CN110022466A - A kind of video analysis platform and its control method based on wisdom big data - Google Patents
A kind of video analysis platform and its control method based on wisdom big data Download PDFInfo
- Publication number
- CN110022466A CN110022466A CN201910332821.8A CN201910332821A CN110022466A CN 110022466 A CN110022466 A CN 110022466A CN 201910332821 A CN201910332821 A CN 201910332821A CN 110022466 A CN110022466 A CN 110022466A
- Authority
- CN
- China
- Prior art keywords
- video
- analysis
- management system
- data
- total management
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- 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
Abstract
The invention discloses a kind of video analysis platforms and its control method based on wisdom big data, belong to the technical field of video analysis processing, including intelligent analysis system, stream media service system, total management system, the intelligent analysis system, stream media service system and total management system successively communicate to connect, total management system communication link is connected to client, and client accesses the total management system by web;The intelligent analysis system is for receiving video data stream and carrying out intellectual analysis to it;The stream media service system is used to receive the final output data of intellectual analysis and pushes to total management system;The total management system is used to receive the preliminary output data of intellectual analysis and provides parameter configuration to intelligent analysis system, serve the security works such as the public security prevention and control of each operation area, in advance intelligent predicting deploy to ensure effective monitoring and control of illegal activities, subsequent quick response, the production run of upkeep operation area stablize provide strength support purpose.
Description
Technical field
The invention belongs to the technical fields of the acquisition of the video information of gas industries, analysis and processing system, specifically, relating to
And a kind of video analysis platform and its control method based on wisdom big data.
Background technique
In recent years, as gas industries are quickly grown, under the leading of industry background and big data business, video is visualized
Information collection, processing and management level but relatively lag behind, therefore establish a set of reasonable gas industries intelligent video monitoring platform
It is very necessary.Intelligent video monitoring platform of this set based on big data established can be corporate operations personnel and management department at different levels
Door provides scientific management information in day-to-day operations management aspect, provides a kind of visual, intuitive video for manager
Monitoring scheme reaches the personnel state for allowing each hierarchy management person that can grasp most base, most details intuitively, in real time, realizes each work
The flattening and detail management at industry area scene.
Currently, each operation area in each oil field is all made of is that physical location is mutually isolated, keeps communicating smooth mode, and
Geographical location between each operation area relatively disperses again.According to the related governing requirements in oil field, each operation area needs to use
Respective independent dispersion management, administrative center's Centralized Monitoring mode.Therefore it needs to understand the management region in real time in administrative center
The security situation of interior all construction areas, construction personnel is very urgent, and how effectively in real time in administrative center's exhibition
Show anomalous video information and the alarm in management region, guarantees the reliable of warning message, complete and real-time just at intelligent view
The task of top priority of frequency analysis.However, due to the development restriction of gas industries professional skill, currently, oil gas field video analysis is main
There are problems that the following aspects:
1, video analysis, which is mostly used, increases intellectual analysis function in front monitoring front-end: increasing abnormal conditions point according to previous front end
From the point of view of analysis, not only accuracy is not high for this processing mode, and video monitoring management platform is provided using front monitoring front-end producer
Integrated Management Platform.Such way to manage, tracking, behavior judgement, the alarm triggering of all targets are all by front end intellectual analysis
After equipment is completed, and warning message is only transmitted through the network to monitoring center, therefore all video analysis must be all pooled to
End or a certain key node are uniformly processed by computer.And it is this more demanding with real-time security property in oil gas field industry
For important type intelligence analysis occasion, it is most important that controllable key monitoring point is established, in the premise for meeting monitoring requirement
Lower appropriate occupancy computer performance and network bandwidth.
2, oilfield operation place mobility of people is big, and each operation area personnel allow the region stopped, time to be that dynamic becomes
Change: face system manager need to be according to operation area construction task dynamic corrections face database, and sets corresponding alarm bar
Part and threshold value, and video analytic system is pushed in time, it is identity validation, prevents in advance, the application such as record, post-mordem forensics in thing
Scene provides strong intelligence support.
3, behavioural analysis: for the safety defense monitoring system in oilfield operation area, it is most important that can be in video area
The movement, behavior, crowd's quantity etc. of goal task are monitored in domain, and pass through the accurate algorithm of intelligent video behavior analysis system
It realizes accurately Activity recognition, abnormity early warning is realized based on various actions rule predetermined.
4, crowd massing tests and analyzes: because of the particularity in oilfield operation area, therefore there is an urgent need in each construction area
The detection of densely populated place degree, demographic are completed, and completes early warning and alarming according to application scenarios and actual effect customization.
Summary of the invention
In consideration of it, the purpose of the present invention is to provide one kind to be based in order to solve the above-mentioned problems in the prior art
The video analysis platform and its control method of wisdom big data are based on big data intelligent searching engine realization search, comparison to reach
And analysis, the security works such as the public security prevention and control of each operation area are served, are broken laws and commit crime for prevention strike, it is pre- to reach intelligence in advance
Survey deploys to ensure effective monitoring and control of illegal activities, subsequent quick response, and the production run of upkeep operation area, which is stablized, provides the purpose of strength support.
The technical scheme adopted by the invention is as follows: a kind of video analysis platform based on wisdom big data, including intelligence point
Analysis system, stream media service system, total management system, the intelligent analysis system and stream media service system communicate to connect,
Stream media service system and total management system communicate to connect, and total management system communication link is connected to client, and client passes through
Web accesses the total management system;The intelligent analysis system is for receiving video data stream and carrying out intellectual analysis to it;Institute
Stream media service system is stated for receiving the final output data of intellectual analysis and pushing to total management system;The integrated pipe
Reason system is used to receive the preliminary output data of intellectual analysis and provides parameter configuration to intelligent analysis system, can be based on big number
Search, comparison and analysis are realized according to intelligent searching engine, and for related management, personnel are checked in time, being capable of real-time exhibition view
Violation mark in frequency source, and alarm is provided.
Further, the video data stream is obtained by front-end video acquisition device, front-end video acquisition device arrangement
In each operation area.
Further, the stream media service system is circumscribed with web server, and web server uses Spring
Framework framework, the framework keep extremely low code to pollute, and independently of various applications using low intrusive design method
Server.
A kind of control method of the video analysis platform based on wisdom big data, the control method are applied to big based on wisdom
The video analysis platform of data comprising following steps:
(1) video data stream is acquired, and by transmission of streams of video data to intelligent analysis system, intelligent analysis system carries out intelligence
It can analyze and obtain preliminary video detection data;
(2) preliminary video detection data is transmitted to total management system, total management system is according to business demand and just
Step video detection data gets parms configuration, and parameter configuration is fed back to intelligent analysis system;
(3) video data stream and preliminary video detection data recombinate folded by intelligent analysis system according to parameter configuration
Add, to obtain final video detection data;
(4) final video detection data is pushed into total management system by stream media service system;
(5) client is checked by final video detection data of the web access mode to total management system;
The above method can be realized deploy to ensure effective monitoring and control of illegal activities in intelligent predicting in advance, subsequent quick response, safeguard the production of each operation area
It is stable.
Further, client can also check video data stream progress directly access in the step (5), to facilitate pipe
Reason personnel can carry out initial data to implement to check.
Further, the stream media service system uses streaming manner, and streaming media service technology can be realized intelligence
The seamless combination and Push Service of result and video flowing can be analyzed, and is realized in the concrete application of petroleum security protection.
Further, intellectual analysis includes object detection and classification method in the step (1), the object detection and classification
Method includes the following steps:
1) several candidate regions are obtained using Selective Search algorithm, by each candidate region resize to system
One resolution ratio;
2) training CNN model, brings each candidate region into CNN model and carries out feature extraction, obtains test feature;
3) all candidate regions are demarcated to obtain candidate frame calibration result, and by test feature and candidate collimation mark
Determine result and be input to SVMs classifier to be trained, obtains the appraisal result to all candidate regions;
4) final candidate frame is obtained by non-maxima suppression method;
Using the above method can not only quick discrimination go out the classification of each object, but also object can be accurately positioned out
Position.
Further, intellectual analysis further includes human body critical point detection method, the inspection of human body key point in the step (1)
Survey method describes skeleton information by key point, and human body critical point detection is the basis of many Computer Vision Tasks,
Basic effect is all played in the research of other related fieldss of computer vision.
The invention has the benefit that
1. using intelligent analysis system to front-end video acquisition device video data stream collected carry out intellectual analysis and
The real-time monitoring, it can be achieved that front-end image data is managed, meanwhile, intelligent analysis system can also will analyze and determine result and report
In alert information superposition to video data stream, the video source with analysis result and alarm screen is formed, then pass through streaming media service
System is pushed, and for related management, personnel are checked in time, can violation mark in real-time exhibition video source, and mention
For alarm, compared to traditional video image analysis mode, intuitive and real-time are had more.
2. being managed using stream media service system to image analysis result and information pushing, convenient for administrative staff in visitor
Family end is remotely accessed, manages each front monitoring front-end;And access has web server on streaming media server, can guarantee pair
Video source with analysis result and alarm screen is pushed in time, and Web server uses Spring Framework framework,
Using low intrusive design method, extremely low code is kept to pollute, and independently of various application servers.
3. total management system provided by the present invention is integrated with the access control system of petroleum industry, job execution management system
And video monitoring system, it can be realized the special management requirement to petroleum industry Contraction in Site.
Detailed description of the invention
Fig. 1 is the logic flow of the control method operation of the video analysis platform provided by the invention based on wisdom big data
Figure.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination;All model trainings are programmed in using Python complete on eight generation of Intel's Duo (6 cores, 6 threads) processor
At.
A kind of video analysis platform based on wisdom big data, including intellectual analysis system are specifically provided in the present embodiment
System, stream media service system, total management system, the intelligent analysis system and stream media service system communicate to connect, and flow matchmaker
Body service system and total management system communicate to connect, and total management system communication link is connected to client, and client passes through the side web
Formula accesses the total management system;Wherein, intelligent analysis system includes first server and the intelligence that is loaded into first server
Can analysis platform, the first server is located at computer room or backstage center, is used under the conditions of reasonable bandwidth occupancy according to having determined
Regular analysis video data stream in real time;Stream media service system includes second server and the stream matchmaker that is loaded into second server
Body service platform;Total management system includes third server and the comprehensive management platform that is loaded into third server.
Above-mentioned intelligent analysis system is for receiving video data stream and carrying out intellectual analysis to it;The intellectual analysis can be realized
Detection to various unlawful practices, comprising: intrusion detection and tracking, personnel fall, personnel are static, do not wear a safety helmet, high-risk apply
Work industry fence etc..
Above-mentioned stream media service system is used to receive the final output data of intellectual analysis and pushes to total management system,
So that administrative staff check;Second server supports more equipment, multi-client access, can fast implement stable equipment access clothes
Business, can carry out service function fractionation according to their own needs, be pushed with realizing to the management of image analysis result and information,
Convenient for administrative staff client remote access, manage each front-end video acquisition device;Streaming media service platform supports real-time streams
Transport protocol (Real Time Streaming Protocol, abbreviation RTSP), the video camera stream matchmaker for supporting security industry to need
Body forwarding capability also supports that (coding mode supports H264/MJPEG/MPEG4, branch to the multi-platform RTSP direct broadcast function of internet industry
Hold AAC/PCMA/PCMU/G726), support crucial frame index (second opens picture), support novel maintenance etc..
The stream media service system is circumscribed with web server, and web server uses Spring Framework framework,
The advantage is that: 1. low intrusive design method, keeps extremely low code to pollute, and independently of various application servers;
2. realizing Write Once, the promise of Run Anywhere based on Spring frame;
3. relying on injection (Dependency Injection, abbreviation DI) mechanism using Spring reduces business object replacement
Complexity, improve component between decoupling ability.
4. to improve software repeated usage ability, using based on towards tangent plane programming (Aspect Oriented
Programming, abbreviation AOP) thought, complete the centralized management of common tasks such as safety, affairs, log etc..
5. the ORM and DAO of Spring provide the good integration with third party's Persistence Layer Framework, and simplify the number of bottom
It is accessed according to library.
6. mandatory use does not place one's entire reliance upon Spring Spring, developer can freely select the part of Spring frame
Or all.
The total management system is used to receive the preliminary output data of intellectual analysis and provides ginseng to intelligent analysis system
Number configuration;Comprehensive management platform in the total management system includes gate inhibition's unit, job execution management unit and video monitoring
Unit;To meet the special management requirement of petroleum industry Contraction in Site.Such as: it marches into the arena people to the violation for not issuing working bill
The identification of member and alarm, temporary construction are marched into the arena personnel's authority recognition etc..
The video data stream is obtained by front-end video acquisition device.Such as: camera, pickup mobile terminal, monitoring
Equipment etc..Each front-end video acquisition device is deployed in place front door, channel or the position for needing to acquire image data respectively, protects
Minimum pixel needed for card acquired image size meets the detected rule, and guarantee that network is unobstructed.
As shown in Figure 1, the present embodiment additionally provides a kind of control method of video analysis platform based on wisdom big data,
The control method is applied to the above-mentioned provided video analysis platform based on wisdom big data comprising following steps:
(1) video data stream is acquired by front-end video acquisition device, and by transmission of streams of video data to intellectual analysis system
System, intelligent analysis system carry out intellectual analysis and obtain preliminary video detection data;
The intellectual analysis provided in this step includes object detection and classification method, the object detection and classification method packet
Include following steps:
1) several candidate regions are obtained using Selective Search algorithm, by each candidate region resize to system
One resolution ratio;Obtain the specific steps of candidate region are as follows:
A. a kind of over-segmentation means are used, zonule (1k --- 2k) are divided the image into;
B. existing zonule is checked, according to the merging highest two neighboring region of compatible rule merging possibility.
It repeats, until whole image is merged into a regional location;
C. all regions once existed, so-called candidate region are exported;
Wherein, merge rule: preferential to merge following four region:
A) color (color histogram) is similar;
B) texture (histogram of gradients) is similar;
C) gross area is small after merging: guaranteeing that the scale of union operation is more uniform, one big region is avoided " to eat successively
Fall " other zonules;
D) after merging, gross area proportion in its BBOX is big: guaranteeing regular shape after merging.BBOX refers to
Bounding Box, is the minimum rectangle comprising object, and target object should be inside minimum rectangle;In object detection, output one
Group (x, y, w, h), in which: x, y represent the upper left corner bbox (or other fixed points, can customize);W, h represent bbox width and
It is high;One group (x, y, w, h) can uniquely determine a posting.
2) training CNN model, brings each candidate region into CNN model and carries out feature extraction, obtains test feature;
3) all candidate regions are demarcated to obtain candidate frame calibration result, and by test feature and candidate collimation mark
Determine result and be input to SVMs classifier to be trained, obtains the appraisal result to all candidate regions;
4) final candidate frame is obtained by non-maxima suppression method, wherein non-maxima suppression method is specific as follows:
Non-maxima suppression (NMS) can regard the search problem of local maximum as, and non-maxima suppression is exactly not
It is curbing for maximum, the method for non-maxima suppression is: first assumes there are 6 rectangle frames, according to the category classification of classifier
Probability sorts, it is assumed that the probability for belonging to vehicle from small to large is respectively A, B, C, D, E, F.
Since maximum probability rectangle frame F, judge whether the degree of overlapping IoU of A~E and F is greater than the threshold of some setting respectively
Value;Assuming that the degree of overlapping of B, D and F are more than threshold value, then just throwing away B, D;And first rectangle frame F of label, it is that we retain
Come.From remaining rectangle frame A, C, E, then the maximum E of select probability judges that the degree of overlapping of E Yu A, C, degree of overlapping are greater than
Certain threshold value, then just throwing away;And marking E is second rectangle frame that we remain;It is repeated always with this, finds institute
There is the rectangle frame being retained.
Wherein, degree of overlapping IoU refers to that Intersection over Union is handed over and compared, i.e. target window (Bounding
Box) and the friendship of original mark window and ratio, for two region R and R ', then the overlapping degree IoU in two regions is calculated as follows:
O (R, R ')=| R ∩ R ' |/| R ∪ R ' |
When training network, positive negative sample is determined according to the IoU value in candidate region and calibration region.
Intellectual analysis provided in the step further includes human body critical point detection method, skeleton critical point detection,
That is Pose Estimation predominantly detects some key points of human body, such as joint, five official ranks, human body critical point detection method
Skeleton information is described by key point.
Human body critical point detection method is mainly there are two direction, one is from top to bottom, another kind be from bottom to top, wherein
From it is upper and on skeleton key point location algorithm mainly include two parts, human testing and single human body key point inspection
It surveys, i.e., everyone detected by algorithm of target detection first, then done on the basis of detection block for single people
Skeleton critical point detection, wherein representative algorithm has G-RMI, CFN, RMPE, Mask R-CNN, and CPN.
And bottom-to-top method also includes two parts, critical point detection and key point cluster, i.e., firstly the need of will scheme
All key points all detected in piece, and all key points are then clustered into different individuals by corresponding strategies,
In representative algorithm that relationship between key point is modeled have PAF, Associative Embedding, Part
Segmentation,Mid-Range offsets。
(2) preliminary video detection data is transmitted to total management system, total management system takes into account intelligent analysis system
Concrete analysis application (such as the tumble personnel alarm, safety cap detection, people of the parameter configuration of detection and preliminary video detection data
Member's permission is undesirable etc.), total management system generates various institutes according to specific business need and preliminary video detection data
The parameter configuration needed, and parameter configuration is fed back into intelligent analysis system;
(3) video data stream and preliminary video detection data recombinate folded by intelligent analysis system according to parameter configuration
Add, recombination superposition can be carried out by character adding equipment, to obtain final video detection data (i.e. with detection and analysis result
Video data);
(4) final video detection data is pushed into total management system by stream media service system;
(5) administrative staff pass through web access mode to the final video detection data of total management system on the client
(i.e. with the video data for testing and analyzing result) is checked that administrative staff on the client can also be to view in the step (5)
Frequency data stream carries out directly access and checks, i.e., directly play by DST PLAYER and check.
The stream media service system uses streaming manner, and streaming manner is then by more matchmakers such as entire AV and 3D
Body file is divided into compressed package one by one by special compress mode, continuous, real-time from video server to subscriber computer to pass
It send.Using streaming media service technology, realizes and Push Service is carried out to the video flowing with analysis result, and the service is pacified in petroleum
It is realized in anti-concrete application.
Embodiment 2
In the present embodiment, the video analysis platform and its controlling party based on wisdom big data to be provided in embodiment 1
Based on method, by taking safety cap tests and analyzes as an example, system intercepts the video source in video monitoring system using as video data stream,
Comprehensive analysis is carried out by each feature such as safety cap type, color, shape to petroleum website and generates parameter configuration, and by the ginseng
Number configuration feeds back to intelligent analysis system, and intelligent analysis system will analyze and determine that result and warning message are added to former video data
On stream, the video source with analysis result and alarm screen is formed, then by the push function of stream media service system, pushed away
It is sent in total management system, for related management, personnel are checked, the mode of checking is divided into web access and DST PLAYER access two
Kind of mode, by treated video pictures (video source i.e. with analysis result and alarm screen), can real-time exhibition simultaneously
The personnel of non-safe wearing cap are marked, and alarm is provided.
The present invention is not limited to above-mentioned optional embodiment, anyone can show that other are various under the inspiration of the present invention
The product of form, however, make any variation in its shape or structure, it is all to fall into the claims in the present invention confining spectrum
Technical solution, be within the scope of the present invention.
Claims (8)
1. a kind of video analysis platform based on wisdom big data, including intelligent analysis system, stream media service system, integrated pipe
Reason system, which is characterized in that the intelligent analysis system and stream media service system communicate to connect, stream media service system with it is comprehensive
Communication connection is closed, total management system communication link is connected to client, and client accesses the integrated management system by web
System;
The intelligent analysis system is for receiving video data stream and carrying out intellectual analysis to it;
The stream media service system is used to receive the final output data of intellectual analysis and pushes to total management system;
The total management system, which is used to receive the preliminary output data of intellectual analysis and provides parameter to intelligent analysis system, matches
It sets.
2. the video analysis platform according to claim 1 based on wisdom big data, which is characterized in that the video data
Stream is obtained by front-end video acquisition device.
3. the video analysis platform according to claim 1 based on wisdom big data, which is characterized in that the Streaming Media clothes
Business system is circumscribed with web server, which uses Spring Framework framework.
4. a kind of control method of the video analysis platform based on wisdom big data, which is characterized in that the control method is applied to
Video analysis platform as claimed in any one of claims 1-3 based on wisdom big data comprising following steps:
(1) video data stream is acquired, and by transmission of streams of video data to intelligent analysis system, intelligent analysis system carries out intelligence point
It analyses and obtains preliminary video detection data;
(2) preliminary video detection data is transmitted to total management system, total management system is according to business demand and preliminary view
Frequency detection data gets parms configuration, and parameter configuration is fed back to intelligent analysis system;
(3) video data stream and preliminary video detection data are carried out recombination superposition according to parameter configuration by intelligent analysis system, with
Obtain final video detection data;
(4) final video detection data is pushed into total management system by stream media service system;
(5) client is checked by final video detection data of the web access mode to total management system.
5. the control method of the video analysis platform according to claim 4 based on wisdom big data, which is characterized in that institute
Video data stream progress directly access can also be checked by stating client in step (5).
6. the control method of the video analysis platform according to claim 4 based on wisdom big data, which is characterized in that institute
Stream media service system is stated using streaming manner.
7. the control method of the video analysis platform according to claim 4 based on wisdom big data, which is characterized in that institute
Stating intellectual analysis in step (1) includes object detection and classification method, which includes the following steps: with classification method
1) several candidate regions are obtained using Selective Search algorithm, by each candidate region resize to unified point
Resolution;
2) training CNN model, brings each candidate region into CNN model and carries out feature extraction, obtains test feature;
3) all candidate regions are demarcated to obtain candidate frame calibration result, and test feature and candidate frame calibration are tied
Fruit is input to SVMs classifier and is trained, and obtains the appraisal result to all candidate regions;
4) final candidate frame is obtained by non-maxima suppression method.
8. the control method of the video analysis platform according to claim 4 based on wisdom big data, which is characterized in that institute
Stating intellectual analysis in step (1) further includes human body critical point detection method, and human body critical point detection method is retouched by key point
State skeleton information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910332821.8A CN110022466A (en) | 2019-04-24 | 2019-04-24 | A kind of video analysis platform and its control method based on wisdom big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910332821.8A CN110022466A (en) | 2019-04-24 | 2019-04-24 | A kind of video analysis platform and its control method based on wisdom big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110022466A true CN110022466A (en) | 2019-07-16 |
Family
ID=67192259
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910332821.8A Pending CN110022466A (en) | 2019-04-24 | 2019-04-24 | A kind of video analysis platform and its control method based on wisdom big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110022466A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110490126A (en) * | 2019-08-15 | 2019-11-22 | 成都睿晓科技有限公司 | A kind of safety cabinet security management and control system based on artificial intelligence |
CN111123866A (en) * | 2019-12-17 | 2020-05-08 | 中国石油集团工程股份有限公司 | Intelligent oil field ground data management and control system |
CN111683270A (en) * | 2020-06-12 | 2020-09-18 | 北京英智数联科技有限公司 | Video analysis system, control system, management system and monitoring system |
CN112766091A (en) * | 2021-01-05 | 2021-05-07 | 中科院成都信息技术股份有限公司 | Video unsafe behavior recognition system and method based on human skeleton key points |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN106303468A (en) * | 2016-11-02 | 2017-01-04 | 北京弘恒科技有限公司 | The warning system of early warning Intelligent Recognition in advance |
CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
CN107277470A (en) * | 2017-08-10 | 2017-10-20 | 四川天翼网络服务有限公司 | A kind of network-linked management method and digitlization police service linkage management method |
US20180150681A1 (en) * | 2016-11-30 | 2018-05-31 | Altumview Systems Inc. | Face detection using small-scale convolutional neural network (cnn) modules for embedded systems |
-
2019
- 2019-04-24 CN CN201910332821.8A patent/CN110022466A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
CN106303468A (en) * | 2016-11-02 | 2017-01-04 | 北京弘恒科技有限公司 | The warning system of early warning Intelligent Recognition in advance |
US20180150681A1 (en) * | 2016-11-30 | 2018-05-31 | Altumview Systems Inc. | Face detection using small-scale convolutional neural network (cnn) modules for embedded systems |
CN107277470A (en) * | 2017-08-10 | 2017-10-20 | 四川天翼网络服务有限公司 | A kind of network-linked management method and digitlization police service linkage management method |
Non-Patent Citations (1)
Title |
---|
陈慧岩等人: "《智能车辆理论与应用》", 31 July 2018 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110490126A (en) * | 2019-08-15 | 2019-11-22 | 成都睿晓科技有限公司 | A kind of safety cabinet security management and control system based on artificial intelligence |
CN110490126B (en) * | 2019-08-15 | 2023-04-18 | 成都睿晓科技有限公司 | Safe deposit box safety control system based on artificial intelligence |
CN111123866A (en) * | 2019-12-17 | 2020-05-08 | 中国石油集团工程股份有限公司 | Intelligent oil field ground data management and control system |
CN111683270A (en) * | 2020-06-12 | 2020-09-18 | 北京英智数联科技有限公司 | Video analysis system, control system, management system and monitoring system |
CN112766091A (en) * | 2021-01-05 | 2021-05-07 | 中科院成都信息技术股份有限公司 | Video unsafe behavior recognition system and method based on human skeleton key points |
CN112766091B (en) * | 2021-01-05 | 2023-09-29 | 中科院成都信息技术股份有限公司 | Video unsafe behavior recognition system and method based on human skeleton key points |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110022466A (en) | A kind of video analysis platform and its control method based on wisdom big data | |
Laufs et al. | Security and the smart city: A systematic review | |
CN108174165A (en) | Electric power safety operation and O&M intelligent monitoring system and method | |
US11328163B2 (en) | Methods and apparatus for automated surveillance systems | |
US8068986B1 (en) | Methods and apparatus related to sensor signal sniffing and/or analysis | |
Tian et al. | IBM smart surveillance system (S3): event based video surveillance system with an open and extensible framework | |
Haering et al. | The evolution of video surveillance: an overview | |
CN103578240B (en) | A kind of security protection service network based on Internet of Things | |
JP5224401B2 (en) | Monitoring system and method | |
CN110428522A (en) | A kind of intelligent safety and defence system of wisdom new city | |
US20150379355A1 (en) | A surveillance system | |
CN108269331A (en) | A kind of intelligent video big data processing system | |
US11615620B2 (en) | Systems and methods of enforcing distancing rules | |
Alshammari et al. | Intelligent multi-camera video surveillance system for smart city applications | |
EP3867841A1 (en) | System for controlling and managing a process within an environment using artificial intelligence techniques and relative method | |
US20210074099A1 (en) | Method and system for providing access control | |
CN105208325B (en) | The land resources monitoring and early warning method captured and compare analysis is pinpointed based on image | |
CN108898104A (en) | A kind of item identification method, device, system and computer storage medium | |
CN106548626A (en) | A kind of comprehensive management platform based on geographical information technology | |
CN109068105A (en) | A kind of prison video monitoring method based on deep learning | |
CN109582824A (en) | A kind of region security management system and method based on video structural | |
US10586130B2 (en) | Method, system and apparatus for providing access to videos | |
CN116452379A (en) | Intelligent campus management system based on big data | |
US20210357654A1 (en) | Systems and methods of identifying persons-of-interest | |
US20150287306A1 (en) | Proactive Loss Prevention 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190716 |
|
RJ01 | Rejection of invention patent application after publication |