-26 | 2016-08-24 | 国家电网公司 | 一种会议电视的视频质量评估方法 |
CN106713901B (zh) * | 2015-11-18 | 2018-10-19 | 华为技术有限公司 | 一种视频质量评价方法及装置 |
CN105812706A (zh) * | 2016-03-17 | 2016-07-27 | 掌赢信息科技(上海)有限公司 | 一种视频通话质量评估方法及电子设备 |
CN107623847B (zh) * | 2016-07-14 | 2020-02-18 | 中国移动通信集团重庆有限公司 | 一种视频业务的视频质量评估方法和装置 |
CN107786676B (zh) * | 2016-08-24 | 2021-07-09 | 中国电信股份有限公司 | 中继通信方法、系统和用于中继通信的终端 |
CN106507101B (zh) * | 2016-11-21 | 2018-12-28 | 中国联合网络通信集团有限公司 | 一种视频业务质量评价方法及装置 |
CN108271016B (zh) * | 2016-12-30 | 2019-10-22 | 上海大唐移动通信设备有限公司 | 视频质量评估方法及装置 |
US20180278947A1 (en) * | 2017-03-24 | 2018-09-27 | Seiko Epson Corporation | Display device, communication device, method of controlling display device, and method of controlling communication device |
CN108809893B (zh) * | 2017-04-27 | 2020-03-27 | 华为技术有限公司 | 一种视频质量评估方法和设备 |
CN107659806B (zh) * | 2017-08-22 | 2019-08-16 | 华为技术有限公司 | 视频质量的评估方法和装置 |
JP6907880B2 (ja) * | 2017-10-24 | 2021-07-21 | オムロン株式会社 | 画像処理装置、画像処理システム、画像処理プログラム |
CN110895794B (zh) * | 2018-09-13 | 2022-11-25 | 浙江宇视科技有限公司 | 视频效果自修复方法和视频自修复装置 |
KR102285738B1 (ko) * | 2018-10-19 | 2021-08-05 | 삼성전자주식회사 | 영상의 주관적 품질을 평가하는 방법 및 장치 |
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 |
IL274803B2 (en) * | 2019-07-16 | 2023-06-01 | Beamr Imaging Ltd | System and method for subjective evaluation of video quality |
CN110691238A (zh) * | 2019-11-06 | 2020-01-14 | 苏州科达科技股份有限公司 | 一种视频重建质量测试方法、装置、设备及可读存储介质 |
CN112235598B (zh) * | 2020-09-27 | 2022-09-20 | 深圳云天励飞技术股份有限公司 | 一种视频结构化处理方法、装置及终端设备 |
CN112995652B (zh) * | 2021-02-01 | 2021-12-07 | 腾讯科技(深圳)有限公司 | 视频质量评估方法及装置 |
CN113709453B (zh) * | 2021-09-13 | 2023-09-08 | 北京车和家信息技术有限公司 | 视频质量评估方法、装置、设备及介质 |
CN117354177B (zh) * | 2023-12-06 | 2024-03-01 | 广州市森锐科技股份有限公司 | 一种基于信创一体机的数据处理方法和系统 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000102041A (ja) * | 1998-09-10 | 2000-04-07 | Tektronix Inc | 画像品質測定方法 |
JP2005159419A (ja) * | 2003-11-20 | 2005-06-16 | Canon Inc | 画像処理装置及び方法、並びにコンピュータプログラム及びコンピュータ可読記憶媒体 |
CN1809175A (zh) * | 2005-01-17 | 2006-07-26 | 华为技术有限公司 | 一种视频质量评估方法 |
CN101184222A (zh) * | 2007-12-10 | 2008-05-21 | 上海华为技术有限公司 | 在无线通信系统中实现视频业务的方法及网元设备 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7948875B2 (en) * | 1997-08-29 | 2011-05-24 | AIP Acquisition, LLC | IP exchange quality testing system and method |
WO2004109586A1 (en) * | 2003-06-05 | 2004-12-16 | Aware, Inc. | Image quality control techniques |
EP1727375A1 (en) * | 2005-05-27 | 2006-11-29 | Psytechnics Limited | Assessment of perceived quality of a packetized video stream |
US20060280242A1 (en) * | 2005-06-13 | 2006-12-14 | Nokia Corporation | System and method for providing one-pass rate control for encoders |
US7865035B2 (en) * | 2005-10-06 | 2011-01-04 | Samsung Electronics Co., Ltd. | Video quality adaptive coding artifact reduction |
US8159960B2 (en) * | 2006-12-18 | 2012-04-17 | Verizon Patent And Licensing Inc. | Content processing device monitoring |
US20100053300A1 (en) * | 2007-02-02 | 2010-03-04 | Einarsson Torbjoern | Method And Arrangement For Video Telephony Quality Assessment |
EP2106154A1 (en) * | 2008-03-28 | 2009-09-30 | Deutsche Telekom AG | Audio-visual quality estimation |
EP2296379A4 (en) | 2008-07-21 | 2011-07-20 | Huawei Tech Co Ltd | METHOD, SYSTEM AND DEVICE FOR EVALUATING A VIDEO QUALITY |
-
2009
- 2009-05-05 EP EP09799953A patent/EP2296379A4/en not_active Withdrawn
- 2009-05-05 WO PCT/CN2009/071633 patent/WO2010009637A1/zh active Application Filing
- 2009-07-20 CN CN200910161628.9A patent/CN101635846B/zh not_active Expired - Fee Related
-
2010
- 2010-12-22 US US12/976,319 patent/US8917777B2/en not_active Expired - Fee Related
-
2014
- 2014-11-26 US US14/555,121 patent/US9723332B2/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000102041A (ja) * | 1998-09-10 | 2000-04-07 | Tektronix Inc | 画像品質測定方法 |
JP2005159419A (ja) * | 2003-11-20 | 2005-06-16 | Canon Inc | 画像処理装置及び方法、並びにコンピュータプログラム及びコンピュータ可読記憶媒体 |
CN1809175A (zh) * | 2005-01-17 | 2006-07-26 | 华为技术有限公司 | 一种视频质量评估方法 |
CN101184222A (zh) * | 2007-12-10 | 2008-05-21 | 上海华为技术有限公司 | 在无线通信系统中实现视频业务的方法及网元设备 |
Non-Patent Citations (1)
Title |
---|
See also references of EP2296379A4 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140286441A1 (en) * | 2011-11-24 | 2014-09-25 | Fan Zhang | Video quality measurement |
US10075710B2 (en) * | 2011-11-24 | 2018-09-11 | Thomson Licensing | Video quality measurement |
CN103002285A (zh) * | 2012-12-06 | 2013-03-27 | 深圳广晟信源技术有限公司 | 视频单元的复杂度生成方法及装置 |
CN103002287A (zh) * | 2012-12-06 | 2013-03-27 | 深圳广晟信源技术有限公司 | 视频单元的复杂度生成方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
CN101635846B (zh) | 2012-04-25 |
US9723332B2 (en) | 2017-08-01 |
EP2296379A1 (en) | 2011-03-16 |
EP2296379A4 (en) | 2011-07-20 |
US20110085605A1 (en) | 2011-04-14 |
US20150085942A1 (en) | 2015-03-26 |
US8917777B2 (en) | 2014-12-23 |
CN101635846A (zh) | 2010-01-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2010009637A1 (zh) | 一种视频质量评估方法、系统及装置 | |
US9319670B2 (en) | Video data quality assessment method and apparatus | |
US9210419B2 (en) | System and method for diagnostic modeling of audio and video quality of service | |
US9723329B2 (en) | Method and system for determining a quality value of a video stream | |
KR20140098248A (ko) | 비디오 스트림 내의 아티팩트를 최소화하는 방법, 비디오 스트림의 속성을 변경하는 시스템 및 컴퓨터 판독가능 매체 | |
US10944973B2 (en) | Estimation of video quality of experience on media servers | |
US9077972B2 (en) | Method and apparatus for assessing the quality of a video signal during encoding or compressing of the video signal | |
US11889122B2 (en) | Quality aware error concealment technique for streaming media | |
KR20050105630A (ko) | 동영상 화질 평가시스템 및 방법 | |
JP4861371B2 (ja) | 映像品質推定装置、方法、およびプログラム | |
US9723266B1 (en) | Lightweight content aware bit stream video quality monitoring service | |
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 | |
Chin et al. | Bitstream-based quality metric for packetized transmission of H. 264 encoded video | |
Wu et al. | ARMOR–A system for adjusting repair and media scaling for video streaming | |
GB2488334A (en) | Decoding a sequence of encoded digital frames | |
Moltchanov | Kamiar Radnosrati Trading-o Compression, Energy E ciency, and QoE In Wireless Network |
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: 09799953 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 4835/KOLNP/2010 Country of ref document: IN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2009799953 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |