CN113038035A - AI video point counting method for live pig breeding - Google Patents
AI video point counting method for live pig breeding Download PDFInfo
- Publication number
- CN113038035A CN113038035A CN202110285790.2A CN202110285790A CN113038035A CN 113038035 A CN113038035 A CN 113038035A CN 202110285790 A CN202110285790 A CN 202110285790A CN 113038035 A CN113038035 A CN 113038035A
- Authority
- CN
- China
- Prior art keywords
- connection controller
- connection
- signal
- access
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000009395 breeding Methods 0.000 title claims abstract description 18
- 230000001488 breeding effect Effects 0.000 title claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 67
- 241000282887 Suidae Species 0.000 claims abstract description 34
- 238000005516 engineering process Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims description 84
- 238000004891 communication Methods 0.000 claims description 38
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000009826 distribution Methods 0.000 claims description 12
- 238000001595 flow curve Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000003491 array Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 239000013307 optical fiber Substances 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000009313 farming Methods 0.000 claims 3
- 230000007246 mechanism Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013136 deep learning model Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000007123 defense Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 229910052709 silver Inorganic materials 0.000 description 2
- 239000004332 silver Substances 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides an AI video point counting method for pig breeding, which comprises the following steps: the method comprises the steps that a server regularly obtains a video of a pig farm through a safety monitoring system, wherein the video is a continuous video; analyzing the video to obtain a video stream of the collected specified closed area, and processing the video stream to obtain a key frame set; splicing the key frames in the key frame combination by adopting an image splicing technology to eliminate repeated images and form a complete image containing all live pigs in the pig farm; counting according to the complete image to obtain the number of live pigs; the counting efficiency and the counting precision are improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an AI video point counting method for pig breeding.
Background
In recent years, stable production and guarantee supply of live pigs become important civil engineering concerned by governments, and policy documents are issued in sequence by all levels of governments, silver insurance guidances and silver insurance bureaus in provinces and cities, so that live pig mortgages are supported to be developed, and the financing requirements of the live pig industry are better met.
With the increase of loan dispensing force for farmers who use pigs as mortgages, it is urgent to reduce risks after loan. The live pig breeding loan evaluates the repayment capacity of the farmer according to the number of live pigs, so that banks need to know the current breeding number of live pigs of the farmer in time and take the breeding number as a means for post-loan management.
At present, the main method for knowing the number of pigs born by farmers is that a bank client manager randomly checks the number of pigs in a farm of the farmers. The method has obvious defects that firstly, time and labor are wasted, a customer manager needs to take time to reach a pig farm of a farmer, the farm is mostly in a remote rural area, the whole process is long in time consumption, if more farmers loan is available, full coverage after loan cannot be achieved, and the efficiency is extremely low; second, the artificial pig spotting error is large. Particularly, in a farm with a large number of pigs, live pigs are in a moving state, and the live pigs move positions in a long-time counting process, so that people are difficult to avoid dazzling and are easy to have counting errors. Thirdly, no effective supervision measures exist, and the operation risk of fraudulent loan communication between a customer manager and a farmer is easy to occur.
In addition, due to the convenience of the network, most services in the modern services involve the use of the network, and banking services are no exception. The existing banking services, including bank-to-individual, bank-to-company, and bank-to-other financial institutions, have become essential work content for network information exchange. Because the bank relates to the property of the user, the bank is one of the main targets of a plurality of network attacks, and the establishment of a safe network environment or the effective inhibition of the loss of the network attack on the property of the user is the important work for maintaining the bank network; particularly, the bank server is required to be connected with the outside, and strict security prevention and control are required in the data interaction process.
The connectivity of existing networks is generally based on both physical connections and signal control. Wherein a physical connection typically exists between the local information device and the network device, typically via a signal line or WIFI connection. The connection is generally controlled by signals, that is, the communication relationship of signals is controlled by software, in the local information device, the network device, and between the network device and the wide area network. However, when a network attack is sent out, an attacker often controls network equipment and signal equipment along with the network equipment and cannot disconnect the network equipment through software control, and at the moment, if the physical connection with the network cannot be disconnected in time, the problem that a large amount of bank information is obtained, stolen or tampered is easily caused. However, the technical development of the prior art for network security mainly focuses on software security control, and once a firewall is broken, it is difficult to artificially disconnect the connection with the wide area network from the physical connection layer at the first time.
Disclosure of Invention
The invention aims to provide an AI video counting method for pig breeding, which improves counting efficiency and counting accuracy.
The invention provides an AI video point counting method for pig breeding, which comprises the following steps:
step 1, a server (7) periodically acquires a video of a pig farm through a safety monitoring system, wherein the video is a continuous video;
step 4, counting according to the complete image to obtain the number of live pigs;
the security monitoring system includes: the system comprises a first network adapter (1), a communication line safety control device (2), a router (3) and a safety monitoring module (4); the network adapter (1) is in signal connection with a first signal end of the communication line safety control device (2) through a first connection controller (5); a second signal output of the communication line safety control device (2) is in signal connection with the router (3) through a second connection controller (6);
the communication line safety control device (2) includes: the device comprises a signal shunt (201), a large-capacity buffer group (202), a data flow monitoring module (203) and a signal rectifier (204); the signal input end of the signal splitter (201) is respectively in signal connection with the first connection controller (5) and the third connection controller (208); the first connection controller (5) is connected with a conventional wide area network through a first network adapter (1), and the third connection controller (208) is connected with an emergency distribution network through a second network adapter (207); the emergency distribution network is only in network connection with a preset connection object; one end of a signal output end of the signal splitter (201) is in signal connection with the data stream monitoring module (203), and the other end of the signal output end is in signal connection with the large-capacity cache group (202) through a fourth connection controller (205); the data stream monitoring module (203) is in signal connection with the signal rectifier (204) through a fifth connection controller (209), and the large-capacity cache group (202) is in signal connection with the signal rectifier (204) through a low-bandwidth signal line; the signal rectifier (204) is in signal connection with a second connection controller (6); the quantum communication module (206) is connected with the safety monitoring module (4) through quantum communication and is connected with the first connection controller (5), the second connection controller (6), the third connection controller (208), the fourth connection controller (205), the fifth connection controller (209) and the signal splitter (201) through unidirectional electric signals; the first connection controller (5), the second connection controller (6) and the fifth connection controller (209) are in a normally-on state, and the third connection controller (208) and the fourth connection controller (205) are in a normally-off state.
