CN103200419B - High-speed recognizing method of change degree of video content - Google Patents
High-speed recognizing method of change degree of video content Download PDFInfo
- Publication number
- CN103200419B CN103200419B CN201310068909.6A CN201310068909A CN103200419B CN 103200419 B CN103200419 B CN 103200419B CN 201310068909 A CN201310068909 A CN 201310068909A CN 103200419 B CN103200419 B CN 103200419B
- Authority
- CN
- China
- Prior art keywords
- video
- frame
- evaluated
- packet
- video content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention provides a high-speed recognizing of a change degree of video content. The high-speed recognizing method of the change degree of the video content comprises building a buffer area for a video to be evaluated according to an application scenario which comprises an offline scenario and an online scenario, initializing local variables, reading a next frame from the head portion of the buffer area built for the video to be evaluated and judging the type of the frame, carrying out a next step if the frame is a key frame, and otherwise, carrying out the current step, calculating the number of the bytes of the frame, accumulating the number of the bytes to a total number of the bytes, reading a next frame from the head portion of the buffer area built for the video to be evaluated, continuing to judge the type of the frame, carrying out a last step if the frame is a forecast frame, and otherwise, carrying out a next step, and calculating the metric of the change degree of the video content through the number of the bytes of the frame and the total number of the bytes. The high-speed recognizing method of the change degree of the video content can evaluate the content character of a video at high speed with low complexity and space spending, and can meet the needs of carrying out simple and fast classification on the video content.
Description
Technical field
The invention belongs to multimedia communication technology field, relate to a kind of method that video content changes that identifies, particularly relate to a kind of method of high speed identification change degree of video content.
Background technology
Along with the development of the Internet, audio-video frequency media stream occupies the main flow of network gradually.But the Internet is a kind of transmission (Best-effort) network of doing one's best, and the situation such as the bandwidth in the transmitting procedure of Streaming Media, packet loss, shake, time delay happens occasionally, they can produce adverse influence to video quality.To improve for the purpose of network performance and overall resource utilization to the research of network service quality QoS (Quality of Service) in the past, the actual use sense that present ISP and ICP then more pays close attention to signed client is subject to, and QoS cannot meet these needs.Therefore the viewing quality that user experience quality QoE (Quality of Experience) describes media user is introduced.
At present, multiple research organization such as ITU, VQEG proposes respective video quality assessment model, more famous to have G.1070, E-Model, Evalvid etc.And these models mainly consider the impact of qos parameter on QoE, but have ignored the impact of video content on QoE.And existing experiment shows, there is difference clearly to the impact of QoE in different video content.The video (as football match etc.) that content change is violent by the impact of packet loss, shake much larger than the mild video (as news report etc.) of content change, as shown in Figure 1.This species diversity causes the accuracy of QoE assessment models lower.
The existing video content recognition technology based on pattern recognition can be analyzed video image information and obtain content information.But the method exists the problems such as the training that recognition speed is slow, resource overhead large, need mass data in early stage, and its information identified is far more than the needs of QoE assessment models, there is resource redundancy and waste.Therefore, be difficult to be introduced in the Real-Time Monitoring of QoE.In addition, also have both at home and abroad correlative study by analyze often open the pixel of image in video information or analysis of encoding after the information of DCT coefficient in predictive frame motion vector, estimate the content information of video.
Summary of the invention
The shortcoming of prior art in view of the above, the object of the present invention is to provide a kind of method of high speed identification change degree of video content, the training that recognition speed is slow, resource overhead large, need mass data in early stage is there is for solving in prior art, and far more than the needs of QoE assessment models, there is the problem of resource redundancy and waste in the information identified.
