CN110868609A - Method for monitoring and standardizing live video - Google Patents
Method for monitoring and standardizing live video Download PDFInfo
- Publication number
- CN110868609A CN110868609A CN201911211715.0A CN201911211715A CN110868609A CN 110868609 A CN110868609 A CN 110868609A CN 201911211715 A CN201911211715 A CN 201911211715A CN 110868609 A CN110868609 A CN 110868609A
- Authority
- CN
- China
- Prior art keywords
- video
- live
- broadcast
- score
- live video
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44218—Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention discloses a method for monitoring and standardizing live video. The method specifically comprises the following steps: (1) after the video live broadcast is started, starting picture acquisition at regular time; (2) carrying out AI face recognition and living body detection on the collected video data; (3) recording each detection success or detection failure, and carrying out standard prompt on the live video; (4) and calculating the effective duration in the live video. The invention has the beneficial effects that: the effective live broadcast duration monitoring can pay salaries by the parameter on one hand, and then can standardize live broadcast of the show, so that the anchor shows own appearance as much as possible, viewers have better experience, and warm prompts can be sent to the anchor; it can be known that in the video live broadcast, the visual effect in each time period has a total score, which is used to evaluate the overall effect of the whole video live broadcast.
Description
Technical Field
The invention relates to the technical field related to live video, in particular to a live video monitoring and standardizing method.
Background
With the continuous development of internet technology, the technology of video live broadcast is also continuously perfected, the popularity is quite high, and the era of national live broadcast is coming. The video live broadcast platform is sprayed out like bamboo shoots in spring after rain. Various types of live broadcast are developed vigorously, such as show, game live broadcast, shopping live broadcast and the like. Some platforms have a fixed anchor for subscription at various time periods in order to allow viewers to enjoy live shows at 24 hours. And then the broadcasting time is used for charging to pay compensation. If only time-based constraints, a cast hang-up, etc. may occur. Such a live broadcast is not meaningful. The current management mode is generally manual management, namely, an administrator randomly checks a live broadcast room, and the mode not only needs the administrator to be online for 24 hours, but also has the situation that the administrator is on-hook once the administrator leaves.
Disclosure of Invention
The invention provides a video live broadcast monitoring and standardizing method capable of counting effective duration and improving live broadcast quality in order to overcome the defects in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for monitoring and standardizing live video comprises the following steps:
(1) after the video live broadcast is started, starting picture acquisition at regular time;
(2) carrying out AI face recognition and living body detection on the collected video data;
(3) recording each detection success or detection failure, and carrying out standard prompt on the live video;
(4) and calculating the effective duration in the live video.
The invention focuses on video live broadcast, and effectively monitors the live broadcast time length. Based on live show, effective live broadcast can be defined as live broadcast with the face appearing in the conspicuous position of the screen. The effective live broadcast duration is monitored, on one hand, compensation can be paid according to the parameter, and then live broadcast of the show field can be standardized, so that the anchor shows own appearance as much as possible, and audiences have better experience. When the client fails to detect the human face living body continuously for multiple times, a warm prompt can be sent to the anchor.
Preferably, in step (1), after the live video is started, the mobile device acquires video stream data, and after the live video is started, a timing task is started, namely, video data is acquired for a short time T2 after a time T1.
Preferably, in step (2), AI face recognition and live body detection are performed on the video data acquired in step (1), and the number of successes S and the number of failures F are recorded.
As another preference, in the step (2), the specific operation is as follows: setting that the whole face needs to be placed in a video picture, and a gap with a certain distance needs to be left at the upper part, the lower part, the left part and the right part, so that the face can be verified to be passed; taking a certain face position as a full score 100 position, and when the face deviates up and down or leftwards and rightwards, the face is proportionally subtracted according to the deviation amount, so that the more the deviation is, the more the division is reduced; certainly, the score needs to be added with the evaluation of live body detection, if the live body detection does not pass the subtraction of the fixed value, the corresponding score of each section of video is given through the step, and the score is not lower than 60 points, so that the recording is successful; if the score is below 60 points, the record fails.