Further, the step 2 is further specifically: analyzing the video to obtain the collected video stream of the appointed closed area, wherein the video stream comprises a moving target moving in the appointed closed area; visual features of videos are extracted from video streams, the features are clustered, and then a key frame set is selected from the clustered video frames, wherein the key frame set is a group of key frame frames used for showing the number of pigs and covers the whole pig farm completely.
Further, the step 3 is further specifically: for the overlapped part existing among the key frames in the key frame set, an image splicing technology is utilized, starting from the gray value of the key frames, the difference of the gray value of a region in the key frames and the region with the same size in the reference image is calculated, after the difference is compared, the similarity degree of the overlapped region in the key frames is judged, if the similarity degree reaches a limit value, the overlapped part is determined, and therefore the range and the position of the overlapped region of the key frames are obtained, the key frame splicing is realized, repeated images are eliminated, and a complete image containing all live pigs in a pig farm is formed.
Further, the step 4 is further specifically: and analyzing the complete image by using an example segmentation and counting technology based on deep learning, identifying and segmenting the live pigs one by one, and counting and recording the number of the live pigs in the pig farm at the current time point.
Further, the first connection controller (5) includes: a first signal line (501) and a second signal line (502); a signal line connecting socket is arranged at one end of the first signal line (501) facing the second signal line (502), and a connecting controller (507) is arranged at one end of the second signal line (502) facing the first signal line (501); the connection controller (507) is provided with a signal line connection plug (8) matched with the optical fiber socket; a connecting plate (506) is arranged outside the connecting controller (507), a threaded through hole is formed in the connecting plate (506), and the stud (504) penetrates through the threaded through hole of the connecting plate (506) and is in threaded connection with the threaded through hole; one end of the stud (504) is rotatably connected with the first fixing plate (505), and the other end of the stud is fixedly connected with the rotating output end of the stepping motor (503).
Furthermore, a second fixing plate (511) is arranged outside the second signal line (502) along the cross section direction; the second fixing plate (511) is provided with a connecting controller positioning guide rail (509) along the axial direction of a second signal line (502); the connecting controller (507) is provided with a sliding groove (508) matched with the connecting controller positioning guide rail (509);
the connecting plate (506) is provided with a positioning through hole, one end of the sliding rod (510) penetrates through the positioning through hole to be fixed with the first fixing plate (505), and the other end of the sliding rod is fixed with the second fixing plate (511);
further, the third connection controller (208), the fifth connection controller (209), and the fourth connection controller (205) have the same structure as the first connection controller (5);
the second connection controller (6) includes: a plurality of first connection controllers (5) arranged in an array, a first fixing device (601) for fixing a first signal line (501), and a second fixing device (602) for fixing a second signal line (502); the second signal lines (502) of the plurality of arrays are respectively connected with a router (603) and/or a network cable interface (604) and/or a data cable (605); the server (7) is in signal connection with the router (603) and/or the network wire interface (604) and/or the data wire (605), so that network intercommunication is realized.
Further, the security monitoring module (4) comprises: monitoring and analyzing abnormal access, monitoring and analyzing abnormal flow, and controlling by a communication line safety control device; the abnormal access monitoring analysis is used for monitoring an access purpose and IP (Internet protocol) and ID (identity) of a visitor and generating abnormal feedback information A for abnormal access; the abnormal flow monitoring analysis is used for monitoring data flow and generating abnormal feedback information B when abnormal flow is generated; the communication line safety control device controls the communication line safety control device (2) according to the abnormal feedback information A and the abnormal feedback information B.
Further, the abnormal access monitoring analysis includes: history records are carried out on the access IP, the ID and the access purpose of the visitor; when the access ID is a non-authorized user, when the IP of the access ID changes or the IP of the access ID changes, an ID or IP abnormity warning is sent to a contact way reserved for the visitor, and abnormity feedback information A is not generated; when the access ID is an authority user and the access IP does not accord with the preset safe IP, generating abnormal feedback information A-1; when the access ID is an authority user and the access purpose does not accord with the preset ID authority, generating abnormal feedback information A-2; when the access ID is an authority user and the access time does not accord with the preset authority working time, generating abnormal feedback information A-3; when the access ID is an authority user and the access ID conflicts or the IP conversion of the access ID occurs in a short time, generating abnormal feedback information A-4;
the abnormal traffic monitoring analysis comprises: firstly, establishing an access flow-time coordinate system by taking time as an X axis and the access quantity of a preset time interval as a Y axis; obtaining a current access flow prediction curve A based on big data analysis, calculating to obtain a current access flow prediction curve B based on historical access amount statistics, and recording the current access flow in real time to obtain a current access flow curve C; calculating the difference between the current Y value of the current access flow curve C and the current Y value of the predicted curve A, marking as C-1, the difference between the current Y value of the current access flow curve C and the current Y value of the predicted curve B before calculation, marking as C-2, and the difference between the current Y value of the predicted curve B and the current Y value of the predicted curve A, and marking as C-3; when C-3 is positive and is lower than the first preset value, one of C-1 or C-2 is higher than the second preset value to generate abnormal feedback information B-1; when C-3 is negative and is lower than the first preset value, one of C-1 or C-2 is higher than the second preset value to generate abnormal feedback information B-2; when the absolute value of C-3 is higher than a first preset value, selecting an estimated curve with the highest fitting degree with the current access flow curve C as a reference curve, and generating abnormal feedback information B-3 when the difference value is higher than a second preset value; when one of the C-1 or the C-2 is higher than the third preset value, generating abnormal feedback information B-4;
the communication line security control device control includes: when the abnormal feedback information B-1, the abnormal feedback information B-2 and the abnormal feedback information B-3 are generated, the fourth connection controller (205) is controlled to be connected, and the fifth connection controller (209) is controlled to be disconnected; when the abnormal feedback information B-4 is generated, the first connection controller (5) is controlled to be disconnected, the third connection controller (208) is controlled to be connected, and a link conversion request is sent to a preset connection object of the emergency distribution network; when any one of the abnormal feedback information A-1 to A-4 is generated, the first connection controller (5) corresponding to the abnormal feedback information source IP in the second connection controller (6) is controlled to be disconnected; when any two or more than two of the abnormal feedback information A-1 to A-4 are generated, the first connection controller (5) is controlled to be disconnected, the third connection controller (208) is controlled to be connected, a link conversion request is sent to a preset connection object of the emergency distribution network, and meanwhile, a safety self-checking program is started; and when the safety self-checking program is started and the abnormal feedback information still cannot be eliminated, controlling the third connection controller (208) to be disconnected, simultaneously controlling the second connection controller (6) to be completely disconnected, and requesting to start the manual safety checking program.
Furthermore, the safety monitoring module (4) is provided with an emergency button; the emergency button is a mechanical circuit switch, and after the emergency button is started, the power supply of the conventional control system of the safety monitoring module (4) is cut off and communicated with the power supply of the standby control system; the standby control system is a one-way control system, and when the standby control system is started, disconnection instructions are sent to the first connection controller (5), the second connection controller (6) and the fifth connection controller (209) through independent signal lines.
One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:
1. compared with the traditional mode of ordering pigs on site by depending on manpower, the time cost is greatly reduced by uploading a video remote analysis point number mode, a customer manager does not need to arrive at the site in person, and various costs consumed on the way are saved; the invention effectively supplements the prior network security monitoring technology, can quickly disconnect the physical connection with the wide area network when the software security protection can not generate effective action, reduces the loss, and can effectively prevent hackers from invading the bank system when interacting data in the server through the camera;
2. compared with the traditional method, the video pig counting method has the advantages that the video pig counting method can count the number of live pigs in one pig farm within seconds by utilizing high-speed operation of a background, and compared with manual pig counting method, the efficiency is greatly improved as the pigs are counted one by one within tens of minutes;
3. compared with the traditional method, the video is shot and automatically uploaded through the mobile phone APP, the video stream is analyzed by the background to finish pig ordering, time is saved, meanwhile, full coverage of post-loan management can be achieved, and loan risks are reduced;
4. compared with the traditional method, the video frequency pig process is reserved in a bank system every time, and the management after each loan can be traced, so that the supervision is facilitated, and the operation risk is reduced.
5. The invention sets corresponding response mechanism aiming at different network abnormal conditions, and can realize various network safety control such as disconnection of the wide area network, disconnection of the local area network, wide area network switching, target local area network disconnection and the like.
6. The invention is provided with an emergency standby network and an information redundancy mechanism, and can carry out corresponding information redundancy processing, wide area network switching and other network safety control when an emergency occurs.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
The invention will be further described with reference to the following examples with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method according to one embodiment of the present invention;
fig. 2 is a schematic structural diagram of a security monitoring system for a wan communication line according to the present invention.
Fig. 3 is a schematic structural diagram of a communication line safety control device according to the present invention.
Fig. 4 is a schematic structural diagram of a first connection controller according to the present invention.
Fig. 5 is a schematic structural diagram of a second connection controller according to the present invention. .
Detailed Description
The AI video counting method for live pig breeding solves the problems of low counting efficiency and cheating credit, and improves the counting efficiency and the counting accuracy.
The technical scheme in the embodiment of the application has the following general idea:
1. the raiser shoots a section of continuous video around the pig farm regularly through the mobile phone APP, and the system automatically uploads the video to the background.
2. The method comprises the steps that after a system background obtains a video, the video is analyzed, the collected video stream of the appointed closed area is obtained, the video stream comprises a moving target moving in the appointed closed area, the characteristics of the video, such as vision, are extracted from the video stream, then the characteristics are clustered, and then a key frame set is selected from the clustered video frames. The key frame set can well display a group of key frame frames of the number of pigs, and can fully cover the whole pig farm.
3. For the overlapped part existing between the image frames, an image splicing technology is utilized, starting from the gray value of the image to be spliced, the difference of the gray value of an area in the image to be registered and the area with the same size in the reference image is calculated by using a least square method or other mathematical methods, the similarity degree of the overlapped area of the image to be spliced is judged after the difference is compared, and therefore the range and the position of the overlapped area of the image to be spliced are obtained, the image splicing is realized, the repeated image is eliminated, and a complete image containing all live pigs in a pig farm is formed.
4. Pig farm images were analyzed using example segmentation and counting techniques based on deep learning. Inputting the acquired image into a trained deep learning model to obtain the deep learning model, wherein the deep learning model is used for identifying a moving target from the input image and outputting parameter information of the moving target; the moving targets are identified from the images through the trained deep learning model, the parameter information of the moving targets is obtained, the image area information and the type labels in the parameter information of different moving targets are used for counting the number of the moving targets in the designated area, and therefore the moving targets of different types are counted through pure machine vision. Identifying and dividing the pigs one by one, and counting and recording the number of live pigs in the pig farm at the current time point.
Example one
As shown in fig. 1 to 5, the present embodiment provides an AI video spot count method for pig breeding, including:
step 1, a server 7 periodically acquires a video of a pig farm through a safety monitoring system, wherein the video is a continuous video;
and 4, analyzing the complete image by using an example segmentation and counting technology based on deep learning, identifying and segmenting the live pigs one by one, and counting and recording the number of the live pigs in the pig farm at the current time point.
As shown in fig. 2 to 5, the security monitoring system includes: the system comprises a first network adapter 1, a communication line safety control device 2, a router 3 and a safety monitoring module 4. The network adapter 1 is in signal connection with a first signal terminal of the communication line safety control device 2 via a first connection controller 5. The second signal output of the communication line safety control device 2 is in signal connection with the router 3 via a second connection controller 6.
The communication line safety control device 2 includes: the system comprises a signal splitter 201, a large-capacity buffer group 202, a data stream monitoring module 203 and a signal rectifier 204. The signal splitter 201 is used for performing controlled conversion on the signal connection relationship of each signal interface, and the signal input ends of the signal splitter 201 are respectively in signal connection with the first connection controller 5 and the third connection controller 208. The first connection controller 5 is connected to a conventional wide area network through a first network adapter 1, and the third connection controller 208 is connected to an emergency distribution network through a second network adapter 207. And the emergency distribution network is only in network connection with a preset connection object. One end of the signal output end of the signal splitter 201 is in signal connection with the data stream monitoring module 203, and the other end of the signal output end is in signal connection with the large-capacity buffer group 202 through the fourth connection controller 205. The data stream monitoring module 203 is in signal connection with the signal rectifier 204 through a fifth connection controller 209, and the large-capacity buffer group 202 is in signal connection with the signal rectifier 204 through a low-bandwidth signal line. The signal rectifier 204 is used for communicating signals of a plurality of signal inlets with signal outlets in a general-branch relation. Because the signal connection relation of the non-specific mechanism of the invention is bidirectional connection, the related expressions of signal input/access, signal output/output and the like are only the signal flow relation when the information is sent from the wide area network to the bank system, and the interface can only input or output the signal. The signal rectifier 204 is in signal connection with the second connection controller 6. The quantum communication module 206 is connected with the security monitoring module 4 through quantum communication, and is connected with the first connection controller 5, the second connection controller 6, the third connection controller 208, the fourth connection controller 205, the fifth connection controller 209 and the signal splitter 201 through unidirectional electrical signals. The first connection controller 5, the second connection controller 6, and the fifth connection controller 209 are in a normally on state, and the third connection controller 208 and the fourth connection controller 205 are in a normally off state. The invention is provided with an emergency standby network and an information redundancy mechanism, and can carry out corresponding information redundancy processing, wide area network switching and other network safety control when an emergency occurs. The emergency network deployment and the preset connection objects only comprise: the system comprises a superior network security emergency processing unit, a superior bank supervision unit and a main large-asset bank client.
The first connection controller 5 includes: a first signal line 501 and a second signal line 502. A signal line connection socket is provided at an end of the first signal line 501 facing the second signal line 502, and a connection controller 507 is provided at an end of the second signal line 502 facing the first signal line 501. The connection controller 507 is provided with a signal line connection plug 8 matched with the optical fiber socket. A connecting plate 506 is arranged outside the connecting controller 507, a threaded through hole is formed in the connecting plate 506, and the stud 504 penetrates through the threaded through hole of the connecting plate 506 and is in threaded connection with the threaded through hole. One end of the stud 504 is rotatably connected to the first fixing plate 505, and the other end is fixedly connected to the rotational output end of the stepping motor 503.
The third connection controller 208, the fifth connection controller 209, and the fourth connection controller 205 have the same configuration as the first connection controller 5.
The second connection controller 6 includes: the first connection controller 5 is disposed in a plurality of arrays, and includes a first fixing device 601 for fixing the first signal line 501 and a second fixing device 602 for fixing the second signal line 502. The second signal lines 502 of the plurality of arrays are connected to a router 603 and/or a network interface 604 and/or a data line 605, respectively. The server 7 is in signal connection with the router 603 and/or the network line interface 604 and/or the data line 605, thereby realizing network intercommunication. Because there are many information systems in the bank, the requirement of each information system for data processing is different, and the connection controller 6 is adopted, and signal connection can be performed for each information system, such as: the server system is connected by a communication data line with larger data communication capacity. For the PC of the staff or the bank counter machine, the network cable connection can be adopted. And for the authority IP equipment, an independent interface is adopted for signal connection.
Because the analysis system of the bank needs to be networked with the video monitoring system of the pig farm in the technology, when the video devices of the bank and the pig farm are networked to acquire video data information, the safety measure and the safety level of the pig farm monitoring system are low, and the pig farm monitoring system can easily become a jump point for lawless persons to attack the internal system of the bank, and therefore, a safer network protection measure is particularly needed at the network connection position of the bank and the pig farm video monitoring system.
The main defense means for network attack in the prior art is a firewall technology based on software defense, but physical network breaking can not be performed in time after a firewall is broken through, so that damage can not be quickly stopped. The invention is an effective supplement to the existing network security monitoring technology, and can quickly disconnect the physical connection with the wide area network when the software security protection can not generate effective action, thereby reducing the loss.
The invention adopts the connection controller to carry out physical connection control on a plurality of key nodes connected with the network. Taking the first connection controller 5 as an example, when in the connected state, the signal line connection plug 8 of the connection controller 507 is inserted into the signal line connection socket of the second signal line 502, so that the first signal line 501 and the second signal line 502 are in a signal communication state. When the signal connection between the first signal line 501 and the second signal line 502 needs to be disconnected, the stepping motor 503 receives a corresponding control instruction or rotates according to the instruction, so as to drive the stud 504 to rotate. The connecting plate 506 screwed with the stud 504 is limited by the connecting controller 507 not to rotate along with the rotation of the stud 504, and then moves along the axial direction of the stud 504 to the direction far away from the first signal line 501 under the rotation action of the rotating thread, so that the connecting controller 507 is driven to move to the direction far away from the first signal line 501, the signal line connecting plug 8 and the signal line connecting socket are separated from each other, the physical disconnection of the signal connection of the first signal line 501 and the second signal line 502 is realized, and otherwise, the physical connection of the signal connection of the first signal line 501 and the second signal line 502 is realized.
The security monitoring module 4 includes: abnormal access monitoring analysis, abnormal flow monitoring analysis and control of a communication line safety control device. The abnormal access monitoring analysis is used for monitoring the access purpose and IP and ID of the visitor and generating abnormal feedback information A for abnormal access. And the abnormal flow monitoring analysis is used for monitoring data flow and generating abnormal feedback information B when the abnormal flow is generated. The communication line safety control device controls the communication line safety control device 2 based on the abnormality feedback information a and the abnormality feedback information B.
The abnormal access monitoring analysis comprises: the visitor's access IP, ID, and access purpose are historical. When the access ID is a non-authorized user, when the IP of the access ID changes or the IP of the access ID changes, an ID or IP abnormity warning is sent to the contact way reserved for the visitor, and abnormity feedback information A is not generated. And when the access ID is the authority user and the access IP does not accord with the preset safe IP, generating abnormal feedback information A-1. And when the access ID is the authority user and the access purpose does not accord with the preset ID authority, generating abnormal feedback information A-2. And when the access ID is the authority user and the access time does not accord with the preset authority working time, generating abnormal feedback information A-3. And when the access ID is the authorized user and the access ID conflicts or the IP conversion of the access ID occurs in a short time, generating abnormal feedback information A-4.
The abnormal traffic monitoring analysis comprises: firstly, time is taken as an X axis, the visit quantity at a preset time interval is taken as a Y axis, and a visit flow-time coordinate system is established. Obtaining a current access flow prediction curve A based on big data analysis, calculating to obtain a current access flow prediction curve B based on historical access flow statistics, and recording the current access flow in real time to obtain a current access flow curve C. And calculating the difference between the current Y value of the current access flow curve C and the current Y value of the predicted curve A, marking as C-1, calculating the difference between the current Y value of the current access flow curve C and the current Y value of the predicted curve B before calculation, marking as C-2, calculating the difference between the current Y value of the predicted curve B and the current Y value of the predicted curve A, and marking as C-3. When C-3 is positive and lower than the first preset value, one of C-1 or C-2 is higher than the second preset value to generate abnormal feedback information B-1. When C-3 is negative and is lower than the first preset value, one of C-1 or C-2 is higher than the second preset value to generate abnormal feedback information B-2. And when the absolute value of the C-3 is higher than a first preset value, selecting an estimated curve with the highest fitting degree with the current access flow curve C as a reference curve, and generating abnormal feedback information B-3 when the difference value is higher than a second preset value. And when one of the C-1 or C-2 is higher than the third preset value, generating abnormal feedback information B-4.
The communication line security control device control includes: and when the abnormal feedback information B-1, the abnormal feedback information B-2 and the abnormal feedback information B-3 are generated, the fourth connection controller 205 is controlled to be connected and the fifth connection controller 209 is controlled to be disconnected. And when the abnormal feedback information B-4 is generated, the first connection controller 5 is controlled to be disconnected, the third connection controller 208 is controlled to be connected, and a link switching request is sent to a preset connection object of the emergency distribution network. When any one of the abnormal feedback information A-1 to A-4 is generated, the first connection controller 5 corresponding to the abnormal feedback information source IP in the second connection controller 6 is controlled to be disconnected. When any two or more than two of the abnormal feedback information A-1 to A-4 are generated, the first connection controller 5 is controlled to be disconnected, the third connection controller 208 is controlled to be connected, a link conversion request is sent to a preset connection object of the emergency distribution network, and meanwhile, a safety self-checking program is started. When the safety self-checking program is started, the abnormal feedback information still cannot be eliminated, the third connection controller 208 is controlled to be disconnected, meanwhile, the second connection controller 6 is controlled to be completely disconnected, and the manual safety checking program is requested to be started.
According to the method, the corresponding response mechanism is set according to the difference of threat levels and types of abnormal states, so that various network safety controls such as disconnection of a wide area network and disconnection of a local area network, wide area network switching, disconnection of internal connection of a target local area network and the like can be realized, and the normal operation of an information system under the condition of low risk can be guaranteed. Moderate risk situations place excessive access to redundant devices and slow response times, providing adequate response and feedback time for firewalls. And switching the general wide area network into an independently operated standby network under the high risk condition, and cutting off the connection relation with the non-safety user. The physical disconnection of the attacked bank relative to the wide area network is realized under the highest risk condition, and the great loss of bank information and customer property is avoided.
In addition, because the security monitoring module 4 controls each connection controller, control signals are transmitted in a single direction and are connected through the quantum communication module, and the interference or control of a network attacker on the connection controllers is avoided to the greatest extent.
Example 2
Based on the safety monitoring system of embodiment 1, as shown in fig. 4, a second fixing plate 511 is disposed outside the second signal line 502 along the cross-sectional direction. The second fixing plate 511 is provided with a connection controller positioning rail 509 along the axial direction of the second signal line 502. The connection controller 507 is provided with a sliding groove 508 matched with a connection controller positioning guide rail 509.
The connecting plate 506 is provided with a positioning through hole, one end of the sliding rod 510 passing through the positioning through hole is fixed with the first fixing plate 505, and the other end is fixed with the second fixing plate 511.
Since the torsion acting on the connection plate 506 and the stud 504 is very large during the movement of the connection plate 506, it is very easy to break the connection plate 506, break the connection plate 506 and the stud 504 at the interface between the connection plate 506 and the connection controller 507. The arrangement can effectively share the torsion force applied to the connecting plate 506 and the stud 504 in the movement process, and the service life of the connecting controller is prolonged.
Example 3
Based on the safety monitoring system of embodiment 1, the safety monitoring module 4 is provided with an emergency button. The emergency button is a mechanical circuit switch, and after the emergency button is started, the power supply of the conventional control system of the safety monitoring module 4 is cut off and communicated with the power supply of the standby control system. The standby control system is a unidirectional control system, and when the standby control system is started, disconnection instructions are sent to the first connection controller 5, the second connection controller 6 and the fifth connection controller 209 through independent signal lines.
This setting can be when the security monitoring module 4 is invalided inefficacy by the invasion, and the control instruction of security monitoring module 4 to first connection controller 5, second connection controller 6, fifth connection controller 209 is cut off in the twinkling of an eye based on the control network of independent operation for above-mentioned connection controller is in the off-state, thereby directly follows the physics disconnection in the wide area network with bank information system completely, avoids the further expansion of loss.
Although specific embodiments of the invention have been described above, it will be understood by those skilled in the art that the specific embodiments described are illustrative only and are not limiting upon the scope of the invention, and that equivalent modifications and variations can be made by those skilled in the art without departing from the spirit of the invention, which is to be limited only by the appended claims.
Claims (10)
1. An AI video point counting method for pig breeding is characterized in that: the method comprises the following steps:
step 1, a server (7) periodically acquires a video of a pig farm through a safety monitoring system, wherein the video is a continuous video;
step 2, analyzing the video, acquiring a video stream of the collected specified closed area, processing the video stream, and acquiring a key frame set;
step 3, splicing the key frames in the key frame combination by adopting an image splicing technology to eliminate repeated images and form a complete image containing all live pigs in the pig farm;
step 4, counting according to the complete image to obtain the number of live pigs;
the security monitoring system includes: the system comprises a first network adapter (1), a communication line safety control device (2), a router (3) and a safety monitoring module (4); the network adapter (1) is in signal connection with a first signal end of the communication line safety control device (2) through a first connection controller (5); a second signal output of the communication line safety control device (2) is in signal connection with the router (3) through a second connection controller (6);
the communication line safety control device (2) includes: the device comprises a signal shunt (201), a large-capacity buffer group (202), a data flow monitoring module (203) and a signal rectifier (204); the signal input end of the signal splitter (201) is respectively in signal connection with the first connection controller (5) and the third connection controller (208); the first connection controller (5) is connected with a conventional wide area network through a first network adapter (1), and the third connection controller (208) is connected with an emergency distribution network through a second network adapter (207); the emergency distribution network is only in network connection with a preset connection object; one end of a signal output end of the signal splitter (201) is in signal connection with the data stream monitoring module (203), and the other end of the signal output end is in signal connection with the large-capacity cache group (202) through a fourth connection controller (205); the data stream monitoring module (203) is in signal connection with the signal rectifier (204) through a fifth connection controller (209), and the large-capacity cache group (202) is in signal connection with the signal rectifier (204) through a low-bandwidth signal line; the signal rectifier (204) is in signal connection with a second connection controller (6); the quantum communication module (206) is connected with the safety monitoring module (4) through quantum communication and is connected with the first connection controller (5), the second connection controller (6), the third connection controller (208), the fourth connection controller (205), the fifth connection controller (209) and the signal splitter (201) through unidirectional electric signals; the first connection controller (5), the second connection controller (6) and the fifth connection controller (209) are in a normally-on state, and the third connection controller (208) and the fourth connection controller (205) are in a normally-off state.
2. The AI video point method for pig breeding according to claim 1, characterized in that: the step 2 is further specifically as follows: analyzing the video to obtain the collected video stream of the appointed closed area, wherein the video stream comprises a moving target moving in the appointed closed area; visual features of videos are extracted from video streams, the features are clustered, and then a key frame set is selected from the clustered video frames, wherein the key frame set is a group of key frame frames used for showing the number of pigs and covers the whole pig farm completely.
3. The AI video point method for pig breeding according to claim 1, characterized in that: the step 3 is further specifically as follows: for the overlapped part existing among the key frames in the key frame set, an image splicing technology is utilized, starting from the gray value of the key frames, the difference of the gray value of a region in the key frames and the region with the same size in the reference image is calculated, after the difference is compared, the similarity degree of the overlapped region in the key frames is judged, if the similarity degree reaches a limit value, the overlapped part is determined, and therefore the range and the position of the overlapped region of the key frames are obtained, the key frame splicing is realized, repeated images are eliminated, and a complete image containing all live pigs in a pig farm is formed.
4. The AI video point method for pig breeding according to claim 1, characterized in that: the step 4 is further specifically as follows: and analyzing the complete image by using an example segmentation and counting technology based on deep learning, identifying and segmenting the live pigs one by one, and counting and recording the number of the live pigs in the pig farm at the current time point.
5. The AI video point method for pig breeding according to claim 1, characterized in that: the first connection controller (5) includes: a first signal line (501) and a second signal line (502); a signal line connecting socket is arranged at one end of the first signal line (501) facing the second signal line (502), and a connecting controller (507) is arranged at one end of the second signal line (502) facing the first signal line (501); the connection controller (507) is provided with a signal line connection plug (8) matched with the optical fiber socket; a connecting plate (506) is arranged outside the connecting controller (507), a threaded through hole is formed in the connecting plate (506), and the stud (504) penetrates through the threaded through hole of the connecting plate (506) and is in threaded connection with the threaded through hole; one end of the stud (504) is rotatably connected with the first fixing plate (505), and the other end of the stud is fixedly connected with the rotating output end of the stepping motor (503).
6. The AI video point method for live pig farming of claim 5, wherein: a second fixing plate (511) is arranged outside the second signal line (502) along the cross section direction; the second fixing plate (511) is provided with a connecting controller positioning guide rail (509) along the axial direction of a second signal line (502); the connecting controller (507) is provided with a sliding groove (508) matched with the connecting controller positioning guide rail (509);
the connecting plate (506) is provided with a positioning through hole, one end of the sliding rod (510) penetrates through the positioning through hole to be fixed with the first fixing plate (505), and the other end of the sliding rod is fixed with the second fixing plate (511).
7. The AI video point method for live pig farming of claim 5, wherein:
the third connection controller (208), the fifth connection controller (209) and the fourth connection controller (205) have the same structure as the first connection controller (5);
the second connection controller (6) includes: a plurality of first connection controllers (5) arranged in an array, a first fixing device (601) for fixing a first signal line (501), and a second fixing device (602) for fixing a second signal line (502); the second signal lines (502) of the plurality of arrays are respectively connected with a router (603) and/or a network cable interface (604) and/or a data cable (605); the server (7) is in signal connection with the router (603) and/or the network wire interface (604) and/or the data wire (605), so that network intercommunication is realized.
8. The AI video point method for pig breeding according to claim 1, characterized in that: the security monitoring module (4) comprises: monitoring and analyzing abnormal access, monitoring and analyzing abnormal flow, and controlling by a communication line safety control device; the abnormal access monitoring analysis is used for monitoring an access purpose and IP (Internet protocol) and ID (identity) of a visitor and generating abnormal feedback information A for abnormal access; the abnormal flow monitoring analysis is used for monitoring data flow and generating abnormal feedback information B when abnormal flow is generated; the communication line safety control device controls the communication line safety control device (2) according to the abnormal feedback information A and the abnormal feedback information B.
9. The AI video point method for pig breeding according to claim 8, wherein: the abnormal access monitoring analysis comprises: history records are carried out on the access IP, the ID and the access purpose of the visitor; when the access ID is a non-authorized user, when the IP of the access ID changes or the IP of the access ID changes, an ID or IP abnormity warning is sent to a contact way reserved for the visitor, and abnormity feedback information A is not generated; when the access ID is an authority user and the access IP does not accord with the preset safe IP, generating abnormal feedback information A-1; when the access ID is an authority user and the access purpose does not accord with the preset ID authority, generating abnormal feedback information A-2; when the access ID is an authority user and the access time does not accord with the preset authority working time, generating abnormal feedback information A-3; when the access ID is an authority user and the access ID conflicts or the IP conversion of the access ID occurs in a short time, generating abnormal feedback information A-4;
the abnormal traffic monitoring analysis comprises: firstly, establishing an access flow-time coordinate system by taking time as an X axis and the access quantity of a preset time interval as a Y axis; obtaining a current access flow prediction curve A based on big data analysis, calculating to obtain a current access flow prediction curve B based on historical access amount statistics, and recording the current access flow in real time to obtain a current access flow curve C; calculating the difference between the current Y value of the current access flow curve C and the current Y value of the predicted curve A, marking as C-1, the difference between the current Y value of the current access flow curve C and the current Y value of the predicted curve B before calculation, marking as C-2, and the difference between the current Y value of the predicted curve B and the current Y value of the predicted curve A, and marking as C-3; when C-3 is positive and is lower than the first preset value, one of C-1 or C-2 is higher than the second preset value to generate abnormal feedback information B-1; when C-3 is negative and is lower than the first preset value, one of C-1 or C-2 is higher than the second preset value to generate abnormal feedback information B-2; when the absolute value of C-3 is higher than a first preset value, selecting an estimated curve with the highest fitting degree with the current access flow curve C as a reference curve, and generating abnormal feedback information B-3 when the difference value is higher than a second preset value; when one of the C-1 or the C-2 is higher than the third preset value, generating abnormal feedback information B-4;
the communication line security control device control includes: when the abnormal feedback information B-1, the abnormal feedback information B-2 and the abnormal feedback information B-3 are generated, the fourth connection controller (205) is controlled to be connected, and the fifth connection controller (209) is controlled to be disconnected; when the abnormal feedback information B-4 is generated, the first connection controller (5) is controlled to be disconnected, the third connection controller (208) is controlled to be connected, and a link conversion request is sent to a preset connection object of the emergency distribution network; when any one of the abnormal feedback information A-1 to A-4 is generated, the first connection controller (5) corresponding to the abnormal feedback information source IP in the second connection controller (6) is controlled to be disconnected; when any two or more than two of the abnormal feedback information A-1 to A-4 are generated, the first connection controller (5) is controlled to be disconnected, the third connection controller (208) is controlled to be connected, a link conversion request is sent to a preset connection object of the emergency distribution network, and meanwhile, a safety self-checking program is started; and when the safety self-checking program is started and the abnormal feedback information still cannot be eliminated, controlling the third connection controller (208) to be disconnected, simultaneously controlling the second connection controller (6) to be completely disconnected, and requesting to start the manual safety checking program.
10. The AI video points method for pig farming of claim 9, wherein: the safety monitoring module (4) is provided with an emergency button; the emergency button is a mechanical circuit switch, and after the emergency button is started, the power supply of the conventional control system of the safety monitoring module (4) is cut off and communicated with the power supply of the standby control system; the standby control system is a one-way control system, and when the standby control system is started, disconnection instructions are sent to the first connection controller (5), the second connection controller (6) and the fifth connection controller (209) through independent signal lines.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2020111786225 | 2020-10-29 | ||
| CN202011178622.5A CN112543289A (en) | 2020-10-29 | 2020-10-29 | AI (artificial intelligence) video point counting method, device, equipment and medium for pig breeding |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113038035A true CN113038035A (en) | 2021-06-25 |
| CN113038035B CN113038035B (en) | 2022-05-17 |
Family
ID=75014058
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011178622.5A Withdrawn CN112543289A (en) | 2020-10-29 | 2020-10-29 | AI (artificial intelligence) video point counting method, device, equipment and medium for pig breeding |
| CN202110285790.2A Active CN113038035B (en) | 2020-10-29 | 2021-03-17 | AI video point counting method for live pig breeding |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011178622.5A Withdrawn CN112543289A (en) | 2020-10-29 | 2020-10-29 | AI (artificial intelligence) video point counting method, device, equipment and medium for pig breeding |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112543289A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764126A (en) * | 2005-11-11 | 2006-04-26 | 上海交通大学 | Method for detecting and monitoring gusty abnormal network flow |
| CN102546624A (en) * | 2011-12-26 | 2012-07-04 | 西北工业大学 | Method and system for detecting and defending multichannel network intrusion |
| KR20130116456A (en) * | 2012-03-28 | 2013-10-24 | 에스케이브로드밴드주식회사 | Distributed denial of service attack protection system and method |
| CN105429987A (en) * | 2015-11-25 | 2016-03-23 | 西安科技大学 | Security system for computer network |
| US20170346851A1 (en) * | 2016-05-30 | 2017-11-30 | Christopher Nathan Tyrwhitt Drake | Mutual authentication security system with detection and mitigation of active man-in-the-middle browser attacks, phishing, and malware and other security improvements. |
| CN107493265A (en) * | 2017-07-24 | 2017-12-19 | 南京南瑞集团公司 | A kind of network security monitoring method towards industrial control system |
| CN108090357A (en) * | 2017-12-14 | 2018-05-29 | 湖南财政经济学院 | A kind of computer information safe control method and device |
| CN109756478A (en) * | 2018-11-28 | 2019-05-14 | 国网江苏省电力有限公司南京供电分公司 | A kind of abnormal multistage standby blocking-up method of industrial control system attack considering priority |
| US10462672B1 (en) * | 2016-09-30 | 2019-10-29 | Symantec Corporation | Systems and methods for managing wireless-network deauthentication attacks |
| US20200175161A1 (en) * | 2018-12-03 | 2020-06-04 | British Telecommunications Public Limited Company | Multi factor network anomaly detection |
-
2020
- 2020-10-29 CN CN202011178622.5A patent/CN112543289A/en not_active Withdrawn
-
2021
- 2021-03-17 CN CN202110285790.2A patent/CN113038035B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764126A (en) * | 2005-11-11 | 2006-04-26 | 上海交通大学 | Method for detecting and monitoring gusty abnormal network flow |
| CN102546624A (en) * | 2011-12-26 | 2012-07-04 | 西北工业大学 | Method and system for detecting and defending multichannel network intrusion |
| KR20130116456A (en) * | 2012-03-28 | 2013-10-24 | 에스케이브로드밴드주식회사 | Distributed denial of service attack protection system and method |
| CN105429987A (en) * | 2015-11-25 | 2016-03-23 | 西安科技大学 | Security system for computer network |
| US20170346851A1 (en) * | 2016-05-30 | 2017-11-30 | Christopher Nathan Tyrwhitt Drake | Mutual authentication security system with detection and mitigation of active man-in-the-middle browser attacks, phishing, and malware and other security improvements. |
| US10462672B1 (en) * | 2016-09-30 | 2019-10-29 | Symantec Corporation | Systems and methods for managing wireless-network deauthentication attacks |
| CN107493265A (en) * | 2017-07-24 | 2017-12-19 | 南京南瑞集团公司 | A kind of network security monitoring method towards industrial control system |
| CN108090357A (en) * | 2017-12-14 | 2018-05-29 | 湖南财政经济学院 | A kind of computer information safe control method and device |
| CN109756478A (en) * | 2018-11-28 | 2019-05-14 | 国网江苏省电力有限公司南京供电分公司 | A kind of abnormal multistage standby blocking-up method of industrial control system attack considering priority |
| US20200175161A1 (en) * | 2018-12-03 | 2020-06-04 | British Telecommunications Public Limited Company | Multi factor network anomaly detection |
Non-Patent Citations (1)
| Title |
|---|
| 贾年: "计算机网络信息安全及其预警系统", 《四川工业学院学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113038035B (en) | 2022-05-17 |
| CN112543289A (en) | 2021-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10171480B2 (en) | Cloud-based surveillance with intelligent tamper protection | |
| CN108040220A (en) | Wisdom garden video monitoring system | |
| CN102387038B (en) | Network video fault positioning system and method based on video detection and comprehensive network management | |
| US9401839B2 (en) | Generation and control of network events and conversion to SCADA protocol data types | |
| CN104137154B (en) | Systems and methods for managing video data | |
| CN101409463A (en) | Protection and video system gang control method for electric power system digitalization transforming plant | |
| CN104486101B (en) | A kind of online power remote IEC104 transmission abnormality detection methods | |
| CN110941228B (en) | Intelligent railway traction substation management and control system | |
| CN105208352B (en) | A kind of network video safety monitoring system and physical isolation method | |
| CN113659705B (en) | Substation operation management system | |
| CN104375485A (en) | Auxiliary monitoring system for electricity transformation and distribution safety production and monitoring method of auxiliary monitoring system for electricity transformation and distribution safety production | |
| CN113535513A (en) | Global background server running state monitoring system and method based on micro-service architecture | |
| CN104851222B (en) | A kind of NVSG relates to the management method of vouching position comprehensive security management system | |
| CN112350858A (en) | Cloud intelligent home data security management system | |
| CN104050807A (en) | On-line parking lot management system | |
| CN113038035B (en) | AI video point counting method for live pig breeding | |
| CN101713974A (en) | Integrated application platform using information flow monitoring as core | |
| CN110751766A (en) | Access control management system and method | |
| CN109639587A (en) | A kind of flow monitoring system based on electric automatization | |
| CN112448949A (en) | Computer network monitoring system | |
| CN117041251A (en) | Multi-data virtualization cluster management system based on edge computing | |
| CN109977962A (en) | A kind of Cable's Fault hidden danger automatic identifying method and system | |
| KR102145421B1 (en) | Digital substation with smart gateway | |
| CN114338214A (en) | Risk control method and system | |
| CN113301560A (en) | Electric power Internet of things terminal control method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |