CN107959863B - Video auditing method and system - Google Patents
Video auditing method and system Download PDFInfo
- Publication number
- CN107959863B CN107959863B CN201610898195.5A CN201610898195A CN107959863B CN 107959863 B CN107959863 B CN 107959863B CN 201610898195 A CN201610898195 A CN 201610898195A CN 107959863 B CN107959863 B CN 107959863B
- Authority
- CN
- China
- Prior art keywords
- video
- screenshot
- original video
- picture
- combined
- 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
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
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
-
- 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
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
-
- 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
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2541—Rights Management
-
- 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, rendering scenes according to MPEG-4 scene graphs
-
- 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
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/462—Content or additional data management, e.g. creating a master electronic program guide from data received from the Internet and a Head-end, controlling the complexity of a video stream by scaling the resolution or bit-rate based on the client capabilities
- H04N21/4627—Rights management associated to the content
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Television Signal Processing For Recording (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a video auditing method and a system, which comprises the following steps: s101, intercepting a video to be audited: obtaining a plurality of original video screenshots or a plurality of original video clips; s102, preprocessing an original video screenshot: obtaining at least one static screenshot combination picture; or obtaining at least one dynamic screenshot combined dynamic image; s103, multi-person and/or multi-stage auditing: outputting the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip for the auditor to audit; the auditor comprises: the method comprises the following steps of automatically uploading the video, watching the video and performing full-time auditor on a website. According to the invention, the content of the video can be audited without completely playing the video to be audited, and for the same video to be audited, a multi-person and/or multi-stage auditing mode is adopted, so that the auditing efficiency is high, the auditing reliability is strong, and the auditing labor intensity is low.
Description
Technical Field
The invention relates to the technical field of video processing, in particular to a video auditing method and a video auditing system. The video includes but is not limited to video uploaded by the user himself.
Background
With the prosperous development of the internet technology, more and more videos are available on the network, and the fishes and dragons are mixed, especially videos uploaded by users. Many websites now support and allow users to upload videos and show them to the public, and the videos uploaded by users themselves may have the following problems: copyright issues (e.g., movie clips uploaded by the user themselves), political, yellow, or severe violence issues, etc., are related, and these videos are often called objectionable. In order to filter bad videos, the content of the videos needs to be reviewed (video review for short).
Taking a video uploaded by a user as an example, in the prior art, the video auditing method mainly adopts the following modes: the auditors play the videos to be audited (videos uploaded by users) one by one from beginning to end, and the auditors audit the videos to be audited in the process of playing the videos to be audited. The auditing mode of the complete playing causes low auditing efficiency, large work pressure of auditors and high labor intensity.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a video auditing method and a video auditing system, which have the advantages of high auditing efficiency, high auditing reliability and low auditing labor intensity, and can realize the auditing of the content of a video without completely playing the video to be audited.
In order to achieve the above purposes, the technical scheme adopted by the invention is as follows:
a video auditing method is characterized by comprising the following steps:
s101, intercepting a video to be audited: acquiring a video file corresponding to a video to be audited, and intercepting the video file to obtain a plurality of original video screenshots or a plurality of original video clips;
s102, preprocessing an original video screenshot:
splicing the plurality of original video screenshots obtained in the step S101 to obtain at least one static screenshot combined picture, wherein the picture refers to a static picture;
or;
splicing the plurality of original video screenshots obtained in the step S101 to obtain at least one dynamic screenshot combined moving picture, wherein the moving picture refers to a dynamic picture;
s103, multi-person and/or multi-stage auditing:
outputting the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip for the auditor to audit;
the auditor comprises: the method comprises the following steps of automatically uploading the video, watching the video and performing full-time auditor on a website.
On the basis of the technical scheme, when the video file is intercepted, a plurality of original video screenshots or a plurality of original video clips are intercepted and obtained according to the total duration of the video file and the intercepted interval duration;
the interval duration is a fixed value or a random value or a user-defined value;
the duration of the original video clip is a fixed value or a random value or a user-defined value;
or:
when a video file is intercepted, intercepting and obtaining a plurality of original video screenshots or a plurality of original video clips according to the number of the original video screenshots or original video clips to be obtained;
the number of the original video screenshots or original video clips is a fixed value or a random value or a user-defined value;
the duration of the original video clip is a fixed value or a random value or a user-defined value.
On the basis of the above technical scheme, in step S102, a plurality of original video screenshots are spliced to obtain a static screenshot combined picture of m x n,
the value of m x n is equal to or greater than the total number of original video shots;
or:
in step S102, a plurality of original video screenshots are spliced to obtain more than two static screenshot combined pictures of m x n,
the value of m x n is less than the total number of original video screenshots;
or:
in step S102, the original video screenshots obtained in step S101 are spliced to obtain a dynamic screenshot combined moving picture, where the screenshot combined moving picture includes all the original video screenshots obtained in step S101;
or:
in step S102, the original video screenshots obtained in step S101 are spliced to obtain two or more dynamic screenshot combined moving pictures, where each screenshot combined moving picture includes a part of the original video screenshots obtained in step S101.
On the basis of the technical scheme, when the auditor is a user who uploads the video or watches the video by himself,
in step S102, before the original video screenshots are spliced, each original video screenshot is preprocessed, so that an auditor cannot see the whole image or see the whole image clearly.
On the basis of the technical scheme, when the auditor is a user who uploads the video or watches the video by himself,
in step S102, before splicing the original video screenshots, each original video screenshot shields a part of the area,
the shielding area occupies 1/5-2/3 of the whole figure.
On the basis of the technical scheme, the area occupied by the shielding is continuous or discontinuous.
On the basis of the technical scheme, the pattern used for shielding is a regular geometric shape or an unqualified pattern.
On the basis of the technical scheme, when the auditor is a user who uploads the video or watches the video by himself,
in step S102, before splicing the original video screenshots, each original video screenshot is subjected to fuzzification processing of a partial area,
the blurring area is 1/5-1/2 of the whole figure.
On the basis of the technical scheme, when the auditor is a user who uploads the video by himself,
when the video is uploaded, the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip are/is output for being audited;
when the auditor is a user watching a video,
when the user waits for video caching or advertisement playing, outputting a screenshot combined picture and/or a screenshot combined moving picture and/or an original video clip for the user to check;
when the auditor is a website full-time auditor, at least the user who uploads the video or watches the video automatically audits the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip which are/is reported by the reporting button.
On the basis of the technical scheme, the screenshot combined picture, the screenshot combined moving picture and the original video clip need to be audited by more than two users who upload videos and watch videos automatically or by more than two website full-time auditors, and can pass the auditing program.
On the basis of the technical scheme, in the step S101, after a plurality of original video screenshots are obtained, image information is extracted through cutting, DCT is calculated to separate the pictures into a collection of fractions, the fingerprints of the pictures are extracted, and similar pictures are kicked off through an edit distance algorithm.
A video auditing system for use in the above method, comprising:
a video screenshot module 10, configured to capture a video file to obtain an original video screenshot; or obtaining an original video clip;
a screenshot processing module 20, configured to splice multiple original video screenshots obtained in the screenshot process into a screenshot combined picture; or splicing the images into a screenshot combined image;
and the video auditing module 30 is used for outputting the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip for auditing by auditing personnel.
On the basis of the above technical solution, the video capture module 10 may capture a video according to parameters such as capture time interval or frame number.
On the basis of the above technical solution, the video capture module 10 includes:
a first capture unit 101, configured to capture a video file according to capture time intervals;
a second capture unit 102, configured to capture a screenshot of the video file according to the frame number of the video file;
a time interval selection unit 103, configured to analyze the video file category and select a corresponding screenshot time interval;
and a size adjusting unit 104, configured to adjust the original video screenshot to a corresponding size according to the screenshot size.
The video auditing method and the system can realize the auditing of the content of the video without completely playing the video to be audited, adopt a multi-person and/or multi-stage auditing mode for the same video to be audited, and have high auditing efficiency, strong auditing reliability and low auditing labor intensity.
The product corresponding to the system of the embodiment of the invention can be an independent video auditing system, and can also form a video auditing system in a plug-in mode on the basis of the existing video player.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flowchart of a video auditing method according to an embodiment of the present invention;
FIG. 2 is a first block diagram of a video review system according to an embodiment of the invention;
FIG. 3 is a block diagram of a video capture module according to an embodiment of the present invention;
fig. 4 is a second block diagram of a video auditing system according to an embodiment of the present invention;
fig. 5 is a diagram of a screenshot processing module according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the video auditing method of the present invention includes the following steps:
s101, intercepting a video to be audited: acquiring a video file corresponding to a video to be audited, and intercepting the video file to obtain a plurality of original video screenshots or a plurality of original video clips;
the format of the original video clip is the same as or different from that of the video to be audited; for example: if the format of the video to be audited is mpg, the format of the original video fragment is mpg; for another example: the format of the video to be audited is rmvb, and the formats of all original video segments are uniformly converted into avi;
s102, preprocessing an original video screenshot:
splicing the plurality of original video screenshots obtained in the step S101 to obtain at least one static screenshot combined picture, wherein the picture refers to a static picture, such as a picture in a jpg format;
or;
splicing the plurality of original video screenshots obtained in the step S101 to obtain at least one dynamic screenshot combined dynamic picture, wherein the dynamic picture refers to a dynamic picture, such as a gif format dynamic picture;
s103, multi-person and/or multi-stage auditing:
outputting the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip for the auditor to audit; the screenshot combined picture and the screenshot combined moving picture come from step S102, and the original video clip comes from step S101;
the auditor comprises: the method comprises the following steps of automatically uploading the video, watching the video and performing full-time auditor on a website. Obviously, the auditor may be other persons, but is not limited to these persons, and may be a full-time auditor of a professional company (third-party company) engaged in video auditing, for example.
On the basis of the technical scheme, when the video file is intercepted, a plurality of original video screenshots or a plurality of original video clips are intercepted and obtained according to the total duration of the video file and the intercepted interval duration;
the interval duration is a fixed value or a random value or a user-defined value;
the duration of the original video clip is a fixed value or a random value or a user-defined value.
Example 1: assuming that the total duration of the video file is 112 minutes and the interval duration is 7 minutes (i.e., the video file is captured every 7 minutes), 16 original video screenshots are obtained. Namely: and (5) carrying out screenshot at equal intervals.
Example 2: assuming that the total time length of the video file is 112 minutes, the interval time length is 7 minutes (i.e., intercepting once every 7 minutes), and the time length of the original video clip is 10s, then 16 original video clips are obtained. Namely: equally spaced and equally long video segments.
Example 3: and setting the total time length of the video files to be 5 minutes and the interval time lengths to be 15s, 35s, 75s, 2m, 3m12s and 4m27s respectively, 6 original video screenshots are obtained. Namely: non-equidistant screen shots. The interval duration may be a random value obtained by operation or a user-defined value, in this example, the interval duration represents at which time point the original video screenshot is acquired, and another scheme may also be to express a time difference between two screenshots.
Example 4: assuming that the total duration of the video file is 5 minutes, the interval durations are 35s, 1m13s, 2m21s, 3m, 3m58s and 4m38s, and the durations of the original video segments are 3s, 4s, 3s, 7s, 3s and 5s, 6 original video segments are obtained. Namely: non-equally spaced non-equal time length video clips. The interval duration and the duration of the original video segment can be calculated random values or user-defined values.
In this scheme, the interval duration and the duration of the original video segment may be selected according to different default fixed values of the video type, for example: the self-timer video corresponds to an interval duration of 5s, the movie corresponds to an interval duration of 8s, and the MV corresponds to an interval duration of 10 s.
In the scheme, the interval duration can be determined, and the number of the intercepted original video screenshots and original video clips is related to the total duration of the video file and is not determined.
On the basis of the technical scheme, when a video file is intercepted, a plurality of original video screenshots or a plurality of original video clips are intercepted and obtained according to the number of the original video screenshots or the original video clips to be obtained;
the number of the original video screenshots or original video clips is a fixed value or a random value or a user-defined value;
the duration of the original video clip is a fixed value or a random value or a user-defined value;
furthermore, the interval duration is a fixed value or a random value or a user-defined value or a value obtained through operation.
Example 1: and setting the total time length of the video file to be 72 minutes, wherein 10 original video clips are required to be obtained, and the original video clips are intercepted once every 7.2 minutes when the time length of the original video clips is 6 seconds. Namely: equally spaced and equally long video segments.
Example 2: and setting the total time length of the video file to be 14 minutes, and intercepting the video file once every 1.5 minutes if 9 original video screenshots need to be obtained. Namely: and (5) carrying out screenshot at equal intervals.
Example 3: and setting the total time length of the video file to be 45 minutes, wherein 5 original video clips are required to be obtained, the time lengths of the original video clips are respectively 6s, 4s, 8s, 5s and 4s, and the original video clips are intercepted every 9 minutes. Namely: equally spaced non-isochronous long video segments. The duration of the original video clip can be a random value obtained by operation or a user-defined value.
In the scheme, the number of the original video screenshots or original video clips is determined, the interval duration is not determined, or the interval duration is selected at equal intervals according to the total duration of the video files.
The change of the interception scheme aims to increase the randomness of the interception time point, provide a basis for improving the accuracy of video audit, and avoid a user from maliciously escaping the audit according to the audit rule, for example: legitimate videos are inserted at the review time point, while other non-review time points are bad videos.
Obviously, in order to improve the auditing efficiency, other further measures can be provided: for example, the top 1/5-1/3 content of the video is reviewed with emphasis to reduce the amount of review and ensure the accuracy of the review.
On the basis of the above technical scheme, in step S102, a plurality of original video screenshots are spliced to obtain a static screenshot combined picture of m x n,
the value of m x n is equal to or greater than the total number of original video shots;
m and n represent the number of rows and columns, respectively, of the image included in the combined picture of the screenshot, for example: 3 × 3 represents: the images included in the screenshot combined picture are 3 rows and 3 columns, and at most 9 original video screenshots can be contained in one screenshot combined picture;
or:
in step S102, a plurality of original video screenshots are spliced to obtain more than two static screenshot combined pictures of m x n,
the value of m n is less than the total number of original video shots, obviously in this case the value of the number of combined pictures of m n shots is equal to or greater than the total number of original video shots, for example: 3 × 2 represents: the image included in one screenshot combination picture is 3 rows and 2 columns, and the total number of the screenshot combination picture is 2, and at most 12 original video screenshots can be included in the two screenshot combination pictures.
In the scheme, in order to obtain the screenshot combined picture, the original video screenshot can be reduced, the picture quality of the screenshot combined picture can also be properly compressed, and the method can be implemented according to the prior art.
On the basis of the technical scheme, in step S102, splicing the plurality of original video screenshots obtained in step S101 to obtain a dynamic screenshot combined dynamic image, wherein the screenshot combined dynamic image comprises the plurality of original video screenshots obtained in all steps S101;
or:
in step S102, the original video screenshots obtained in step S101 are spliced to obtain two or more dynamic screenshot combined moving pictures, where each screenshot combined moving picture includes a part of the original video screenshots obtained in step S101.
On the basis of the technical scheme, when the auditor is a user who uploads the video or watches the video by himself,
in step S102, before splicing the original video screenshots, each original video screenshot pre-processes the original video screenshot, so that an auditor cannot see the whole image or see the whole image clearly, that is: and (5) screenshot and mass review preprocessing.
On the basis of the technical scheme, when the auditor is a user who uploads the video or watches the video by himself,
in step S102, before splicing the original video screenshots, each original video screenshot shields a part of the area,
the shielding area accounts for 1/5-2/3 of the whole figure, and more preferably 1/4-1/3 of the whole figure. The lower limit of the occlusion ratio may be smaller, for example 1/6 or smaller, and the upper limit of the occlusion ratio should not be too large, otherwise the accuracy of the audit is affected.
The occlusion regions for each original video shot are the same or different.
On the basis of the technical scheme, the area occupied by the shielding is continuous or discontinuous. For example: when the triangle is adopted for shielding in a diagonal line mode, the occupied shielding area is continuous; for another example: when the grid lines are adopted for shielding, the shielding occupied area is discontinuous.
On the basis of the technical scheme, the pattern used for shielding is a regular geometric shape or an unqualified pattern. For example: star, rectangular, circular, triangular, bar, etc. are regular geometric shapes; for another example: cloud, lightning, snowflake and the like are irregular patterns. For another example: the geographical outline of a province or a country, the coastline, etc. are irregular figures. For another example: the character shape (for example, the shape of the three characters to be checked as the occlusion) is an irregular figure.
On the basis of the technical scheme, when the auditor is a user who uploads the video or watches the video by himself,
in step S102, before splicing the original video screenshots, each original video screenshot is subjected to fuzzification processing of a partial area,
the blurring area is 1/5-1/2 of the whole figure.
The fuzzification processing areas of each original video screenshot are the same or different, and specifically include: the positions of the blurring regions in the figure are the same or different, and the areas of the blurring regions are the same or different.
It should be noted that the fuzzification processing and the shielding of a partial area in the screenshot censoring preprocessing are performed to avoid the influence of a bad picture (a static picture or a dynamic picture referred to be audited by the auditor) on the auditor when the auditor is a user who uploads a video or watches a video, and to avoid malicious acquisition, utilization and propagation of the bad picture by the auditor. Obviously, such image preprocessing methods that do not affect the auditing and are beneficial to the social customs of the public are not just the two aforementioned methods, and both methods belong to the protection scope of the present invention. For example: adding an account number of an uploader as a watermark in the screenshot, and for example: the screenshot is transformed from a color map to a grayscale map.
On the basis of the technical scheme, when the auditor is a user who uploads the video by himself,
and when the video is uploaded, outputting the screenshot combination picture and/or the screenshot combination moving picture and/or the original video clip for the review.
Example 1: the background of the uploading window is a screenshot combined picture, when a user who uploads a video automatically suspects that the picture is a bad picture, a reporting button in the uploading window is clicked, if the user confirms that the picture has no problem, a normal button in the uploading window is clicked, and then a file can be selected and uploaded.
Example 2: and if the picture is confirmed to be not problematic, clicking a normal button in the uploading window, and normally playing the screenshot combined moving picture.
Example 3: and if the video clip is confirmed to be out of order, clicking a normal button in the uploading window to normally play the original video clip.
On the basis of the technical scheme, when the auditor is a user watching the video,
and when the user waits for video caching or advertisement playing, outputting the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip for the user to check.
Example 1: when waiting for video caching, a screen displays a character pattern in the caching, a progress bar is a screenshot combined moving picture, when a user watching a video suspects that the picture is a bad picture, a reporting button in an uploading window is clicked, the screenshot combined moving picture is replaced by other legal pictures, if the user confirms that the picture has no problem, a normal button in the uploading window is clicked, and the screenshot combined moving picture is played normally.
Example 2: before the advertisement is played, the screen displays the combined picture of the screenshot or the original video clip,
when a user watching the video suspects that the picture is a bad picture, clicking a reporting button in the uploading window, and if the picture is confirmed to have no problem, clicking a normal button in the uploading window, and then skipping the advertisement to directly watch the video;
and if the user watching the video suspects that the video segment is illegal, clicking a report button in the uploading window, replacing the original video segment with other legal video segments or pictures or characters, and if the user confirms that the video segment has no problem, clicking a normal button in the uploading window, and then skipping the advertisement to directly watch the video.
On the basis of the technical scheme, when the auditor is a website full-time auditor, at least the audit is carried out on screenshot combined pictures and/or screenshot combined moving pictures and/or original video clips reported by a user who uploads videos or a user watching videos through a reporting button.
In the scheme, the work of a website full-time auditor is not conflicted with the existing work, the website full-time auditor can be fused, the workload can be dispersed through the mass audit process of the user who uploads the video and watches the video, the audit efficiency and the accuracy can be effectively improved, punishment processing can be given to the user who uploads the video and watches the video without responsibility and in disorder, and the reward processing can be given to the user who uploads the video and watches the video with high accuracy and is earnest by the user who uploads the video and watches the user who watches the video with high accuracy and is earnest by the user who uploads the video and watches the video with poor audit.
After the audience review process, the review workload of a website full-time auditor can be greatly reduced, key contents can be audited one by one according to actual needs, the audit omission or the audit error is avoided, and because the video to be audited is not required to be played completely, only the screenshot combined picture and/or the screenshot combined dynamic picture and/or the original video clip are audited, the workload, the working intensity and the working efficiency can be greatly improved.
Furthermore, considering the situation that the user who uploads the video by himself or the user who watches the video may be a minor, when the user who uploads the video by himself or the user who watches the video performs the auditing, whether to accept to receive the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip can be controlled through the parental mode. And if the screenshot combination picture and/or the screenshot combination motion picture and/or the original video clip are not accepted to be received, the screenshot combination picture and/or the screenshot combination motion picture and/or the original video clip are not output to the screenshot combination picture and/or the screenshot combination motion picture and/or the original video clip.
On the basis of the technical scheme, the screenshot combined picture, the screenshot combined moving picture and the original video clip need to be audited by more than two users who upload videos and watch videos automatically or by more than two website full-time auditors, and can pass the auditing program.
Obviously, the more auditors are used in the process of numerous auditions, the more favorable the auditors are for avoiding missing or misaudits, and the more favorable the auditors are for reducing the workload of the website full-time auditors. And users who upload videos by themselves and users who watch videos also become auditors for monitoring the video contents.
On the basis of the above technical solution, in step S101, after obtaining a plurality of original video screenshots, image information is extracted by cutting, a DCT (Discrete Cosine Transform) is calculated to separate a picture into a set of fractions, a fingerprint of the picture is extracted, and a similar picture is kicked off by an edit distance algorithm.
For example: the specific steps of kicking off similar pictures are as follows:
dividing the picture into 8 × 8 parts;
the DCT can be conveniently calculated for each picture compression process, and the compression is recommended to be 32 x 32;
changing the zoomed small picture into a 256-level gray scale image;
calculating a DCT to separate the picture into a set of fractions;
the DCT is scaled down, leaving 8 x 8 in the upper left corner (lowest frequency of these representative pictures);
calculating the average value of all the pixel points after DCT reduction, recording the average value as 1 when the average value is larger than the average value, and otherwise, recording the average value as 0;
combining 64 information bits, wherein the sequence is kept consistent at will, because the pictures are divided into 64 parts, one picture can generate 64 fingerprints, and the 64 fingerprints are sequentially combined into a sequence;
comparing fingerprints: and calculating the editing distance, wherein the larger the editing distance is, the more inconsistent the pictures are, on the contrary, the smaller the editing distance is, the more similar the pictures are, and when the distance is 0, the pictures are completely the same.
For the video auditing method, the invention also provides a video auditing system, as shown in fig. 2-5, the system comprises:
a video screenshot module 10, configured to capture a video file to obtain an original video screenshot; or obtaining an original video clip;
a screenshot processing module 20, configured to splice multiple original video screenshots obtained in the screenshot process into a screenshot combined picture; or splicing the images into a screenshot combined image;
and the video auditing module 30 is used for outputting the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip for auditing by auditing personnel.
The video capture module 10 may capture a video according to parameters such as capture time interval (interval duration) or frame number. Therefore, referring to fig. 3, a structure diagram of a video screenshot module according to an embodiment of the present invention is shown. As shown in fig. 3, the video capture module 10 may include:
a first capture unit 101, configured to capture a video file according to capture time intervals;
a second capture unit 102, configured to capture a screenshot of the video file according to the frame number of the video file;
a time interval selection unit 103, configured to analyze the video file category and select a corresponding screenshot time interval;
and a size adjusting unit 104, configured to adjust the original video screenshot to a corresponding size according to the screenshot size.
The first capture unit 101 may preset a capture time interval, or may have a user entry for receiving the capture time interval set by the user. Under the condition that the user does not set the screenshot time interval, the time interval selection unit 103 analyzes the video file category and selects a corresponding screenshot time interval; the first capturing unit 101 captures a picture according to the capturing time interval selected by the time interval selecting unit 103.
Specifically, the time interval selecting unit 103 may include: a category identification subunit and a time interval selection subunit. And the category identification subunit is used for acquiring label information set for the video file when the video file is uploaded by a user, wherein the label information contains category information of the video file, and the category of the video file is identified according to the content of the label information. And the time interval selection subunit is used for selecting the corresponding screenshot time interval according to the video file type.
The second capture unit 102 may capture a screen according to a preset algorithm according to the frame number of the video file, or receive an instruction of a user from a user entry, and capture a screen according to the frame number of the video file by a method set by the user.
The size adjustment unit 104 may adjust the size of the original video screenshot captured by the first capture unit 101 or the second capture unit 102. The size adjustment unit 104 may preset a screenshot size, or receive a parameter set by the user as the screenshot size through the user portal.
The screenshot processing module 20 can set the number of original video screenshots included in one screenshot combination picture according to actual requirements. For example: when the screen resolution of a user is low, 9 original video screenshots can be spliced into a screenshot combined picture to ensure the definition of the picture; when the screen resolution of the user is high, 20 original video screenshots can be spliced into a screenshot combined picture, so that the auditing efficiency is improved.
Generally, a file of a picture type may be large, so referring to fig. 5, a screenshot processing module 20 of the video auditing system according to the embodiment of the present invention may include:
a screenshot combining unit 201, configured to splice multiple original video screenshots into a screenshot combined picture;
and the picture compression unit 202 is configured to compress the picture quality of the screenshot combined picture.
As a single video auditing system, in order to support various formats of video files, referring to fig. 4, the system according to the embodiment of the present invention further includes: and the video decoding module 40 is configured to analyze a format of the video file and invoke a corresponding decoder to decode the video file.
The video auditing method and system provided by the invention are described in detail above. The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for those skilled in the art, the specific embodiments and the application range may be changed according to the idea of the present invention. In view of the above, the present disclosure should not be construed as limiting the invention.
Those not described in detail in this specification are within the skill of the art.
Claims (11)
1. A video auditing method is characterized by comprising the following steps:
s101, intercepting a video to be audited: acquiring a video file corresponding to a video to be audited, and intercepting the video file to obtain a plurality of original video screenshots or a plurality of original video clips;
s102, preprocessing an original video screenshot:
splicing the plurality of original video screenshots obtained in the step S101 to obtain at least one static screenshot combined picture, wherein the picture refers to a static picture;
or;
splicing the plurality of original video screenshots obtained in the step S101 to obtain at least one dynamic screenshot combined moving picture, wherein the moving picture refers to a dynamic picture;
s103, multi-person and/or multi-stage auditing:
outputting the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip for the auditor to audit;
the auditor comprises: the method comprises the following steps that users who upload videos automatically, users who watch videos and website full-time auditors;
when the auditor is the user who uploads the video or the user who watches the video by himself,
in step S102, before splicing the original video screenshots, preprocessing each original video screenshot to ensure that an auditor cannot see the whole picture or see the whole picture clearly; the method specifically comprises the following steps:
in step S102, before splicing the original video screenshots, each original video screenshot shields a part of the area,
the shielding area accounts for 1/5-2/3 of the whole picture;
alternatively, the first and second electrodes may be,
in step S102, before splicing the original video screenshots, each original video screenshot is subjected to fuzzification processing of a partial area,
the blurring area is 1/5-1/2 of the whole figure.
2. A video auditing method according to claim 1 where: when the video file is intercepted, intercepting and obtaining a plurality of original video screenshots or a plurality of original video clips according to the total duration of the video file and the intercepted interval duration;
the interval duration is a fixed value or a random value or a user-defined value;
the duration of the original video clip is a fixed value or a random value or a user-defined value;
or:
when a video file is intercepted, intercepting and obtaining a plurality of original video screenshots or a plurality of original video clips according to the number of the original video screenshots or original video clips to be obtained;
the number of the original video screenshots or original video clips is a fixed value or a random value or a user-defined value;
the duration of the original video clip is a fixed value or a random value or a user-defined value.
3. A video auditing method according to claim 1 where: in step S102, the original video screenshots are stitched to obtain a static screenshot combination picture of m × n,
the value of m x n is equal to or greater than the total number of original video shots;
or:
in step S102, a plurality of original video screenshots are spliced to obtain more than two static screenshot combined pictures of m x n,
the value of m x n is less than the total number of original video screenshots;
or:
in step S102, the original video screenshots obtained in step S101 are spliced to obtain a dynamic screenshot combined moving picture, where the screenshot combined moving picture includes all the original video screenshots obtained in step S101;
or:
in step S102, the original video screenshots obtained in step S101 are spliced to obtain two or more dynamic screenshot combined moving pictures, where each screenshot combined moving picture includes a part of the original video screenshots obtained in step S101.
4. A video auditing method according to claim 1 where: the area occupied by the occlusion is continuous or discontinuous.
5. A video auditing method according to claim 1 where: the pattern used for shielding is a regular geometric shape or an irregular pattern.
6. A video auditing method according to claim 1 where: when the auditor is the user who uploads the video by himself,
when the video is uploaded, the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip are/is output for being audited;
when the auditor is a user watching a video,
when the user waits for video caching or advertisement playing, outputting a screenshot combined picture and/or a screenshot combined moving picture and/or an original video clip for the user to check;
when the auditor is a website full-time auditor, at least the user who uploads the video or watches the video automatically audits the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip which are/is reported by the reporting button.
7. A video auditing method according to claim 1 where: the screenshot combined picture, the screenshot combined moving picture and the original video clip need to be audited by more than two users who upload videos and watch videos by themselves or by more than two website full-time auditors, and can pass the auditing program.
8. A video auditing method according to claim 1 where: in step S101, after obtaining a plurality of original video screenshots,
dividing the picture into 8 × 8 parts;
the DCT can be conveniently calculated for each picture compression process, and the compression is recommended to be 32 x 32;
changing the zoomed small picture into a 256-level gray scale image;
calculating DCT;
reducing DCT, and reserving 8 x 8 at the upper left corner;
calculating the average value of all the pixel points after DCT reduction, recording the average value as 1 when the average value is larger than the average value, and otherwise, recording the average value as 0;
combining 64 information bits, wherein the sequence is kept consistent at will, because the pictures are divided into 64 parts, one picture can generate 64 fingerprints, and the 64 fingerprints are sequentially combined into a sequence;
comparing fingerprints: and calculating an editing distance, wherein the larger the editing distance is, the more inconsistent the pictures are, otherwise, the smaller the editing distance is, the more similar the pictures are, and when the distance is 0, the description is completely the same, and the similar pictures are kicked off.
9. A video review system for implementing the method of any one of claims 1 to 8, comprising:
the video screenshot module (10) is used for screenshot the video file to obtain an original video screenshot; or obtaining an original video clip;
a screenshot processing module (20) for splicing a plurality of original video screenshots obtained in the screenshot process into a screenshot combined picture; or splicing the images into a screenshot combined image;
and the video auditing module (30) is used for outputting the screenshot combined picture and/or the screenshot combined moving picture and/or the original video clip for auditing by auditing personnel.
10. A video review system according to claim 9, wherein: the video screenshot module (10) can perform screenshot according to parameters such as screenshot time interval or frame number.
11. A video review system according to claim 10, wherein: the video capture module (10) comprises:
the first screenshot unit (101) is used for screenshot the video file according to the screenshot time interval;
the second interception unit (102) is used for carrying out screenshot on the video file according to the frame sequence number of the video file;
a time interval selection unit (103) for analyzing the video file category and selecting a corresponding screenshot time interval;
and the size adjusting unit (104) is used for adjusting the original video screenshot into a corresponding size according to the screenshot size.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610898195.5A CN107959863B (en) | 2016-10-14 | 2016-10-14 | Video auditing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610898195.5A CN107959863B (en) | 2016-10-14 | 2016-10-14 | Video auditing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107959863A CN107959863A (en) | 2018-04-24 |
| CN107959863B true CN107959863B (en) | 2020-04-03 |
Family
ID=61953116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610898195.5A Active CN107959863B (en) | 2016-10-14 | 2016-10-14 | Video auditing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107959863B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110505490A (en) * | 2018-05-18 | 2019-11-26 | 阿里巴巴集团控股有限公司 | Multi-medium data recognition methods and system |
| CN109831697B (en) * | 2018-12-28 | 2021-05-21 | 广州华多网络科技有限公司 | Method and system for detecting violation processing duration |
| CN109803152B (en) * | 2018-12-28 | 2021-05-21 | 广州华多网络科技有限公司 | Violation auditing method and device, electronic equipment and storage medium |
| CN111901608B (en) * | 2020-06-28 | 2023-04-07 | 上海文化广播影视集团有限公司 | Video program film examination system and method |
| CN111797752A (en) * | 2020-06-29 | 2020-10-20 | 广州市百果园信息技术有限公司 | Illegal video detection method, device, equipment and storage medium |
| CN111866605B (en) * | 2020-07-09 | 2022-10-18 | 北京齐尔布莱特科技有限公司 | Video auditing method and server |
| CN111897998A (en) * | 2020-07-10 | 2020-11-06 | 苏州跃盟信息科技有限公司 | Video processing method and processing system |
| CN111901639A (en) * | 2020-07-31 | 2020-11-06 | 上海博泰悦臻电子设备制造有限公司 | Multimedia video uploading method, device and system, storage medium and platform |
| CN112788356B (en) * | 2020-12-30 | 2023-04-28 | 百果园技术(新加坡)有限公司 | Live broadcast auditing method, device, server and storage medium |
| JP7130073B2 (en) * | 2021-01-29 | 2022-09-02 | 株式会社ドワンゴ | Distribution server, content distribution method, content distribution program, and recording medium |
| CN113163225B (en) * | 2021-05-20 | 2022-05-06 | 广州方硅信息技术有限公司 | Method, device, equipment and medium for checking and outputting character special effect information through transport |
| CN113905282B (en) * | 2021-10-22 | 2024-02-20 | 贝壳找房(北京)科技有限公司 | Video file uploading processing method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101631192A (en) * | 2009-08-25 | 2010-01-20 | 北京中科大洋科技发展股份有限公司 | Censoring terminal of domestic-appliance digital media program content |
| CN101742228A (en) * | 2008-11-19 | 2010-06-16 | 新奥特硅谷视频技术有限责任公司 | Preprocessing method and system applied to digital court |
| CN102006424A (en) * | 2010-11-22 | 2011-04-06 | 亿览在线网络技术（北京）有限公司 | Video reviewing method and system |
| CN103716690A (en) * | 2013-12-27 | 2014-04-09 | 广州华多网络科技有限公司 | Multimedia live broadcast whistle-blowing method, terminal, server and system |
| CN105376199A (en) * | 2014-08-25 | 2016-03-02 | 腾讯科技（北京）有限公司 | Information processing method, system, server and client |
| CN105577652A (en) * | 2015-12-16 | 2016-05-11 | 上海东方传媒技术有限公司 | Mobile film censoring system in broadcast television field |
| CN105657479A (en) * | 2014-11-10 | 2016-06-08 | 腾讯数码（天津）有限公司 | Video processing method and device |
-
2016
- 2016-10-14 CN CN201610898195.5A patent/CN107959863B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101742228A (en) * | 2008-11-19 | 2010-06-16 | 新奥特硅谷视频技术有限责任公司 | Preprocessing method and system applied to digital court |
| CN101631192A (en) * | 2009-08-25 | 2010-01-20 | 北京中科大洋科技发展股份有限公司 | Censoring terminal of domestic-appliance digital media program content |
| CN102006424A (en) * | 2010-11-22 | 2011-04-06 | 亿览在线网络技术（北京）有限公司 | Video reviewing method and system |
| CN103716690A (en) * | 2013-12-27 | 2014-04-09 | 广州华多网络科技有限公司 | Multimedia live broadcast whistle-blowing method, terminal, server and system |
| CN105376199A (en) * | 2014-08-25 | 2016-03-02 | 腾讯科技（北京）有限公司 | Information processing method, system, server and client |
| CN105657479A (en) * | 2014-11-10 | 2016-06-08 | 腾讯数码（天津）有限公司 | Video processing method and device |
| CN105577652A (en) * | 2015-12-16 | 2016-05-11 | 上海东方传媒技术有限公司 | Mobile film censoring system in broadcast television field |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107959863A (en) | 2018-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107959863B (en) | Video auditing method and system | |
| KR102082816B1 (en) | Method for improving the resolution of streaming files | |
| CN106792100B (en) | Video bullet screen display method and device | |
| CN107534796B (en) | Video processing system and digital video distribution system | |
| CN104519401B (en) | Video segmentation point preparation method and equipment | |
| CN112967080A (en) | Advertisement putting effect monitoring system | |
| US20030098869A1 (en) | Real time interactive video system | |
| CN105898583B (en) | Image recommendation method and electronic equipment | |
| CN109756746A (en) | Video reviewing method, device, server and storage medium | |
| CN107147939A (en) | Method and apparatus for adjusting net cast front cover | |
| CN1750618A (en) | Method of viewing audiovisual documents on a receiver, and receiver for viewing such documents | |
| CN105704559A (en) | Poster generation method and apparatus thereof | |
| CN111372116B (en) | Video playing prompt information processing method and device, electronic equipment and storage medium | |
| WO2022188510A1 (en) | Method and device for reviewing video, and computer readable storage medium | |
| CN102006424A (en) | Video reviewing method and system | |
| CN112435244A (en) | Live video quality evaluation method and device, computer equipment and storage medium | |
| CN103455966B (en) | Digital watermark embedding apparatus, data waterprint embedded method and digital watermark detecting device | |
| Zhou et al. | A brief survey on adaptive video streaming quality assessment | |
| CN113038185B (en) | Bullet screen processing method and device | |
| CN106604047A (en) | Multi-video-stream video direct broadcasting method and device | |
| CN110198454B (en) | Method and device for monitoring channel content replacement in real time | |
| CN113569719B (en) | Video infringement judging method and device, storage medium and electronic equipment | |
| CN105491462A (en) | System and method for outputting time-lapse summary based on compressed video | |
| CN112235592B (en) | Live broadcast method, live broadcast processing method, device and computer equipment | |
| CN107872705A (en) | A kind of methods, devices and systems of data acquisition |
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 |