CN109905423B - Intelligent management system - Google Patents
Intelligent management system Download PDFInfo
- Publication number
- CN109905423B CN109905423B CN201711292718.2A CN201711292718A CN109905423B CN 109905423 B CN109905423 B CN 109905423B CN 201711292718 A CN201711292718 A CN 201711292718A CN 109905423 B CN109905423 B CN 109905423B
- Authority
- CN
- China
- Prior art keywords
- cloud platform
- analysis
- unit
- data
- storage unit
- 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.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent management system, which is used for monitoring equipment and comprises: the system comprises a private cloud platform, a resource scheduling unit and a public cloud platform; the private cloud platform is arranged locally and comprises a first uniform storage unit and an analysis network unit; the public cloud platform comprises a second uniform storage unit and a training cluster; the resource scheduling unit is used for data interaction between the private cloud platform and the public cloud platform; the analysis network unit analyzes the data of the monitoring equipment and converts the unstructured data of the monitoring equipment into structured data; the training cluster is used for training a deep neural network cluster meeting business requirements and comprises a learning framework and a learning algorithm library; the first unified storage unit and the second unified storage unit are used for storing information of the monitoring equipment and the analysis network unit; the invention provides an intelligent management system capable of storing, analyzing and retrieving monitoring equipment information in large quantities.
Description
Technical Field
The invention relates to the field of communication, in particular to an intelligent management system.
Background
A large amount of terminal sensing equipment such as a camera for vehicle management, a garden monitoring camera for regional security monitoring and camera equipment for managing and monitoring assets in a garden building are often deployed in construction of the garden, the community and the campus. Although ubiquitous video monitoring networks form the comprehensive coverage of a perception system, the existing monitoring system and management system cannot well solve the problems due to the fact that the unstructured characteristics of video data and the data volume of the video data form certain pressure on storage resources. How to effectively store and analyze the perception data and simultaneously solve the requirements of quick retrieval and capture are important targets and directions for establishing intelligent communities, parks and campuses.
Therefore, the intelligent management system of the monitoring device in the prior art has the disadvantages of large data volume and insufficient data storage.
Disclosure of Invention
In order to solve the technical problem, the invention provides an intelligent management system capable of storing a large amount of data and a method thereof.
An intelligent management system for monitoring equipment, comprising: the system comprises a private cloud platform, a resource scheduling unit and a public cloud platform; the private cloud platform is arranged locally and comprises a first uniform storage unit and an analysis network unit; the public cloud platform comprises a second unified storage unit and a training cluster;
the resource scheduling unit is used for data interaction between the private cloud platform and the public cloud platform; the analysis network unit analyzes the data of the monitoring equipment and converts the unstructured data of the monitoring equipment into structured data; the training cluster is used for training a deep neural network cluster meeting business requirements and comprises a learning framework and a learning algorithm library; the first unified storage unit and the second unified storage unit are used for storing information of the monitoring device and the analysis network unit.
Preferably, the analysis network unit employs machine vision technology.
Preferably, the private cloud platform further comprises:
the preprocessing unit is used for finishing the grabbing of video streams, the extraction of key frames, the clustering of related images and the noise reduction; and/or
The data storage, analysis and display unit is used for constructing a structured storage database and establishing a feature search engine and a data BI display system;
and the data of the preprocessing unit and the data storage, analysis and display unit are stored in the first unified storage unit and the second unified storage unit.
Preferably, the resource scheduling unit further includes a deployment template for unifying the service resources of different templates between the private cloud platform and the public cloud platform.
Preferably, the resource scheduling unit further includes:
the training model is used for sensing the training progress of the public cloud and triggering the private cloud and the public cloud platform to synchronize the training model; and/or
And the marking data set is used for triggering the update operation of the public cloud start training model by using the new marking data.
The method for intelligently managing the system comprises the following steps of:
1) Capturing a video stream, capturing the video stream of the monitoring device;
2) Predefining analysis, wherein the analysis mode comprises video stream analysis and picture analysis, and the analysis target comprises people stream detection, abnormal object intrusion detection, traffic stream analysis, multi-target identification and park asset management;
3) Analyzing the video stream, preprocessing the video stream and importing the video stream into a deep analysis network;
4) The method comprises the steps of picture analysis, namely, capturing key frames through images, clustering key frames in the same scene, carrying out noise reduction processing, and storing preprocessed images into a unified storage unit;
5) Pushing video and image processing tasks to a task processing queue;
6) Starting a resource arranging engine of a deep analysis network to distribute computing resources according to the computing resource requirements of the tasks;
7) Downloading a machine vision model for analysis from a model library according to a task processing target;
8) Analyzing the task resources and outputting an analysis result, wherein the analysis result comprises a marked video, an image and a structured data table;
9) And further analyzing and displaying the analyzed data.
Compared with the prior art, the technical scheme of the invention has the following advantages: in the aspect of system architecture, the invention adopts a hybrid cloud architecture, and fully utilizes the edge computing capability of a private cloud platform of local resources and the mass storage and infinitely expandable computing capability of the cloud end of a public cloud platform; in the aspect of system deployment, through the design of a resource scheduling module, the invention can flexibly carry out resource migration and scheduling between the private cloud and the public cloud, and simultaneously, the dynamic scaling of service capacity is realized by utilizing a template arranging engine; the first analysis network unit and the second analysis network unit can also be used for respectively solving the problems of people flow detection, traffic flow detection, park asset statistical management and the like by training model libraries aiming at different services in a public cloud.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of an intelligent management system according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of another intelligent management system according to an embodiment of the invention;
FIG. 3 is a flow chart of a method of an intelligent management system of an embodiment of the invention.
Detailed Description
The conception, specific structure and technical effects of the present invention will be further described in conjunction with the accompanying drawings to fully understand the purpose, characteristics and effects of the present invention.
Example 1
As shown in fig. 1, an intelligent management system includes: the cloud platform comprises a private cloud platform 1, a resource scheduling unit 2 and a public cloud platform 3, wherein the private cloud platform 1 comprises a first unified storage unit 1.1 and an analysis network unit 1.3, and the public cloud platform 3 comprises a second unified storage unit 3.1 and a training cluster 3.2.
The private cloud platform 1 is a locally deployed computing resource, is used for solving the requirements of business on real-time performance and compliance, and performs video detection service by using an analysis model trained from a public cloud; the system comprises a first uniform storage unit 1.1, a first video server and a second uniform storage unit, wherein the first uniform storage unit is used for storing video key frame images, marking sample data and training models and synchronizing between a public cloud and a private cloud; and the analysis network unit 1.3 is used for effectively analyzing the related video/image data by adopting a deep learning framework and using a deep learning training model and converting the unstructured data into structured data for storage.
The public cloud platform 3 is a public open cloud platform resource and is matched with a private cloud platform to complete mixed cloud service deployment, and meanwhile, the characteristics of the public cloud in the aspects of computing capacity and expandability are fully utilized, so that the expansion of future services is facilitated; the system comprises a second uniform storage unit 3.1, a first uniform storage unit and a second uniform storage unit, wherein the second uniform storage unit is used for storing video key frame images, marking sample data and training models and synchronizing between a public cloud and a private cloud; and the training cluster 3.2 is used for training a deep neural network cluster meeting the service requirement, and a plate complete set training and improved training model based on transfer learning in the training process, and comprises a deep learning framework and a deep learning algorithm library.
And the resource scheduling unit 2 is used for constructing a bridge between the private cloud and the public cloud, and can complete distribution of different service resources between the public cloud platform and the private cloud platform.
Example 2
As shown in fig. 2, an intelligent management system includes a private cloud platform 1, a resource scheduling unit 2, and a public cloud platform 3, where the private cloud platform 1 includes a first uniform storage unit 1.1, a preprocessing unit 1.2, an analysis network unit 1.3, and a data storage, analysis, and display unit 1.4; the public cloud platform 3 comprises a second uniform storage unit 3.1 and a training cluster 3.2; the resource scheduling unit 2 comprises a label data set 2.1, a training model 2.2 and a deployment module 2.3.