For achieving the above object and other relevant objects, the invention provides a kind of method of high speed identification change degree of video content.Described method comprises:
S1, is set to 0 by the key frame byte number in frame of video and total bytes, and be that video to be evaluated sets up buffering area according to application scenarios, described application scenarios comprises off-line scene and online scene, initialization local variable; When application scenarios is Online Judge, for video to be evaluated sets up meshwork buffering district, in network-caching district, element is the data packet queue that service end sends to client order, and the meshwork buffering district set up for video to be evaluated is pointed to the network packet queue of media stream server end; When application scenarios is off-line test and appraisal, for video to be evaluated sets up filebuf, the element in described filebuf is the successive frame of video to be measured;
S2, reads next frame from setting up buffering area stem for video to be evaluated, when application scenarios is off-line evaluation and test, element in file cache district is frame, directly from buffer area, read first frame, by first frame data stored in interim frame data buffer memory, and perform next step, when application scenarios is Online Judge, for the element in the network-caching district that video to be evaluated is set up is packet, need first to read all packets depositing first frame, more described data packet group is dressed up a complete frame, continue to perform next step, for the Media Stream of Real-time Transport Protocol, in order to ensure the number needing the packet read, employing empties interim frame data buffered data, head of the queue packet is read from the buffering area set up for video to be evaluated, check in packet, whether Real-time Transport Protocol territory has flag bit, and the data of the RTP data field in described packet are taken out stored in interim frame data buffered data, if view Real-time Transport Protocol territory in packet to there is flag bit, so illustrate that described packet is last packet of institute's load carrying frame, and illustrate assembled what a frame, next step can be performed, if view Real-time Transport Protocol territory in packet to there is not flag bit, so illustrate that described packet is one, the centre packet of institute's load carrying frame,
S3, judges, from setting up as video to be evaluated whether the frame that buffering area stem reads is key frame, if so, then to perform next step; If not, then return step S2, re-execute step S2;
S4, calculates the shared byte number of described interim frame data buffering, and is added to total bytes;
S5, read next frame stored in described interim frame data buffering from setting up buffering area stem for video to be evaluated, this step is consistent with step S2;
S6, judges, from setting up as video to be evaluated whether the frame that buffering area stem reads is predictive frame, if so, then to return step S4; If not, then next step is performed;
S7, calculates change degree of video content metric.
Preferably, when application scenarios is Online Judge, represent that video to be evaluated exists; When application scenarios is off-line evaluation and test, represent that video to be evaluated is real-time generation; Under off-line application scenarios, for video to be evaluated set up frame in filebuf deposit order must with video storage sequence consensus to be evaluated; Under application on site scene, for frame in the network-caching district that video to be evaluated is set up deposit order must with Video coding to be evaluated after sequence consensus.
Preferably, described step S2 also comprises: read next frame under different application scene from setting up buffering area stem for video to be evaluated, executive mode is different; When off-line application scenarios, setting up for video to be evaluated the element deposited in filebuf is frame of video, therefore directly from filebuf, reads frame and return; When application on site scene, be network packet for what deposit in the network-caching district that video to be evaluated is set up, need the packet deposited all to read, be assembled into a complete frame of video and return again.
Preferably, in described step S4, if described interim frame data buffering is key frame, so key frame byte number is the shared byte number of described interim frame data buffering.
Preferably, to be an interval be described change degree of video content metric MDVC [0,1) decimal, MDVC represents the severe degree that video content changes.
As mentioned above, the method for high speed identification change degree of video content of the present invention, has following beneficial effect:
1, computation complexity of the present invention is low, and space expense is little, the feature of fast convergence rate, can solve video content classification problem;
2, the present invention can the content character of rapid analysis video;
3, the present invention can be used for the video (but being not limited only to these two kinds codings) identifying MPEG4, the coding such as H.264, and has higher accuracy.
Accompanying drawing explanation
Fig. 1 is shown as the method flow diagram of the method for high speed identification change degree of video content of the present invention.
Fig. 2 (a) is shown as the schematic diagram of the difference of football match video QoE model.
Fig. 2 (b) is shown as the schematic diagram of the difference of news report video QoE model.
Fig. 3 is shown as the relation schematic diagram of video content and MDVC under different coding parameter in the method for high speed identification change degree of video content of the present invention.
Different MOS curve synoptic diagrams after the video that Fig. 4 is shown as different content in the method for high speed identification change degree of video content of the present invention affects by packet loss.
Embodiment
Below by way of specific instantiation, embodiments of the present invention are described, those skilled in the art the content disclosed by this specification can understand other advantages of the present invention and effect easily.The present invention can also be implemented or be applied by embodiments different in addition, and the every details in this specification also can based on different viewpoints and application, carries out various modification or change not deviating under spirit of the present invention.
Refer to accompanying drawing.It should be noted that, the diagram provided in the present embodiment only illustrates basic conception of the present invention in a schematic way, then only the assembly relevant with the present invention is shown in graphic but not component count, shape and size when implementing according to reality is drawn, it is actual when implementing, and the kenel of each assembly, quantity and ratio can be a kind of change arbitrarily, and its assembly layout kenel also may be more complicated.
Below in conjunction with embodiment and accompanying drawing, the present invention is described in detail.
Current main flow coding, such as, H.264, MPEG4 etc., is divided into key frame (I frame) by frame of video, and predictive frame (P frame, B frame) two classes.Wherein, described key frame is for depositing complete image information, and described predictive frame is used for depositing a large amount of motion vector and a small amount of image information.Under same-code condition, described encoding condition comprises the coding parameters such as resolution, code check, GOP (GROUPOF PICTURE is called for short picture group) pattern, and the information that motion vector comprises is larger, so before and after video, frame change is faster, and therefore video motion degree Shaoxing opera is strong.By the statistics to predictive frame byte number, can estimate the movement degree of video, and the method recognition speed of high speed identification change degree of video content of the present invention is fast, ephemeral data amount is little, can be applied in Real-Time Monitoring.
The present embodiment provides a kind of method of high speed identification change degree of video content, and described method as shown in Figure 1, specifically comprises:
S1, initialization step, key frame byte number (KeySize) in frame of video and total bytes (TotalSize) are set to 0, according to application scenarios Task (off-line or online) for video to be evaluated sets up buffering area (pFrameBuffer), described application scenarios comprises off-line scene and online scene, initialization local variable; When application scenarios Task is Online Judge, for video to be evaluated sets up meshwork buffering district, in network-caching district, element is the data packet queue that service end sends to client order, and the meshwork buffering district (pFrameBuffer) set up for video to be evaluated is pointed to the network packet queue of media stream server end; When application scenarios (Task) is tested and assessed for off-line, for video to be evaluated sets up filebuf, the element in described filebuf is the successive frame of video to be measured; Wherein, when application scenarios Task is Online Judge, namely represent that video to be evaluated exists, such as, the video-on-demand service such as VoD; When application scenarios Task is off-line evaluation and test, represent that video to be evaluated generates in real time, such as, video conference, live service.Setting up buffering area (pFrameBuffer) for video to be evaluated can be partial frame in one section of video flowing, also can be all frames of whole video.Under off-line application scenarios, for video to be evaluated set up frame in filebuf deposit order must with video storage sequence consensus to be evaluated; Under application on site scene, for frame in the network-caching district that video to be evaluated is set up deposit order must with Video coding to be evaluated after sequence consensus.
S2, next frame is read from setting up buffering area (pFrameBuffer) stem for video to be evaluated, when application scenarios Task is off-line evaluation and test, element in file cache district (pFrameBuffer) is frame, directly from buffering area, read first frame, by first frame data stored in interim frame data buffer memory, and perform next step, when application scenarios Task is Online Judge, for the element in the network-caching district (pFrameBuffer) that video to be evaluated is set up is packet, need first to read all packets depositing first frame, more described data packet group is dressed up a complete frame, continue to perform next step, for Real-time Transport Protocol (Real-timeTransport Protocol, be called for short real time transport protocol) Media Stream, in order to ensure the number needing the packet read, employing empties interim frame data buffered data, head of the queue packet is read from the buffering area (pFrameBuffer) set up for video to be evaluated, check in packet, whether Real-time Transport Protocol territory has Mark flag bit, and the data of the RTP data field in described packet are taken out stored in interim frame data buffered data, if view Real-time Transport Protocol territory in packet to there is flag bit, so illustrate that described packet is last packet of institute's load carrying frame, and illustrate assembled what a frame, next step can be performed, if view Real-time Transport Protocol territory in packet to there is not flag bit, so illustrate that described packet is one, the centre packet of institute's load carrying frame, it is noted that read next frame under different application scene from setting up buffering area (pFrameBuffer) stem for video to be evaluated, executive mode is different, when off-line application scenarios, setting up for video to be evaluated the element deposited in filebuf is frame of video, therefore directly from filebuf, reads frame and return, when application on site scene, be network packet for what deposit in the network-caching district that video to be evaluated is set up, need the packet deposited all to read, be assembled into a complete frame of video and return again.
S3, judge from set up as video to be evaluated buffering area (pFrameBuffer) stem read frame whether be key frame, if so, then perform next step; If not, then return step S2, re-execute step S2;
S4, calculates the shared byte number (Size) of described interim frame data buffering, and is added to total bytes (TotalSize).If described interim frame data buffering is key frame, so key frame byte number (KeySize) is the shared byte number (Size) of described interim frame data buffering;
S5, read next frame stored in described interim frame data buffering from setting up buffering area (pFrameBuffer) stem for video to be evaluated, this step is consistent with step S2, when application scenarios Task is off-line evaluation and test, the element in file cache district (pFrameBuffer) is frame, directly from buffering area, reads first frame, by first frame data stored in interim frame data buffer memory, and performs next step, when application scenarios Task is Online Judge, for the element in the network-caching district (pFrameBuffer) that video to be evaluated is set up is packet, need first to read all packets depositing first frame, more described data packet group is dressed up a complete frame, continue to perform next step, for Real-time Transport Protocol (Real-time Transport Protocol, be called for short real time transport protocol) Media Stream, in order to ensure the number needing the packet read, employing empties interim frame data buffered data, head of the queue packet is read from the buffering area (pFrameBuffer) set up for video to be evaluated, check in packet, whether Real-time Transport Protocol territory has Mark flag bit, and the data of the RTP data field in described packet are taken out stored in interim frame data buffered data, if view Real-time Transport Protocol territory in packet to there is flag bit, so illustrate that described packet is last packet of institute's load carrying frame, and illustrate assembled what a frame, next step can be performed, if view Real-time Transport Protocol territory in packet to there is not flag bit, so illustrate that described packet is one, the centre packet of institute's load carrying frame.It is noted that read next frame under different application scene from setting up buffering area (pFrameBuffer) stem for video to be evaluated, executive mode is different; When off-line application scenarios, setting up for video to be evaluated the element deposited in filebuf is frame of video, therefore directly from filebuf, reads frame and return; When application on site scene, be network packet for what deposit in the network-caching district that video to be evaluated is set up, need the packet deposited all to read, be assembled into a complete frame of video and return again.
S6, judge from set up as video to be evaluated buffering area (pFrameBuffer) stem read frame whether be predictive frame, if so, then return step S4; If not, then next step is performed;
S7, calculates change degree of video content metric MDVC, namely
to be an interval be described change degree of video content metric MDVC [0,1) decimal, MDVC represents the severe degree that video content changes.Qualitatively, MDVC is larger, illustrates that video content features is more active.
In actual applications, the method of the high speed identification change degree of video content described in the present embodiment can solve the problem of video content estimation with comparatively fast calibrating, for video QoE assessment models provides quantitative data, make model realization content-adaptive, the difference of QoE model is held as shown in Figure 2 in different video, Fig. 2 (a) is football match video QoE model, and Fig. 2 (b) is news report video QoE model.The present invention can test with following the feasibility proving it.In experiment, the video segment of 12 different contents is divided into two groups, one group is high-speed mobile (Fast-Moving Video) video, and one group for move at a slow speed (Slow-MovingVideo) video.By all videos according to different coding parameters, as shown in table 1, carry out encoding and calculate respective MDVC value.
Table 1: test parameter value
| Parameter | Value |
| Frame per second fps_v | 24,25,30,48,60 |
| Code check bitrate_v | 386k,512k,1024k,2400k,5000k |
| Resolution res_v | 320x240,352x288,640x480,960x720 |
| GOP size λ | 12,30,60,120 |
| The B frame frequency of occurrences β of P interframe | 0,1,2,3,4 |
| Type of coding | H.264,MPEG4 |
Fig. 3 shows the relation of video content and MDVC under different coding parameter, in figure ' zero ' and ' ◇ ' represent H.264 with the MDVC value of mobile video at a slow speed of MPEG4 coding, '+' and ' * ' the expression MDVC value of high-speed mobile video of H.264 encoding with MPEG4.From figure, result can be seen, the MDVC value of high-speed mobile video all higher than mobile video at a slow speed, demonstrates the correctness of the method under all encoding conditions.
Utilize the calculating of MDVC, content relevant parameter can be provided for video QoE assessment models.Different MOS curves after the video that Fig. 4 shows different content affects by packet loss.Can see, MDVC larger (high-motion video), MOS value declines faster, illustrates that video QoE damages Shaoxing opera strong.In QoE assessment models, introduce this video content measure, can be that QoE assessment realizes content-adaptive, thus improve accuracy of measurement.
The method of high speed identification change degree of video content of the present invention can with lower computation complexity and space expense, and the content character of assessment video at a high speed, can meet and carry out the simply needs of Fast Classification to video content.Namely the present invention can be used for the video-on-demand service such as VoD, can be used for the real-time streaming service such as video conference again.
Feature of the present invention uses less room and time expense, the content character of rapid analysis video, relative to the video content analysis method based on pattern recognition, it is low that this algorithm possesses computation complexity, space expense is little, the feature of fast convergence rate, can solve video content classification problem.Practice shows, this algorithm can be used for the video (but being not limited only to these two kinds codings) identifying MPEG4, the coding such as H.264, and has higher accuracy.
The present invention can under O (1) computation complexity rapid evaluation change degree of video content, and be applicable to online and that off-line two kinds is common video playback scene, for user experience quality (QoE) assessment models of video and video and audio mixing provides content metric parameter, improve the assessment accuracy of model.
In sum, the present invention effectively overcomes various shortcoming of the prior art and tool high industrial utilization.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not for limiting the present invention.Any person skilled in the art scholar all without prejudice under spirit of the present invention and category, can modify above-described embodiment or changes.Therefore, such as have in art usually know the knowledgeable do not depart from complete under disclosed spirit and technological thought all equivalence modify or change, must be contained by claim of the present invention.
Claims (4)
1. identify at a high speed a method for change degree of video content, it is characterized in that, described method comprises:
S1, is set to 0 by the key frame byte number in frame of video and total bytes, and be that video to be evaluated sets up buffering area according to application scenarios, described application scenarios comprises off-line scene and online scene, initialization local variable; When application scenarios is Online Judge, for video to be evaluated sets up meshwork buffering district, in network-caching district, element is the data packet queue that service end sends to client order, and the meshwork buffering district set up for video to be evaluated is pointed to the network packet queue of media stream server end; When application scenarios is off-line test and appraisal, for video to be evaluated sets up filebuf, the element in described filebuf is the successive frame of video to be measured;
S2, reads next frame from setting up buffering area stem for video to be evaluated, when application scenarios is off-line evaluation and test, element in file cache district is frame, directly from buffer area, read first frame, by first frame data stored in interim frame data buffer memory, and perform next step, when application scenarios is Online Judge, for the element in the network-caching district that video to be evaluated is set up is packet, need first to read all packets depositing first frame, more described data packet group is dressed up a complete frame, continue to perform next step, for the Media Stream of Real-time Transport Protocol, in order to ensure the number needing the packet read, employing empties interim frame data buffered data, head of the queue packet is read from the buffering area set up for video to be evaluated, check in packet, whether Real-time Transport Protocol territory has flag bit, and the data of the RTP data field in described packet are taken out stored in interim frame data buffered data, if view Real-time Transport Protocol territory in packet to there is flag bit, so illustrate that described packet is last packet of institute's load carrying frame, and illustrate assembled what a frame, next step can be performed, if view Real-time Transport Protocol territory in packet to there is not flag bit, so illustrate that described packet is one, the centre packet of institute's load carrying frame,
S3, judges, from setting up as video to be evaluated whether the frame that buffering area stem reads is key frame, if so, then to perform next step; If not, then return step S2, re-execute step S2;
S4, calculates the shared byte number of described interim frame data buffering, and is added to total bytes;
S5, read next frame stored in described interim frame data buffering from setting up buffering area stem for video to be evaluated, this step is consistent with step S2;
S6, judges, from setting up as video to be evaluated whether the frame that buffering area stem reads is predictive frame, if so, then to return step S4; If not, then next step is performed;
S7, calculates change degree of video content metric.
2. the method for high speed identification change degree of video content according to claim 1, is characterized in that: when application scenarios is Online Judge, represents that video to be evaluated exists; When application scenarios is off-line evaluation and test, represent that video to be evaluated is real-time generation; Under off-line application scenarios, for video to be evaluated set up frame in filebuf deposit order must with video storage sequence consensus to be evaluated; Under application on site scene, for frame in the network-caching district that video to be evaluated is set up deposit order must with Video coding to be evaluated after sequence consensus.
3. the method for high speed identification change degree of video content according to claim 1, is characterized in that: in described step S4, if described interim frame data buffering is key frame, so key frame byte number is the shared byte number of described interim frame data buffering.