Preferably, in step (3), each detection success or detection failure is recorded, and as long as N detection failures are continuously received, the upper layer is called back, which means that the broadcast of the anchor in the period of time does not meet the specification, and a popup window is adopted for prompting in the earlier stage.
Preferably, in step (3), if the main broadcast still does not hear the suggestion, a message is pushed to the platform administrator, so that the administrator can further verify and even close the current live broadcast.
As another preference, in the step (3), for N consecutive times of scores lower than a certain set score, a frame-flipping warm reminder is performed; for M continuous scores lower than the set score, the live ID and the simple description are sent to the administrator, and the administrator performs manual management, wherein M is larger than N.
Preferably, in step (4), the effective duration in the live video is calculated by a formula, that is, the effective duration is S (T1+ T2).
As another preferred mode, in the step (4), after the live video broadcast is finished, the scores of each video segment in the live video broadcast process are recorded as g1 to gn respectively, and then the total average score g is calculated by dividing the total number of the scores; and after the number which is scored to be 0 in the total number of the scores is removed, obtaining a new total number of the scores, and then calculating the average score.
The invention has the beneficial effects that: the effective live broadcast duration monitoring can pay salaries by the parameter on one hand, and then can standardize live broadcast of the show, so that the anchor shows own appearance as much as possible, viewers have better experience, and warm prompts can be sent to the anchor; it can be known that in the video live broadcast, the visual effect in each time period has a total score, which is used to evaluate the overall effect of the whole video live broadcast.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
fig. 2 is a flow chart of another method of the present invention.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
In the embodiment shown in fig. 1, a method for live video monitoring and specification specifically includes the following steps:
(1) after the video live broadcast is started, starting picture acquisition at regular time; after the live video broadcast is started, the mobile device acquires video stream data, and after the live video broadcast is started, a timing task is started, namely video data of a short time T2 is acquired after a period of time T1 (for example, T1 is 8s, T2 is 2s, and a certain time is needed because living body detection needs the face shaking condition for judgment);
(2) carrying out AI face recognition and living body detection on the collected video data; performing AI face recognition and living body detection on the video data acquired in the step (1), and recording the number S of successful faces and the number F of failed faces (if the face is located at a certain position in the center of a screen, the face is determined to be successful, so that the watching effect is better);
the video data collected in the previous step are transmitted to AI face recognition and living body detection, in order to have better video live broadcast watching effect, the whole face needs to be placed in a video picture, and a gap with a certain distance is left at the upper part, the lower part, the left part and the right part, so that the video data can be verified to be passed; taking a certain face position as a full-scale 100-point position (for example, the face is in the middle of the screen, and is spaced by 20% from top to bottom and from left to right), when the face is shifted up and down or shifted left and right, the face is proportionally divided according to the offset, and the more the face is shifted, the more the face is divided; certainly, the score needs to be added with the evaluation of the live body detection, if the live body detection does not pass the process of subtracting the score by a fixed value (because the existing live body detection technology has certain limitation, all the live body detection technologies do not directly position the score of 0), the corresponding score of each section of video is given through the process, and the score is not less than 60, so that the recording is successful; if the score is below 60 points, recording failure;
(3) recording each detection success or detection failure, and carrying out standard prompt on the live video; recording each detection success or detection failure, and calling back the upper layer as long as N detection failures are continuously received, which means that the broadcasting of the anchor in the period of time does not meet the specification, and prompting by adopting a popup window at the early stage; if the anchor broadcast still does not hear the suggestion, the message is pushed to a platform administrator, so that the administrator further verifies and even closes the live broadcast;
as shown in fig. 2, if the score is lower than a certain set score (e.g. 60 points) for N consecutive times (e.g. 12 times, that is, for 2 consecutive minutes), a frame-flicking and warm-up reminder is performed, such as "you are not good at the current position, and please adjust in time to obtain the best effect"; for M (say, 30) consecutive scores (say, 5 minutes) below the set score, sending the live ID and a brief description to the administrator for the administrator to manually manage, where M is greater than N;
(4) calculating the effective duration in the live video broadcast; calculating the effective duration of the live video by a formula, namely the effective duration is S (T1+ T2);
after the video live broadcast is finished, performing complete objective evaluation on the quality of the whole video, recording the scores of each video segment in the video live broadcast process as g 1-gn respectively, and dividing the scores by the total number of the scores to calculate the overall average score g; sometimes, the anchor leaves for some reasons and forgets to close, and under the condition, the overall average score is reduced, so that the new total score number is obtained after the number which is scored as 0 in the total score number is removed, and then the average score is calculated.
After the live broadcast is finished, the method can calculate the effective duration of the live broadcast, and can be convenient for a platform to calculate; the method has the advantages that the constraint of effective duration statistics is realized, the content of live video can be better normalized, and the quality of the content broadcasted by the anchor is improved. Based on the method, the visual effect in each time period in the live video can be known, and a total score is provided for evaluating the overall effect of the whole live video; the anchor of the live video can know the live broadcast effect in real time, and the live broadcast can be better specified due to real-time reminding; and the administrator of the live broadcast platform can also manage the live broadcast of the video in real time after receiving the prompt.
Claims (9)
1. A method for monitoring and standardizing live video is characterized by comprising the following steps:
(1) after the video live broadcast is started, starting picture acquisition at regular time;
(2) carrying out AI face recognition and living body detection on the collected video data;
(3) recording each detection success or detection failure, and carrying out standard prompt on the live video;
(4) and calculating the effective duration in the live video.
2. A method for monitoring and regulating live video broadcast as claimed in claim 1, wherein in step (1), after the live video broadcast is started, the mobile device acquires video stream data, and after the live video broadcast is started, a timing task is started, that is, video data is acquired for a short time T2 after a time T1.
3. The method as claimed in claim 2, wherein in step (2), AI face recognition and live body detection are performed on the video data collected in step (1), and the successful number S and the failed number F are recorded.
4. A method for monitoring and normalizing live video according to claim 3, wherein in the step (2), the specific operation mode is as follows: setting that the whole face needs to be placed in a video picture, and a gap with a certain distance needs to be left at the upper part, the lower part, the left part and the right part, so that the face can be verified to be passed; taking a certain face position as a full score 100 position, and when the face deviates up and down or leftwards and rightwards, the face is proportionally subtracted according to the deviation amount, so that the more the deviation is, the more the division is reduced; certainly, the score needs to be added with the evaluation of live body detection, if the live body detection does not pass the subtraction of the fixed value, the corresponding score of each section of video is given through the step, and the score is not lower than 60 points, so that the recording is successful; if the score is below 60 points, the record fails.
5. A method as claimed in claim 3, wherein in step (3), each detection success or detection failure is recorded, and as long as N detection failures are continuously received, the upper layer is called back, which means that the broadcast of the main broadcast in the period of time does not meet the specification, and a popup window is used for prompting in the early stage.
6. A method as claimed in claim 5, wherein in step (3), if the anchor has no hearing advice, a message is pushed to the platform administrator to let the administrator further verify or even turn off the live broadcast.
7. The method for monitoring and standardizing the live video broadcast as claimed in claim 4, wherein in the step (3), for N consecutive scores lower than a certain set score, a frame-flipping warm reminder is performed; for M continuous scores lower than the set score, the live ID and the simple description are sent to the administrator, and the administrator performs manual management, wherein M is larger than N.
8. A method as claimed in claim 3, 5 or 6, wherein in step (4), the active duration of the live video is calculated by the formula (S) (T1+ T2).
9. The method for monitoring and regulating the live video broadcast according to claim 4 or 7, wherein in the step (4), after the live video broadcast is finished, the scores of each video segment in the live video broadcast process are recorded as g1 to gn respectively, and then the total average score g is calculated by dividing the total number of the scores; and after the number which is scored to be 0 in the total number of the scores is removed, obtaining a new total number of the scores, and then calculating the average score.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911211715.0A CN110868609B (en) | 2019-12-02 | 2019-12-02 | Method for monitoring and standardizing live video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911211715.0A CN110868609B (en) | 2019-12-02 | 2019-12-02 | Method for monitoring and standardizing live video |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110868609A true CN110868609A (en) | 2020-03-06 |
CN110868609B CN110868609B (en) | 2021-08-13 |
Family
ID=69657039
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911211715.0A Active CN110868609B (en) | 2019-12-02 | 2019-12-02 | Method for monitoring and standardizing live video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110868609B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111586432A (en) * | 2020-06-05 | 2020-08-25 | 广州繁星互娱信息科技有限公司 | Method and device for determining air-broadcast live broadcast room, server and storage medium |
CN111683263A (en) * | 2020-06-08 | 2020-09-18 | 腾讯科技(深圳)有限公司 | Live broadcast guiding method, device, equipment and computer readable storage medium |
CN111698529A (en) * | 2020-06-19 | 2020-09-22 | 广州繁星互娱信息科技有限公司 | Live broadcast monitoring method, device, equipment and computer readable storage medium |
CN111787347A (en) * | 2020-07-15 | 2020-10-16 | 广州繁星互娱信息科技有限公司 | Live broadcast time length calculation method, live broadcast display method, device and equipment |
CN113780217A (en) * | 2021-09-16 | 2021-12-10 | 中国平安人寿保险股份有限公司 | Live broadcast auxiliary prompting method and device, computer equipment and storage medium |
CN114466210A (en) * | 2022-01-27 | 2022-05-10 | 广州方硅信息技术有限公司 | Live broadcast quality detection processing method and device, equipment, medium and product thereof |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140357879A1 (en) * | 2011-12-26 | 2014-12-04 | Laboratoires Expanscience | Use of whole soft avocados for preparing avocado oil rich in unsaponifiables |
US20160191995A1 (en) * | 2011-09-30 | 2016-06-30 | Affectiva, Inc. | Image analysis for attendance query evaluation |
CN105872773A (en) * | 2016-06-01 | 2016-08-17 | 北京奇虎科技有限公司 | Video broadcast monitoring method and device |
CN106331695A (en) * | 2016-08-24 | 2017-01-11 | 合肥数酷信息技术有限公司 | Video and audio-based detection and data analysis system |
CN106791900A (en) * | 2016-12-15 | 2017-05-31 | 北京小米移动软件有限公司 | Live recommendation method and device |
CN107992832A (en) * | 2017-12-08 | 2018-05-04 | 阳光暖果(北京)科技发展有限公司 | A kind of face tracking System and method for |
CN109104615A (en) * | 2018-07-10 | 2018-12-28 | 神盾网络安全信息化中心股份有限公司 | A kind of live broadcasting method based on the network information security |
CN109151387A (en) * | 2018-08-27 | 2019-01-04 | 杭州当虹科技股份有限公司 | A kind of dollying head recognition of face low latency solution based on webRTC |
-
2019
- 2019-12-02 CN CN201911211715.0A patent/CN110868609B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160191995A1 (en) * | 2011-09-30 | 2016-06-30 | Affectiva, Inc. | Image analysis for attendance query evaluation |
US20140357879A1 (en) * | 2011-12-26 | 2014-12-04 | Laboratoires Expanscience | Use of whole soft avocados for preparing avocado oil rich in unsaponifiables |
CN105872773A (en) * | 2016-06-01 | 2016-08-17 | 北京奇虎科技有限公司 | Video broadcast monitoring method and device |
CN106331695A (en) * | 2016-08-24 | 2017-01-11 | 合肥数酷信息技术有限公司 | Video and audio-based detection and data analysis system |
CN106791900A (en) * | 2016-12-15 | 2017-05-31 | 北京小米移动软件有限公司 | Live recommendation method and device |
CN107992832A (en) * | 2017-12-08 | 2018-05-04 | 阳光暖果(北京)科技发展有限公司 | A kind of face tracking System and method for |
CN109104615A (en) * | 2018-07-10 | 2018-12-28 | 神盾网络安全信息化中心股份有限公司 | A kind of live broadcasting method based on the network information security |
CN109151387A (en) * | 2018-08-27 | 2019-01-04 | 杭州当虹科技股份有限公司 | A kind of dollying head recognition of face low latency solution based on webRTC |
Non-Patent Citations (1)
Title |
---|
闫艺丹: "我国网络直播道德失范与规范策略研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111586432A (en) * | 2020-06-05 | 2020-08-25 | 广州繁星互娱信息科技有限公司 | Method and device for determining air-broadcast live broadcast room, server and storage medium |
CN111586432B (en) * | 2020-06-05 | 2022-05-17 | 广州繁星互娱信息科技有限公司 | Method and device for determining air-broadcast live broadcast room, server and storage medium |
CN111683263A (en) * | 2020-06-08 | 2020-09-18 | 腾讯科技(深圳)有限公司 | Live broadcast guiding method, device, equipment and computer readable storage medium |
CN111698529A (en) * | 2020-06-19 | 2020-09-22 | 广州繁星互娱信息科技有限公司 | Live broadcast monitoring method, device, equipment and computer readable storage medium |
CN111698529B (en) * | 2020-06-19 | 2022-02-22 | 广州繁星互娱信息科技有限公司 | Live broadcast monitoring method, device, equipment and computer readable storage medium |
CN111787347A (en) * | 2020-07-15 | 2020-10-16 | 广州繁星互娱信息科技有限公司 | Live broadcast time length calculation method, live broadcast display method, device and equipment |
CN113780217A (en) * | 2021-09-16 | 2021-12-10 | 中国平安人寿保险股份有限公司 | Live broadcast auxiliary prompting method and device, computer equipment and storage medium |
CN114466210A (en) * | 2022-01-27 | 2022-05-10 | 广州方硅信息技术有限公司 | Live broadcast quality detection processing method and device, equipment, medium and product thereof |
CN114466210B (en) * | 2022-01-27 | 2024-04-16 | 广州方硅信息技术有限公司 | Live broadcast quality detection processing method and device, equipment and medium thereof |
Also Published As
Publication number | Publication date |
---|---|
CN110868609B (en) | 2021-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110868609B (en) | Method for monitoring and standardizing live video | |
CN101077014B (en) | Methods and apparatus to monitor audio/visual content from various sources | |
CN109377293B (en) | Advertisement putting effect monitoring method and system | |
US7614064B2 (en) | Determining program boundaries through viewing behavior | |
CN108718417B (en) | Generation method, device, server and the storage medium of direct broadcasting room preview icon | |
US8584155B2 (en) | System, method and apparatus for viewer detection and action | |
US9883241B2 (en) | System and method for automatic content recognition and audience measurement for television channels and advertisements | |
KR100946222B1 (en) | Affective television monitoring and control | |
CN105872580B (en) | The recording method and device of live video | |
KR100904331B1 (en) | Device and method for reproducing content such as video information | |
WO2017113741A1 (en) | Face-recognition-based advertisement recommendation method and device | |
JP2003111106A (en) | Apparatus for acquiring degree of concentration and apparatus and system utilizing degree of concentration | |
JP2003052003A (en) | Processing method of video containing baseball game | |
US20120297409A1 (en) | System and method for scalable, high accuracy, sensor and id based audience measurement system based on distributed computing architecture | |
CN109215422A (en) | A kind of system and method for monitoring online course video study | |
CN111010587A (en) | Live broadcast control method, device and system | |
WO2017107464A1 (en) | Video tracking and playing method and apparatus | |
US20190174202A1 (en) | System and method for an interactive live streaming media platform to limited subscribers | |
US20070280635A1 (en) | Method and apparatus capable of adjusting recording time dynamically | |
CN107493501A (en) | A kind of audio-video frequency content filtration system and method | |
CN115734007B (en) | Video editing method, device, medium and video processing system | |
Wilk et al. | The influence of camera shakes, harmful occlusions and camera misalignment on the perceived quality in user generated video | |
US20230360431A1 (en) | Quantifying user engagement with a media item | |
US20220116463A1 (en) | Remote audience participation at live events | |
CN117319758B (en) | Live broadcast method and live broadcast system based on cloud platform |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |