CN109413213A - Cluster monitoring system based on system on chip - Google Patents
Cluster monitoring system based on system on chip Download PDFInfo
- Publication number
- CN109413213A CN109413213A CN201811562550.7A CN201811562550A CN109413213A CN 109413213 A CN109413213 A CN 109413213A CN 201811562550 A CN201811562550 A CN 201811562550A CN 109413213 A CN109413213 A CN 109413213A
- Authority
- CN
- China
- Prior art keywords
- sub
- monitoring
- monitor
- server
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 89
- 238000012545 processing Methods 0.000 claims description 32
- 230000002547 anomalous effect Effects 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 abstract description 10
- 238000004891 communication Methods 0.000 abstract description 7
- 230000007812 deficiency Effects 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 23
- 230000005540 biological transmission Effects 0.000 description 12
- 206010000117 Abnormal behaviour Diseases 0.000 description 9
- 238000000034 method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of cluster monitoring system based on system on chip, which includes, the sub- end of monitor and server terminal;The phase generator terminal is made of monitoring camera and light source;The sub- end of monitor is connected with monitoring camera by CAN bus;The sub- end of monitor includes processor CPU, memory, GPS positioning system, SIM network communication module, wifi wireless communication module, memory.The present invention can effectively promote the precision and efficiency of detection, and reduce the erection cost of monitoring system.The present invention is able to solve traditional deficiency monitored by people, reduces human cost, avoids due to people's monitoring for a long time and the tired careless omission for leading to accident detection.
Description
Technical field
The present invention relates to embedded OSs and related hardware, more particularly to a kind of cluster video monitoring system.
Background technique
In recent years, video monitoring has been widely used in the environment such as campus security, traffic monitoring and indoor monitoring.With
The promotion of monitoring quantity, need a kind of quick, stable method to be monitored management, the sight of cluster monitoring to video content
Point, which is also taken advantage of a situation, to be suggested.Traditional artificial monitoring method is only applicable to that scene is single, in a limited number of environment of camera, and is supervising
Control camera quantity is more, monitoring scene is complicated, unconventional behavior and the duration it is short when, manual method is easy to fail.With
The machine learning method introduced afterwards obtains crucial conclusion by the methods of depth network Automatic analysis video content, is promoted
Quality monitoring and efficiency.But this kind of algorithm is at present in order to guarantee its monitoring accuracy and efficiency, generallys use that the number of plies is more, frame
The depth network of structure complexity, thus video analysis can not be completed in monitoring client or mobile terminal, need to upload the data to high property
Energy server is handled.It is less to the operating pressure of server and when monitoring probe negligible amounts, but monitoring probe number
When amount increases, then the hardware index such as calculated performance, transmission bandwidth width for needing that great amount of cost is spent to promote server, for collection
The popularization of group's monitoring, out tape carry out very big difficulty.
Existing video monitoring system, monitoring client is usually only responsible for the acquisition of video, transmission, and terminal server then needs
The data of acquisition are carried out, handled and recorded.Such construction has high requirement to server end, needs higher fortune
Calculation ability and biggish bandwidth width, system building higher cost;And it cannot be according to the difference of monitored environment, to policing algorithm
It is adjusted, lacks flexibility.
In existing technical solution, monitoring camera is mutually separated with video analysis, and cost is especially high, and is wanted to environment deployment
Ask high.Including the following aspects:
(1) the collected picture of monitoring camera needs to be uploaded to server end in real time, and thus transmission of video needs bandwidth
Situation at high cost, such as being transmitted using WiFi, only can be suitably used for short-distance transmission, and have signal disturbed.Such as use twisted pair
Etc. modes transmit, need to increase the deployment of route, under group's monitoring condition, considerably increase lower deployment cost, while bringing all
Mostly such as the inconvenience of line management.
(2) server end is needed to be added collected data to monitoring and be handled in real time, since current camera is mostly height
Clear camera, can be very big to the data volume of this server-side processes, meanwhile, general monitoring is mostly group's monitoring, and server end needs
Multi-path video data is analyzed and processed, thus the increased pressure of server end, to this to GPU, CPU of server end, interior
It is very high to deposit configuration requirement, Processing Algorithm is required high.This C/S structure is used simultaneously, multi-path monitoring camera is connected to server,
If once server end causes server end that this memory spilling or even delay machine etc. occurs and asks since processing data pressure is excessive
Topic occurs, and can directly result in the collapse of monitoring system.