4. the method for high speed identification change degree of video content according to claim 1, is characterized in that: to be an interval be described change degree of video content metric MDVC [0,1) decimal, MDVC represents the severe degree that video content changes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310068909.6A CN103200419B (en) | 2013-03-05 | 2013-03-05 | High-speed recognizing method of change degree of video content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310068909.6A CN103200419B (en) | 2013-03-05 | 2013-03-05 | High-speed recognizing method of change degree of video content |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103200419A CN103200419A (en) | 2013-07-10 |
| CN103200419B true CN103200419B (en) | 2015-04-08 |
Family
ID=48722759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310068909.6A Expired - Fee Related CN103200419B (en) | 2013-03-05 | 2013-03-05 | High-speed recognizing method of change degree of video content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103200419B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104410860B (en) * | 2014-11-28 | 2017-08-15 | 北京航空航天大学 | A kind of method of high definition ROI videos real-time quality regulation |
| CN108900804B (en) * | 2018-07-09 | 2020-11-03 | 南通世盾信息技术有限公司 | Self-adaptive video stream processing method based on video entropy |
| CN111783226B (en) * | 2020-06-29 | 2024-03-19 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and storage medium for generating automatic driving scene measurement parameters |
| CN115243101B (en) * | 2022-06-20 | 2024-04-12 | 上海众源网络有限公司 | Video dynamic and static ratio identification method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101835058A (en) * | 2009-03-11 | 2010-09-15 | 华为技术有限公司 | Method, system and equipment for detecting quality of experience of video |
| CN102223262A (en) * | 2011-05-20 | 2011-10-19 | 同济大学 | Evaluation platform and method of quality of experience of video based on QoS |
| CN102223565A (en) * | 2010-04-15 | 2011-10-19 | 上海未来宽带技术及应用工程研究中心有限公司 | Streaming media video quality estimation method based on video content features |
-
2013
- 2013-03-05 CN CN201310068909.6A patent/CN103200419B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101835058A (en) * | 2009-03-11 | 2010-09-15 | 华为技术有限公司 | Method, system and equipment for detecting quality of experience of video |
| CN102223565A (en) * | 2010-04-15 | 2011-10-19 | 上海未来宽带技术及应用工程研究中心有限公司 | Streaming media video quality estimation method based on video content features |
| CN102223262A (en) * | 2011-05-20 | 2011-10-19 | 同济大学 | Evaluation platform and method of quality of experience of video based on QoS |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103200419A (en) | 2013-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | QARC: Video quality aware rate control for real-time video streaming based on deep reinforcement learning | |
| US10841358B2 (en) | System and method for determining quality of a media stream | |
| Wamser et al. | Modeling the YouTube stack: From packets to quality of experience | |
| Kim et al. | A study on a QoS/QoE correlation model for QoE evaluation on IPTV service | |
| US8798150B2 (en) | Bi-directional video compression for real-time video streams during transport in a packet switched network | |
| US20170347159A1 (en) | Qoe analysis-based video frame management method and apparatus | |
| Gómez et al. | YouTube QoE evaluation tool for Android wireless terminals | |
| CN103200419B (en) | High-speed recognizing method of change degree of video content | |
| Kim et al. | QoE assessment model for multimedia streaming services using QoS parameters | |
| Hoßfeld et al. | QoE of YouTube video streaming for current Internet transport protocols | |
| Xu et al. | Modeling buffer starvations of video streaming in cellular networks with large-scale measurement of user behavior | |
| Botia Valderrama et al. | Nonintrusive method based on neural networks for video quality of experience assessment | |
| Zhang et al. | A content-adaptive video quality assessment method for online media service | |
| KR102084469B1 (en) | Method and system for real time measuring quality of video call service | |
| Vogt et al. | Demo of QoEyes: Towards Virtual Reality Streaming QoE Estimation Entirely in the Data Plane | |
| Schulz et al. | Analysis and Modeling of Downlink Traffic in Cloud-Rendering Architectures for Augmented Reality | |
| Pham-Thi et al. | Correlating objective factors with video quality experienced by end users on P2PTV | |
| Riker et al. | A hybrid prediction and assessment quality of experience approach for videostreaming applications over wireless mesh networks | |
| Valderrama et al. | Research Article Nonintrusive Method Based on Neural Networks for Video Quality of Experience Assessment | |
| Ghani et al. | Objective video streaming qoe measurement based on prediction model | |
| Gaviria Gómez | Nonintrusive method based on neural networks for video quality of experience assessment | |
| Cerqueira et al. | A parametric QoE video quality estimator for Wireless Networks | |
| JP2011004354A (en) | Video quality estimating device, video quality estimation method, and control program for the video quality estimating device | |
| Hosek et al. | On predicting video quality expectations of mobile users | |
| Zhang et al. | Optimal QoS mapping for streaming video over differentiated services networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150408 Termination date: 20180305 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |