CN111246168A - Video content batch supervision cluster system and method - Google Patents
Video content batch supervision cluster system and method Download PDFInfo
- Publication number
- CN111246168A CN111246168A CN202010046008.7A CN202010046008A CN111246168A CN 111246168 A CN111246168 A CN 111246168A CN 202010046008 A CN202010046008 A CN 202010046008A CN 111246168 A CN111246168 A CN 111246168A
- Authority
- CN
- China
- Prior art keywords
- video
- module
- supervision
- real
- time
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/91—Television signal processing therefor
- H04N5/913—Television signal processing therefor for scrambling ; for copy protection
Abstract
The invention discloses a video content batch supervision cluster system which comprises a video acquisition module, a video supervision module, an emergency processing module and a cloud end, wherein the video acquisition module is connected with the video supervision module, the cloud end is connected with the video supervision module, the emergency processing module is connected with the video supervision module, the video supervision module comprises a shared file library and at least one video supervision server connected with the shared file library, the video supervision servers are connected through a high-speed network, the video supervision server is connected with the cloud end, and the video supervision server is connected with the emergency processing module. The video monitoring module adopts a cluster system, distributes batch video data through a preset mechanism, and reduces the processing amount of each video monitoring server under the condition that the total work amount of the video monitoring module is not changed, thereby reducing the load of the server and improving the video monitoring processing efficiency.
Description
Technical Field
The invention belongs to the technical field of video supervision, and particularly relates to a video content batch supervision cluster system and a video content batch supervision cluster method.
Background
With the rapid development of the internet, the internet media, especially video, has become an important medium for transmitting information by virtue of the advantages of large information amount, wide coverage, high information transmission speed and the like. In the internet era, network media are closely related to daily life of people, and rapidly rise to become a main mode of information dissemination, and meanwhile, the spiritual culture life of people is also influenced. A '37 th time China Internet development condition statistical report' issued by a China Internet information center (CNNIC) in 2016 shows that as long as 12 months in 2015, the scale of Chinese network video users reaches 5.04 hundred million, the utilization rate of the network video users is 73.2%, and 6.5 percentage points are increased compared with the end of 2014. The mobile phone video user scale is 4.05 hundred million, the mobile phone video user scale is increased by 9228 ten thousand compared with the mobile phone video user scale at the end of 2014, and the increase rate is 29.5%. The usage rate of the mobile phone network video is 65.4%, and the mobile phone network video is increased by 9.2 percentage points compared with the mobile phone network video at the end of 2014. The video is widely applied to services such as online browsing, downloading, communication and sharing in the network.
The video is also a double-edged sword, and due to the openness and interactivity of the sword, the information spread by the video is relatively mixed, so that bad information often causes bad influence. Moreover, the network media also involve security problems, such as that some commercial spys, terrorists, etc. may utilize the redundant information hidden in the network video to spread the hidden bad information and even plan some terrorist activities. Network security is becoming more important, so there is an urgent need to strengthen the supervision of network video content.
In addition, the video talk of network media is eliminated, the non-civilization phenomenon in life also frequently occurs, and in order to improve the overall quality of people, cameras are installed in places where the non-civilization phenomenon or crime easily occurs in each large cell to monitor behavior of people.
In view of the above two reasons, the processing amount of video content supervision is increasing, and some video contents, such as crime scenes monitored by a cell, video transmission with yellow violence, etc., need to be processed very quickly so as to take timely measures to reduce the loss of personal and property. However, due to the limitation of the processing server, the processing amount and the processing efficiency are contradictory, and in view of this, how to perform video content supervision quickly and achieve quick response is an urgent problem to be solved.
Disclosure of Invention
In order to solve the above problems, the present invention provides a video content batch supervision cluster system and method, which achieve the purpose of improving the supervision efficiency and processing efficiency of video content.