(3) monitoring camera mutually separates the cost that will increase system maintenance with video processing.
Summary of the invention
Ground of the invention purpose is to provide a kind of cluster monitoring system based on system on chip, to make up the prior art not
Foot.
For existing video monitoring system, the analysis detection of video content is realized in server end, and terminal camera is only
The acquisition and transmission work for being responsible for image are easy to greatly increase the operation pressure of server end when monitored scene is more.No
Demand is monitored suitable for actual scene.Cluster monitoring system provided by the present invention, can be according to the difference of monitoring environment, to monitoring
Algorithm is adjusted, to achieve the purpose that monitor different target.
In order to achieve the above objectives, the present invention take the specific technical proposal is:
A kind of cluster monitoring system based on system on chip, which includes, the sub- end of monitor and server terminal;It is described
Phase generator terminal is made of monitoring camera and light source;The sub- end of monitor is connected with monitoring camera by CAN bus;The server
Terminal is connected by wifi with the sub- end of the monitor;The server terminal includes mobile terminal, wifi, high-performance server
And memory;The phase generator terminal carries out data acquisition, and the sub- end of monitor carries out data processing;The server terminal is to institute
It states and monitors the handled abnormal data analyzed in sub- end and carry out being analyzed to identify again, and to the data of the sub- end acquisition of the monitoring
It is stored.
Further, an embedded unit is set in the sub- end of the monitor, including processor CPU, memory, GPS fixed
Position system, SIM network communication module, wifi wireless communication module, memory.
Further, the embedded unit uses hikey970 development board, and development board is furnished with 12 core Mali- of high-order
G72MP12 graphics processor GPU.
Further, front end depth network is carried at the sub- end of the monitor, and network uses residual sum bottleneck structure, and the number of plies is
4 layers.Front end 3 kinds of behaviors of depth network major prognostic: normal behaviour, abnormal behaviour and doubtful behavior.
Further, the server terminal carries rear end depth network, equally uses residual sum bottleneck structure, and the number of plies is
7 layers.Rear end depth network is further processed abnormal behaviour and doubtful behavior, and abnormal behaviour and doubtful behavior are divided into illegally
Intrusion behavior illegally flees from behavior, disaster-stricken dangerous act.
Above system workflow: video data is acquired by the monitoring camera in real time, by the video data of acquisition by CAN
Bus transfer runs depth network into the embedded unit, and as video data is passed to embedded system by CAN bus
After system, event monitoring is done by GPU, the processing analysis of video is carried out, obtains result;If the result queue of analysis is abnormal thing
Part then needs the video by this analysis processing to be uploaded to the server terminal, carries out processing again;Otherwise, this time
Video is only to be sent to server end to be stored, without doing analysis processing.
Above-mentioned behavior is defined as follows: normal behaviour does not include dangerous play, in the area legal behavior, such as just
Normal exchange, walking etc.;Abnormal behaviour and doubtful behavior, be comprising dangerous, illegal behavior, such as personnel without authorization into
Enter, leave some specific region;Or the hazardous acts such as fire may occur.The two difference is that abnormal behaviour is in front end depth
Network is the very normal behaviour of higher score, and doubtful behavior is then the improper behavior for obtaining lower score.
The advantages of the present invention:
Cluster video monitoring processing system proposed by the invention, core are to realize the on-line analysis of video, that is, are being supervised
Control end carries out processing analysis to video content.Video data transmission to particular server is not done at concentration under normal circumstances
Reason, but decentralized processing video content, real-time Transmission processing result, server are responsible for recording and analyzing as a result, and handling special feelings
Condition;Be effectively reduced the operation pressure of server end in this way, reduce system cost, and terminal can according to environment adjustment algorithm,
With higher flexibility.
The present invention can be used in detecting the foreign body intrusion of on-site and two class abnormal behaviours of illegally leaving the post, and can effectively promote inspection
The precision and efficiency of survey, and reduce the erection cost of monitoring system.The present invention is able to solve the deficiency that tradition is monitored by people, reduces
Human cost is avoided due to people's monitoring for a long time and the tired careless omission for leading to accident detection;The present invention passes through in monitoring
End and server terminal carry out video analysis processing twice, it is ensured that can accurately note abnormalities event, prevent anomalous event
Wrong report;The present invention carries out the detection of anomalous event by joined the sub- end of monitoring, monitor video data in multiple sub- ends of monitoring,
Server end is only handled the anomalous event detected in the sub- end of monitoring, greatly alleviates the data processing of server end
Pressure also avoids to be collapsed using server as center node by monitoring system caused by server delay machine.
Detailed description of the invention
Fig. 1 is cluster monitoring schematic diagram in embodiment 1.
Fig. 2 is monitoring system configuration diagram of the present invention.
Fig. 3 is testing process schematic diagram of the present invention.
Fig. 4 is front end depth network structure of the invention.
Fig. 5 is terminal depth network structure of the invention.
Specific embodiment
The present invention is explained further and is illustrated below by way of specific embodiment and in conjunction with attached drawing.
Embodiment 1:
As shown in Fig. 2, a kind of cluster monitoring system based on system on chip, which includes, the sub- end of monitor and service
Device terminal;The phase generator terminal is made of monitoring camera and light source;The sub- end of the monitor and monitoring camera pass through CAN bus phase
Even;The sub- end of monitor includes processor CPU, memory, GPS positioning system, SIM network communication module, wifi channel radio
Believe module, memory;The server terminal is connected by wifi with the sub- end of the monitor;The server terminal includes moving
Dynamic terminal, wifi, high-performance server and memory;The phase generator terminal carries out data acquisition, and the sub- end of monitor is counted
According to processing;The server terminal carries out being analyzed to identify again to the abnormal data of analysis handled by the sub- end of the monitoring, with
And the data of the sub- end acquisition of the monitoring are stored;An embedded unit is set in the sub- end of monitor, which matches
There are CPU, GPU, memory and memory, the embedded unit uses hikey970 development board, and development board is furnished with 12 core of high-order
Mali-G72MP12 graphics processor GPU.
As shown in figure 3, above system workflow: video data is acquired in real time by the monitoring camera, by the view of acquisition
Frequency runs the incident Detection Algorithm of deep learning, as video data according to being transmitted in the embedded unit by CAN bus
After being passed to embedded system by CAN bus, event monitoring is done by GPU, the processing analysis of video is carried out, obtains result;
If the result queue of analysis is anomalous event, the video by this analysis processing is needed to be uploaded to the server terminal,
Carry out processing again;Otherwise, this time video is only to be sent to server end to be stored, without doing analysis processing.
Front end depth network is carried at the sub- end of monitor, as shown in figure 4, network uses residual sum bottleneck structure, the number of plies
It is 4 layers.Front end 3 kinds of behaviors of depth network major prognostic: normal behaviour, abnormal behaviour and doubtful behavior.
The server terminal carries rear end depth network, as shown in figure 5, equally using residual sum bottleneck structure, the number of plies
It is 7 layers.Rear end depth network is further processed abnormal behaviour and doubtful behavior, abnormal behaviour and doubtful behavior is divided into non-
Method intrusion behavior illegally flees from behavior, disaster-stricken dangerous act.
As shown in Figure 1, present system can detect two application scenarios of indoor and outdoors.Pass through different things
Part detection algorithm, indoor office worker leave the post to detect, and do intrusion detection to outdoor.
In plant area's office section, whether monitoring camera is mainly responsible for monitoring personnel on duty;In article storage section, prison
Control camera, which is mainly responsible for, has monitored whether illegal invasion;And in gate sentry, monitoring camera is then responsible for carrying out disengaging personnel and vehicle
It captures, detects non-registered personnel and vehicle.Thus inside a big garden, the purposes of phase generator terminal should be according to its institute
Monitor area type, and corresponding variation occurs.
The server terminal be furnished with high-performance GPU processor, can parallel processing multi-channel video number, pass through transmission medium
It is connected with the sub- end of monitor, the video data real-time transmission at each sub- end of monitor to server terminal, the video counts of transmission
According to being that have passed through the analysis of monitor end treated video data and event detection outcome label data;Wherein, label data
In indicate monitoring camera ID, is corresponding to it with end time, the server terminal by reading at the beginning of anomalous event
Monitoring camera the correspondence time in video data, secondary analysis is carried out to this segment data and is handled, as to monitoring sub- end
Anomalous event mark carry out confirmation again;If secondary processing result is shown as anomalous event, server end needs
Special mark is carried out to this section of video data, while server end is alarmed by weblication to the APP push being attached thereto
Signal.Note: server end weblication can be built by Django.If the secondary treatment result of server end marks
For non-anomalous event, then server end only stores without doing specially treated video.
Embodiment 2:
Present system, including the sub- end of monitor and server terminal are disposed in prison;The phase generator terminal is by monitoring phase
Machine and light source composition;The sub- end of monitor is connected with monitoring camera by CAN bus;The sub- end of monitor includes processor
CPU, memory, GPS positioning system, SIM network communication module, wifi wireless communication module, memory;The server terminal
It is connected by wifi with the sub- end of the monitor;The server terminal includes mobile terminal, wifi, high-performance server and is deposited
Reservoir;The phase generator terminal carries out data acquisition, and the sub- end of monitor carries out data processing;The server terminal is to the prison
It controls the handled abnormal data analyzed in sub- end and carries out being analyzed to identify again, and the data of the sub- end acquisition of the monitoring are carried out
Storage;An embedded unit is set in the sub- end of monitor, which is furnished with CPU, GPU, memory and memory, the insertion
Formula unit uses hikey970 development board, and development board is furnished with 12 core Mali-G72MP12 graphics processor GPU of high-order.
Above system workflow: video data is acquired by the monitoring camera in real time, by the video data of acquisition by CAN
Bus transfer runs the incident Detection Algorithm of deep learning into the embedded unit, and as video data passes through CAN bus
After being passed to embedded system, event monitoring is done by GPU, the processing analysis of video is carried out, obtains result;If the knot of analysis
Fruit is labeled as anomalous event, then needs the video by this analysis processing to be uploaded to the server terminal, carry out again
Processing;Otherwise, this time video is only to be sent to server end to be stored, without doing analysis processing.
It is deployed in prison environment, prison environment has mobility of people big, needs to monitor in real time, therefore need in prison
A large amount of deployment abnormal monitorings, if using it is traditional by personnel monitoring by the way of, it is easy to lead to ignoring for anomalous event, base
Anomalous event analysis is carried out in the mode of central server, not only needs the video data to each monitoring client to transmit, cloth
Line is at high cost and performance difficulty, while excessive to the pressure of central processing, needs to handle multi-channel video, server cost simultaneously
It is excessively high, or even need to dispose multiple servers.Once central server, which breaks down, leads to delay machine, entire monitoring system paralysis,
Therefore this mode disadvantage is very big.
Anomalous event monitoring system through the invention, by just having carried out the prison of anomalous event on each sub- end of monitoring
It surveys, monitors and whether fight in environment at the prison, or whether someone leaves specified region, if event of escaping from prison,
The extraction that abnormal results are directly carried out on monitoring sub- end, only needs abnormal data being transmitted to server in time, at this time due to different
The Video Events segment of ordinary affair part is relatively short, and data volume is relatively small, so transmission mode can be transmitted using WiFi,
Reduce the requirement disposed to route.In addition it monitors sub- end and has also carried out the storage of monitor video, if memory capacity reaches the upper limit
Later, the data of storage can be uploaded in server and is saved.Without uploading in real time, mitigate network transmission pressure.?
After server receives anomalous event, server carries out secondary confirmation judgement, then if it is anomalous event, can be by short
The mode of letter or mobile phone app issue corresponding warning message.
Effectively prison environment can be monitored in real time from there through present system, find prison ring in time
Exception information in border.If being once abnormal information timely can give warning message, Ke Yiyou to corresponding personnel
Effect avoid occurring in prison it is various such as fight, the generation for the events such as escape from prison.
Claims (6)
1. a kind of cluster monitoring system based on system on chip, which is characterized in that the system includes, the sub- end of monitor and server
Terminal;The phase generator terminal is made of monitoring camera and light source;The sub- end of monitor is connected with monitoring camera by CAN bus;
Embedded unit is equipped in the sub- end of monitor;The server terminal includes mobile terminal, wifi, high-performance server and
Memory;The phase generator terminal carries out data acquisition, and the sub- end of monitor carries out data processing;The server terminal is to described
Monitor the handled abnormal data analyzed in sub- end and carry out being analyzed to identify again, and to the data of the sub- end acquisition of the monitoring into
Row storage.
2. cluster monitoring system as described in claim 1, which is characterized in that an embedded single is arranged in the sub- end of monitor
Member, the unit are furnished with CPU, GPU, memory and memory.
3. cluster monitoring system as described in claim 1, which is characterized in that the working-flow: by the monitoring phase
Machine acquires video data in real time, and the video data of acquisition is transmitted in the embedded unit by CAN bus, runs depth net
Network after as video data is passed to embedded system by CAN bus, does event monitoring by GPU, carries out the processing of video
Analysis, obtains result;If the result queue of analysis is anomalous event, the video by this analysis processing is needed to be uploaded to institute
Server terminal is stated, processing again is carried out;Otherwise, this time video is only to be sent to server end to be stored, without doing
Analysis processing.
4. cluster monitoring system as described in claim 1, which is characterized in that the embedded unit is developed using hikey970
Plate, development board are furnished with 12 core Mali-G72MP12 graphics processor GPU of high-order.
5. cluster monitoring system as described in claim 1, which is characterized in that carry front end depth net in the sub- end of monitor
Network, network use residual sum bottleneck structure, and the number of plies is 4 layers.
6. cluster monitoring system as described in claim 1, which is characterized in that the server terminal carries rear end depth net
Network, equally uses residual sum bottleneck structure, and the number of plies is 7 layers.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811562550.7A CN109413213A (en) | 2018-12-20 | 2018-12-20 | Cluster monitoring system based on system on chip |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811562550.7A CN109413213A (en) | 2018-12-20 | 2018-12-20 | Cluster monitoring system based on system on chip |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109413213A true CN109413213A (en) | 2019-03-01 |
Family
ID=65460184
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811562550.7A Pending CN109413213A (en) | 2018-12-20 | 2018-12-20 | Cluster monitoring system based on system on chip |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109413213A (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101898567A (en) * | 2010-04-07 | 2010-12-01 | 西南交通大学 | Railway foreign body limit-intruding monitoring system based on intelligent video |
CN103108159A (en) * | 2013-01-17 | 2013-05-15 | 新疆电力公司乌鲁木齐电业局 | Electric power intelligent video analyzing and monitoring system and method |
CN103297751A (en) * | 2013-04-23 | 2013-09-11 | 四川天翼网络服务有限公司 | Wisdom skynet video behavior analyzing system |
CN105306925A (en) * | 2015-10-09 | 2016-02-03 | 福州市超智电子科技有限公司 | Monitoring system and monitoring method for video monitoring front-end equipment |
CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
CN106982359A (en) * | 2017-04-26 | 2017-07-25 | 深圳先进技术研究院 | A kind of binocular video monitoring method, system and computer-readable recording medium |
CN207218923U (en) * | 2017-09-15 | 2018-04-10 | 温州大学 | A kind of non real-time monitoring system under flow-sensitive environment |
CN108062349A (en) * | 2017-10-31 | 2018-05-22 | 深圳大学 | Video frequency monitoring method and system based on video structural data and deep learning |
CN108288251A (en) * | 2018-02-11 | 2018-07-17 | 深圳创维-Rgb电子有限公司 | Image super-resolution method, device and computer readable storage medium |
CN108876853A (en) * | 2017-11-30 | 2018-11-23 | 北京旷视科技有限公司 | Image position method, device, system and storage medium |
WO2018218286A1 (en) * | 2017-05-29 | 2018-12-06 | Saltor Pty Ltd | Method and system for abnormality detection |
