CN111935539A - Video detection method, system, electronic device and storage medium - Google Patents
Video detection method, system, electronic device and storage medium Download PDFInfo
- Publication number
- CN111935539A CN111935539A CN202010697738.3A CN202010697738A CN111935539A CN 111935539 A CN111935539 A CN 111935539A CN 202010697738 A CN202010697738 A CN 202010697738A CN 111935539 A CN111935539 A CN 111935539A
- Authority
- CN
- China
- Prior art keywords
- video
- picture
- quality
- video file
- file
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 10
- 230000006399 behavior Effects 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 238000004383 yellowing Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 238000012795 verification Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000006835 compression Effects 0.000 description 5
- 238000007906 compression Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 239000003292 glue Substances 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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]
- H04N21/40—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
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/80—Responding to QoS
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4753—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for user identification, e.g. by entering a PIN or password
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The application relates to a method, a system, an electronic device and a storage medium for video detection, wherein the method for video detection comprises the following steps: checking the identity check code of the video file in the state of uploading the video file; if the identity check code does not exist, the video file is separated into pictures; judging whether the quality of the picture meets a preset quality standard or not; if the quality of the picture does not accord with the preset quality standard, the uploading is stopped, so that the problem of low efficiency of uploading video files is solved, and the video is uploaded quickly and accurately.
Description
Technical Field
The present application relates to the field of video transmission, and in particular, to a method, a system, an electronic device, and a storage medium for video detection.
Background
Video websites are popular at present, and compared with traditional video media, the video websites have the following characteristics: the program capacity is very large; the program types are various, and the related range is wide; the program can be accepted by self-ordering and two-way interaction; meanwhile, the network video is simple to store and convenient to receive, and as a new network media, the internet user can publish, browse and share video works on line on a video website.
In the related technology, a video website can receive a lot of videos uploaded by a user every day, but the videos have different quality and can be illegal, generally, the user needs to upload the videos to a server side, and the uploaded videos are detected through a server side program, so that server resources are greatly wasted, and if the video files of the user are large, the waiting time is long, and the user experience is not friendly.
At present, no effective solution is provided for the problem of low efficiency of uploading video files in the related technology.
Disclosure of Invention
The embodiment of the application provides a video detection method, a video detection system, an electronic device and a storage medium, and aims to at least solve the problem of low efficiency of uploading video files in the related art.
In a first aspect, an embodiment of the present application provides a method for video detection, including: the method comprises the steps that under the state of uploading a video file, an identity check code of the video file is checked; if the identity check code does not exist, the video file is separated into pictures; judging whether the quality of the picture meets a preset quality standard or not; and if the quality of the picture does not meet the preset quality standard, stopping uploading.
In one embodiment, after the verifying the identity check code of the video file, the method includes: storing the identity check code and a corresponding table of the quality of the video file in an index database, establishing an index according to the corresponding table, providing an interface for searching the video file according to the corresponding table and the index, searching a local system file according to the interface, and judging whether the quality of the picture in the video meets a preset quality standard or not under the condition that the identity check code of the video file is recorded in the local system file.
In one embodiment, the verifying the identity tag of the video file comprises: and acquiring an information summarization algorithm MD5 of the video file, and using the information summarization algorithm MD5 as an identity check code of the video file.
In one embodiment, the separating the video file into pictures comprises:
and converting the program of the FFmpeg into a wasm file for decoding the sound and the picture by using a compiler Emscript, and separating the video file into pictures by operating and calling the wasm file for decoding the sound and the picture by a browser.
In one embodiment, the determining whether the quality of the picture meets a preset quality standard includes:
after the picture is obtained, loading a tensoflow.js library file by using a browser, then loading a training model, wherein the training model comprises a model for identifying picture resolution, a model for judging picture violation and a model for judging picture yellowing, comparing the picture with the training model, and judging whether the quality of the picture meets a preset quality standard.
In one embodiment, after determining whether the quality of the picture meets a preset quality standard, the method includes: establishing an index database, storing the identity check code and the quality of the video file in a corresponding table formed by the index database, and inquiring the picture quality of the video file by taking the identity check code as an index after the identity check code of the video file is checked.
In one embodiment, the determining whether the quality of the picture meets a preset quality standard includes: and labeling the picture according to the quality of the picture, and judging which type of violation behavior the video belongs to according to the label.
In a second aspect, an embodiment of the present application provides a system for video detection, where the system includes: a front-end server and a back-end server;
the front-end server checks the identity check code of the video file in the state that the front-end server uploads the video file to the back-end server;
the front-end server judges that if the identity check code does not exist, the video file is separated into pictures;
the front-end server judges whether the quality of the picture meets a preset quality standard or not;
the front-end server judges whether the quality of the picture does not meet the preset quality standard, and stops uploading the video file to a rear-end server;
the front-end server is configured to execute any one of the video detection methods described above.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor, when executing the computer program, implements the method for video detection as described in the first aspect.
In a fourth aspect, the present application provides a storage medium, on which a computer program is stored, which when executed by a processor, implements the method for video detection as described in the first aspect above.
Compared with the related art, the method for detecting the video, provided by the embodiment of the application, is characterized in that the identity check code of the video file is checked in the state of uploading the video file; if the identity check code does not exist, the video file is separated into pictures; judging whether the quality of the picture meets a preset quality standard or not; if the quality of the picture does not accord with the preset quality standard, uploading is stopped, the problem of low efficiency of uploading video files is solved, and the video is uploaded quickly and accurately.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic diagram of an application scenario of video detection according to an embodiment of the present application;
FIG. 2 is a flow chart of a method of video detection according to an embodiment of the present application;
FIG. 3 is a diagram illustrating a split picture of a video detection method according to an embodiment of the present application;
FIG. 4 is a diagram illustrating a method for determining picture quality according to an embodiment of the present disclosure;
fig. 5 is a flowchart of an embodiment of a video detection method according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference herein to "a plurality" means greater than or equal to two. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
In this embodiment, an application scenario of video detection is provided, and fig. 1 is a schematic diagram of an application scenario of video detection according to an embodiment of the present application, as shown in fig. 1, the system includes: a front-end server 10 and a back-end server 12;
in a state that the front-end server 10 uploads a video file to the back-end server 12, the front-end server 10 verifies an identity check code of the video file, wherein the front-end server 10 performs identity check on the video file;
the front-end server 10 determines that the video file is separated into pictures if the identity check code does not exist;
the front-end server 10 determines whether the quality of the picture meets a preset quality standard;
the front-end server 10 determines that the video file is not uploaded to the back-end server 12 if the quality of the picture does not meet the preset quality standard;
in the related art, it is generally required that after a user uploads a video file to a back-end server 12 through a front-end server 10, the uploaded video file is detected by a server program in the back-end server 12, and the video file is uploaded to the back-end server 12 for detection, which wastes server resources, in the case of a large video file, the time for uploading the video file and the video file being detected by the back-end server 12 program is very slow, and meanwhile, the front-end server 10 needs a slow waiting process for waiting for a feedback result of video review, during which the front-end server 10 is not fully utilized, but passively waits for a feedback opinion of the back-end server 12, but the method of the present invention for local video file detection by the front-end server 10 can obtain a feedback opinion of the video before the detection by the back-end server 12, the video can be detected before or during uploading, the quality of the video file is judged, the problem of low efficiency of uploading the video file is solved, and the video can be uploaded quickly and accurately.
The present embodiment provides a method for video detection, and fig. 2 is a flowchart of a method for video detection according to an embodiment of the present application, and as shown in fig. 2, the flowchart includes the following steps:
step S201, in the state of uploading the video file, the identity check code of the video file is checked, and the identity check code is generated through an encryption algorithm, wherein the check video file can be checked by watching the video, but the video watching can lead to longer time for checking the video file, the check algorithm is set through the device itself, so that whether the quality and the content of the video are changed or not can be judged by watching the video, the check algorithm adopts an encryption algorithm more, the security can be better ensured, and the encryption algorithm can include: the CRC Algorithm, the parity check Algorithm or the information summarization Algorithm (MD 5 for short), the CRC Algorithm is an important linear block code, the appointed relation between data bits and check bits is established through mathematical operation, the document can be judged whether to be falsified by applying the CRC, the parity check Algorithm is that the number of '1' in the group of codes is odd or even, if odd check is used, when the receiving end receives the group of codes, the number of '1' is checked to be odd, the correctness of the transmission code is determined, the MD5 is an irreversible encryption Algorithm, the Algorithm can be encrypted into a unique code with fixed length corresponding to any character string, any modification of a video file can cause the change of the encryption code, the safety of the file is ensured, the quality of the video can be quickly judged through the encryption algorithms, repeatedly searching and viewing the content of the video;
step S202, if the identity check code does not exist, the video file is separated into pictures, wherein if the identity check code of the video file exists, the quality of the video file can be directly indexed through the identity check code of the index database, when the record of the video quality in the index database is unqualified, the uploading is directly stopped, and when the identity check code does not appear in the video, the pictures can be directly intercepted through manual interception, or video software can be selected for interception, for example: opening video software, selecting a screenshot in a user-defined time period, and completely intercepting a picture of a certain time period of a video, or selecting a scenario to completely intercept the whole video picture; the system can also be used with its own functions, such as: the photo folder is F: \ digital file, if the video file format generated by the camera is mp4, all video files can be filtered through the function of the system itself, firstly, the digital photo folder is opened, and then, the mp4 keyword is input into the search box at the upper right corner of the window, at this time, the system can automatically filter all video files under the photo directory, select the above files all, cut the files, and then paste the files into a newly-built folder, and all the video files can be transferred to a new position, thus, only the photo files are left under the photo folder, if the video files are in other formats (such as avi or rmvb), the avi or rmvb keyword is input into the search box; alternatively, to maintain the directory structure of the video file, automatic extraction may be implemented by means of compression software. Clicking a right mouse button on a folder of the digital photos, selecting 'adding to a compressed file', defining a storage path and a file name of a compressed package under a 'conventional' tab, selecting 'storing' in a compression mode, and selecting 'deleting the file after compression'. Then switching to the "file" tab, entering ". jpg" in "file to exclude"; and finally, performing compression to obtain compression packages of all video files, deleting the original video files and only remaining the photo files, and capturing the pictures in the video by the method.
Step S203, judging whether the quality of the picture meets a preset quality standard, wherein the video quality is checked in the related technology, the audio and video is checked through the combination of manual work and machine learning, the machine aspect is to cut frames of the video, and then the images of the key frames are identified and matched to obtain a judgment result; the audio is mainly based on voice recognition, and then a judgment result is obtained through matching of keywords; because the machine audit has misjudgment, the machine audit is assisted with manual examination for 24 hours to judge whether the quality of the video meets the preset quality standard;
step S204, if the quality of the picture does not meet the preset quality standard, stopping uploading, wherein the determining the quality of the picture includes: judging whether the definition of the picture reaches a preset definition value or not, or judging whether the picture comprises illegal information or not.
Through the steps S201 to S204, in the related art, whether the video is illegal or has other problems is identified by uploading the video to the back-end server for detection and passively waiting for a detection result, in the method, the video detection program is directly called through the browser, the video detection can be performed while the browser uploads the video, the quality of the video can be judged before the picture is uploaded to the back-end detection, and then the uploading is continued or stopped, so that the efficiency of uploading the video is greatly increased, the waste of transmission resources is avoided, the detection can be completed before or during the uploading of the video, the efficiency of uploading the video file is improved, and the user experience is increased.
In one embodiment, after the identification code of the video file is checked, a corresponding table of the identification code and the quality of the video file is stored in an index database, an index is established according to the corresponding table, an interface for searching the video file is provided according to the corresponding table and the index, a local system file is searched according to the interface, and under the condition that the identification code of the video file is recorded in the local system file, whether the quality of the picture in the video meets a preset quality standard is judged, the index database can contain the identification code of the video, the video detection time can be included, the specific description of the quality can be used for determining the uploading time of the video and the quality of the video, and the quality of the video can be fed back to the front end through the quality description problem, and stopping or pausing the video uploading, and prompting the user what aspect of the video quality is in question when the video is uploaded.
In one embodiment, the verifying the identity tag of the video file comprises: the information digest algorithm MD5 of the video file is obtained, the information digest algorithm MD5 is used as an identity check code of the video file, wherein the calculation principle of the MD5 value is that input information is processed by 512-bit packets, each packet is divided into 16 32-bit sub-packets, after a series of processing, the output of the algorithm consists of four 32-bit packets, the four 32-bit packets are concatenated to generate a 128-bit hash value, the MD5 is used as verification to generate a unique 'digital fingerprint' for any file (regardless of size, format and number), and by means of the 'digital fingerprint', whether a source file is changed or not can be known by checking whether the values of the MD5 are changed before and after the file. When downloading software, a user often finds that a downloading page of the software can provide a long character string besides a downloading address of the software, the character string is actually an MD5 value of the software, and the effect of the method is that after the software is downloaded, a downloaded file is subjected to MD5 verification once by special software, so that the file obtained by the user and the file provided by the site are the same file, and the safety of the file is enhanced, so that the method can calculate the file verification MD5 value at a browser end, does not need to be uploaded to a server for verification, overcomes the problem that the video quality detection is started when the video file is uploaded to a back-end server 12, directly calls the content of a local index database through the MD5 value, and then judges; if the local index database does not have the identity verification code, the detected identity verification code is stored in the index database, and after the feedback of the video file quality detected by the back-end server is carried out, the feedback of the video file quality is stored in the index database of the front-end server, so that the video file quality can be directly linked to the index of the identity verification code when the file is uploaded next time, the problem that the file uploading of the video consumes long time is solved, and the file uploading efficiency is low.
In an embodiment, fig. 3 is a schematic diagram of a separated picture of a video detection method according to an embodiment of the present application, and as shown in fig. 3, the separating the video file into pictures includes:
converting a program of the FFmpeg into a wap file for decoding a sound and a picture by using a compiler Emscript, and converting the FFmpeg program into a wap file for decoding the sound and the picture by a browser and separating the video file into a picture, wherein the picture is separated by converting the FFmpeg written in C + + into four files of libavformat.a, libavcodec.a, libavutil.a and libswscale.a by the Emscript compiler, continuously converting the files into decoder entries of lid _ cycle.app and decoder.app and further into libffmpeg _ decoder.js and libffmpeg _ decoder.wap which can be loaded by the browser, loading the wap file in the browser, using a video processing method exposed by the wap glue file, processing the video into a video by the interface of the FFmpeg software, wherein the video processing software is converted into a video by the JS glue file, and then directly converting the video into a video by the video processing software, and forming the picture into a picture by the browser without manual video processing method, the efficiency of video processing is increased. In an embodiment, fig. 4 is a schematic diagram of determining the quality of a picture according to the video detection method of the embodiment of the present application, and as shown in fig. 4, the determining whether the quality of the picture meets the preset quality standard includes:
after obtaining the pictures, loading a tensirflow.js library file by using a browser, then loading a training model, wherein the training model comprises a model for identifying the resolution of the pictures, a model for judging picture violation and a model for judging picture yellowing, comparing the pictures with the training model, judging whether the quality of the pictures meets a preset quality standard, loading tensirflow.js by using the browser, providing a machine learning environment, training a deep learning module in advance by using Python, generating a web _ model comprising a group1-shard1of1, tensirflowjs _ model.pb and weight, and identifying the quality of the pictures by labeling the problem of the video quality on each label, and obtaining the judgment of the video quality by analyzing the labels of all the pictures, so that the quality of the videos can be judged rapidly through the quality of the pictures, the efficiency of video upload is increased.
In one embodiment, after judging whether the quality of the picture meets a preset quality standard, an index database is established, the identity check code and the quality of the video file are stored in a corresponding table formed by the index database, after the identity check code of the video file is checked, the picture quality of the video file is inquired by taking the identity verification code as an index, wherein the index database allows a large amount of data to be stored, an interface for searching data is provided, the index can also be established, the data is stored persistently, the inquiry efficiency of the data is improved, the next detection is facilitated, the quality description of the video is directly called out, the quality problem of the video is judged, when the quality problem of the video is found, the uploading of the video file is stopped, the resource occupation is greatly reduced, and the video detection efficiency is increased.
In one embodiment, the determining whether the quality of the picture meets a predetermined quality standard includes: the method includes the steps that a label is marked on a picture according to the quality of the picture, and the video is judged to belong to which type of violation behaviors according to the label, for example, a short video website is on fire more and more at present, a server can receive videos uploaded by a plurality of users every day, but the video quality is uneven and comprises the problems of poor resolution, violation yellow-related behavior and the like.
The present embodiment further provides an electronic device, which is used to implement the foregoing embodiments and preferred embodiments, and the description of the electronic device that has been already made is omitted. As used hereinafter, the terms "module," "unit," "subunit," and the like may implement a combination of software and/or hardware for a predetermined function. Although the means described in the following embodiments are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated, comprising a memory having stored therein a computer program and a processor arranged to execute the computer program to perform the steps of any of the above-described method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
and step S1, verifying the ID check code of the video file.
In step S2, if the id check code does not exist, the video file is separated into pictures.
Step S3, determining whether the quality of the picture meets a predetermined quality standard.
Step S4, if the quality of the picture does not meet the predetermined quality standard, stopping uploading
It should be noted that, for specific examples in this embodiment, reference may be made to examples described in the foregoing embodiments and optional implementations, and details of this embodiment are not described herein again.
In addition, in combination with the video detection method in the foregoing embodiments, the embodiments of the present application may provide a storage medium to implement. The storage medium having stored thereon a computer program; the computer program, when executed by a processor, implements any of the video detection methods in the above embodiments.
In one embodiment, fig. 5 is a flowchart of a specific embodiment of a video detection method according to an embodiment of the present application, as shown in fig. 5, detecting whether a video is illegal,
step S501, uploading a video on a browser by a user;
step S502, the MD5 value of the video is calculated, a corresponding table of the MD5 value of the video and the video quality is prepared, an index database is used for storage, local cache data is firstly searched, whether the quality data of the MD5 value video exists or not is judged, wherein a relational database allows a large amount of data to be stored, a search interface is provided, an index can be established, the storage is lasting, and the query efficiency is improved; if yes, directly obtaining a video result; if not, entering a video judgment method;
step S503, firstly, using WebAssemly technology to compile FFmpeg, compiling an FFmpeg library compiled by C language into a wasm file through an Emscript tool, converting the FFmpeg written by C + + into libavformat.a, libavcode.a, libavutil.a and libswscale.a through an Emscript compiler, continuously converting the files into a flap _ cycle.app and a decoder entry of the decoder.app, further converting the files into libffmpeg _ decoder.js and libffmpeg _ decoder.wasm which can be loaded by a browser, loading the wasm file in the browser, using a JS glue file, using a wasm exposed video processing method, processing a video into a picture through an interface exposed by the FFmpeg, and storing the picture in an index for storage;
step S504, determining the video quality through the trained model includes the following steps: js, and providing a machine learning environment; a deep learning module is pre-trained by Python to generate a web _ model, wherein the web _ model comprises group 1-board 1of1, tensoflowjs _ model.pb, weights.manifest.json; loading the trained model from the server, traversing the picture, analyzing and labeling; analyzing the labels of all the pictures to obtain whether the judgment of the video quality is illegal;
step S505, caching the obtained quality and the MD5 value to the local, so as to facilitate the next judgment;
step S506, a user selects a video file to upload at a browser end, general video detection is carried out at a server end, if the video is uploaded for a long time, server computing power is wasted after the video is uploaded, in the existing method, the browser firstly carries out video detection during the video uploading process, if the video is qualified, the video is continuously uploaded, if the video has problems, the uploading is interrupted, page feedback is directly given, the video detection efficiency is greatly accelerated, and the accuracy of the video detection is improved by using a machine learning method.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be understood by those skilled in the art that various technical features of the above embodiments can be combined arbitrarily, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, the scope of the present description should be considered as being described in the present specification.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of video detection, comprising:
the method comprises the steps that under the state of uploading a video file, an identity check code of the video file is checked;
if the identity check code does not exist, the video file is separated into pictures;
judging whether the quality of the picture meets a preset quality standard or not;
and if the quality of the picture does not meet the preset quality standard, stopping uploading.
2. The method of claim 1, wherein after the verifying the identity check code of the video file, the method comprises: storing the identity check code and a corresponding table of the quality of the video file in an index database, establishing an index according to the corresponding table, providing an interface for searching the video file according to the corresponding table and the index, searching a local system file according to the interface, and judging whether the quality of the picture in the video meets a preset quality standard or not under the condition that the identity check code of the video file is recorded in the local system file.
3. The method of claim 1, wherein verifying the identity tag of the video file comprises: and acquiring an information summarization algorithm MD5 of the video file, and using the information summarization algorithm MD5 as an identity check code of the video file.
4. The method of claim 1, wherein the separating the video file into pictures comprises:
and converting the program of the FFmpeg into a wasm file for decoding the sound and the picture by using a compiler Emscript, and separating the video file into pictures by operating and calling the wasm file for decoding the sound and the picture by a browser.
5. The method of claim 1, wherein the determining whether the quality of the picture meets a predetermined quality standard comprises:
after the picture is obtained, loading a tensoflow.js library file by using a browser, then loading a training model, wherein the training model comprises a model for identifying picture resolution, a model for judging picture violation and a model for judging picture yellowing, comparing the picture with the training model, and judging whether the quality of the picture meets a preset quality standard.
6. The method according to claim 1, wherein after determining whether the quality of the picture meets a predetermined quality standard, the method comprises: establishing an index database, storing the identity check code and the quality of the video file in a corresponding table formed by the index database, and inquiring the picture quality of the video file by taking the identity check code as an index after the identity check code of the video file is checked.
7. The method of claim 1, wherein the determining whether the quality of the picture meets a predetermined quality standard comprises: and labeling the picture according to the quality of the picture, and judging which type of violation behavior the video belongs to according to the label.
8. A system for video inspection, the system comprising: a front-end server and a back-end server;
the front-end server checks the identity check code of the video file in the state that the front-end server uploads the video file to the back-end server;
the front-end server judges that if the identity check code does not exist, the video file is separated into pictures;
the front-end server judges whether the quality of the picture meets a preset quality standard or not;
the front-end server judges whether the quality of the picture does not meet the preset quality standard, and stops uploading the video file to a rear-end server;
the front-end server is used for executing a video detection method according to any one of claims 1 to 7.
9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is configured to execute the computer program to perform a method of video detection as claimed in any one of claims 1 to 7.
10. A storage medium having a computer program stored thereon, wherein the computer program is arranged to perform a method of video detection as claimed in any one of claims 1 to 7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010697738.3A CN111935539A (en) | 2020-07-20 | 2020-07-20 | Video detection method, system, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010697738.3A CN111935539A (en) | 2020-07-20 | 2020-07-20 | Video detection method, system, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111935539A true CN111935539A (en) | 2020-11-13 |
Family
ID=73313354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010697738.3A Pending CN111935539A (en) | 2020-07-20 | 2020-07-20 | Video detection method, system, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111935539A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113099299A (en) * | 2021-03-10 | 2021-07-09 | 北京蜂巢世纪科技有限公司 | Video editing method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105847874A (en) * | 2016-04-20 | 2016-08-10 | 乐视控股（北京）有限公司 | Live broadcasting device and live broadcasting terminal |
| EP3160110A1 (en) * | 2014-06-23 | 2017-04-26 | ZTE Corporation | File transmission method and apparatus, terminal, wearable device and storage medium |
| CN110209647A (en) * | 2019-05-15 | 2019-09-06 | 深圳市麦谷科技有限公司 | A kind of file uploading method that supporting cloudy storage service and system |
| CN110267106A (en) * | 2019-06-25 | 2019-09-20 | 四川长虹电器股份有限公司 | Real-time blocking relates to the method for yellow audio-video, intercepts terminal, equipment and application |
-
2020
- 2020-07-20 CN CN202010697738.3A patent/CN111935539A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3160110A1 (en) * | 2014-06-23 | 2017-04-26 | ZTE Corporation | File transmission method and apparatus, terminal, wearable device and storage medium |
| CN105847874A (en) * | 2016-04-20 | 2016-08-10 | 乐视控股（北京）有限公司 | Live broadcasting device and live broadcasting terminal |
| CN110209647A (en) * | 2019-05-15 | 2019-09-06 | 深圳市麦谷科技有限公司 | A kind of file uploading method that supporting cloudy storage service and system |
| CN110267106A (en) * | 2019-06-25 | 2019-09-20 | 四川长虹电器股份有限公司 | Real-time blocking relates to the method for yellow audio-video, intercepts terminal, equipment and application |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113099299A (en) * | 2021-03-10 | 2021-07-09 | 北京蜂巢世纪科技有限公司 | Video editing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9734261B2 (en) | Context aware query selection | |
| RU2601201C2 (en) | Method and device for analysis of data packets | |
| US9880983B2 (en) | Methods and systems for uniquely identifying digital content for eDiscovery | |
| CN106878265B (en) | Data processing method and device | |
| Poisel et al. | A comprehensive literature review of file carving | |
| CN111614599B (en) | Webshell detection method and device based on artificial intelligence | |
| WO2015139507A1 (en) | Method and apparatus for detecting security of a downloaded file | |
| CN110457628B (en) | Webpage version checking method, device, equipment and storage medium | |
| CN107766469A (en) | A kind of method for caching and processing and device | |
| CN111008348A (en) | Anti-crawler method, terminal, server and computer readable storage medium | |
| CN111008405A (en) | Website fingerprint identification method based on file Hash | |
| CN112733057A (en) | Network content security detection method, electronic device and storage medium | |
| US20210019511A1 (en) | Systems and methods for extracting data from an image | |
| CN114650176A (en) | Phishing website detection method and device, computer equipment and storage medium | |
| CN107786529B (en) | Website detection method, device and system | |
| CN111935539A (en) | Video detection method, system, electronic device and storage medium | |
| CN113221535B (en) | Information processing method, device, computer equipment and storage medium | |
| CN112579623A (en) | Method, device, storage medium and equipment for storing data | |
| CN107040606A (en) | Method and apparatus for handling http request | |
| Aggarwal et al. | A targeted data extraction system for mobile devices | |
| EP3944111A1 (en) | System and method for generating a minimal forensic image of a dataset of interest | |
| CN115437930A (en) | Identification method of webpage application fingerprint information and related equipment | |
| KR100986479B1 (en) | System and method for digital evidence acquisition | |
| US20180150752A1 (en) | Identifying artificial intelligence content | |
| CN117807280B (en) | Silence automatic triggering type document collection method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201113 |