The private cloud platform 1 is a locally deployed computing resource, is used for solving the requirements of business on real-time performance and compliance, and performs video detection service by using an analysis model trained from a public cloud; the method comprises the following steps:
the preprocessing unit 1.2 is used for finishing the functions of video stream capture, key frame extraction, related image clustering, noise reduction and the like;
the data storage, analysis and display unit 1.4 is used for constructing a structured storage database and establishing a feature search engine and a data BI display system;
the analysis network unit 1.3 is used for effectively analyzing related video/image data by adopting a deep learning framework and using a deep learning training model, and converting unstructured data into structured data for storage;
the first uniform storage unit 1.1 is used for storing video key frame images, marking sample data and training models and synchronizing between a public cloud and a private cloud.
The public cloud platform 3 is a public open cloud platform resource and is matched with a private cloud platform to complete mixed cloud service deployment, and meanwhile, the characteristics of the public cloud in the aspects of computing capacity and expandability are fully utilized, so that the expansion of future services is facilitated; the method comprises the following steps:
the second uniform storage unit 3.1 is used for storing the video key frame images, marking sample data and training models and synchronizing between the public cloud and the private cloud;
and the training cluster 3.2 is used for training a deep neural network cluster meeting the service requirement, and a plate complete set training and improved training model based on transfer learning in the training process, and comprises a deep learning framework and a deep learning algorithm library.
The resource scheduling unit 2 is used for constructing a bridge between the private cloud and the public cloud, and can complete distribution of different service resources between the public cloud platform and the private cloud platform, and is specifically divided into the following functional modules:
the deployment template 2.3 unifies different service resources into a resource deployment template, and can rapidly complete deployment by using infrastructure, namely code technology;
the training model 2.2 is used for sensing the training progress of the public cloud and triggering the private cloud and the public cloud platform to synchronize the training model;
and the marking data set 2.1 is used for triggering the update operation of the public cloud start training model by using the new marking data.
As shown in fig. 3, a method of intelligently managing a system includes the steps of:
1) Capturing a video stream, and acquiring the video stream through a video stream capturing unit;
2) Business users predefine analysis targets and modes, wherein the modes comprise video stream analysis and picture analysis, and the analysis targets comprise people stream detection, abnormal object intrusion detection, traffic stream analysis, multi-target identification, park asset management and the like;
3) Analyzing the video stream, preprocessing the video stream and importing the preprocessed video stream into a deep analysis network;
4) Picture analysis, namely firstly capturing key frames through images, clustering key frames in the same scene, denoising, and storing preprocessed images in a unified storage unit;
5) Pushing a video/image processing task to a task processing queue;
6) Starting a resource arranging engine of a deep analysis network to distribute computing resources according to the computing resource requirements of the tasks;
7) Downloading a machine vision model for analysis from a model library according to a task processing target;
8) Analyzing the task resources and outputting an analysis result, wherein the analysis result comprises a marked video/image and a structured data table;
9) And further analyzing and displaying the analyzed data.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the prior art according to the concepts of the present invention should be within the scope of protection determined by the claims.
Claims (3)
1. An intelligent management system for monitoring equipment, comprising: the system comprises a private cloud platform, a resource scheduling unit and a public cloud platform; the private cloud platform is arranged locally and comprises a first uniform storage unit and an analysis network unit; the public cloud platform comprises a second unified storage unit and a training cluster; the resource scheduling unit is used for data interaction between the private cloud platform and the public cloud platform; the resource scheduling unit also comprises a deployment template which is used for unifying the service resources of different templates between the private cloud platform and the public cloud platform; the analysis network unit analyzes the data of the monitoring equipment and converts the unstructured data of the monitoring equipment into structured data; the training cluster is used for training a deep neural network cluster meeting business requirements and comprises a learning framework and a learning algorithm library; the first unified storage unit and the second unified storage unit are used for storing information of the monitoring device and the analysis network unit, and the resource scheduling unit further includes: the training model is used for sensing the training progress of the public cloud and triggering the private cloud and the public cloud platform to synchronize the training model; and/or a tagged data set for triggering an update operation of the public cloud start training model using the new tagged data;
the following method steps are carried out by the intelligent management system:
1) Capturing a video stream, and acquiring the video stream through a video stream capturing unit;
2) Business users predefine analysis targets and modes, wherein the modes comprise video stream analysis and picture analysis, and the analysis targets comprise people stream detection, abnormal object intrusion detection, traffic stream analysis, multi-target identification and park asset management;
3) Analyzing the video stream, preprocessing the video stream and importing the video stream into a deep analysis network;
4) Picture analysis, namely firstly capturing key frames through images, clustering key frames in the same scene, denoising, and storing preprocessed images in a unified storage unit;
5) Pushing a video/image processing task to a task processing queue;
6) Starting a resource arranging engine of a deep analysis network to distribute computing resources according to the computing resource requirements of the tasks;
7) Downloading a machine vision model for analysis from a model library according to a task processing target;
8) Analyzing the task resources and outputting an analysis result, wherein the analysis result comprises a marked video/image and a structured data table;
9) And analyzing and displaying the analyzed data.
2. An intelligent management system according to claim 1, wherein said analysis network element employs machine vision techniques.
3. The intelligent management system of claim 1, wherein the private cloud platform further comprises: the preprocessing unit is used for finishing the grabbing of video streams, the extraction of key frames, the clustering of related images and the noise reduction; and/or a data storage, analysis and display unit, which is used for constructing a structured storage database and establishing a feature search engine and a data BI display system; the data of the preprocessing unit and the data storage, analysis and display unit are stored in the first unified storage unit and the second unified storage unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711292718.2A CN109905423B (en) | 2017-12-08 | 2017-12-08 | Intelligent management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711292718.2A CN109905423B (en) | 2017-12-08 | 2017-12-08 | Intelligent management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109905423A CN109905423A (en) | 2019-06-18 |
| CN109905423B true CN109905423B (en) | 2022-11-08 |
Family
ID=66940197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711292718.2A Active CN109905423B (en) | 2017-12-08 | 2017-12-08 | Intelligent management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109905423B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111026359B (en) * | 2019-12-17 | 2021-10-15 | 支付宝(杭州)信息技术有限公司 | Method and device for judging numerical range of private data in multi-party combination manner |
| CN111539555A (en) * | 2020-03-30 | 2020-08-14 | 南京南瑞信息通信科技有限公司 | Mixed cloud platform-based field management system |
| CN111524018B (en) * | 2020-04-10 | 2022-09-09 | 深圳新致软件有限公司 | Insurance industry intelligent robot application program capacity integration method and system |
| CN113810943A (en) * | 2021-09-09 | 2021-12-17 | 国网信息通信产业集团有限公司北京分公司 | Intelligent visual detection system and method |
| CN114124973B (en) * | 2021-09-27 | 2023-06-09 | 烽火通信科技股份有限公司 | Mirror image synchronization method and device for multi-cloud scene |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107066507A (en) * | 2017-01-10 | 2017-08-18 | 中国人民解放军国防科学技术大学 | A kind of semantic map constructing method that cloud framework is mixed based on cloud robot |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106270B (en) * | 2013-02-02 | 2016-06-29 | 深圳先进技术研究院 | cloud data fusion method and system |
| US10348581B2 (en) * | 2013-11-08 | 2019-07-09 | Rockwell Automation Technologies, Inc. | Industrial monitoring using cloud computing |
| CN104050530A (en) * | 2014-05-30 | 2014-09-17 | 深圳市道尔智控科技股份有限公司 | Cloud platform management system for parking lots |
| CN104363410B (en) * | 2014-10-08 | 2017-05-10 | 江苏一米智能科技股份有限公司 | Enterprise mobile monitoring system and method based on hybrid cloud and Internet of Things |
| CN105898204A (en) * | 2014-12-25 | 2016-08-24 | 支录奎 | Intelligent video recorder enabling video structuralization |
| CN104777762A (en) * | 2015-03-24 | 2015-07-15 | 惠州Tcl移动通信有限公司 | Vehicle-mounted system monitoring method and terminal thereof |
| CN104902005A (en) * | 2015-04-13 | 2015-09-09 | 中国联合网络通信集团有限公司 | Method and system for resource scheduling in hybrid cloud, and private cloud |
| CN105654047A (en) * | 2015-12-21 | 2016-06-08 | 中国石油大学(华东) | Online video intelligent processing system based on deep learning in cloud environment |
| CN106305371A (en) * | 2016-08-24 | 2017-01-11 | 电子科技大学 | Cloud-based agricultural Internet of things production and management system |
| CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
| CN106506244A (en) * | 2016-12-20 | 2017-03-15 | 郑州云海信息技术有限公司 | A kind of unified supervision device of mixed cloud |
| CN107071004A (en) * | 2017-03-24 | 2017-08-18 | 上海云首信息科技有限公司 | A kind of mixed cloud control scheduling system and dispatching method |
| CN107067365A (en) * | 2017-04-25 | 2017-08-18 | 中国石油大学(华东) | The embedded real-time video stream processing system of distribution and method based on deep learning |
| CN107145546A (en) * | 2017-04-26 | 2017-09-08 | 北京环境特性研究所 | Monitor video personnel's fuzzy retrieval method based on deep learning |
-
2017
- 2017-12-08 CN CN201711292718.2A patent/CN109905423B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107066507A (en) * | 2017-01-10 | 2017-08-18 | 中国人民解放军国防科学技术大学 | A kind of semantic map constructing method that cloud framework is mixed based on cloud robot |
Non-Patent Citations (3)
| Title |
|---|
| "Resource and Instance Hour Minimization for Deadline Constrained DAG Applications Using Computer Clouds";Hao Wu;《IEEE》;20150309;全文 * |
| "云环境下基于预测的虚拟服务器整合研究与实现";刘晓艳;《中国优秀硕士学位论文全文数据库信息科技辑》;20160515;全文 * |
| "云计算环境下资源需求预测与优化配置方法研究";石春菊;《信息通信》;20160515;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109905423A (en) | 2019-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109905423B (en) | Intelligent management system | |
| CN111405241B (en) | Edge calculation method and system for video monitoring | |
| US10812761B2 (en) | Complex hardware-based system for video surveillance tracking | |
| US9251425B2 (en) | Object retrieval in video data using complementary detectors | |
| US11082668B2 (en) | System and method for electronic surveillance | |
| US9704393B2 (en) | Integrated intelligent server based system and method/systems adapted to facilitate fail-safe integration and/or optimized utilization of various sensory inputs | |
| CN107004271B (en) | Display method, display apparatus, electronic device, computer program product, and storage medium | |
| CN102158689B (en) | Video monitoring system and method | |
| CN106060470B (en) | Video monitoring method and system | |
| WO2012095867A2 (en) | An integrated intelligent server based system and method/systems adapted to facilitate fail-safe integration and /or optimized utilization of various sensory inputs | |
| CN102752574A (en) | Video monitoring system and method | |
| Civelek et al. | Automated moving object classification in wireless multimedia sensor networks | |
| CN114255432A (en) | Video stream processing method, device, electronic equipment, storage medium and system | |
| CN111753743B (en) | Face recognition method and system based on gatekeeper | |
| CN115002414A (en) | Monitoring method, monitoring device, server and computer readable storage medium | |
| US20210117686A1 (en) | Methods and systems for customized image and video analysis | |
| CN116248861A (en) | Intelligent video detection method, system and device | |
| Fares et al. | Edge/fog-based architecture design for intelligent surveillance systems in smart cities: A software perspective | |
| CN113128294B (en) | Road event evidence obtaining method and device, electronic equipment and storage medium | |
| Kumar et al. | Real-time, YOLO-based intelligent surveillance and monitoring system using jetson TX2 | |
| CN113206935A (en) | Campus dual-prevention security prevention and control cloud platform and method | |
| CN112347996A (en) | Scene state judgment method, device, equipment and storage medium | |
| CN111950969A (en) | Rural comprehensive social treatment system | |
| Bigdeli et al. | Vision processing in intelligent CCTV for mass transport security | |
| Aswini et al. | Automatic Car Parking System Using Raspberry-Pi with Cloud Storage Environment |
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 |