CN103888846A - Wireless video streaming service self-adaption rate control method based on QoE - Google Patents
Wireless video streaming service self-adaption rate control method based on QoE Download PDFInfo
- Publication number
- CN103888846A CN103888846A CN201410076993.0A CN201410076993A CN103888846A CN 103888846 A CN103888846 A CN 103888846A CN 201410076993 A CN201410076993 A CN 201410076993A CN 103888846 A CN103888846 A CN 103888846A
- Authority
- CN
- China
- Prior art keywords
- bit rate
- coding bit
- packet loss
- trend
- qoe
- 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.)
- Granted
Links
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a wireless video streaming service self-adaption rate control method based on the QoE. The method includes the steps of setting up a QoE evaluation model at a receiving end to be used for calculating the quality of user experience, periodically feeding the packet loss rate, the end-to-end one-way time delay and user experience quality information which are obtained at the receiving end back to a sending end through a real-time transmission control protocol, conducting subdivision on network states through the sending end according to the user experience quality and by combining the packet loss rate with the increase or decrease trend of the end-to-end one-way time delay, and judging the network congestion degree. When the user experience quality decreases to a threshold value, the sending end of the wireless video streaming service starts a coding bit rate adjustment unit and adjusts the coding bit rate in a self-adaption mode by taking corresponding strategies according to the monitored network congestion degree, and therefore the user experience quality is improved. According to the method, the user experience quality of the video steaming service can be accurately evaluated in real time, network congestion is reduced through the self-adaption rate control method, and the user experience quality is effectively improved.
Description
Technical field
The present invention relates to mobile communication technology field, relate in particular to a kind of wireless video streaming service adaptation method of rate control based on QoE.
Background technology
Along with the develop rapidly of wireless video streaming business, people's life is risen and is incorporated gradually in the application such as wireless video conference, video monitoring in the world.But, due to wireless network bandwidth resource-constrained and unsteadiness thereof, video stream traffic can be subject to the impact of network fluctuation in the process of transmission big data quantity, even can cause the loss of packet when serious, causes the video flow quality that user watches well not guaranteed.Therefore the video flowing Quality of experience that, research valid wireless video stream traffic transfer control method is watched lifting user is most important.
In order to realize the lifting to wireless video streaming quality of service, existing control technology is the transmission rate to video flowing at transmitting terminal conventionally, it is coding bit rate, carry out self adaptation adjustment, when the sufficient network of bandwidth throughput is during in idle condition, video streaming services device improves coding bit rate to promote the definition of video playback; When the not enough network of bandwidth throughput is during in congestion state, video streaming services device reduces the packet loss of coding bit rate to reduce to cause because of congested.
What current method of rate control was paid close attention to mostly is how to promote service quality (Quality of Service, QoS), as minimizes packet loss, maximize throughput etc.But because QoS is a technical indicator, what it was described is the ability that network provides service on the basis that guarantees professional skill, and it can not directly reflect the satisfaction of user to business.But, the final purpose of wireless video streaming business service is available to the customer satisfaction system quality of experiencing, standardization body of International Telecommunications Union is by user experience quality (Quality of Experience, QoE) be defined as the index of weighing user's subjective feeling, it refers to that, by a kind of application of terminal use institute perception or the overall acceptable degree of business, it can intuitively reflect that user is to using the subjective sensation of business.QoE contributes to Virtual network operator to understand and the closely-related parameter that affects of user satisfaction, finally improves user's loyalty to keep on top in fierce market competition.Therefore, based on QoE, wireless video streaming business being carried out speed control and is not only the emphasis of academia research, is also that Virtual network operator guarantees that good Quality of experience is to keep here and the key of the scale that extends one's service.
Due to wireless video streaming business transmission mechanism complexity, its QoE is subject to the impact of numerous influencing factors such as code encoding/decoding mode, network condition, terminal parameter.What QoE assessment technology was studied is the relation between QoE and its influencing factor.Current QoE assessment technology majority carries out in video streaming services device side, but video server can not directly obtain the Video stream information that user terminal is watched, and the QoE influencing factor that existing QoE assessment technology is considered is not comprehensive, and this causes the assessment accuracy of QoE not high.In addition, it is not careful that existing adaptation rate control method is divided network state, causes its method of rate control easily in the time of network state generation acute variation, to cause the concussion adjustment to coding bit rate, thereby affect the user experience quality of wireless video streaming.Therefore, to promote the subjective feeling of user to business, not yet there is good solution in the how QoE of accurate evaluation wireless video streaming business carry out the control of efficient adaptive speed, at present.
Summary of the invention
The object of the invention is the deficiency in order to overcome existing solution, a kind of wireless video streaming service adaptation method of rate control based on QoE is provided.Method of the present invention is set up QoE assessment models for calculating user experience quality at receiving terminal, by RTCP Real-time Transport Control Protocol (Real-time Transport Control Protocol, RTCP) packet loss periodically receiving terminal being obtained, end-to-end One Way Delay and user experience quality information feed back to transmitting terminal, the user experience quality that transmitting terminal calculates according to QoE assessment models, associating packet loss and end-to-end One Way Delay growth trend segment network state and judge network congestion degree.In the time that the user experience quality being calculated by QoE assessment models drops to certain threshold value, the transmitting terminal of wireless video streaming business starts coding bit rate adjustment unit and according to the network congestion degree of monitoring, take corresponding strategy to adjust adaptively coding bit rate, to realize the lifting of user experience quality.
For achieving the above object, adaptation rate control method of the present invention comprises time delay trend analysis unit, packet loss statistic unit, QoE assessment unit, coding bit rate adjustment unit;
Described time delay trend analysis unit is for judging that wireless video streaming business data packet is transferred to the One Way Delay growth trend of receiving terminal from transmitting terminal, specifically: by RTP (Real-time Transport Protocol, RTP) timestamp information of header obtains the One Way Delay of packet, judge that by comparision testing One Way Delay is the trend that increases or reduce again, finally a kind of indication information using One Way Delay growth trend as network congestion degree is input to coding bit rate adjustment unit;
Described packet loss statistic unit is for calculating the end-to-end packet loss of wireless video streaming business in each coding bit rate adjustment cycle, specifically: the sequence number information statistics by RTP header obtains packet loss, affect parameter as network layer and be input to QoE assessment unit, and by weighted mean method, packet loss is carried out to smoothing processing and reduce because of the packet loss concussion causing that suddenlys change of offered load situation, packet loss after smoothing processing is as a kind of indication information of network congestion degree, by RTCP Real-time Transport Control Protocol (Real-time Transport Control Protocol, RTCP) feed back to the coding bit rate adjustment unit of transmitting terminal from receiving terminal,
Described QoE assessment unit is mapped as user experience quality score for the cross-layer of input is affected to parameter by calculating, i.e. Mean Opinion Score value (Mean Opinion Score, MOS), and Mean Opinion Score value is input to coding bit rate adjustment unit;
Described coding bit rate adjustment unit is used for associating packet loss and One Way Delay growth trend and network state is segmented and judged network congestion degree, in conjunction with the Mean Opinion Score value of QoE assessment unit output, take corresponding strategy to adjust adaptively coding bit rate again.
The concrete steps of the inventive method are:
Step 1: adopt H.264 mode to encode wireless video streaming at transmitting terminal, become the video flowing sequence with Z kind different coding bit rate, with set L '={ l
1, l
2..., l
z, (l
1< l
2< ... < l
z) represent, L ' is coding bit rate set, and { l is set
1, l
2..., l
zvalue contain video flow quality and become best experienced coding bit rate value from the poorest, the coding bit rate of choosing at random user's initial request wireless video streaming business is l
k(k=1,2 ..., Z); Wherein, k is coding bit rate grade;
Step 2: at each coding bit rate adjustment cycle, calculate user experience quality by QoE assessment unit;
The QoE influencing factor of wireless video streaming business is numerous, the present invention has considered that the end-to-end cross-layer that affects QoE affects parameter, comprises application layer parameter (coding bit rate, frame per second, resolution), network layer parameter (packet loss), video content features parameter (temporal information, spatial information, monochrome information, colouring information) and terminal equipment parameter (screen size).Wherein, coding bit rate refers to the bit number of transmission of video in the unit interval, frame per second refers to the frame number of video demonstration per second, resolution refers to the pixel quantity that terminal is shown, packet loss refers to that institute's lost data packets quantity accounts for the ratio of sent packet, video content features refers to space, time, brightness, the colouring information of video, and terminal size refers to the actual size of terminal screen.Above-mentioned application layer parameter and network layer parameter can obtain by analyzing decoder end bit stream information (RTP bag bit number, sampling time, RTP packet number etc.); Video content features is by calculating frame pixel difference, edge block information, monochrome information, colouring information extraction at Video Decoder end; The international mobile equipment identification number (International Mobile Equipment Identity, IMEI) that terminal size information exchange is crossed inquiring user terminal equipment obtains.QoE assessment models is arranged on receiving terminal by the present invention, therefore more presses close to subjective user's actual impression, can reflect more exactly the Quality of experience of user to video stream traffic.
In step 2, pass through radial basis function neural network (Radial Basis Function Neural Networks, RBFN) algorithm is set up QoE assessment models, radial basis function neural network algorithm comprises input layer, hidden layer, output layer, set input layer and there is N input, hidden layer has L hidden unit, output layer has output, i.e. a user experience quality.Set up QoE assessment models by radial basis function neural network algorithm and comprise two steps: training process and test process, idiographic flow is as follows:
Step (2-1) training process uses the cross-layer of training set to affect parameter and subjective user experience quality value to the training of QoE model, and training set is expressed as
wherein vector x
srepresent s input of radial basis function neural network algorithm, s=1,2 ..., S, S represents to input the number of sample, x
scomprise N cross-layer parameter, expression formula is x
s=[x
1, x
2..., x
n]
t, y
srepresent that input sample is x
sdraw corresponding Quality of experience score value, the span 1≤y of using by method of subjective appraisal
s≤ 5, the concrete steps of training process are as follows:
(2-1-1) choose at random L initial cluster center, make iterations t=1;
(2-1-2) calculate input sample x
swith cluster centre c
m(t) distance between, expression formula is || x
s-c
m(t) ||, m=1,2 ..., L,, wherein c
m(t) cluster centre of m hidden unit of the t time iteration of expression;
(2-1-3) according to minimal distance principle to input sample x
sclassify, as m (x
s)=min||x
s-c
m(t) || time, x
sbe classified as m class, be expressed as x
s∈ R
m(t), R wherein
m(t) represent m Clustering Domain, || || represent Euclidean distance;
(2-1-4) recalculate the cluster centre of each hidden unit
wherein N
mbe m Clustering Domain R
m(t) the input number of samples comprising in;
If (2-1-5)
proceed to step (2-1-2); Otherwise m hidden unit cluster centre of finishing iteration and definite radial basis function neural network algorithm is c
m, and proceed to step (2-1-6);
(2-1-6) definition P is overlap coefficient, calculates expansion constant by adjacency method
representative and c
ma most contiguous P cluster centre, σ
mrepresent the expansion constant of m hidden unit;
(2-1-7) determine the output weight w=H of radial basis function neural network algorithm by least square method
+y, wherein w represents the output weight w by m hidden unit
mthe weight vector forming, expression formula is w=[w
1, w
2..., w
l]
t, m=1,2 ..., L, y=[y
1, y
2..., y
s]
t, H=[h
sm]
s × Lrepresent input sample x
sat the output h of m hidden unit
smthe hidden unit matrix forming, h
smexpression formula is
h
tthe transposition of representing matrix H, H
+the pseudoinverse of representing matrix H, expression formula is H
+=(H
th)
-1h
t.
Step (2-2) test process is to complete after the training process of radial basis function neural network algorithm in step (2-1), by test set sample input QoE assessment unit, if the error between the QoE assessed value of being calculated by radial basis function neural network algorithm and QoE actual value is lower than default error convergence threshold value, QoE assessment models is set up complete.
Step 3: in each coding bit rate adjustment cycle, by the user experience quality MOS being calculated by QoE assessment unit and QoE threshold mos
thcompare, if MOS>=MOS
th, keep the coding bit rate of transmitting terminal constant, if MOS < is MOS
th, transmitting terminal starts coding bit rate adjustment unit, network state is segmented and judged network congestion degree in conjunction with packet loss and One Way Delay growth trend, takes corresponding strategy to adjust adaptively coding bit rate.
Described in step 3, work as MOS < MOS
thtime, the step of adaptation rate control method is:
(3-1) by paired compare test (Paired Comparison Test, PCT) numerical value S
pCTwith difference compare test (Paired Difference Test, PDT) numerical value S
pDTthe One Way Delay growth trend DT of specified data bag from transmitting terminal to receiving terminal, if S
pCT> 0.55 or S
pDT> 0.44, One Way Delay shows a rising trend, and is designated as DT=1, otherwise One Way Delay is and reduces trend, is designated as DT=0, wherein S
pCTwith S
pDTexpression formula be respectively
Receiving terminal records the One Way Delay { D of K the packet of receiving by the timestamp information of RTP header
1, D
2..., D
k, and be divided into according to the priority arrival order of K packet
group, the mediant of every group of packet One Way Delay is
the value rule of I (X) is
(3-2) the level and smooth packet loss of t coding bit rate adjustment cycle of calculating is
wherein p
1, p
2..., p
qrepresent front q the most contiguous coding bit rate adjustment cycle, i.e. t, t-1, t-2 ..., t-q+1 the historical packet loss that coding bit rate adjustment cycle is corresponding, λ
irepresent the weight coefficient of historical packet loss, span 0 < λ
i< 1.
(3-3) by RTCP Real-time Transport Control Protocol by packet loss, end-to-end One Way Delay and user experience quality property information cycle feed back to transmitting terminal from receiving terminal, at the initial time of t+1 coding bit rate adjustment cycle, the coding bit rate adjustment unit of transmitting terminal, according to the One Way Delay growth trend DT (t) and packet loss p (t) with t the coding bit rate adjustment cycle (3-2) calculating by step (3-1), takes corresponding strategy to adjust adaptively coding bit rate.Two packet loss threshold value p are set
land p
h, wherein p
lexpression user experience quality reaches and is satisfied with MOS
htime corresponding packet loss, p
hrepresent that user experience quality reaches acceptable degree MOS
thtime corresponding packet loss, and have 0 < p
l< p
h< 1,1 < MOS
th< MOS
h< 5, the concrete adjustment strategy of coding bit rate adjustment unit is:
If (3-3-1). p (t) < p
l, illustrate that network condition is good and packet loss is minimum, therefore can promote QoE by increasing coding bit rate, the amplitude of increase is determined by One Way Delay growth trend:
If (3-3-1-1) DT (t)=0, illustrates that One Way Delay is for reducing trend, network condition is the trend that improves, and increases significantly coding bit rate, and expression formula is BR (t+1)=min{BR (t)+Δ
1, R
max, wherein BR (t) represents t the coding bit rate in coding bit rate adjustment cycle,
Δ
1the growth factor being inversely proportional to packet loss p (t), to guarantee the p at p < that increases of coding bit rate
lin scope, dynamically adjust, realize and in the situation that network state is good, significantly raise coding bit rate, avoided causing poor user experience quality, R because continuing long low coding bit rate
maxeffect be constraint coding bit rate adjustment, to prevent that coding bit rate from infinitely increasing;
If (3-3-1-2) DT (t)=1, illustrates that One Way Delay is increase trend, network condition is variation trend, increases by a small margin coding bit rate, and expression formula is BR (t+1)=min{BR (t)+Δ
2, R
max, wherein
Δ
2the growth factor being inversely proportional to packet loss p (t), Δ
2can guarantee that the coding bit rate BR (t+1) after adjusting is no more than the twice of initial value BR (t), this adjustment mode has been avoided causing network congestion by excessively increasing coding bit rate in the time of network condition variation;
If (3-3-2). p
l< p (t) < p
h, illustrate that network has occurred slight congested, need further to take different adjustment strategies according to One Way Delay growth trend:
If (3-3-2-1) DT (t)=0, illustrate that One Way Delay is for reducing trend, be network condition be improve trend and have the ability alleviate slightly congested, for fear of being fluctuateed by the frequent video flow quality of bringing of adjusting of coding bit rate, now keep original coding bit rate constant, i.e. BR (t+1)=BR (t);
If (3-3-2-2) DT (t)=1, illustrate that One Way Delay is increase trend, be that network condition is variation trend, therefore should lower coding bit rate increases the weight of with avoid congestion, because now network is in slight congestion state, reducing coding bit rate is BR (t+1)=max{ (BR (t)-Δ
3× BR (t)), R
min, wherein Δ
3be the descending factors with exponential form, expression formula is
Δ
3not only can realize coding bit rate BR (t+1) reduces along with the increase of packet loss p (t), and can also realize the increase along with packet loss p (t), BR (t) fall increases, and can guarantee that the coding bit rate BR (t+1) after adjusting is not less than the half of initial value BR (t) simultaneously.This adjustment mode not only can reduce coding bit rate when congested network is slight, and has avoided coding bit rate to lower and too lowly video flow quality has been caused to damage, R
mineffect be constraint coding bit rate adjustment, to prevent that coding bit rate from infinitely reducing;
If (3-3-3). p > p
h, illustrate that network is because packet loss is crossed the heavy congestion that mostly occurred, need further to take different adjustment strategies according to One Way Delay growth trend:
If (3-3-3-1) DT (t)=0, illustrate that One Way Delay is for reducing trend, be that network condition is the trend that improves, but because network congestion has seriously produced too much packet loss, therefore still need to reduce coding bit rate with alleviating network congestion, expression formula is BR (t+1)=max{ Δ × BR (t), R
min, wherein Δ=max (Δ
4, Δ
5),
If (3-3-3-2) DT (t)=1, illustrate that One Way Delay is increase trend, network condition is variation trend, now should be to reduce by a larger margin coding bit rate, expression formula is BR (t+1)=max{ Δ × BR (t), R
min), Δ=min (Δ
4, Δ
5);
Above-mentioned at generation heavy congestion, i.e. p > p
htime, Δ is the descending factors with multiplier form, it can guarantee at least the declined half of initial value BR (t) of coding bit rate BR (t+1), reduces packet loss alleviating network congestion thereby realize.
