CN105245950B - Video ads supervise broadcasting method and device - Google Patents
Video ads supervise broadcasting method and device Download PDFInfo
- Publication number
- CN105245950B CN105245950B CN201510624774.6A CN201510624774A CN105245950B CN 105245950 B CN105245950 B CN 105245950B CN 201510624774 A CN201510624774 A CN 201510624774A CN 105245950 B CN105245950 B CN 105245950B
- Authority
- CN
- China
- Prior art keywords
- frame
- picture
- pictures
- time period
- cutting
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 59
- 238000012790 confirmation Methods 0.000 claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims description 39
- 230000008859 change Effects 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 238000012806 monitoring device Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 22
- 238000010586 diagram Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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]
- H04N21/40—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
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
- H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
-
- 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention provides a kind of video ads prison broadcasting methods and device, wherein method to include：The video ads data that acquisition electrical screen plays in real time；Video ads data are carried out according to preset interval time to cut frame processing, several is obtained and cuts frame picture, and frame picture is cut to several and is ranked up according to the time point before cutting frame processing；The frame picture of cutting after sequence is grouped according to preset time period, image recognition, the material time section cut corresponding to frame picture after being grouped are carried out to all frame pictures of cutting in every group；Frame picture of cutting in material time section is subjected to image comparison with preset normal pictures, determines whether targeted advertisements play.Video ads prison broadcasting method and device provided by the invention, it can be effectively guaranteed 24 hours and the prison of video ads is broadcast, and pass through the confirmation of material time section, effectively save the analyzing processing required time, it can also accurately judge whether to have broadcasted targeted advertisements simultaneously, reduce cost of labor and time cost.
Description
Technical Field
The invention relates to the field of video advertisements, in particular to a video advertisement monitoring method and a video advertisement monitoring device.
Background
With the development of science and technology and the continuous development of the media industry, the media has greater and greater influence on the daily life of people, so that the rapid development of the media advertisement industry is promoted, and with the continuous development of the advertisement industry, various playing forms such as television advertisements, outdoor advertisements, internet advertisements and the like are developed; since various advertisement playing forms, especially advertisements played on electronic screens, are usually played in a streaming manner, it is difficult for advertisers to determine whether relevant advertisements are played.
In the prior art, monitoring and broadcasting are generally performed through manual inspection, specifically, monitoring personnel need to go to a place to be monitored every day to monitor the broadcasting of a video advertisement, and then statistics is performed to obtain a monitoring report so as to report the monitoring report to an advertiser.
However, in the process of implementing the technical scheme, the inventor finds that the following defects exist in the prior art: monitoring personnel can not track advertisement playing in 24 hours, so whether relevant advertisements are played or not is difficult to judge, and the method of manually collecting and monitoring consumes time and labor and is inaccurate in judgment.
Disclosure of Invention
The invention provides a video advertisement monitoring and broadcasting method and device, which are used for solving the problems that monitoring personnel in a personnel monitoring mode in the prior art cannot track advertisement broadcasting for 24 hours, so that whether relevant advertisements are broadcasted or not is judged very well, and time and labor are consumed and judgment is not accurate through a manual collection and monitoring mode.
One aspect of the present invention is to provide a video advertisement monitoring method, including:
collecting video advertisement data played by an electronic screen in real time;
performing frame cutting processing on the video advertisement data according to preset interval time to obtain a plurality of frame cutting pictures, and sequencing the plurality of frame cutting pictures according to time points before the frame cutting processing;
grouping the sequenced frame cutting pictures according to a preset time period, and carrying out image recognition on all the frame cutting pictures in each group to obtain a key time period corresponding to the grouped frame cutting pictures;
and comparing the frame cutting picture in the key time period with a preset standard picture to determine whether the target advertisement is played.
The video advertisement monitoring and broadcasting method performs image recognition on all the frame-cutting pictures in each group to obtain the key time periods corresponding to the grouped frame-cutting pictures, and specifically includes:
and if the change degrees of the feature points of all the frame-cutting pictures in the grouped group are less than or equal to a first preset threshold, taking the time period corresponding to the group as a key time period.
The video advertisement monitoring method compares the frame-cut picture in the key time period with a preset standard picture to determine whether a target advertisement is played specifically includes:
comparing the characteristic points of all frame-cutting pictures in the key time period with the characteristic points of the standard pictures one by one;
if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is larger than or equal to a second preset threshold value, determining that the target advertisement is played; or,
and if the number of the feature points of the frame cutting picture matched with the number of the feature points of the standard picture is less than a second preset threshold value, determining that the target advertisement is not played.
Before comparing the frame-cut picture in the key time period with a preset standard picture, the video advertisement monitoring method further includes:
and performing frame cutting processing on the standard video data according to preset interval time to obtain the standard frame cutting picture.
Another aspect of the present invention is to provide a video advertisement monitoring device, including:
the video image acquisition module is used for acquiring video advertisement data played by the electronic screen in real time;
the video image frame cutting and sequencing module is used for carrying out frame cutting processing on the video advertisement data according to preset interval time to obtain a plurality of frame cutting pictures and sequencing the plurality of frame cutting pictures according to time points before the frame cutting processing;
the key time period confirmation module is used for grouping the sequenced frame cutting pictures according to a preset time period, and carrying out image identification on all the frame cutting pictures in each group to obtain a key time period corresponding to the grouped frame cutting pictures;
and the picture comparison module is used for carrying out picture comparison on the frame-cutting picture in the key time period and a preset standard picture and determining whether the target advertisement is played.
In the video advertisement monitoring and broadcasting apparatus, the key time period confirmation module is specifically configured to:
and if the change degrees of the feature points of all the frame-cutting pictures in the grouped group are less than or equal to a first preset threshold, taking the time period corresponding to the group as a key time period.
The video advertisement monitoring and broadcasting device as described above, the picture comparison module is further configured to:
comparing the characteristic points of all frame-cutting pictures in the key time period with the characteristic points of the standard pictures one by one;
if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is larger than or equal to a second preset threshold value, determining that the target advertisement is played; or,
and if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is less than a second preset threshold value, determining that the target advertisement is played.
Before the frame-cut picture in the key time period is compared with the preset standard picture, the video advertisement monitoring and playing device further comprises:
and the video image frame cutting processing module is used for carrying out frame cutting processing on the standard video information according to preset interval time to obtain the standard frame cutting picture.
According to the video advertisement monitoring and broadcasting method and device, the video advertisement played by the electronic screen is collected in real time, the frame cutting processing is carried out on the video advertisement, the key time period is judged according to the change degree of all frame cutting picture information in the preset time period, the frame cutting picture in the key time period is compared with the standard picture or video information for analysis and comparison, the monitoring and broadcasting of the video advertisement within 24 hours are effectively guaranteed, the time required by the analysis and processing is effectively saved through the confirmation of the key time period, meanwhile, whether the target advertisement is broadcasted or not can be accurately judged, the efficiency of monitoring and broadcasting the advertisement is effectively improved, the labor cost and the time cost are reduced, and the popularization and the application of the market are facilitated.
Drawings
Fig. 1 is a schematic flow chart illustrating a video advertisement monitoring method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a video advertisement monitoring method according to another embodiment of the present invention;
FIG. 3 is a flowchart illustrating a video advertisement monitoring method according to another embodiment of the present invention;
fig. 4 is a schematic structural diagram of a video advertisement monitoring device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a video advertisement monitoring device according to another embodiment of the present invention.
In the figure:
1. a video image acquisition module; 2. a video image frame cutting and sorting module; 3. a critical time period confirmation module; 4. a picture comparison module; 5. and the video image frame cutting processing module.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Example 1
Fig. 1 is a schematic flow chart of a video advertisement monitoring method according to embodiment 1; referring to fig. 1, the present invention provides a method for monitoring and broadcasting video advertisements, which specifically includes:
s1: collecting video advertisement data played by an electronic screen in real time;
s2: performing frame cutting processing on the video advertisement data according to preset interval time to obtain a plurality of frame cutting pictures, and sequencing the plurality of frame cutting pictures according to time points before the frame cutting processing;
s3: grouping the sequenced frame cutting pictures according to a preset time period, and carrying out image recognition on all the frame cutting pictures in each group to obtain a key time period corresponding to the grouped frame cutting pictures;
s4: and comparing the frame cutting picture in the key time period with a preset standard picture to determine whether the target advertisement is played.
The specific implementation manner of acquiring the video advertisement data played by the electronic screen in real time is not limited, and a person skilled in the art can select the manner of acquiring the video advertisement data according to specific conditions, for example, a video acquisition device (such as a camera, a video recorder and the like) can acquire the video advertisement data played in 24 hours in real time, and then frame-cutting the acquired video advertisement data; in addition, the specific method for frame cutting processing is not limited, and a person skilled in the art can use the frame cutting method in the prior art to cut frames of the video advertisement data, as long as the frame cutting processing of the video advertisement data can be realized, and then a plurality of frame cutting pictures are obtained, which is not described herein again; after the frame cutting, a plurality of frame cutting pictures are obtained, the frame cutting pictures can have time point information corresponding to the pictures before the frame cutting, the plurality of pictures obtained after the frame cutting are sequenced according to the time point information, and then the sequenced pictures are grouped according to a preset time period.
In order to more clearly understand the technical scheme of the invention, the inventor exemplifies the following data: if 240000 cut-frame pictures are obtained after frame cutting processing is performed on video information obtained in 24 hours, assuming that a preset time period is 9s, dividing 25 cut-frame pictures in every 9s into 1 group, then dividing 240000 cut-frame pictures obtained in 24 hours into a plurality of picture groups with 9s time and enough 25 cut-frame pictures, and then analyzing and processing the plurality of cut-frame pictures in each group, namely analyzing and processing the 25 cut-frame pictures in 9s, thereby obtaining whether the time period corresponding to the picture group with 9s time is a key time period, wherein the specific preset time period is set by an advertiser and a video monitor, and a skilled person in the art can set the time period according to the needs of the advertiser and does not need to repeat the setting; after the information of the key time periods is judged, for advertisement video data acquired in real time for 24 hours, a plurality of key time periods inevitably exist, then, frame-cut pictures in the confirmed plurality of key time periods are subjected to image comparison with preset standard pictures one by one, and whether a target advertisement (an advertisement which is mainly required to be played) is played or not is judged according to an image comparison result, wherein a specific method and an implementation mode of the image comparison are not limited, and the technical personnel in the field can set the image comparison at will as long as a judgment result of judging whether the target advertisement is played or not can be achieved, and the description is omitted.
According to the video advertisement monitoring and broadcasting method provided by the invention, the video advertisement played by the electronic screen is collected in real time, then the frame cutting processing is carried out on the video advertisement, the key time period is judged according to the change degree of all frame cutting picture information in the preset time period, then the frame cutting picture in the key time period is compared with the standard picture or the video information for analysis and comparison, the monitoring and broadcasting of the video advertisement within 24 hours are effectively ensured, the time required by the analysis and processing is effectively saved through the confirmation of the key time period, meanwhile, whether the target advertisement is broadcasted or not can be accurately judged, the advertisement monitoring and broadcasting efficiency is effectively improved, the labor cost and the time cost are reduced, and the popularization and the application of the market are facilitated.
Example 2
This embodiment is a supplementary description of the above embodiment, specifically, step 3: grouping the sequenced frame cutting pictures according to a preset time period, and carrying out image recognition on all the frame cutting pictures in each group to obtain a key time period corresponding to the grouped frame cutting pictures; the method specifically comprises the following steps:
if the change degrees of the feature points of all the frame-cutting pictures in the grouped group are less than or equal to a first preset threshold, taking the time period corresponding to the group as a key time period;
wherein, as to the implementation manners and processes of step 1, step 2 and step 4 are the same as those of step 1, the above statements may be specifically referred to, and are not repeated herein; in addition, as for the judgment process of the key time period, the invention mainly judges the change degree of the feature points of all the frame-cut pictures in the grouped group, continues to take the 9s time and 25 frame-cut pictures in the embodiment 1 as a group as an example, compares the 25 frame-cut pictures in the group one by one, if the change degrees of the feature points of the 25 frame-cut pictures are all less than or equal to the first preset threshold, it indicates that the time staying in a certain picture in the period is longer, it is determined that the advertisement frame is important, and therefore, the time period corresponding to the 9s time period is determined as the key time period, if the variation degree of the feature points of all the frame-cutting pictures in the grouped group is greater than the first preset threshold, if the change degree of the advertisement picture in the 9s time is larger, the time slot corresponding to the group is not taken as the key time slot; the specific range of the first preset threshold is not limited, and those skilled in the art can set the threshold according to the needs of the advertiser as long as the information of the key time period can be determined, which is not described herein again.
The key time period information is judged by judging the change degree of the characteristic points of all the cut frame pictures in the grouped back group, so that the efficiency of judging the key time period is effectively increased, the accuracy of judging whether the target advertisement is played or not by comparing the cut frame pictures in the key time period with the preset standard pictures is improved, and the accuracy and the reliability of the method are improved.
Example 3
Fig. 2 is a schematic flow chart of a video advertisement monitoring method, and as can be seen from fig. 2, this embodiment is a supplementary description of the above embodiment, specifically, step 4: comparing the frame-cutting picture in the key time period with a preset standard picture, and determining whether the target advertisement is played specifically comprises:
s41: comparing the characteristic points of all frame-cutting pictures in the key time period with the characteristic points of the standard pictures one by one;
s42: judging whether the number of the feature points of the frame cutting picture matched with the number of the feature points of the standard picture is larger than or equal to a second preset threshold value or not;
s43: if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is larger than or equal to a second preset threshold value, determining that the target advertisement is played; or,
s44: and if the number of the feature points of the frame cutting picture matched with the number of the feature points of the standard picture is less than a second preset threshold value, determining that the target advertisement is not played.
Wherein, for the specific implementation manners and processes of step 1, step 2, and step 3 being the same as those of the steps in embodiments 1 and 2, a person skilled in the art may refer to the description of the implementation manners and processes of the steps in embodiments 1 and 2, and details are not repeated herein; in addition, for step 4, a specific implementation manner of comparing the frame-cut pictures in the key time period with the preset standard pictures is described, and all the frame-cut pictures in the key time period are compared with the standard pictures, wherein the comparison mainly refers to feature points in the pictures, in the judgment process, if the number of the feature points of the frame-cut pictures matched with the feature points of the standard pictures is greater than or equal to a second preset threshold, the frame-cut pictures are matched with the standard pictures, wherein the frame-cut pictures are certain frame-cut pictures in the key time period, that is, when the standard pictures are matched with certain frame-cut pictures in the key time period, the conclusion that the target advertisement is played can be obtained, if the number of the feature points of the frame-cut pictures matched with the feature points of the standard pictures is less than the second preset threshold, all the frame-cutting pictures in the key time period are not matched with the standard pictures, wherein the frame-cutting pictures are all the frame-cutting pictures in the key time period, namely when the standard pictures are compared with all the frame-cutting pictures in the key time period and are not matched, the conclusion that the target advertisement is not played can be obtained; in addition, the specific range of the second preset threshold is not limited, and those skilled in the art can arbitrarily set the second preset threshold according to the needs of the advertiser, which is not described herein again.
The method for judging whether the target advertisement is played or not by comparing the characteristic points of all the frame-cutting pictures in the key time period with the characteristic points of the standard pictures one by one and then comparing the matched number of the compared characteristic points with the second preset threshold value effectively ensures the accuracy of judging whether the target advertisement is played or not, in addition, the comparison range is improved.
Example 4
Fig. 3 is a schematic flow chart of a video advertisement monitoring method according to still another embodiment, and referring to fig. 3, this embodiment is a supplementary description of the above embodiment, specifically, in step 4: before comparing the frame-cut picture in the key time period with a preset standard picture, the method further comprises:
and performing frame cutting processing on the standard video data according to preset interval time to obtain the standard frame cutting picture.
Wherein, as to the implementation manners and processes of step 1, step 2, step 3, and step 4 are the same as those of the steps in embodiment 1, embodiment 2, and embodiment 3, the above description may be specifically referred to, and details are not repeated herein; in addition, it should be noted that, for the preset standard pictures mentioned in embodiment 1, embodiment 2 and embodiment 3, the advertiser provides standard contrast information of the target advertisement to be played, where the standard contrast information includes standard picture information and standard video information, and when the advertiser provides the standard picture information, which is the case in embodiment 1, embodiment 2 and embodiment 3, it can be determined whether the target advertisement is played by the solutions in embodiment 1, embodiment 2 and embodiment 3.
When the advertiser provides video information, which is the case of the present embodiment, frame cutting processing needs to be performed on the standard video information provided by the advertiser, so as to obtain standard frame cutting picture information corresponding to the standard video information, and then the standard frame cutting picture information is compared with the frame cutting picture information in the key time period, and the specific comparison process may refer to the description in embodiment 3 and is not repeated again.
Specifically, the skilled person can, but not limited to, the following ways, one of which is: when the target advertisement to be played provided by the advertiser has strong pertinence, that is, the video playing time of the provided standard video advertisement information is short and temporary, wherein specific short judgment criteria are different, a person skilled in the art can set the time according to the requirement of the advertiser, if the short time can be set within 5 minutes or within 10 minutes, then all frame-cutting pictures obtained after the standard video frame-cutting processing can be directly used as standard frame-cutting pictures, then all the standard frame-cutting pictures are compared with the frame-cutting pictures in the key time period one by one, and the specific comparison process can refer to the statement contents and is not repeated again.
In another case, when the target advertisement to be played provided by the advertiser has no strong pertinence, that is, the video playing time of the provided standard video advertisement information is long, corresponding to the above exemplary time data, for example, the video playing time exceeding 5 minutes or 10 minutes can be calculated as the range of the video playing time being long, in such a case, after the video advertisement is subjected to frame cutting processing according to the preset interval time, the corresponding time points before the frame cutting processing can be installed on a plurality of obtained frame cutting pictures for sorting, then the sorted frame cutting pictures are grouped according to a preset time period, all the frame cutting pictures in each group are subjected to image recognition to obtain the key time period corresponding to the grouped frame cutting pictures, then all the standard frame cutting pictures in the key period are compared with the frame cutting pictures one by one to obtain the conclusion whether the target advertisement is played or not, the above confirmation of the key time period and the comparison process between the standard frame-cut picture and the frame-cut picture are similar to the confirmation process and the comparison process between step 3 and step 4 in embodiments 2 and 3, and the specific processes may refer to the above description and are not described herein again.
When the standard advertisement contrast information provided by the advertiser is the video advertisement information, the video advertisement information can be subjected to frame cutting processing to obtain the standard frame cutting picture information, and then the standard frame cutting picture information is compared with the frame cutting picture information to obtain the conclusion whether the target advertisement is played.
Example 5
FIG. 4 is a schematic structural diagram of a video advertisement monitoring device; referring to fig. 4, according to another aspect of the present invention, there is provided a video advertisement monitoring apparatus, including:
the video image acquisition module 1 is used for acquiring video advertisement data played by the electronic screen in real time;
the video image frame cutting and sorting module 2 is used for performing frame cutting processing on the video advertisement data according to preset interval time to obtain a plurality of frame cutting pictures and sorting the plurality of frame cutting pictures according to time points before the frame cutting processing;
the key time period confirmation module 3 is used for grouping the sequenced frame cutting pictures according to a preset time period, and carrying out image recognition on all the frame cutting pictures in each group to obtain a key time period corresponding to the grouped frame cutting pictures;
and the picture comparison module 4 is used for performing picture comparison on the frame-cut picture in the key time period and a preset standard picture and determining whether the target advertisement is played.
The implementation manner of acquiring the video advertisement data in real time by the video image acquisition module 1 is not particularly limited, the video advertisement data may be acquired by a camera or a video recorder, or the video advertisement may be acquired by other manners, and a person skilled in the art may set the acquisition manner according to design requirements as long as the function of acquiring the video advertisement data in real time can be realized, and details are not repeated herein; in addition, the specific mode of performing frame cutting processing on the video advertisement data through the video image frame cutting sequencing module 2 is not limited, and a person skilled in the art can perform frame cutting on the video advertisement data by using a frame cutting method in the prior art as long as the frame cutting processing on the video advertisement data can be realized to obtain a plurality of frame cutting pictures; in addition, after the frame cutting processing, the video image frame cutting ordering module 2 also orders the plurality of frame cutting pictures after the frame cutting processing, wherein the plurality of frame cutting pictures are attached with corresponding time point information before the frame cutting processing, so that the video image frame cutting ordering module 2 can realize the action of ordering the plurality of frame cutting pictures by ordering the time point information; then, grouping the sequenced frame cutting pictures according to a preset time period through a key time period confirmation module 3, analyzing and processing the change degrees of all the frame cutting pictures in the grouping, and judging key time period information; the specific determination process may refer to the specific description in embodiment 1, which is not described herein again; after the confirmation is performed by the key time period confirmation module 3, a plurality of pieces of key time period information may exist, then the image comparison module 4 performs image comparison on the frame-cut images in the confirmed key time periods with a preset standard image one by one, and determines whether a target advertisement (an advertisement which is mainly requested to be played) is played according to an image comparison result, wherein a specific method and an implementation manner of the image comparison are not limited, and a person skilled in the art can set the image comparison at will as long as a determination result of determining whether the target advertisement is played can be achieved, and further description is omitted.
The video advertisement monitoring and broadcasting device provided by the invention collects the video advertisement played by an electronic screen in real time through the video image collecting module 1, then carries out frame cutting and sequencing processing on the video advertisement through the video image frame cutting and sequencing module 2, judges the key time period through the change degree of all frame cutting picture information in the preset time period through the key time period confirmation module 3, finally analyzes and compares the frame cutting picture in the comparison key time period with the standard picture or the video information through the picture comparison module 4, effectively ensures the monitoring and broadcasting of the video advertisement within 24 hours, effectively saves the time required by the analysis and processing through the confirmation of the key time period, and simultaneously can accurately judge whether the target advertisement is broadcasted or not, effectively improves the efficiency of advertisement monitoring and broadcasting, reduces the labor cost and the time cost, and further ensures the stable reliability of the device, and the market competitiveness of the device is improved, and the popularization and the application of the market are facilitated.
Example 6
This embodiment is a further supplementary description of embodiment 5, specifically, the critical time period confirmation module 3 is specifically configured to:
and if the change degrees of the feature points of all the frame-cutting pictures in the grouped group are less than or equal to a first preset threshold, taking the time period corresponding to the group as a key time period.
The key time period confirmation module 3 judges the key time period by comparing the feature point variation degrees of all the frame-cut pictures in each group after grouping with the first preset threshold value, so that the accuracy and the judgment efficiency of the judgment of the key time period are effectively improved, wherein the specific range of the first preset threshold value is not limited, and the technical personnel in the field can set the key time period according to the requirements or experiences of advertisers, and the detailed description is omitted herein; in addition, the judgment standard of the variation degree of the feature points of all the cut pictures in each group is not specifically limited, and the skilled person can set the variation degree according to the specific actual situation; in addition, the process of how to perform the analysis and judgment is the same as that in embodiment 2, and specific reference may be made to the description in embodiment 2, which is not repeated herein.
The key time period information is judged by judging the change degree of the characteristic points of all the cut frame pictures in the grouped back group through the key time period confirmation module 3, the efficiency of judging the key time period is effectively improved, the accuracy of judging whether the target advertisement is played or not by comparing the cut frame pictures in the key time period with the preset standard pictures is improved, the accuracy and the reliability of using the device are improved, and the accuracy and the reliability of analyzing and judging results are ensured.
Example 7
This embodiment is a further supplementary description of the above embodiment, specifically, the picture comparison module 4 is further configured to:
comparing the characteristic points of all frame-cutting pictures in the key time period with the characteristic points of the standard pictures one by one;
the judged data are as follows: whether the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is larger than or equal to a second preset threshold value or not is judged;
if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is larger than or equal to a second preset threshold value, determining that the target advertisement is played; or,
and if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is less than a second preset threshold value, determining that the target advertisement is played.
The above process illustrates an implementation manner of performing image comparison on the frame-cut picture in the key time period and the preset standard picture by using the picture comparison module 4, and comparing all the frame-cut pictures in the key time period with the standard picture, where the comparison mainly refers to the feature points in the pictures, and the specific analysis and determination process through the feature points is the same as the specific analysis process in embodiment 3 in the present application, and reference may be made to the description in embodiment 3, and details are not repeated herein; in addition, the specific range of the second preset threshold is not limited, and those skilled in the art can arbitrarily set the second preset threshold according to the needs of the advertiser, which is not described herein again.
The method for judging whether the target advertisement is played or not through comparing the characteristic points of all the cut frame pictures in the key time period with the characteristic points of the standard pictures one by one through the picture comparison module 4 and then comparing the matched number of the compared characteristic points with the second preset threshold value effectively ensures the accuracy of judging whether the target advertisement is played or not, in addition, the comparison range is improved.
Example 8
As can be seen from fig. 5, the structural schematic diagram of a video advertisement monitoring and playing device according to yet another embodiment of fig. 5 is a specific supplementary description of the above embodiment, specifically, before performing image comparison between a frame cut picture in the key time period and a preset standard picture, the structural schematic diagram further includes:
and the video image frame cutting processing module 5 is used for performing frame cutting processing on the standard video information according to preset interval time to obtain the standard frame cutting picture.
It should be noted that, for the preset standard pictures mentioned in embodiment 5, embodiment 6 and embodiment 7, which are provided by the advertiser, that is, the advertiser provides standard contrast information of the target advertisement to be played, where the standard contrast information includes standard picture information and standard video information, when the advertiser provides the standard picture information, which is the case mentioned in embodiment 5, embodiment 6 and embodiment 7, it can be determined whether the target advertisement is played by the solutions in embodiment 5, embodiment 6 and embodiment 7.
When the advertiser provides video information, which is the case of the present embodiment, frame cutting processing needs to be performed on the standard video information provided by the advertiser, so as to obtain standard frame cutting picture information corresponding to the standard video information, and then the standard frame cutting picture information is compared with the frame cutting picture information in the key time period, and the specific comparison process may refer to the description in embodiment 7 and is not repeated again.
In addition, when the standard video advertisement provided by the advertiser has different durations, the video image frame-cutting processing module 5 can also have different detailed functional functions according to specific actual conditions.
Specifically, the inventors have exemplified the following two cases, one of which is: when the target advertisement to be played provided by the advertiser has strong pertinence, that is, the video playing time of the provided standard video advertisement information is short and temporary, wherein specific short judgment criteria are different, a person skilled in the art can set the time according to the requirement of the advertiser, if the short time can be set within 5 minutes or within 10 minutes, then all frame-cut pictures obtained after the standard video frame-cut processing module 5 performs frame-cut processing on the standard video can be directly used as standard frame-cut pictures, then all the standard frame-cut pictures are compared with the frame-cut pictures in the key time period one by one, and the specific comparison process can refer to the statement contents and is not repeated again.
In another case, when the target advertisement to be played provided by the advertiser is not highly targeted, that is, the video playing time of the provided standard video advertisement information is long, corresponding to the above exemplary time data, for example, the video playing time exceeding 5 minutes or 10 minutes can be calculated as a range of the video playing time being long, in such a case, after the video advertisement is subjected to frame cutting processing according to the preset interval time by the video image frame cutting processing module 5, the obtained plurality of frame cutting pictures can be arranged and sequenced at the corresponding time points before the frame cutting processing, then the sequenced frame cutting pictures can be grouped according to a preset time period by the sequencing submodule included in the video image frame cutting processing module 5, and all the frame cutting pictures in each group are subjected to image recognition by the key time period confirmation submodule included in the video image frame cutting processing module 5, obtaining a key time period corresponding to the grouped frame-cutting pictures, and comparing all standard frame-cutting pictures in the key time period with the frame-cutting pictures one by one to obtain a conclusion whether the target advertisement is played, wherein the processes of confirming the key time period and comparing the standard frame-cutting pictures with the frame-cutting pictures are similar to those of the embodiment 2 and the embodiment 3, and the specific process can refer to the above description and is not repeated herein.
When the standard advertisement contrast information provided by the advertiser is video advertisement information, the video advertisement information can be subjected to frame cutting processing through the video image frame cutting processing module 5 to obtain standard frame cutting picture information, then the standard frame cutting picture information is compared with the frame cutting picture information to obtain a conclusion whether the target advertisement is played, through the video image frame cutting processing module 5, the use range of the device is effectively expanded, the practicability of the device is improved, and the popularization and the application of the market are facilitated.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. A video advertisement monitoring method is characterized by comprising the following steps:
collecting video advertisement data played by an electronic screen in real time;
performing frame cutting processing on the video advertisement data according to preset interval time to obtain a plurality of frame cutting pictures, and sequencing the plurality of frame cutting pictures according to time points before the frame cutting processing;
grouping the sequenced frame cutting pictures according to a preset time period, and carrying out image recognition on all the frame cutting pictures in each group to obtain a key time period corresponding to the grouped frame cutting pictures; if the change degrees of the feature points of all the frame-cutting pictures in the grouped group are less than or equal to a first preset threshold, taking the time period corresponding to the group as a key time period;
and comparing the frame cutting picture in the key time period with a preset standard picture to determine whether the target advertisement is played.
2. The method according to claim 1, wherein the step of comparing the frame-cut picture in the key time period with a preset standard picture to determine whether the target advertisement is played specifically comprises:
comparing the characteristic points of all frame-cutting pictures in the key time period with the characteristic points of the standard pictures one by one;
if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is larger than or equal to a second preset threshold value, determining that the target advertisement is played; or,
and if the number of the feature points of the frame cutting picture matched with the number of the feature points of the standard picture is less than a second preset threshold value, determining that the target advertisement is not played.
3. The method according to claim 1 or 2, wherein before the comparing the frame-cut picture in the key time period with a preset standard picture, the method further comprises:
and performing frame cutting processing on the standard video data according to preset interval time to obtain the standard frame cutting picture.
4. A video advertisement monitoring device, comprising:
the video image acquisition module is used for acquiring video advertisement data played by the electronic screen in real time;
the video image frame cutting and sequencing module is used for carrying out frame cutting processing on the video advertisement data according to preset interval time to obtain a plurality of frame cutting pictures and sequencing the plurality of frame cutting pictures according to time points before the frame cutting processing;
the key time period confirmation module is used for grouping the sequenced frame cutting pictures according to a preset time period, and carrying out image identification on all the frame cutting pictures in each group to obtain a key time period corresponding to the grouped frame cutting pictures;
the picture comparison module is used for carrying out picture comparison on the frame-cutting picture in the key time period and a preset standard picture and determining whether the target advertisement is played or not;
the critical time period confirmation module is specifically configured to:
and if the change degrees of the feature points of all the frame-cutting pictures in the grouped group are less than or equal to a first preset threshold, taking the time period corresponding to the group as a key time period.
5. The apparatus of claim 4, wherein the picture comparison module is further configured to:
comparing the characteristic points of all frame-cutting pictures in the key time period with the characteristic points of the standard pictures one by one;
if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is larger than or equal to a second preset threshold value, determining that the target advertisement is played; or,
and if the number of the feature points of the frame cutting picture matched with the feature points of the standard picture is less than a second preset threshold value, determining that the target advertisement is played.
6. The apparatus for monitoring and playing video advertisements according to claim 4 or 5, further comprising, before the image comparison between the cut-frame picture in the key time period and a preset standard picture:
and the video image frame cutting processing module is used for carrying out frame cutting processing on the standard video information according to preset interval time to obtain the standard frame cutting picture.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510624774.6A CN105245950B (en) | 2015-09-25 | 2015-09-25 | Video ads supervise broadcasting method and device |
| TW105102764A TWI574556B (en) | 2015-09-25 | 2016-01-29 | Method and device for monitoring video advertisement displaying |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510624774.6A CN105245950B (en) | 2015-09-25 | 2015-09-25 | Video ads supervise broadcasting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105245950A CN105245950A (en) | 2016-01-13 |
| CN105245950B true CN105245950B (en) | 2018-09-14 |
Family
ID=55043389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510624774.6A Active CN105245950B (en) | 2015-09-25 | 2015-09-25 | Video ads supervise broadcasting method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105245950B (en) |
| TW (1) | TWI574556B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106937130B (en) * | 2017-03-14 | 2019-12-03 | 引力互动科技（武汉）有限公司 | A kind of system and method for launching advertisement in net cast |
| CN107770490A (en) * | 2017-09-30 | 2018-03-06 | 广东博媒广告传播有限公司 | A kind of LED advertisements identification monitoring system |
| CN111275468A (en) * | 2018-12-04 | 2020-06-12 | 山东快发网络科技有限公司 | Advertisement putting condition monitoring method, shooting server and shooting equipment |
| CN110264235A (en) * | 2019-05-07 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Advertisement detecting method, system, device and electronic equipment |
| CN110234022A (en) * | 2019-05-30 | 2019-09-13 | 阿里巴巴集团控股有限公司 | A kind of video prison broadcasting method, device, system and equipment |
| US10944493B2 (en) | 2019-05-30 | 2021-03-09 | Advanced New Technologies Co., Ltd. | Monitoring video broadcasts |
| CN110337029A (en) * | 2019-07-10 | 2019-10-15 | 秒针信息技术有限公司 | A kind of information prison broadcasting method and device playing form based on electronic equipment |
| CN112416275A (en) * | 2019-08-23 | 2021-02-26 | 陕西坤同半导体科技有限公司 | Display screen detection system and method |
| CN111263108A (en) * | 2019-12-20 | 2020-06-09 | 中译语通文娱科技(青岛)有限公司 | Intelligent production video monitoring method |
| CN111768235B (en) * | 2020-06-29 | 2024-10-22 | 京东科技控股股份有限公司 | Monitoring method, device, equipment and storage medium |
| CN112291606B (en) * | 2020-10-30 | 2022-10-11 | 成都新潮传媒集团有限公司 | Advertisement monitoring method, advertisement monitoring device and computer readable storage medium |
| CN113572901B (en) * | 2021-07-30 | 2023-11-14 | 联通沃音乐文化有限公司 | Method for detecting video color bell playing effect in real time |
| CN114979691B (en) * | 2022-05-23 | 2023-07-28 | 上海影谱科技有限公司 | Statistical analysis method and system for advertisement of retransmission rights of sports event |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100669896B1 (en) * | 1999-11-10 | 2007-01-18 | 톰슨 라이센싱 | Fading feature for a dvd recorder |
| TWM315388U (en) * | 2006-11-17 | 2007-07-11 | Taiwan Video System Co Ltd | Advertisement broadcasting and monitoring system |
| US8326043B2 (en) * | 2007-04-13 | 2012-12-04 | Ipharro Media Gmbh | Video detection system and methods |
| CN101241552B (en) * | 2008-01-24 | 2010-08-11 | 北京六维世纪网络技术有限公司 | Image characteristic recognition method and device |
| CN101339662B (en) * | 2008-08-13 | 2011-07-20 | 北京六维世纪网络技术有限公司 | Method and device for creating video frequency feature data |
| WO2010087125A1 (en) * | 2009-01-29 | 2010-08-05 | 日本電気株式会社 | Time segment representative feature vector generation device |
| CN103139657B (en) * | 2013-02-04 | 2016-04-20 | 青岛海信传媒网络技术有限公司 | The verification method of the ad content of advertisement machine management system, advertisement machine and broadcasting thereof |
| CN103237233B (en) * | 2013-03-28 | 2017-01-25 | 深圳Tcl新技术有限公司 | Rapid detection method and system for television commercials |
| CN103605991A (en) * | 2013-10-28 | 2014-02-26 | 复旦大学 | Automatic video advertisement detection method |
| CN103731634B (en) * | 2013-12-04 | 2017-02-15 | 西安诺瓦电子科技有限公司 | Media monitoring method and media monitoring system |
| CN104394463B (en) * | 2014-11-28 | 2018-09-18 | 北京国双科技有限公司 | The monitoring method and device that advertisement plays |
-
2015
- 2015-09-25 CN CN201510624774.6A patent/CN105245950B/en active Active
-
2016
- 2016-01-29 TW TW105102764A patent/TWI574556B/en active
Also Published As
| Publication number | Publication date |
|---|---|
| TWI574556B (en) | 2017-03-11 |
| CN105245950A (en) | 2016-01-13 |
| TW201713120A (en) | 2017-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105245950B (en) | Video ads supervise broadcasting method and device | |
| CN109377293B (en) | Advertisement putting effect monitoring method and system | |
| Covell et al. | Advertisement detection and replacement using acoustic and visual repetition | |
| CN106992974B (en) | Live video information monitoring method, device and equipment | |
| CN103873852A (en) | Multi-mode parallel video quality fault detection method and device | |
| CN105872760A (en) | Video play monitoring method and device | |
| CN104394433A (en) | Method and device for detecting play times of multimedia file in television channel | |
| CN103763585A (en) | User characteristic information obtaining method and device and terminal device | |
| EP3171593A1 (en) | Testing system, testing method, computer program product, and non-transitory computer readable data carrier | |
| CN102469350A (en) | Method, device and system for advertisement statistics | |
| CN112583642B (en) | Abnormality detection method, abnormality detection model, electronic device, and computer-readable storage medium | |
| CN105354042A (en) | Application installation processing method and apparatus | |
| CN107122773A (en) | A kind of video commercial detection method, device and equipment | |
| EP2122609B1 (en) | Research data gathering | |
| EP3920541A1 (en) | Method for obtaining television rating points for television channels | |
| CN111369792B (en) | Traffic incident analysis method and device and electronic equipment | |
| US8988219B2 (en) | Alert system based on camera identification | |
| CN110602481B (en) | Video quality detection method and device in video monitoring system | |
| CN103916705A (en) | Method and device for achieving mosaic navigation at electronic terminal | |
| CN110633680A (en) | Video-based people number abnormity detection method | |
| US10136185B2 (en) | System and method for detecting unknown TV commercials from a live TV stream | |
| Ramires et al. | An audio-only method for advertisement detection in broadcast television content | |
| CN111355948B (en) | Method for performing an operation status check of a camera and camera system | |
| CN116133031A (en) | Building network quality assessment method, device, electronic equipment and medium | |
| CN113992984A (en) | Elevator advertisement monitoring and broadcasting method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100041 Beijing, Shijingshan District Xing Xing street, building 30, room 3, building 9, room 9014 Applicant after: Jing Shuo Technology (Beijing) Limited by Share Ltd Address before: 100010 Beijing city Dongcheng District bamboo rod alley No. 1 9 1007 Applicant before: JINGSHUO CENTURY TECHNOLOGY (BEIJING) CO., LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201223 Address after: Floor 29, 30, 31, 32, No. 701, Yunjin Road, Xuhui District, Shanghai, 200030 Patentee after: Shanghai minglue artificial intelligence (Group) Co.,Ltd. Address before: Room 9014, 9 / F, building 3, yard 30, Shixing street, Shijingshan District, Beijing 100041 Patentee before: ADMASTER TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| TR01 | Transfer of patent right |