The patent provides a video content supervises cluster system in batches, including video acquisition module, video supervision module, emergency treatment module and high in the clouds, video acquisition module is connected with video supervision module, and the high in the clouds is connected with video supervision module, emergency treatment module with video supervision module connects, wherein, video supervision module including the shared file storehouse and with an at least video supervision server that the shared file storehouse is connected, connect through high-speed network between the video supervision server, the video supervision server with the high in the clouds is connected, the video supervision server with emergency treatment module connects.
Furthermore, the video acquisition module is connected with the real-time video data module and the non-real-time video database; the real-time video data module comprises data acquisition equipment and a Beidou positioning system, wherein the data acquisition equipment is used for acquiring real-time video information, carrying positioning information of the Beidou positioning system and uploading the real-time video information to the shared file library through the video acquisition module; and the video acquisition module simultaneously acquires the non-real-time video information in the non-real-time video database and uploads the non-real-time video information to the shared file library.
Furthermore, the video acquisition module is connected with the shared file library through an encryption gateway protocol.
Further, the shared file library dynamically allocates the real-time video information or the non-real-time video information to the at least one video surveillance server through a decryption gateway corresponding to the encryption gateway according to a predetermined mechanism.
Further, the predetermined mechanism includes allocation according to real-time and non-real-time characteristics, allocation according to positioning areas, or allocation according to video surveillance server load.
Furthermore, the video supervision server comprises a video steganalysis module and a video analysis module, and the video steganalysis module is connected with the video analysis module.
The invention also discloses a video content batch supervision clustering method, which comprises the following steps:
step 1, a video acquisition module acquires video information and sends a supervision request to a video supervision module;
step 2, a shared file library in the video supervision module distributes supervision requests sent by the video acquisition module to at least one video supervision server according to a preset distribution mechanism;
step 3, the video monitoring server compares the training data stored in the cloud with the video information to monitor the video content;
and 4, if the video monitoring server does not find that the video content has the content consistent with the training data, the video monitoring server passes the verification, if the video monitoring server finds that the video content has the content consistent with the training data, the video monitoring server sends an instruction to the emergency processing module, and the emergency processing module carries out emergency processing according to the instruction.
Further, the video acquisition module acquires video information in real time by using data acquisition equipment and a Beidou positioning system and directly calls the video information from a non-real-time video database; and then sends a supervision request to the video supervision module through the encryption gateway.
Further, the shared file library distributes the supervision request sent by the video acquisition module to at least one video supervision server according to real-time and non-real-time characteristics, or according to a positioning area, or according to the load of the video supervision server after decryption.
Further, before the video supervision server performs comparison processing on the training data and the video information stored in the cloud, steganalysis processing is performed, and the process comprises feature selection and extraction, feature fusion, feature training and strategy fusion.
By utilizing the scheme, the invention can at least obtain the following beneficial effects:
1. the video monitoring module adopts a cluster system, distributes batch video data through a preset mechanism, and reduces the processing amount of each video monitoring server under the condition that the total work amount of the video monitoring module is not changed, thereby reducing the load of the server and improving the video monitoring processing efficiency.
2. The video acquisition module performs real-time video acquisition and non-real-time video acquisition according to different scenes, and realizes a multi-scene batch video processing function.
3. When the video acquisition module sends a request to the video supervision module, the video information is encrypted through the encryption gateway, so that the safety during data transmission is ensured, and the problems of video information leakage and the like are avoided.
4. When the video supervision module processes video contents, the video supervision module also utilizes a steganalysis means to restrain the phenomenon that video information containing pornography, violence, national security and the like is hidden on a normal carrier and transmitted by utilizing steganography.
5. The emergency processing module is matched with the Beidou positioning system to timely master the position of a video problem, and an emergency strategy is timely generated, so that loss or harm are reduced to the maximum extent.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the invention will be described in detail hereinafter, by way of illustration and not limitation, with reference to the accompanying drawings. In the drawings:
fig. 1 is a system architecture diagram of a video content bulk administration cluster provided in accordance with the present invention.
FIG. 2 is a flowchart of steganalysis provided in accordance with the present invention
Detailed Description
While specific embodiments of the invention are described below in conjunction with the contents of the accompanying drawings of the specification, it should be noted that the description of well-known components and processing techniques and processes has been omitted to avoid unnecessarily limiting the invention.
One embodiment of the invention provides a video content batch supervision cluster system.
Fig. 1 shows a video content batch supervisory cluster system architecture diagram provided in accordance with the present invention. The system comprises: the intelligent monitoring system comprises a video acquisition module, a video monitoring module, an emergency processing module and a cloud end, wherein the video acquisition module is connected with the video monitoring module, the cloud end is connected with the video monitoring module, and the emergency processing module is connected with the video monitoring module. The video monitoring module comprises a shared file library and at least one video monitoring server connected with the shared file library, the video monitoring servers are connected through a high-speed network, the video monitoring server is connected with the cloud end, and the video monitoring server is connected with the emergency processing module.
Video acquisition module
First, the video information referred to herein is explained to include two types: one type is real-time video information, i.e., video information acquired by a data acquisition device, such as a camera, and the other type is non-real-time video information, i.e., video information that a video producer wants to upload to a network, and the non-real-time video information is generally stored in a database to be checked.
The video acquisition module acquires the two types of information through a high-speed network, such as a gigabit Internet network or a 5G network, and sends a supervision request to the video supervision module after being encrypted through the encryption gateway. Certainly, in order to be matched with a following emergency processing module, the Beidou positioning system is utilized to acquire the position information of the acquisition point of the data acquisition equipment while acquiring real-time video information. The Beidou positioning system adopted by the invention is configured by including but not limited to a Beidou antenna arranged on a shell, and a processor, a Beidou baseband chip, an A/D converter and a radio frequency front end which are arranged in the shell, wherein the processor adopts an ARM processor with a quad-core Cortex-A9 architecture, the A/D converter adopts a conversion chip with the model of AD7778, the processor is respectively connected with the Beidou baseband chip and a main control chip, the Beidou baseband chip is connected with the radio frequency front end through the A/D converter, and the radio frequency front end is connected with the Beidou antenna.
In addition, real-time video information acquired by the data acquisition equipment can be uploaded to a cloud end for backup storage, and then as a suboptimal scheme, the video acquisition module can acquire the real-time video information from the cloud end, but in this way, corresponding acquisition delay can also be generated.
Video monitoring module
As will be understood from the foregoing, the cluster (cluster) technology is a relatively new technology, and relatively high gains in performance, reliability and flexibility can be obtained at relatively low cost through the cluster technology, and task scheduling is a core technology in a cluster system.
A cluster is a group of mutually independent computers interconnected by a high-speed network, which form a group and are managed in a single system mode. A client interacts with a cluster, which appears as a stand-alone server. The cluster configuration is for improved availability and scalability.
The method is popular and is the same service, which is deployed on a plurality of servers, and different servers run the same code to do the same thing.
The video monitoring module of the invention just utilizes the advantages of cluster deployment, and decrypts the video information in the shared file library and distributes the video information to each video monitoring server through a distribution mechanism. The distribution mechanism is preset, for example, videos can be distinguished according to real-time and non-real-time characteristics, real-time video information is distributed to the video monitoring server A, and non-real-time video information is distributed to the video monitoring server B; the video monitoring server load can be distributed according to the video monitoring server load, for example, the load of each video monitoring server for processing video monitoring is 2000, and the total number of the video monitoring servers is 5, but 10000 video monitoring requests are received in the shared file library, so that 2000 video monitoring servers can be distributed for processing, and the problem caused by server overload is avoided while the processing efficiency is improved; in addition, when real-time video information is processed, the acquisition positions of the real-time video information can be distributed according to a Beidou positioning system, for example, three cells A, B and C are arranged, and the distance is long, so that the real-time video information of the three cells can be distributed to three video monitoring servers A, B and C respectively, but the three video monitoring servers have certain requirements, namely, each video monitoring server is required to be correspondingly connected with the emergency processing modules A, B and C of the cells, and the emergency processing efficiency can be improved.
The shared file library can also be used as a storage library, and the selection of the storage structure is generally considered from two aspects: a. a time complexity; b. spatial complexity. Due to the large amount of video supervision requests sent by the video acquisition module, the shared file library must process data quickly, otherwise, the processing may be too slow, which may cause the overflow of packets in the memory. In this case, an effective data storage structure must be adopted, which can support fast storage and reading of video data and can store as much video data as possible with as little memory as possible. Based on the two requirements, the invention can adopt a circular queue with the storage unit size of 1500 bytes and the length of 500 units for storage, and the total size is about 50 Ok. The structure can support frequent insertion and deletion of data, dynamic memory release and allocation are not needed, and the memory space with a fixed size can be repeatedly used. Data read may be waited for when the queue is full; the writing of data may be awaited when the queue is empty. The most ideal storage structure is considered from the aspects of time complexity and space complexity.
In addition, each video supervision server comprises a video steganalysis module and a video analysis module, and the detailed technical scheme of video steganalysis mainly comprises feature selection and extraction, feature fusion, feature training and strategy fusion. Because the number of video supervision requests of the video acquisition module is huge, so that the involved video steganography methods are many, the characteristics which are easy to steganography operation are required to be selected as much as possible to achieve a high detection rate and then extracted. If the features are more, the effects are brought, the features can be classified firstly and then added into corresponding sub-classifiers for feature fusion training, and the dimension of the features is reduced without being too large. The extracted features are stored in a feature library of a cloud, and with the continuous development of video steganalysis, a new video steganalysis method can be continuously generated, so that the feature library can be continuously supplemented with new features and is continuously improved. And selecting a training learning method of a support vector machine to perform steganalysis through each sub-classifier, then obtaining a result, and performing strategy fusion through a multi-voting method. And finally storing the obtained fusion result into a strategy library.
Emergency processing module
The invention considers two application scenes, namely real-time video information and non-real-time video information, and the two application scenes are respectively processed as an emergency processing module behind a video monitoring module.
Aiming at real-time video information, activities of a monitored area are mainly collected in real time, and after the activities are analyzed by a video monitoring module, if dangerous situations are found, emergency treatment can be started. For example, the video acquisition module uploads the environmental information of the engineering machinery vehicle to the cloud end, so that a monitoring center manager can know the running condition of the external engineering machinery vehicle in time, the engineering machinery vehicle is monitored, the current position of the engineering machinery vehicle is positioned through the Beidou positioning system, the monitoring personnel can lock the position of the engineering machinery vehicle, and the engineering machinery vehicle can be found in time.
Aiming at non-real-time video information, the legality of video content is mainly checked, for example, if a jittering APP user expects to upload a video, the request is sent to a jittering pending library, a video acquisition module acquires the video, the video is encrypted and transmitted to a shared file library of a video monitoring module, the shared file library is decrypted and then distributed to a video monitoring server according to a preset distribution mechanism, and video monitoring processing is performed, wherein the video monitoring processing is video steganography analysis firstly, whether hidden illegal information exists in the checked video or not is performed, if not, the video analysis processing is performed, the two steps of analysis processing processes are performed, the illegal information is not found, and the video is transmitted to the Internet through an Internet network or a 5G network through checking; if a problem is found in the process of monitoring and processing the video, the video is blackened and deleted through the emergency processing module, video source information is traced, a warning is given to a user, and an alarm signal is directly sent to a police department if the video is serious.
Another embodiment of the present invention provides a video content batch supervision clustering method, which comprises the following working steps:
step 1, a video acquisition module acquires video information and sends a supervision request to a video supervision module;
step 2, a shared file library in the video supervision module distributes supervision requests sent by the video acquisition module to at least one video supervision server according to a preset distribution mechanism;
step 3, the video monitoring server compares the training data stored in the cloud with the video information to monitor the video content;
and 4, if the video monitoring server does not find that the video content has the content consistent with the training data, the video monitoring server passes the verification, if the video monitoring server finds that the video content has the content consistent with the training data, the video monitoring server sends an instruction to the emergency processing module, and the emergency processing module carries out emergency processing according to the instruction.
As a further embodiment, the video acquisition module acquiring video information comprises acquiring video information in real time and directly retrieving video information from a non-real-time video database by using a data acquisition device and a beidou positioning system; and then sends a supervision request to the video supervision module through the encryption gateway.
As a further embodiment, the shared file repository, after decryption, distributes the surveillance requests sent by the video acquisition modules to at least one video surveillance server according to real-time and non-real-time characteristics, or according to a positioning area, or according to a video surveillance server load.
As a further embodiment, before performing comparison processing on the training data and the video information stored by the video monitoring server according to the cloud, steganalysis processing is performed.
The working process of the present invention is explained based on the case of real-time video information and non-real-time video information characteristic distribution by the cluster system distribution mechanism.
At a certain moment, the elevator in the cell A is put on the shelf by someone, the scene is shot by a monitoring camera near the elevator, real-time video information is formed, the real-time video information is collected by a video collection module through a network communication module, and meanwhile, the video collection module collects the position information of the elevator in the cell A through a Beidou positioning system; meanwhile, a certain jitter user wants to upload a section of video to the network to form non-real-time video information which is stored in a jitter database, and a video acquisition module acquires the non-real-time video information in the jitter database through a 5G network; the video acquisition module encrypts the real-time video information and the non-real-time video information, and a gateway encryption strategy can be adopted. The video acquisition module sends the monitoring request of the real-time video information and the non-real-time video information to the video monitoring module.
The video supervision module decrypts the video after passing the request, certainly, the decryption strategy corresponds to the encryption strategy, the decrypted video is identified as real-time video information and non-real-time video information, at this time, two video supervision servers a and B exist, the real-time video information is distributed to the server a and the non-real-time video information is distributed to the server B according to a distribution mechanism, and in addition, the emergency processing module a connected with the server a needs to be considered to be nearest to the cell a.
Two sections of videos are subjected to two steps of video steganalysis and video analysis on respective servers, wherein the video steganalysis process comprises feature selection extraction, feature fusion, feature training and strategy fusion. Because the number of video supervision requests of the video acquisition module is huge, so that the involved video steganography methods are many, the characteristics which are easy to steganography operation are required to be selected as much as possible to achieve a high detection rate and then extracted. If the features are more, the effects are brought, the features can be classified firstly and then added into corresponding sub-classifiers for feature fusion training, and the dimension of the features is reduced without being too large. The extracted features are stored in a feature library of a cloud, and with the continuous development of video steganalysis, a new video steganalysis method can be continuously generated, so that the feature library can be continuously supplemented with new features and is continuously improved. And selecting a training learning method of a support vector machine to perform steganalysis through each sub-classifier, then obtaining a result, and performing strategy fusion through a multi-voting method. And finally storing the obtained fusion result into a strategy library. The video analysis process is to call data in the cloud for comparison and analysis, and actually, the middle of the video analysis process also has many details, such as feature extraction and the like, which are much simpler and much simpler than video steganalysis.
When the server A finds that a violent incident occurs in the real-time video information, emergency treatment is carried out through an emergency treatment module A connected with the server A, for example, the A server is just arranged in a duty room of an A cell. When the server B finds that illegal behaviors occur in the non-real-time video information, the position of a video author is traced through the emergency processing module B for processing.
The above example only lists two video surveillance processing methods, and in practice, the amount of video surveillance requests sent by the video capture module is huge, so the above example should also consider the storage structure of the shared file library, and its selection should generally consider from two aspects: a. a time complexity; b. spatial complexity. Due to the large amount of video supervision requests sent by the video acquisition module, the shared file library must process data quickly, otherwise, the processing may be too slow, which may cause the overflow of packets in the memory. In this case, an effective data storage structure must be adopted, which can support fast storage and reading of video data and can store as much video data as possible with as little memory as possible. Based on the two requirements, the invention can adopt a circular queue with the storage unit size of 1500 bytes and the length of 500 units for storage, and the total size is about 50 Ok. The structure can support frequent insertion and deletion of data, dynamic memory release and allocation are not needed, and the memory space with a fixed size can be repeatedly used. Data read may be waited for when the queue is full; the writing of data may be awaited when the queue is empty. The most ideal storage structure is considered from the aspects of time complexity and space complexity.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the present invention belongs.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention.
Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The utility model provides a video content supervises cluster system in batches, includes video acquisition module, video supervision module, emergency treatment module and high in the clouds, video acquisition module with video supervision module connects, the high in the clouds with video supervision module connects, emergency treatment module with video supervision module connects, its characterized in that, video supervision module include share file storehouse and with at least one video supervision server that share file storehouse is connected, connect through high-speed network between the video supervision server, the video supervision server with the high in the clouds is connected, the video supervision server with emergency treatment module connects.
2. The system of claim 1, wherein the video capture module is coupled to a real-time video data module and a non-real-time video database; the real-time video data module comprises data acquisition equipment and a Beidou positioning system, wherein the data acquisition equipment is used for acquiring real-time video information, carrying positioning information of the Beidou positioning system and uploading the real-time video information to the shared file library through the video acquisition module; and the video acquisition module simultaneously acquires the non-real-time video information in the non-real-time video database and uploads the non-real-time video information to the shared file library.
3. The system of claim 2, wherein the video capture module is connected to the shared file repository via an encryption gateway protocol.
4. The system of claim 3, wherein the shared file repository dynamically distributes the real-time video information or the non-real-time video information to the at least one video surveillance server via a decryption gateway corresponding to the encryption gateway according to a predetermined mechanism.
5. The system of claim 4, wherein the predetermined mechanism comprises allocation by real-time and non-real-time characteristics, allocation by location area, or allocation by video surveillance server load.
6. The system of claim 1, wherein the video surveillance server comprises a video steganalysis module and a video analysis module, and wherein the video steganalysis module and the video analysis module are connected.
7. A video content batch supervision clustering method is characterized by comprising the following steps:
step 1, a video acquisition module acquires video information and sends a supervision request to a video supervision module;
step 2, a shared file library in the video supervision module distributes supervision requests sent by the video acquisition module to at least one video supervision server according to a preset distribution mechanism;
step 3, the video monitoring server compares the training data stored in the cloud with the video information to monitor the video content;
and 4, if the video monitoring server does not find that the video content has the content consistent with the training data, the video monitoring server passes the verification, if the video monitoring server finds that the video content has the content consistent with the training data, the video monitoring server sends an instruction to the emergency processing module, and the emergency processing module carries out emergency processing according to the instruction.
8. The method of claim 7, wherein the video capture module capturing video information comprises capturing video information in real-time using a data capture device and a Beidou positioning system and retrieving video information directly from a non-real-time video database; and then sends a supervision request to the video supervision module through the encryption gateway.
9. The method of claim 7, wherein the shared repository of files is decrypted and distributes the surveillance requests sent by the video capture modules to at least one video surveillance server according to real-time and non-real-time characteristics or according to location areas or according to video surveillance server load.
10. The method of claim 7, wherein the steganalysis process is performed before the video surveillance server performs the comparison process between the video information and the training data stored in the cloud, and the process includes feature selection extraction, feature fusion, feature training, and policy fusion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010046008.7A CN111246168A (en) | 2020-01-15 | 2020-01-15 | Video content batch supervision cluster system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010046008.7A CN111246168A (en) | 2020-01-15 | 2020-01-15 | Video content batch supervision cluster system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111246168A true CN111246168A (en) | 2020-06-05 |
Family
ID=70871042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010046008.7A Pending CN111246168A (en) | 2020-01-15 | 2020-01-15 | Video content batch supervision cluster system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111246168A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106101100A (en) * | 2016-06-14 | 2016-11-09 | 南京邮电大学 | A kind of video content supervisory systems based on steganalysis and method |
| CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
| CN208172984U (en) * | 2018-05-21 | 2018-11-30 | 北卡科技有限公司 | A kind of public safety command dispatching system of emergency cooperative |
| US10374885B2 (en) * | 2016-12-13 | 2019-08-06 | Amazon Technologies, Inc. | Reconfigurable server including a reconfigurable adapter device |
| CN110443109A (en) * | 2019-06-11 | 2019-11-12 | 万翼科技有限公司 | Abnormal behaviour monitor processing method, device, computer equipment and storage medium |
| CN110505444A (en) * | 2019-07-10 | 2019-11-26 | 广西盛源行电子信息股份有限公司 | Safety defense monitoring system based on big data |
-
2020
- 2020-01-15 CN CN202010046008.7A patent/CN111246168A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106101100A (en) * | 2016-06-14 | 2016-11-09 | 南京邮电大学 | A kind of video content supervisory systems based on steganalysis and method |
| CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
| US10374885B2 (en) * | 2016-12-13 | 2019-08-06 | Amazon Technologies, Inc. | Reconfigurable server including a reconfigurable adapter device |
| CN208172984U (en) * | 2018-05-21 | 2018-11-30 | 北卡科技有限公司 | A kind of public safety command dispatching system of emergency cooperative |
| CN110443109A (en) * | 2019-06-11 | 2019-11-12 | 万翼科技有限公司 | Abnormal behaviour monitor processing method, device, computer equipment and storage medium |
| CN110505444A (en) * | 2019-07-10 | 2019-11-26 | 广西盛源行电子信息股份有限公司 | Safety defense monitoring system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109714192B (en) | Monitoring method and system for monitoring cloud platform | |
| Wang et al. | Adaptive and fault-tolerant data processing in healthcare IoT based on fog computing | |
| CN104573611B (en) | A kind of distributed recognition of face group system | |
| EP2688296B1 (en) | Video monitoring system and method | |
| CN107104961B (en) | distributed real-time video monitoring processing system based on ZooKeeper | |
| CN111274340B (en) | Method, equipment and storage medium for monitoring and processing people stream density | |
| Zhe et al. | DoS attack detection model of smart grid based on machine learning method | |
| WO2017076256A1 (en) | Load balancing method, related device and system | |
| CN108600698A (en) | A kind of safety defense monitoring system and its method based on cloud platform | |
| CN105354247A (en) | Geographical video data organization management method supporting storage and calculation linkage | |
| Hong et al. | Optimizing cloud-based video crowdsensing | |
| CN108769576B (en) | Intelligent video processing method and system | |
| CN107566785B (en) | Big data-oriented video monitoring system and method | |
| CN106791639A (en) | Video frequency monitoring method and system under large-scale data concurrent environment | |
| CN103079058A (en) | Video monitoring system based on cloud computing | |
| CN110491068A (en) | A kind of data transmission of internet of things cloud platform | |
| Chang et al. | Effective distributed service architecture for ubiquitous video surveillance | |
| CN111246168A (en) | Video content batch supervision cluster system and method | |
| CN117061165A (en) | Safety protection system based on space-time data lake technology of monitoring and control system | |
| CN113573150A (en) | Video stream processing method and device, electronic equipment and storage medium | |
| JP2023525112A (en) | Method and device for detecting user data of user equipment UE and storage medium | |
| CN112039936B (en) | Data transmission method, first data processing equipment and monitoring system | |
| CN110134578B (en) | Data processing method and device | |
| KR101049574B1 (en) | Event processing device and method using bookmarks | |
| CN113595958B (en) | Security detection system and method for Internet of things equipment |
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: 20200605 |