CN209845008U (en) * | 2018-12-20 | 2019-12-24 | 泉州装备制造研究所 | Cluster monitoring system based on system on chip |
-
2018
- 2018-12-20 CN CN201811562550.7A patent/CN109413213A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101898567A (en) * | 2010-04-07 | 2010-12-01 | 西南交通大学 | Railway foreign body limit-intruding monitoring system based on intelligent video |
CN103108159A (en) * | 2013-01-17 | 2013-05-15 | 新疆电力公司乌鲁木齐电业局 | Electric power intelligent video analyzing and monitoring system and method |
CN103297751A (en) * | 2013-04-23 | 2013-09-11 | 四川天翼网络服务有限公司 | Wisdom skynet video behavior analyzing system |
CN105306925A (en) * | 2015-10-09 | 2016-02-03 | 福州市超智电子科技有限公司 | Monitoring system and monitoring method for video monitoring front-end equipment |
CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
CN106982359A (en) * | 2017-04-26 | 2017-07-25 | 深圳先进技术研究院 | A kind of binocular video monitoring method, system and computer-readable recording medium |
WO2018218286A1 (en) * | 2017-05-29 | 2018-12-06 | Saltor Pty Ltd | Method and system for abnormality detection |
CN207218923U (en) * | 2017-09-15 | 2018-04-10 | 温州大学 | A kind of non real-time monitoring system under flow-sensitive environment |
CN108062349A (en) * | 2017-10-31 | 2018-05-22 | 深圳大学 | Video frequency monitoring method and system based on video structural data and deep learning |
CN108876853A (en) * | 2017-11-30 | 2018-11-23 | 北京旷视科技有限公司 | Image position method, device, system and storage medium |
CN108288251A (en) * | 2018-02-11 | 2018-07-17 | 深圳创维-Rgb电子有限公司 | Image super-resolution method, device and computer readable storage medium |
CN209845008U (en) * | 2018-12-20 | 2019-12-24 | 泉州装备制造研究所 | Cluster monitoring system based on system on chip |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105120217B (en) | Intelligent camera mobile detection alert system and method based on big data analysis and user feedback | |
CN104635706B (en) | The cluster monitored by personnel detected based on information source and the application method of pre-warning system | |
CN103108159B (en) | Electric power intelligent video analyzing and monitoring system and method | |
CN105208528B (en) | A kind of system and method for identifying with administrative staff | |
CN110794785A (en) | Internet of things-based construction site edge calculation Internet of things analysis and alarm system and method | |
CN104023064B (en) | Statistical method of working hours of field personnel based on intelligent mobile terminal and activity characteristic analysis | |
CN105607617A (en) | Security fault diagnosis system and method based on Internet of Things | |
CN206272770U (en) | A kind of vehicle and face bayonet system | |
CN112087528B (en) | Intelligent water environment monitoring system and method based on deep learning | |
CN110209723A (en) | A kind of equipment information collection system based on Internet of Things big data | |
CN106817560A (en) | It is a kind of to distributed terminal display device real-time monitoring system and monitoring method | |
CN107017957A (en) | A kind of networking type radio broadcasting monitoring device, system and method | |
CN110969215A (en) | Clustering method and device, storage medium and electronic device | |
CN109684494A (en) | A kind of scenic spot looking-for-person method, system and cloud server | |
CN104835272A (en) | High-voltage power transmission iron tower antitheft system | |
CN106327791A (en) | Exceptional event real-time alarm method and system | |
CN105139471A (en) | Inspection method for electrical equipment | |
CN108733073A (en) | Unmanned plane managing and control system, method and readable medium in a kind of region | |
CN104361658B (en) | The detection method and device of a kind of region Nei Ge places people information | |
CN105070058B (en) | A kind of accurate road condition analyzing method and system based on real-time road video | |
CN110657841A (en) | Intelligent dust monitoring equipment for railway construction site | |
CN106453256A (en) | Password feature library system with automatic learning function and learning method thereof | |
CN105811578B (en) | Transmission line of electricity monitor supervision platform and its Power Supply Monitoring algorithm and image warning algorithm | |
CN104881904B (en) | Power transmission inspection field supervision system based on mobile intelligent terminal | |
CN117612107A (en) | Method for detecting abnormal personnel in place |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190301 |