Step 4: repeat above-mentioned steps 2~step 3, until wireless video streaming service request finishes.
Can be found out by above-mentioned provided technical scheme, the advantage of the wireless video streaming service adaptation method of rate control based on QoE proposed by the invention is:
First, existing conventional rate control method is to promote QoS as target, ignore this key character of user's subjective feeling, be different from the method for rate control based on QoS, method proposed by the invention has considered that user watches the subjective feeling of wireless video streaming business, take promote QoE as target design adaptive method of rate control.
Second, QoE assessment models proposed by the invention is positioned at receiving terminal, arrange like this and can directly obtain the video stream traffic parameter information that user watches, can more press close to subjective user's actual impression, therefore QoE assessment models can reflect the Quality of experience of user to video stream traffic in real time, exactly.
The 3rd, it is comprehensive that the QoE assessment models of setting up by the RBFN algorithm in machine Learning Theory considers that end-to-end cross-layer affects parameter, comprise video streaming content feature, application layer, network layer and terminal equipment parameter, above-mentioned cross-layer parameter is extracted from decoder bit stream information and mobile terminal side, and do not need source video information to make reference, therefore concrete enforcement is simple.In addition, the QoE assessment models of setting up can learn to extract and approach the relation between input and output by training process, and therefore QoE assessment accuracy is high.
The 4th, the wireless video streaming service adaptation method of rate control based on QoE proposed by the invention to be to promote QoE as target, and associating packet loss and One Way Delay growth trend segment network state and judge network congestion degree.In the time that the user experience quality being calculated by QoE assessment models drops to certain threshold value, video stream traffic transmitting terminal start adjustment unit and according to monitoring network congestion degree, take corresponding strategy to make correct response to the network state of segmentation, therefore can effectively promote the user experience quality of video stream traffic.
Of the present invention proposed method has solved in current method of rate control user experience quality has been assessed to inaccurate problem, can segment and also accurately judge network congestion degree network state, and then take corresponding strategy to adjust adaptively coding bit rate, effectively realize the lifting of user experience quality.
Accompanying drawing explanation
Fig. 1 is the wireless video streaming service adaptation speed control system block diagram based on QoE of the present invention.
Fig. 2 is that adaptive coding bit rate of the present invention is adjusted flow chart.
Fig. 3 is end-to-end wireless video streaming business transmission example block diagram of the present invention.
Fig. 4 is the system block diagram of QoE assessment models of the present invention.
Fig. 5 is QoE assessment models Establishing process figure of the present invention.
Embodiment
For making technical scheme of the present invention, object and advantage clearer, below in conjunction with accompanying drawing, the specific embodiment of the present invention is described in further detail.
The present invention is directed to the deficiency in current method of rate control, a kind of wireless video streaming service adaptation method of rate control based on QoE has been proposed on the basis of accurate evaluation user experience quality, can network state be segmented and accurately be judged the Congestion Level SPCC of network, take corresponding strategy to adjust adaptively coding bit rate, thereby realize the lifting of user's Quality of experience.The present invention is applicable to wireless network scenario, as WLAN, WCDMA, CDMA2000, TD-SCDMA, LTE network etc.The system block diagram of the described adaptation rate control method based on QoE as shown in Figure 1, comprises following functions unit:
Described time delay trend analysis unit is for judging that wireless video streaming business data packet is transferred to the One Way Delay growth trend of receiving terminal from transmitting terminal, specifically: the One Way Delay that obtains packet by the timestamp information of RTP header, judge that by comparision testing One Way Delay is the trend that increases or reduce again, finally a kind of indication information using One Way Delay growth trend as network congestion degree is input to coding bit rate adjustment unit;
Described packet loss statistic unit is for calculating the end-to-end packet loss of wireless video streaming business in each coding bit rate adjustment cycle, specifically: the sequence number information statistics by RTP header obtains packet loss, affect parameter as network layer and be input to QoE assessment unit, and by weighted mean method, packet loss is carried out to smoothing processing and reduce because of the packet loss concussion causing that suddenlys change of offered load situation, packet loss after smoothing processing, as a kind of indication information of network congestion degree, feeds back to the coding bit rate adjustment unit of transmitting terminal from receiving terminal by RTCP;
Described QoE assessment unit is mapped as user experience quality score MOS for the cross-layer of input is affected to parameter by calculating, and MOS is input to coding bit rate adjustment unit;
Described coding bit rate adjustment unit is used for associating packet loss and One Way Delay growth trend segments network state and judges network congestion degree, then the MOS exporting in conjunction with QoE assessment unit, takes corresponding strategy to adjust adaptively coding bit rate.
Adaptive coding bit rate of the present invention is adjusted flow chart as shown in Figure 2, and concrete steps are as follows:
Step 1: at transmitting terminal, wireless video streaming is encoded to the video flowing sequence with Z=6 kind coding bit rate, with coding bit rate set L '={ 85.1kbps, 129.9kbps, 256.3kbps, 392.8kbps, 510.4kbp, 1030.2kbps} represents, these six values have contained video flow quality and have become best experienced coding bit rate value from the poorest, and the coding bit rate of choosing at random user's initial request wireless video streaming business is 256.3kbps.
Step 2: coding bit rate adjustment cycle T=1s is set, periodically calculates user experience quality by QoE assessment models.
Fig. 3 is end-to-end wireless video streaming business transmission example block diagram of the present invention, QoE assessment models of the present invention is arranged on receiving terminal, end-to-end cross-layer is affected to parameter as input, comprise application layer parameter (coding bit rate, frame per second, resolution), network layer parameter (packet loss), video content features parameter (temporal information, spatial information, monochrome information, colouring information) and terminal equipment parameter (screen size).Wherein, coding bit rate refers to the bit number of transmission of video in the unit interval, frame per second refers to the frame number of video demonstration per second, resolution refers to the pixel quantity that terminal is shown, packet loss refers to that institute's lost data packets quantity accounts for the ratio of sent packet, video content features refers to space, time, brightness, the colouring information of video, and terminal size refers to the actual size of terminal screen.Above-mentioned application layer parameter and network layer parameter can obtain by analyzing decoder end bit stream information (RTP bag bit number, sampling time, RTP packet number etc.); Video content features is by calculating frame pixel difference, edge block information, monochrome information, colouring information extraction at Video Decoder end; The international mobile equipment identification number IMEI that terminal size information exchange is crossed inquiring user terminal equipment obtains.
QoE assessment models system block diagram described in step 2 as shown in Figure 4.
Set up QoE assessment models by RBFN algorithm, RBFN algorithm comprises input layer, hidden layer, output layer, sets input layer and has N input, and hidden layer has L hidden unit, and output layer has output, i.e. a user experience quality.Set up QoE assessment models by RBFN algorithm and comprise two steps: training process and test process, as shown in Figure 5, concrete steps are as follows for QoE assessment models Establishing process:
Step (2-1) produces data set: different cross-layer parameters is set, wherein coding bit rate span is 16kbps-640kbps, the desirable 5-30fps of frame per second, the desirable QCIF of resolution, CIF, 4CIF, packet loss span 0-20%, desirable 110x50mm-250 × the 200mm of terminal size, video content types is desirable at a slow speed, the video flowing of middling speed, rapid movement.Under the various combination of cross-layer parameter, the video flow quality of user being watched by method of subjective appraisal is carried out MOS scoring, MOS span [1,5], thus produce training set and test set sample data.Utilize training set sample data to carry out repetition training to model, and definite cluster centre and expansion constant, the concrete steps of training process are as follows:
(2-1-1) the cluster centre number of input RBFN algorithm, overlap coefficient, stopping criterion for iteration, default error convergence threshold value; Utilize the sample of data centralization 80% as training sample, training sample set is expressed as
wherein vector x
srepresent s input of RBFN algorithm, s=1,2 ..., S, S represents to input the number of sample, x
scomprise N cross-layer parameter, expression formula is x
s=[x
1, x
2..., x
n]
t, y
srepresent that input sample is x
sdraw the corresponding Quality of experience score value of using by method of subjective appraisal.
(2-1-2) choose at random L initial cluster center, make iterations t=1;
(2-1-3) calculate input sample x
swith cluster centre c
m(t) distance between, expression formula is || x
s-c
m(t) ||, m=1,2 ..., L,, wherein c
m(t) cluster centre of m hidden unit of the t time iteration of expression;
(2-1-4) according to minimal distance principle to input sample x
sclassify, as m (x
s)=min||x
s-c
m(t) || time, x
sbe classified as m class, be expressed as x
s∈ R
m(t), R wherein
m(t) represent m Clustering Domain, || || represent Euclidean distance;
(2-1-5) recalculate the cluster centre of each hidden unit
wherein N
mbe m Clustering Domain R
m(t) the input number of samples comprising in;
If (2-1-6) c
m(t+1) ≠ c
m(t), proceed to step (2-1-3); Otherwise m hidden unit cluster centre of finishing iteration and definite RBFN algorithm is c
m, and proceed to step (2-1-7);
(2-1-7) definition P is overlap coefficient, calculates expansion constant by adjacency method
representative and c
ma most contiguous P cluster centre, σ
mrepresent the expansion constant of m hidden unit;
(2-1-8) determine the output weight w=H of RBFN algorithm by least square method
+y, wherein w represents the output weight w by m hidden unit
mthe weight vector forming, expression formula is w=[w
1, w
2..., w
l]
t, m=1,2 ..., L, y=[y
1, y
2..., y
s]
t, H=[h
sm]
s × Lrepresent input sample x
sat the output h of m hidden unit
smthe hidden unit matrix forming, h
smexpression formula is
h
tthe transposition of representing matrix H, H
+the pseudoinverse of representing matrix H, expression formula is H
+=(H
th)
-1h
t.
Step (2-2) test process is to complete after the training process of RBFN algorithm in step (2-1), the input QoE assessment models using remaining data centralization 20% sample as test sample book, if the error between the QoE assessed value of being calculated by RBFN algorithm and QoE actual value is preset error convergence threshold value, QoE assessment models is set up completely, and step-up error convergence threshold is 10
-3.
Step 3: in each coding bit rate adjustment cycle, by the user experience quality MOS being calculated by QoE assessment models and QoE threshold mos
thcompare, MOS is set
th=3.5, represent that user experience quality reaches acceptable threshold value, if MOS>=MOS
th, keep the coding bit rate of transmitting terminal constant, if MOS < is MOS
th, transmitting terminal starts coding bit rate adjustment unit, network state is segmented and judged network congestion degree in conjunction with packet loss and One Way Delay growth trend, takes corresponding strategy to adjust adaptively coding bit rate.
Described in step 3, work as MOS < MOS
thtime, the step of adaptation rate control method is:
(3-1) by paired compare test PCT numerical value S
pCTwith difference compare test PDT numerical value S
pDTthe One Way Delay growth trend DT of specified data bag from transmitting terminal to receiving terminal, if S
pCT> 0.55 or S
pDT> 0.44, One Way Delay shows a rising trend, and is designated as DT=1, otherwise One Way Delay is and reduces trend, is designated as DT=0, wherein S
pCTwith S
pDTexpression formula be respectively
Receiving terminal records the One Way Delay { D of K the packet of receiving by the timestamp information of Real-time Transport Protocol header
1, D
2..., D
k, and be divided into according to the priority arrival order of K packet
group, the mediant of every group of packet One Way Delay is
the value rule of I (X) is
(3-2) the level and smooth packet loss of t coding bit rate adjustment cycle of calculating is
wherein p
1, p
2..., p
qrepresent front q the most contiguous coding bit rate adjustment cycle, i.e. t, t-1, t-2 ..., t-q+1 the historical packet loss that coding bit rate adjustment cycle is corresponding, λ
irepresent the weight coefficient of historical packet loss, span 0 < λ
i< 1, can arrange q=8, weight coefficient herein
(3-3) by rtcp protocol by packet loss, end-to-end One Way Delay and user experience quality property information cycle feed back to transmitting terminal from receiving terminal, at the initial time of t+1 coding bit rate adjustment cycle, the coding bit rate adjustment unit of transmitting terminal, according to the One Way Delay growth trend DT (t) and packet loss p (t) with t the coding bit rate adjustment cycle (3-2) calculating by step (3-1), takes corresponding strategy to adjust adaptively coding bit rate.Two packet loss threshold value p are set
land p
h, wherein p
lexpression user experience quality reaches and is satisfied with MOS
h=4.0 o'clock corresponding packet loss, p
hexpression user experience quality reaches can acceptance threshold MOS
th=3.5 o'clock corresponding packet loss, value is respectively p
l=1.04%, p
h=2.11%.The concrete adjustment strategy of coding bit rate adjustment unit is:
If (3-3-1). p (t) < p
l, illustrate that network condition is good and packet loss is minimum, therefore can promote QoE by increasing coding bit rate, the amplitude of increase is determined by One Way Delay growth trend:
If (3-3-1-1) DT (t)=0, illustrates that One Way Delay is for reducing trend, network condition is the trend that improves, and increases significantly coding bit rate, and expression formula is BR (t+1)=min{BR (t)+Δ
1, R
max, wherein BR (t) represents t the coding bit rate in coding bit rate adjustment cycle,
Δ
1the growth factor being inversely proportional to packet loss p (t), to guarantee the p at p < that increases of coding bit rate
lin scope, dynamically adjust, realize and in the situation that network state is good, significantly raise coding bit rate, avoided causing poor user experience quality, R because continuing long low coding bit rate
maxeffect be constraint coding bit rate adjustment, to prevent that coding bit rate from infinitely increasing, and gets R
max=1030.2kbps;
If (3-3-1-2) DT (t)=1, illustrates that One Way Delay is increase trend, network condition is variation trend, increases by a small margin coding bit rate, and expression formula is BR (t+1)=min{BR (t)+Δ
2, R
max, wherein
Δ
2the growth factor being inversely proportional to packet loss p (t), Δ
2can guarantee that the coding bit rate BR (t+1) after adjusting is no more than the twice of initial value BR (t), this adjustment mode has been avoided causing network congestion by excessively increasing coding bit rate in the time of network condition variation;
If (3-3-2). p
l< p (t) < p
h, illustrate that network has occurred slight congested, need further to take different adjustment strategies according to One Way Delay growth trend:
If (3-3-2-1) DT (t)=0, illustrate that One Way Delay is for reducing trend, be network condition be improve trend and have the ability alleviate slightly congested, for fear of being fluctuateed by the frequent video flow quality of bringing of adjusting of coding bit rate, now keep original coding bit rate constant, i.e. BR (t+1)=BR (t);
If (3-3-2-2) DT (t)=1, illustrate that One Way Delay is increase trend, be that network condition is variation trend, therefore should lower coding bit rate increases the weight of with avoid congestion, because now network is in slight congestion state, reducing coding bit rate is BR (t+1)=max{ (BR (t)-Δ
3× BR (t)), R
min, wherein Δ
3be the descending factors with exponential form, expression formula is
Δ
3not only can realize coding bit rate BR (t+1) reduces along with the increase of packet loss p (t), and can also realize the increase along with packet loss p (t), BR (t) fall increases, and can guarantee that the coding bit rate BR (t+1) after adjusting is not less than the half of initial value BR (t) simultaneously.This adjustment mode not only can reduce coding bit rate when congested network is slight, and has avoided coding bit rate to lower and too lowly video flow quality has been caused to damage, R
mineffect be constraint coding bit rate adjustment, to prevent that coding bit rate from infinitely reducing, and gets R
min=85.1kbps;
If (3-3-3). p > p
h, illustrate that network is because packet loss is crossed the heavy congestion that mostly occurred, need further to take different adjustment strategies according to One Way Delay growth trend:
If (3-3-3-1) DT (t)=0, illustrate that One Way Delay is for reducing trend, be that network condition is the trend that improves, but because network congestion has seriously produced too much packet loss, therefore still need to reduce coding bit rate with alleviating network congestion, expression formula is BR (t+1)=max{ Δ × BR (t), R
min, wherein Δ=max (Δ
4, Δ
5),
If (3-3-3-2) DT (t)=1, illustrate that One Way Delay is increase trend, network condition is variation trend, now should be to reduce by a larger margin coding bit rate, expression formula is BR (t+1)=max{ Δ × BR (t), R
min), Δ=min (Δ
4, Δ
5);
Above-mentioned in generation heavy congestion, as p > p
htime, Δ is the descending factors with multiplier form, it can guarantee at least the declined half of initial value BR (t) of coding bit rate BR (t+1), reduces packet loss alleviating network congestion thereby realize.
Step 4: repeat above-mentioned steps 2~step 3, until wireless video streaming service request finishes.
Claims (2)
1. the wireless video streaming service adaptation method of rate control based on QoE, is characterized in that the method comprises time delay trend analysis unit, packet loss statistic unit, QoE assessment unit, coding bit rate adjustment unit;
Described time delay trend analysis unit is for judging that wireless video streaming business data packet is transferred to the One Way Delay growth trend of receiving terminal from transmitting terminal, specifically: the One Way Delay that obtains packet by the timestamp information of RTP header, judge that by comparision testing One Way Delay is the trend that increases or reduce again, finally a kind of indication information using One Way Delay growth trend as network congestion degree is input to coding bit rate adjustment unit;
Described packet loss statistic unit is for calculating the end-to-end packet loss of wireless video streaming business in each coding bit rate adjustment cycle, specifically: the sequence number information statistics by RTP header obtains packet loss, affect parameter as network layer and be input to QoE assessment unit, and by weighted mean method, packet loss is carried out to smoothing processing and reduce because of the packet loss concussion causing that suddenlys change of offered load situation, packet loss after smoothing processing is as a kind of indication information of network congestion degree, feed back to the coding bit rate adjustment unit of transmitting terminal from receiving terminal by RTCP Real-time Transport Control Protocol,
Described QoE assessment unit is mapped as user experience quality score for the cross-layer of input is affected to parameter by calculating, i.e. Mean Opinion Score value, and Mean Opinion Score value is input to coding bit rate adjustment unit;
Described coding bit rate adjustment unit is used for associating packet loss and One Way Delay growth trend and network state is segmented and judged network congestion degree, in conjunction with the Mean Opinion Score value of QoE assessment unit output, take corresponding strategy to adjust adaptively coding bit rate again.
2. the wireless video streaming service adaptation method of rate control based on QoE as claimed in claim 1, is characterized in that the concrete steps of the method are:
Step 1: adopt H.264 mode to encode wireless video streaming at transmitting terminal, become the video flowing sequence with Z kind different coding bit rate, with set L '={ l
1, l
2..., l
z, (l
1< l
2< ... < l
z) represent, L ' is coding bit rate set, and { l is set
1, l
2..., l
zvalue contain video flow quality and become best experienced coding bit rate value from the poorest, the coding bit rate of choosing at random user's initial request wireless video streaming business is l
k(k=1,2 ..., Z); Wherein, k is coding bit rate grade;
Step 2: at each coding bit rate adjustment cycle, calculate user experience quality by QoE assessment unit, set up QoE assessment models by radial basis function neural network algorithm exactly, radial basis function neural network algorithm comprises input layer, hidden layer, output layer, set input layer and there is N input, hidden layer has L hidden unit, and output layer has output, i.e. a user experience quality;
Set up QoE assessment models by radial basis function neural network algorithm and comprise training process and test process, idiographic flow is as follows:
Step (2-1) training process uses the cross-layer of training set to affect parameter and subjective user experience quality value to the training of QoE model, and training set is expressed as
wherein vector x
srepresent s input of radial basis function neural network algorithm, s=1,2 ..., S, S represents to input the number of sample, x
scomprise N cross-layer parameter, expression formula is x
s=[x
1, x
2..., x
n]
t, y
srepresent that input sample is x
sdraw corresponding Quality of experience score value, the span 1≤y of using by method of subjective appraisal
s≤ 5, the concrete steps of training process are as follows:
(2-1-1) choose at random L initial cluster center, make iterations t=1;
(2-1-2) calculate input sample x
swith cluster centre c
m(t) distance between, expression formula is || x
s-c
m(t) ||, m=1,2 ..., L,, wherein c
m(t) cluster centre of m hidden unit of the t time iteration of expression;
(2-1-3) according to minimal distance principle to input sample x
sclassify, as m (x
s)=min||x
s-c
m(t) || time, x
sbe classified as m class, be expressed as x
s∈ R
m(t), R wherein
m(t) represent m Clustering Domain, || || represent Euclidean distance;
(2-1-4) recalculate the cluster centre of each hidden unit
wherein N
mbe m Clustering Domain R
m(t) the input number of samples comprising in;
If (2-1-5) c
m(t+1) ≠ c
m(t), proceed to step (2-1-2); Otherwise m hidden unit cluster centre of finishing iteration and definite radial basis function neural network algorithm is c
m, and proceed to step (2-1-6);
(2-1-6) definition P is overlap coefficient, calculates expansion constant by adjacency method
representative and c
ma most contiguous P cluster centre, σ
mrepresent the expansion constant of m hidden unit;
(2-1-7) determine the output weight w=H of radial basis function neural network algorithm by least square method
+y, wherein w represents the output weight w by m hidden unit
mthe weight vector forming, expression formula is w=[w
1, w
2..., w
l]
t, m=1,2 ..., L, y=[y
1, y
2..., y
s]
t, H=[h
sm]
s × Lrepresent input sample x
sat the output h of m hidden unit
smthe hidden unit matrix forming, h
smexpression formula is
h
tthe transposition of representing matrix H, H
+the pseudoinverse of representing matrix H, expression formula is H
+=(H
th)
-1h
t;
Step (2-2) test process is to complete after the training process of radial basis function neural network algorithm in step (2-1), by test set sample input QoE assessment unit, if the error between the QoE assessed value of being calculated by radial basis function neural network algorithm and QoE actual value is lower than default error convergence threshold value, QoE assessment models is set up complete;
Step 3: in each coding bit rate adjustment cycle, by the user experience quality MOS being calculated by QoE assessment unit and QoE threshold mos
thcompare;
If MOS>=MOS
th, keep the coding bit rate of transmitting terminal constant;
If MOS < is MOS
th, transmitting terminal starts coding bit rate adjustment unit, adjusts adaptively coding bit rate, and concrete steps are:
(3-1) by paired compare test numerical value S
pCTwith difference compare test numerical value S
pDTthe One Way Delay growth trend DT of specified data bag from transmitting terminal to receiving terminal, if S
pCT> 0.55 or S
pDT> 0.44, One Way Delay shows a rising trend, and is designated as DT=1, otherwise One Way Delay is and reduces trend, is designated as DT=0, wherein S
pCTwith S
pDTexpression formula be respectively
Receiving terminal records the One Way Delay { D of K the packet of receiving by the timestamp information of RTP header
1, D
2..., D
k, and be divided into according to the priority arrival order of K packet
group, the mediant of every group of packet One Way Delay is
The value rule of I (X) is
(3-2) the level and smooth packet loss of t coding bit rate adjustment cycle of calculating is
i=1,2 ..., q, wherein p
1, p
2..., p
qrepresent front q the most contiguous coding bit rate adjustment cycle, i.e. t, t-1, t-2 ..., t-q+1 the historical packet loss that coding bit rate adjustment cycle is corresponding, λ
irepresent the weight coefficient of historical packet loss, span 0 < λ
i< 1;
(3-3) by RTCP Real-time Transport Control Protocol by packet loss, end-to-end One Way Delay and user experience quality property information cycle feed back to transmitting terminal from receiving terminal, at the initial time of t+1 coding bit rate adjustment cycle, the coding bit rate adjustment unit of transmitting terminal, according to the One Way Delay growth trend DT (t) and packet loss p (t) with t the coding bit rate adjustment cycle (3-2) calculating by step (3-1), takes corresponding strategy to adjust adaptively coding bit rate; Two packet loss threshold value p are set
land p
h, wherein p
lexpression user experience quality reaches and is satisfied with MOS
htime corresponding packet loss, p
hrepresent that user experience quality reaches acceptable degree MOS
thtime corresponding packet loss, and have 0 < p
l< p
h< 1,1 < MOS
th< MOS
h< 5, the concrete adjustment strategy of coding bit rate adjustment unit is:
If (3-3-1). p (t) < p
l, illustrate that network condition is good and packet loss is minimum, therefore can promote QoE by increasing coding bit rate, the amplitude of increase is determined by One Way Delay growth trend:
If (3-3-1-1) DT (t)=0, illustrates that One Way Delay is for reducing trend, network condition is the trend that improves, and increases significantly coding bit rate, and expression formula is BR (t+1)=min{BR (t)+Δ
1, R
max, wherein BR (t) represents t the coding bit rate in coding bit rate adjustment cycle,
Δ
1the growth factor being inversely proportional to packet loss p (t), to guarantee the p at p < that increases of coding bit rate
lin scope, dynamically adjust, realize and in the situation that network state is good, significantly raise coding bit rate, avoided causing poor user experience quality, R because continuing long low coding bit rate
maxeffect be constraint coding bit rate adjustment, to prevent that coding bit rate from infinitely increasing;
If (3-3-1-2) DT (t)=1, illustrates that One Way Delay is increase trend, network condition is variation trend, increases by a small margin coding bit rate, and expression formula is BR (t+1)=min{BR (t)+Δ
2, R
max, wherein
Δ
2the growth factor being inversely proportional to packet loss p (t), Δ
2can guarantee that the coding bit rate BR (t+1) after adjusting is no more than the twice of initial value BR (t), this adjustment mode has been avoided causing network congestion by excessively increasing coding bit rate in the time of network condition variation;
If (3-3-2). p
l< p (t) < p
h, illustrate that network has occurred slight congested, need further to take different adjustment strategies according to One Way Delay growth trend:
If (3-3-2-1) DT (t)=0, illustrate that One Way Delay is for reducing trend, be network condition be improve trend and have the ability alleviate slightly congested, for fear of being fluctuateed by the frequent video flow quality of bringing of adjusting of coding bit rate, now keep original coding bit rate constant, i.e. BR (t+1)=BR (t);
If (3-3-2-2) DT (t)=1, illustrate that One Way Delay is increase trend, be that network condition is variation trend, therefore should lower coding bit rate increases the weight of with avoid congestion, because now network is in slight congestion state, reducing coding bit rate is BR (t+1)=max{ (BR (t)-Δ
3× BR (t)), R
min, wherein Δ
3be the descending factors with exponential form, expression formula is
Δ
3not only can realize coding bit rate BR (t+1) reduces along with the increase of packet loss p (t), and can also realize the increase along with packet loss p (t), BR (t) fall increases, and can guarantee that coding bit rate BR (t+1) after adjusting is higher than the half that equals initial value BR (t) simultaneously;
If (3-3-3). p > p
h, illustrate that network is because packet loss is crossed the heavy congestion that mostly occurred, need further to take different adjustment strategies according to One Way Delay growth trend:
If (3-3-3-1) DT (t)=0, illustrate that One Way Delay is for reducing trend, be that network condition is the trend that improves, but because network congestion has seriously produced too much packet loss, therefore still need to reduce coding bit rate with alleviating network congestion, expression formula is BR (t+1)=max{ Δ × BR (t), R
min, wherein Δ=max (Δ
4, Δ
5),
If (3-3-3-2) DT (t)=1, illustrate that One Way Delay is increase trend, network condition is variation trend, now should be to reduce by a larger margin coding bit rate, expression formula is BR (t+1)=max{ Δ × BR (t), R
min), Δ=min (Δ
4, Δ
5);
Above-mentioned at generation heavy congestion, i.e. p > p
htime, Δ is the descending factors with multiplier form, it can guarantee at least the declined half of initial value BR (t) of coding bit rate BR (t+1), reduces packet loss alleviating network congestion thereby realize;
Step 4: repeat above-mentioned steps 2~step 3, until wireless video streaming service request finishes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410076993.0A CN103888846B (en) | 2014-03-04 | 2014-03-04 | Wireless video streaming service self-adaption rate control method based on QoE |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410076993.0A CN103888846B (en) | 2014-03-04 | 2014-03-04 | Wireless video streaming service self-adaption rate control method based on QoE |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103888846A true CN103888846A (en) | 2014-06-25 |
CN103888846B CN103888846B (en) | 2017-02-08 |
Family
ID=50957534
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410076993.0A Active CN103888846B (en) | 2014-03-04 | 2014-03-04 | Wireless video streaming service self-adaption rate control method based on QoE |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103888846B (en) |
Cited By (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104519325A (en) * | 2014-12-29 | 2015-04-15 | 重庆邮电大学 | Wireless video monitoring system self-adaptive guaranteeing method based on 4G network |
CN105049930A (en) * | 2015-08-14 | 2015-11-11 | 浙江大学 | Wireless video streaming service QoE estimation method based on support vector machine |
CN105262699A (en) * | 2015-10-29 | 2016-01-20 | 浙江大华技术股份有限公司 | Network adaptive coding adjustment method and device |
CN105611322A (en) * | 2014-11-14 | 2016-05-25 | 台湾艾特维股份有限公司 | Video bandwidth adjustment device and adjustment method thereof |
CN105812097A (en) * | 2016-03-16 | 2016-07-27 | 北京邮电大学 | Self-adaptive AMR code rate adjusting method based on network states |
CN105828069A (en) * | 2016-04-06 | 2016-08-03 | 上海交通大学 | Encoder adaptive adjustment method based on subjective quality evaluation |
CN105871744A (en) * | 2016-03-31 | 2016-08-17 | 北京小米移动软件有限公司 | Method and device for controlling traffic dynamically |
CN105933329A (en) * | 2016-06-12 | 2016-09-07 | 浙江大学 | Video streaming business code rate self-adaption method based on online study |
CN106411565A (en) * | 2015-07-31 | 2017-02-15 | 想象技术有限公司 | Estimating processor load |
CN106533963A (en) * | 2017-01-11 | 2017-03-22 | 深圳云视融通科技有限公司 | Network congestion control method of streaming media transmission |
CN106933585A (en) * | 2017-03-07 | 2017-07-07 | 吉林大学 | A kind of self-adapting multi-channel interface system of selection under distributed cloud environment |
CN107276910A (en) * | 2017-06-07 | 2017-10-20 | 上海迪爱斯通信设备有限公司 | The real-time adjusting apparatus of video code rate and system, video server |
CN107770473A (en) * | 2016-08-16 | 2018-03-06 | 大唐移动通信设备有限公司 | A kind of audio, video data transfer control method and device |
CN107888579A (en) * | 2017-11-06 | 2018-04-06 | 浙江大学 | A kind of mobile video user experience quality index modeling method of non-interfering type |
CN107968944A (en) * | 2017-12-04 | 2018-04-27 | 深圳市瑞科慧联科技有限公司 | A kind of image transfer method and system |
CN108029045A (en) * | 2016-02-29 | 2018-05-11 | 华为技术有限公司 | Method for optimizing video, user equipment and the network equipment |
CN108064058A (en) * | 2016-11-07 | 2018-05-22 | 中兴通讯股份有限公司 | Jamming control method and device, base station |
CN108495182A (en) * | 2018-03-23 | 2018-09-04 | 山西大学 | A kind of audio quality self-adjusting control method |
CN108574840A (en) * | 2017-03-10 | 2018-09-25 | 华为技术有限公司 | A kind of method and device of assessment quality of experience of video |
CN108848415A (en) * | 2018-05-04 | 2018-11-20 | 北京大学 | A kind of the network real-time video transmission method and device of adaptive learning |
CN109120933A (en) * | 2018-10-11 | 2019-01-01 | 广州酷狗计算机科技有限公司 | Dynamic adjusts method, apparatus, equipment and the storage medium of code rate |
CN109905326A (en) * | 2019-03-26 | 2019-06-18 | 武汉大学 | A kind of rate drawdown parameter optimization method based on the Congestion Level SPCC factor |
CN109982112A (en) * | 2017-12-27 | 2019-07-05 | 豪威科技股份有限公司 | Embedded multimedia system with the adaptive bit rate control for power-efficient stream video |
CN110324621A (en) * | 2019-07-04 | 2019-10-11 | 北京达佳互联信息技术有限公司 | Method for video coding, device, electronic equipment and storage medium |
US10637790B2 (en) | 2016-01-25 | 2020-04-28 | Huawei Technologies Co., Ltd. | Control method and apparatus, and network controller |
CN111245769A (en) * | 2018-11-28 | 2020-06-05 | 深圳技威时代科技有限公司 | Audio and video transmission method and device and storage medium |
CN111385574A (en) * | 2018-12-28 | 2020-07-07 | 北京字节跳动网络技术有限公司 | Code rate control method and device in video coding, mobile terminal and storage medium |
CN111901642A (en) * | 2020-07-31 | 2020-11-06 | 成都云格致力科技有限公司 | Real-time video code rate self-adaptive control method and system based on reinforcement learning |
WO2020258427A1 (en) * | 2019-06-28 | 2020-12-30 | 合肥工业大学 | Qoe-based adaptive vr video acquisition and transmission method |
CN112291495A (en) * | 2020-10-16 | 2021-01-29 | 厦门大学 | Wireless video low-delay anti-interference transmission method based on reinforcement learning |
CN112565884A (en) * | 2020-11-27 | 2021-03-26 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, terminal, server and storage medium |
CN112823527A (en) * | 2018-10-05 | 2021-05-18 | 交互数字Ce专利控股公司 | Method implemented at a device capable of running an adaptive streaming session and corresponding device |
CN112911650A (en) * | 2021-03-28 | 2021-06-04 | 高小翎 | Mobile high-definition video intelligent bidirectional detection bandwidth control system |
CN113473190A (en) * | 2021-08-05 | 2021-10-01 | 佳源科技股份有限公司 | Audio and video flexible transmission device and transmission method based on reinforcement learning |
CN113497671A (en) * | 2020-04-02 | 2021-10-12 | 成都鼎桥通信技术有限公司 | Data processing method, device, equipment, storage medium and terminal equipment |
CN113660488A (en) * | 2021-10-18 | 2021-11-16 | 腾讯科技(深圳)有限公司 | Method and device for carrying out flow control on multimedia data and training flow control model |
CN115002819A (en) * | 2021-10-20 | 2022-09-02 | 荣耀终端有限公司 | Network quality evaluation method and device |
CN116017092A (en) * | 2022-12-12 | 2023-04-25 | 中国科学院计算技术研究所 | QoE quantization method and transmission system parameter adjustment method based on QoE quantization method |
CN116708843A (en) * | 2023-08-03 | 2023-09-05 | 清华大学 | User experience quality feedback regulation system in semantic communication process |
CN116743609A (en) * | 2023-08-14 | 2023-09-12 | 清华大学 | QoE evaluation method and device for video streaming media based on semantic communication |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102547475B (en) * | 2012-02-21 | 2014-01-15 | 德科仕通信(上海)有限公司 | Method and system for improving quality of service alarming accuracy of Internet protocol (IP) video media stream |
CN102802089B (en) * | 2012-09-13 | 2014-12-31 | 浙江大学 | Shifting video code rate regulation method based on experience qualitative forecast |
CN103475951A (en) * | 2013-08-20 | 2013-12-25 | 南京邮电大学 | User-experience-based real-time video transmission rate self-adaption method |
-
2014
- 2014-03-04 CN CN201410076993.0A patent/CN103888846B/en active Active
Non-Patent Citations (2)
Title |
---|
XINGGONG ZHANG ET.AL: "Modeling and analysis of Skype video calls:rate control and video quality", 《IEEE TRANSACTIONS ON MULTIMEDIA》 * |
YAQIAN KANG,HUIFANG CHEN,LEI XIE: "An artificial-neural-network-based QoE estimation model for video streaming over wireless networks", 《2013 2ND IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA》 * |
Cited By (66)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105611322A (en) * | 2014-11-14 | 2016-05-25 | 台湾艾特维股份有限公司 | Video bandwidth adjustment device and adjustment method thereof |
CN104519325A (en) * | 2014-12-29 | 2015-04-15 | 重庆邮电大学 | Wireless video monitoring system self-adaptive guaranteeing method based on 4G network |
CN104519325B (en) * | 2014-12-29 | 2018-12-07 | 大唐移动通信设备有限公司 | A kind of adaptive support method of wireless video monitoring system based on 4G network |
CN106411565A (en) * | 2015-07-31 | 2017-02-15 | 想象技术有限公司 | Estimating processor load |
CN106411565B (en) * | 2015-07-31 | 2021-06-25 | 想象技术有限公司 | Method for estimating processor load, apparatus, system and medium for transmitting media stream |
CN105049930A (en) * | 2015-08-14 | 2015-11-11 | 浙江大学 | Wireless video streaming service QoE estimation method based on support vector machine |
CN105262699A (en) * | 2015-10-29 | 2016-01-20 | 浙江大华技术股份有限公司 | Network adaptive coding adjustment method and device |
CN105262699B (en) * | 2015-10-29 | 2018-07-03 | 浙江大华技术股份有限公司 | A kind of network self-adapting code adjustment method and device |
US10637790B2 (en) | 2016-01-25 | 2020-04-28 | Huawei Technologies Co., Ltd. | Control method and apparatus, and network controller |
CN108029045A (en) * | 2016-02-29 | 2018-05-11 | 华为技术有限公司 | Method for optimizing video, user equipment and the network equipment |
CN105812097A (en) * | 2016-03-16 | 2016-07-27 | 北京邮电大学 | Self-adaptive AMR code rate adjusting method based on network states |
CN105812097B (en) * | 2016-03-16 | 2019-04-23 | 北京邮电大学 | A kind of AMR code rate self-adapting regulation method based on network state |
CN105871744A (en) * | 2016-03-31 | 2016-08-17 | 北京小米移动软件有限公司 | Method and device for controlling traffic dynamically |
CN105828069A (en) * | 2016-04-06 | 2016-08-03 | 上海交通大学 | Encoder adaptive adjustment method based on subjective quality evaluation |
CN105933329A (en) * | 2016-06-12 | 2016-09-07 | 浙江大学 | Video streaming business code rate self-adaption method based on online study |
CN105933329B (en) * | 2016-06-12 | 2018-11-20 | 浙江大学 | Video stream traffic code rate adaptive approach based on on-line study |
CN107770473B (en) * | 2016-08-16 | 2020-05-26 | 大唐移动通信设备有限公司 | Audio and video data transmission control method and device |
CN107770473A (en) * | 2016-08-16 | 2018-03-06 | 大唐移动通信设备有限公司 | A kind of audio, video data transfer control method and device |
CN108064058A (en) * | 2016-11-07 | 2018-05-22 | 中兴通讯股份有限公司 | Jamming control method and device, base station |
US11751096B2 (en) | 2016-11-07 | 2023-09-05 | Zte Corporation | Congestion control method and device, and base station |
CN108064058B (en) * | 2016-11-07 | 2022-11-01 | 中兴通讯股份有限公司 | Congestion control method and device and base station |
CN106533963A (en) * | 2017-01-11 | 2017-03-22 | 深圳云视融通科技有限公司 | Network congestion control method of streaming media transmission |
CN106533963B (en) * | 2017-01-11 | 2019-05-03 | 深圳云视融通科技有限公司 | A kind of method for controlling network congestion of streaming media |
CN106933585B (en) * | 2017-03-07 | 2020-02-21 | 吉林大学 | Self-adaptive multi-channel interface selection method under distributed cloud environment |
CN106933585A (en) * | 2017-03-07 | 2017-07-07 | 吉林大学 | A kind of self-adapting multi-channel interface system of selection under distributed cloud environment |
CN108574840A (en) * | 2017-03-10 | 2018-09-25 | 华为技术有限公司 | A kind of method and device of assessment quality of experience of video |
CN107276910A (en) * | 2017-06-07 | 2017-10-20 | 上海迪爱斯通信设备有限公司 | The real-time adjusting apparatus of video code rate and system, video server |
CN107888579B (en) * | 2017-11-06 | 2020-06-09 | 浙江大学 | Non-interference mobile video user experience quality index modeling method |
CN107888579A (en) * | 2017-11-06 | 2018-04-06 | 浙江大学 | A kind of mobile video user experience quality index modeling method of non-interfering type |
CN107968944B (en) * | 2017-12-04 | 2020-01-17 | 深圳市瑞科慧联科技有限公司 | Image transmission method and system |
CN107968944A (en) * | 2017-12-04 | 2018-04-27 | 深圳市瑞科慧联科技有限公司 | A kind of image transfer method and system |
CN109982112B (en) * | 2017-12-27 | 2021-10-22 | 豪威科技股份有限公司 | System and method for video streaming |
CN109982112A (en) * | 2017-12-27 | 2019-07-05 | 豪威科技股份有限公司 | Embedded multimedia system with the adaptive bit rate control for power-efficient stream video |
CN108495182A (en) * | 2018-03-23 | 2018-09-04 | 山西大学 | A kind of audio quality self-adjusting control method |
CN108848415B (en) * | 2018-05-04 | 2021-01-15 | 北京大学 | Network real-time video transmission method and device for adaptive learning |
CN108848415A (en) * | 2018-05-04 | 2018-11-20 | 北京大学 | A kind of the network real-time video transmission method and device of adaptive learning |
CN112823527A (en) * | 2018-10-05 | 2021-05-18 | 交互数字Ce专利控股公司 | Method implemented at a device capable of running an adaptive streaming session and corresponding device |
US11936704B2 (en) | 2018-10-05 | 2024-03-19 | Interdigital Madison Patent Holdings, Sas | Method to be implemented at a device able to run one adaptive streaming session, and corresponding device |
CN109120933A (en) * | 2018-10-11 | 2019-01-01 | 广州酷狗计算机科技有限公司 | Dynamic adjusts method, apparatus, equipment and the storage medium of code rate |
CN111245769A (en) * | 2018-11-28 | 2020-06-05 | 深圳技威时代科技有限公司 | Audio and video transmission method and device and storage medium |
CN111245769B (en) * | 2018-11-28 | 2022-09-30 | 深圳技威时代科技有限公司 | Audio and video transmission method and device and storage medium |
CN111385574A (en) * | 2018-12-28 | 2020-07-07 | 北京字节跳动网络技术有限公司 | Code rate control method and device in video coding, mobile terminal and storage medium |
CN109905326A (en) * | 2019-03-26 | 2019-06-18 | 武汉大学 | A kind of rate drawdown parameter optimization method based on the Congestion Level SPCC factor |
WO2020258427A1 (en) * | 2019-06-28 | 2020-12-30 | 合肥工业大学 | Qoe-based adaptive vr video acquisition and transmission method |
US11831883B2 (en) | 2019-06-28 | 2023-11-28 | Hefei University Of Technology | QoE-based adaptive acquisition and transmission method for VR video |
CN110324621B (en) * | 2019-07-04 | 2021-05-18 | 北京达佳互联信息技术有限公司 | Video encoding method, video encoding device, electronic equipment and storage medium |
CN110324621A (en) * | 2019-07-04 | 2019-10-11 | 北京达佳互联信息技术有限公司 | Method for video coding, device, electronic equipment and storage medium |
CN113497671A (en) * | 2020-04-02 | 2021-10-12 | 成都鼎桥通信技术有限公司 | Data processing method, device, equipment, storage medium and terminal equipment |
CN111901642B (en) * | 2020-07-31 | 2022-09-30 | 成都云格致力科技有限公司 | Real-time video code rate self-adaptive control method and system based on reinforcement learning |
CN111901642A (en) * | 2020-07-31 | 2020-11-06 | 成都云格致力科技有限公司 | Real-time video code rate self-adaptive control method and system based on reinforcement learning |
CN112291495B (en) * | 2020-10-16 | 2021-08-03 | 厦门大学 | Wireless video low-delay anti-interference transmission method based on reinforcement learning |
CN112291495A (en) * | 2020-10-16 | 2021-01-29 | 厦门大学 | Wireless video low-delay anti-interference transmission method based on reinforcement learning |
CN112565884B (en) * | 2020-11-27 | 2024-03-05 | 北京达佳互联信息技术有限公司 | Image processing method, device, terminal, server and storage medium |
CN112565884A (en) * | 2020-11-27 | 2021-03-26 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, terminal, server and storage medium |
CN112911650A (en) * | 2021-03-28 | 2021-06-04 | 高小翎 | Mobile high-definition video intelligent bidirectional detection bandwidth control system |
CN113473190A (en) * | 2021-08-05 | 2021-10-01 | 佳源科技股份有限公司 | Audio and video flexible transmission device and transmission method based on reinforcement learning |
CN113473190B (en) * | 2021-08-05 | 2022-06-28 | 佳源科技股份有限公司 | Audio and video flexible transmission device and transmission method based on reinforcement learning |
CN113660488B (en) * | 2021-10-18 | 2022-02-11 | 腾讯科技(深圳)有限公司 | Method and device for carrying out flow control on multimedia data and training flow control model |
CN113660488A (en) * | 2021-10-18 | 2021-11-16 | 腾讯科技(深圳)有限公司 | Method and device for carrying out flow control on multimedia data and training flow control model |
CN115002819A (en) * | 2021-10-20 | 2022-09-02 | 荣耀终端有限公司 | Network quality evaluation method and device |
CN116017092A (en) * | 2022-12-12 | 2023-04-25 | 中国科学院计算技术研究所 | QoE quantization method and transmission system parameter adjustment method based on QoE quantization method |
CN116017092B (en) * | 2022-12-12 | 2024-06-14 | 中国科学院计算技术研究所 | QoE quantization method and transmission system parameter adjustment method based on QoE quantization method |
CN116708843A (en) * | 2023-08-03 | 2023-09-05 | 清华大学 | User experience quality feedback regulation system in semantic communication process |
CN116708843B (en) * | 2023-08-03 | 2023-10-31 | 清华大学 | User experience quality feedback regulation system in semantic communication process |
CN116743609B (en) * | 2023-08-14 | 2023-10-17 | 清华大学 | QoE evaluation method and device for video streaming media based on semantic communication |
CN116743609A (en) * | 2023-08-14 | 2023-09-12 | 清华大学 | QoE evaluation method and device for video streaming media based on semantic communication |
Also Published As
Publication number | Publication date |
---|---|
CN103888846B (en) | 2017-02-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103888846A (en) | Wireless video streaming service self-adaption rate control method based on QoE | |
CN102802089B (en) | Shifting video code rate regulation method based on experience qualitative forecast | |
CN102710374B (en) | Speed control method in wireless streaming media transmission | |
CN1839597B (en) | Quality-of-experience (QOE) measurement for wireless communication networks | |
Alreshoodi et al. | Survey on QoE\QoS correlation models for multimedia services | |
CN101578842B (en) | Content- and link-dependent coding adaptation for multimedia telephony | |
CN101026552B (en) | Apparatus and method for determining transmission policies for a plurality of applications of different types | |
CN102868666B (en) | Based on the implementation method of the mutual stream media quality Surveillance of Consumer's Experience | |
CN108696403A (en) | A kind of encrypted video QoE evaluating methods based on the study of network flow latent structure | |
WO2013159502A1 (en) | Video quality evaluation method and device | |
CN106134130A (en) | The system and method estimated for the dynamic effective speed of real-time video flow | |
CN103475951A (en) | User-experience-based real-time video transmission rate self-adaption method | |
CN107333091A (en) | Audio-video conversion method and device | |
CN102318266A (en) | Monitoring media services in telecommunications networks | |
CN103648058A (en) | 3G media stream cross-layer rate control method based on channel measurement | |
CN103152599A (en) | Mobile video service user experience quality evaluation method based on ordinal regression | |
Piamrat et al. | QoE-aware scheduling for video-streaming in High Speed Downlink Packet Access | |
CN104796443A (en) | Mobile streaming media QoE (Quality of Experience) correction method and server | |
JP6033058B2 (en) | Communication path identification device | |
CN107277499B (en) | A kind of video quality evaluation method and device | |
CN104219090A (en) | System and method for media multipath relay transmission business quality-of-experience collaborative evaluation | |
Araújo et al. | A hybrid energy-aware video bitrate adaptation algorithm for mobile networks | |
Feng-Hui et al. | QoE issues of OTT services over 5G network | |
CN105141404A (en) | Method for wireless resource allocation based on QoE (Quality of Experience) in LTE-A (Long Term Evolution-Advanced) system | |
Tang et al. | QoE-based resource allocation algorithm for multi-applications in downlink LTE systems |
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 |