CN104618693A - Cloud computing based online processing task management method and system for monitoring video - Google Patents
Cloud computing based online processing task management method and system for monitoring video Download PDFInfo
- Publication number
- CN104618693A CN104618693A CN201510065491.2A CN201510065491A CN104618693A CN 104618693 A CN104618693 A CN 104618693A CN 201510065491 A CN201510065491 A CN 201510065491A CN 104618693 A CN104618693 A CN 104618693A
- Authority
- CN
- China
- Prior art keywords
- video analysis
- intelligent video
- virtual
- task
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007726 management method Methods 0.000 title claims abstract description 108
- 238000012544 monitoring process Methods 0.000 title claims abstract description 66
- 238000012545 processing Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims description 232
- 230000008569 process Effects 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 238000013508 migration Methods 0.000 claims description 2
- 230000005012 migration Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 7
- 108090000201 Carboxypeptidase B2 Proteins 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000002680 cardiopulmonary resuscitation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a cloud computing based online processing task management system for monitoring video. The system is respectively connected with a client and a front end camera and comprises an intelligent video analyzing algorithm management module, a cloud resource management module, a cloud computing physical resource model and a virtual intelligent video analyzing server. The invention further discloses a cloud computing based online processing task management method for monitoring video. According to the method and system, a group of interconnected server groups in a data center is unified to be managed by the cloud computing technology, and the server groups coordinate to provide a user the intelligent monitoring video online processing task management service; the system is high in telescopic performance; the intelligent video analyzing algorithm can be dynamically configured as requirement, thus the management is convenient, and the cost is greatly reduced; in addition, the video processing task provided by the user can be reasonably dispatched to enable balanced load of the computing groups, and therefore, the resource utilization rate is increased, and efficient cloud computing service is provided to the user.
Description
Technical Field
The application relates to the field of intelligent video monitoring and cloud computing, in particular to an online intelligent monitoring video online processing task management system, a cloud resource management system and a cloud resource scheduling method, and particularly relates to a monitoring video online processing task management method and system based on cloud computing.
Background
With the rapid development of computer technology, network technology and multimedia technology, video surveillance systems have evolved from traditional analog video surveillance systems to IP-based network video surveillance systems. Along with the continuous acceleration of the national modernization construction level and the economic development, the construction of a large-scale social security network video monitoring system is promoted to the strategic height of creating a 'safe city' in each city, so that the requirements on building a city-level or provincial monitoring network with unified technical standard, network interconnection and intercommunication and information resource sharing are provided.
The scale of the video monitoring system is rapidly enlarged, but the monitoring system does not have enough manpower to monitor, so that the real-time monitoring in multiple regions and long time is difficult to ensure, and massive real-time video information is difficult to process in time, therefore, the monitoring system with network real-time intelligent video analysis is urgently needed to extract key video information and perform early warning on abnormal monitoring scene events. On the other hand, the traditional centralized monitoring video processing server cannot meet the requirement of high-definition video on network flow, and the working efficiency of the online intelligent monitoring video processing system is seriously influenced. In addition, in a conventional intelligent video monitoring system, an intelligent video analysis algorithm is usually integrated in an embedded chip of a video analysis server or a camera, a fixed type of analysis algorithm is provided, and a user cannot customize a task according to requirements. When a user needs to use a new video analysis algorithm, system upgrade or expansion capability, a video analysis server needs to be additionally purchased or a camera needs to be replaced, so that the cost is high, and the system management is inconvenient. The single server can obtain stronger computing power by increasing the number of processors and the speed of other components, but is limited by the computer architecture, the main frequency and the like, and the problems that the high-performance server is expensive in price, poor in expandability, incapable of fundamentally solving single-point faults, insufficient in server resources and the like can also be encountered.
The above practical requirements are summarized, and a mass monitoring video data processing scheme which is efficient, flexible, stable, low in cost and convenient to manage is needed.
Disclosure of Invention
The application provides a cloud computing-based monitoring video online processing task management method and system, which can realize high-efficiency, flexible, stable, low-cost and conveniently managed massive monitoring video data processing.
The embodiment of the application provides a monitoring video online processing task management system based on cloud computing, the monitoring video online processing task management system is respectively connected with a client and a front-end camera, and the monitoring video online processing task management system comprises: the system comprises an intelligent video analysis algorithm management module, a cloud resource management module, a cloud computing physical resource module and a virtual intelligent video analysis server;
the intelligent video analysis algorithm management module is used for managing video analysis tasks of the client, storing and managing related information of the virtual intelligent video analysis server, monitoring the running state of the virtual intelligent video analysis server, and deploying and starting the virtual intelligent video analysis server on the virtual computing server; sending resource application and revocation requests to a cloud computing physical resource module;
the cloud resource management module is used for dynamically creating, deleting and viewing the virtual intelligent video analysis server on the cloud computing physical resource module according to needs;
the cloud computing physical resource module is used for deploying a server virtualization environment and is provided with cloud computing physical resources for generating a virtual intelligent video analysis server;
the virtual intelligent video analysis servers are generated on the cloud computing physical resources provided by the cloud computing physical resource module, each virtual intelligent video analysis server comprises one or more video analysis algorithms and is used for receiving and decoding a video stream transmitted by the monitoring camera, taking charge of carrying out online analysis on the monitoring video stream and then sending the result of the video analysis to the client.
The embodiment of the application also provides a cloud computing-based monitoring video online processing task management method, which comprises the following steps:
a task request stage: the client sends a monitoring video online processing task request Q ═ C, J, T to the intelligent video analysis algorithm management module, and then waits for a task deployment result of the intelligent video analysis algorithm management module; c ═ C1, C2, …, cn } is a camera set, J ═ { J1, J2, …, J3} is a video analysis algorithm set, and T ═ T1, T2] is a task execution time period;
a task deployment stage: after receiving the task request Q, the intelligent video analysis algorithm management module judges: if no virtual intelligent video analysis server capable of meeting the task request Q exists in the current cloud computing physical resource module, a virtual computing server meeting the resource configuration required by the task request Q is dynamically generated through a cloud resource management module, then a required intelligent video analysis algorithm application mirror image is deployed to the virtual computing server, so that a virtual intelligent video analysis server meeting the task requirement is generated, the virtual intelligent video analysis server is started to execute a video analysis task, and relevant information of the virtual intelligent video analysis server is returned to a client; if the current cloud computing physical resource module is provided with a virtual intelligent video analysis server capable of meeting the task request Q, the virtual intelligent video analysis server is adaptively scheduled according to the load condition of the virtual intelligent video analysis server cluster, the virtual intelligent video analysis server is started to execute a video analysis task, and corresponding virtual intelligent video analysis server cluster information is returned to the client;
and a task processing stage: after receiving the virtual intelligent video analysis server information returned by the intelligent video analysis algorithm management module, the client can monitor and receive the video analysis result returned by the virtual intelligent video analysis server. The virtual intelligent video analysis server acquires and decodes the standard monitoring video stream from the front-end camera, calls a J-demand video analysis algorithm, performs online analysis on the video stream, and returns an analysis result to the client.
According to the technical scheme, the cloud computing technology is adopted to uniformly manage the interconnected server clusters in the data centers, and the server clusters cooperate with each other to provide intelligent monitoring video online processing task management service for users, so that the system has good flexibility, an intelligent video analysis algorithm can be dynamically configured as required, the management is convenient, and the cost is greatly reduced. In addition, the scheme of the application can reasonably schedule the video processing tasks submitted by the users, so that the load of the computing cluster is balanced, the resource utilization rate is improved, and efficient cloud computing service is provided for the users.
Drawings
Fig. 1 is a structural diagram of a cloud computing-based monitoring video online processing task management system according to an embodiment of the present application.
Fig. 2 is a schematic operation flow diagram of an IVAM scheduling intelligent video analysis task provided in an embodiment of the present application;
fig. 3 is a schematic diagram of a specific processing flow in a task request phase in an intelligent video analysis task for scheduling by an IVAM according to an embodiment of the present application;
fig. 4 is a schematic diagram of a specific processing flow in a task deployment phase in an intelligent video analysis task for scheduling in an IVAM according to an embodiment of the present application;
FIG. 5 is a diagram illustrating the detailed processing from step 404 to step 405 in the flowchart shown in FIG. 4;
FIG. 6 is a diagram illustrating a specific processing procedure of step 403 in the flowchart shown in FIG. 4;
fig. 7 is a schematic diagram of a specific processing flow of a task processing stage in an intelligent video analysis task for scheduling by an IVAM according to an embodiment of the present application;
fig. 8 is a schematic view of a service interaction flow of an IVAM scheduling intelligent video analysis task in the task end stage when a time period T required in a task Q expires in the task Q provided by the embodiment of the present application;
fig. 9 is a schematic view of a service interaction flow when a CS sends a request for revoking a vuu to an IVAM in a task ending stage in an IVAM scheduling intelligent video analysis task provided in an embodiment of the present application.
Detailed Description
The application aims to provide a monitoring video online processing task management method and system based on cloud computing, the distributed architecture design and the extensible capability of the cloud computing are fully utilized, a large-scale monitoring video online analysis function is supported, the on-demand calling capability of an intelligent video analysis algorithm is formed by establishing an intelligent video analysis algorithm management function module (IVAM) and a Cloud Video Analysis Cluster (CVAC), the diversified and flexible intelligent analysis requirements of customers are met, the dynamic expansion of the monitoring scale can be realized, more perfect functions are achieved, more efficient and reliable system performance is obtained, and meanwhile, the cost performance is higher. The basic design concept is as follows: the method comprises the steps of carrying out unified management and scheduling on a physical computing server cluster of a data center based on a cloud computing technology, dynamically generating and configuring virtual video analysis computing resources according to resource conditions required by tasks and load conditions of a current server cluster when a monitoring video online processing task request exists, and providing video analysis services for users according to needs.
Cloud computing is an emerging computing mode, is a distributed computing technology, and is mainly characterized in that a large number of computing resources connected by a network are uniformly managed and scheduled to form a computing resource pool for users to serve as required. The user obtains the needed resources and services through the network in an on-demand and easily-extensible mode, and the computer and the server in the network provide the services to the outside and are enabled to be transparent.
In order to make the technical principle, characteristics and technical effects of the technical scheme of the present application clearer, the technical scheme of the present application is explained in detail with reference to specific embodiments below.
The structure of a cloud computing-based monitoring video online processing task management system (hereinafter referred to as system) provided in the embodiment of the present application is shown in fig. 1, and the system includes: an intelligent video analysis algorithm management module (IVAM)102, a cloud resource management module (CRMU)103, a cloud computing physical resource module (CPR)104, and a virtual intelligent video analysis server (vuu) 105. In addition, when the system is working normally, the system also needs to be connected with a Client (CS)101) and a front-end camera (PU) 106. The following is illustrated for each part in fig. 1:
client (CS) 101: and the non-system core module is formed by one or more computers, is a requester for monitoring the online video processing task and is also a receiver for video analysis results. The intelligent video analysis task can be submitted to the monitoring video online processing task management system, intelligent analysis result data can be obtained from the VIVU 105, and video analysis results can be stored and displayed generally. When the monitoring video does not need to be analyzed any more, the intelligent video analysis task can be cancelled to the monitoring video online processing task management system.
Intelligent video analysis algorithm management module (IVAM) 102: the system belongs to a system core function module, consists of a server, is a request response entry module of a monitoring video online processing task management system, provides a system access mode for CS 101, and provides two system access modes: firstly, the video is presented in a Web page form, and a user can manage and monitor the video online processing task management system through a webpage; the second is to enable the CS 101 to use the service provided by the monitoring video online processing task management system in the form of a Web service interface. The CS 101 performs task customization and submission through the service exposed interface. When the vuu 105 is no longer needed by the CS 101, a computing resource withdrawal request can be initiated to the IVAM 102.
According to another embodiment of the present application, the intelligent video analysis algorithm management module (IVAM)102 further comprises the following functional units:
intelligent video analysis algorithm management unit: the intelligent video analysis algorithm mirror image storage device is used for storing a plurality of intelligent video analysis algorithm mirror images, and a user can perform management operations such as adding, deleting and searching on the video analysis algorithm mirror images;
intelligent video analysis task management unit: the video analysis task for managing the CS comprises monitoring and responding task requests, storing and managing task information, controlling the execution process of tasks and the like;
VIVU management unit: the method comprises the steps of storing and managing the related information of the VIVU, monitoring the running state of the VIVU, sending a virtual computing server resource application and revocation request to the CRMU, and deploying and starting the VIVU on the virtual computing server;
a system task scheduling unit: the intelligent video analysis task scheduling system is used for adaptively scheduling an intelligent video analysis task to a corresponding VIVU for video analysis according to the running state of the current VIVU cluster;
an authentication management unit: the method is used for managing the identity information of the CS, verifying the identity of the CS and controlling the behavior of the CS.
Cloud resource management module (CRMU) 103: the cloud computing basic resource request response entry module is responsible for integrating CPR 104 of a data center, shielding the heterogeneity and the dynamics of basic resource, and providing flexible, friendly and transparent data center basic resource management service for the system.
According to another embodiment of the present application, the cloud resource management module 103 includes the following functional units:
a cloud host management unit: the virtual intelligent video analysis server can be dynamically managed as required, such as creation, deletion, viewing and the like, main stream operating systems such as Windows, Linux, BSD and the like are supported, the virtual intelligent video analysis server can be remotely started, closed, restarted and logged in, and the virtual intelligent video analysis server of the virtual intelligent video analysis server can be subjected to thermal migration;
a mirror image management unit: the mirror image file can be created, deleted and inquired, and the rapid configuration of the software environment and the rapid deployment of the service are realized;
cloud host state monitoring unit: monitoring the running state of a cloud host of a data center in real time, and collecting, storing and graphically displaying state values of a CPU, a memory, a hard disk, a network I/O and the like of the cloud host;
an authentication management unit: the identity information of the user is managed, the identity of the user can be verified, and the behavior of the user can be controlled.
Cloud computing physical resource module (CPR) 104: the data center physical computing server cluster is uniformly managed by the CRMU, deploys a server virtualization environment and can generate a virtual computing server on the server virtualization environment.
Virtual intelligent video analytics server (vuu) 105: the method belongs to a system core function module, after the IVAM 102 applies for virtual computing server resources from the CRMU 103, the virtual computing server is created on a physical resource CPR 104, and then the IVAM 102 deploys a video analysis algorithm application mirror image to the created virtual computing server, thereby generating a VIVU 105. Each vuu 105 contains one or more video analysis algorithms capable of receiving and decoding the video stream transmitted by the surveillance camera PU 106, responsible for on-line analysis of the surveillance video stream, and then sending the results of the video analysis to the CS 101. Meanwhile, the vuu 105 periodically reports its running status, including CPU, memory, hard disk and network I/O status values.
Front-end camera (PU) 106: the system consists of a plurality of network cameras, is arranged in a monitoring area and is responsible for collecting and coding a monitoring video stream and transmitting the monitoring video stream through an IP network.
When a client 101 front-end monitoring camera video stream carries out an analysis task, an intelligent video analysis algorithm management module (IVAM)102 applies for virtual resources from a Cloud Video Analysis Cluster (CVAC) according to the resource demand condition of the video analysis task and generates a corresponding virtual intelligent video analysis server (VIVU) which receives video data sent by the front-end monitoring camera, the system can determine key factors influencing the system performance according to the difference among the tasks, and determines server nodes distributed to the tasks according to the characteristics of the video analysis task and the resource occupation condition of each virtual intelligent video analysis server, so that the virtual intelligent video analysis server cluster has balanced load and high resource utilization rate, improves the system task execution efficiency and can efficiently and uniformly manage the intelligent video analysis servers, effectively meeting the requirements of users.
The cloud computing-based monitoring video online processing task management method is shown in fig. 2 and comprises the following operation steps:
step 201: a task request stage: and the CS sends a monitoring video online processing task request Q to the IVAM, and then waits for a task deployment result of the IVAM.
Step 202: a task deployment stage: after the IVAM receives the task request Q, judging: if no VIVU capable of meeting the task request Q exists in the current CPR, a virtual calculation server meeting the resource configuration required by the task request Q is dynamically generated through the CRMU, then the required intelligent video analysis algorithm application mirror image is deployed to the virtual calculation server, so that the VIVU meeting the task requirement is generated, the VIVU is started to execute a video analysis task, and the related information of the VIVU is returned to the CS; and if the current CPR has the VIVU capable of meeting the task request Q, adaptively scheduling the VIVU according to the load condition of the VIVU cluster, starting the VIVU to execute a video analysis task, and returning corresponding VIVU cluster information to the CS.
When the IVAM sends a computing resource application to the CRMU, the CRMU generates a virtual computing server with corresponding resource configuration on CPR according to the load condition of the current physical basic resource CPR, and returns the relevant information of the virtual computing server to the IVAM. When the IVAM sends a computing resource canceling request to the CRMU, the CRMU deletes the corresponding virtual computing server on the CPR.
Step 203: and a task processing stage: after receiving the VIVU information returned by the IVAM, the CS can monitor and receive the video analysis result returned by the VIVU. The VIVU acquires and decodes a standard monitoring video stream from the PU, calls a video analysis algorithm required by J, performs online analysis on the video stream, and returns an analysis result to the CS.
Step 204: and a task ending stage: when the task is finished, namely the time period T required in the task Q is cut off, the IVAM stops the video analysis work of the VIVU; or when CS sends cancel VIVU request to IVAM, IVAM sends cancel request of computing resource to CRMU, then CRMU withdraws the computing resource occupied by corresponding VIVU.
The specific processing procedure of the task request phase is shown in fig. 3, and includes the following steps:
step 301: the CS logs in the IVAM, and the IVAM carries out identity verification on the CS;
step 302: the CS sends a monitoring video online processing task request Q to the IVAM, wherein C is { C, J, T } (C is { C1, C2, …, cn } is a camera set, J is { J1, J2, …, J3} is a video analysis algorithm set, and T is [ T1, T2] is a task execution time period), and then waits for a task deployment result of the IVAM.
The process flow of the task deployment phase is shown in fig. 4, and the phase includes the following manipulation steps:
step 401: the IVAM receives the task request Q.
Step 402: and judging whether a VIVU cluster meeting the task request Q exists, if so, executing a step 403, and otherwise, executing a step 404.
Step 403: the vuus is scheduled according to the vuu cluster load and then step 406 is performed.
Step 404: and applying for the virtual machine from the CRMU.
Step 405: an algorithm is deployed on the virtual machine to generate the VIVU.
Step 406: and starting the VIVU cluster to execute a video analysis task.
Step 407: and returning the VIVU cluster information to the CS.
If there is no vuu capable of satisfying task request Q in the current CPR, the specific flow of service interaction (corresponding to steps 404 to 405 in fig. 4) is as shown in fig. 5, and includes the following steps:
step 501: the method comprises the following steps that (1) an IVAM logs in a CRMU, and the CRMU verifies the identity of the IVAM;
step 502: the IVAM sends a request for generating a virtual machine to the CRMU, and dynamically generates a virtual computing server which meets the resource configuration required by the task request Q;
step 503 is as follows: the CRMU selects a physical server set subbPR in the CPR based on a BFilter filtering and scheduling algorithm according to the load condition of the current physical basic resource CPR, issues the virtual machine mirror image to the selected subbPR, and generates a virtual computing server cluster with corresponding resource configuration on the subbPR;
BFilter filter scheduling algorithm: since each virtual computing server has the same processing capacity and at least Nk video analysis tasks can be processed in parallel, it is necessary to create Ncpr ═ Nc × Nj/Nk virtual servers (where Nc is the number of cameras in C and Nj is the number of tasks in J). For creating each virtual computing server, the virtual computing environment state of the physical servers in all the CPRs is obtained, then the physical servers which do not meet the resources required by Q are filtered out (for example, 4G memory is required, and the insufficient 4G memory is directly filtered out), then weight scoring is carried out on all the physical servers left after filtering (for example, the larger the residual memory is, the higher the scoring is), finally, a plurality of hosts with the highest scoring (default 5) are extracted, and one of the plurality of physical servers is randomly selected as a candidate virtual computing server.
Step 504: the CRMU returns the information of the virtual computing server cluster to the IVAM;
step 505: the IVAM deploys an intelligent video analysis algorithm application mirror image required by the Q to a virtual computing server cluster, so that a VIVU cluster meeting task requirements is generated;
step 506: the VIVU cluster reports the running state of the VIVU cluster (including the conditions of whether the VIVU cluster runs normally, video analysis tasks are being executed, CPU, memory, hard disk, network I/O and other state values) to the IVAM;
step 507: the IVAM sends a task execution command Q1 to the VIVU cluster, wherein { C, J }, and the VIVU is started to execute a video analysis task;
step 508: the IVAM returns the information of the VIVU cluster to the CS.
If there are vuus in the current CPR that can satisfy task request Q, its business interaction flow (corresponding to step 403 in fig. 4) is as shown in fig. 6:
step 601: the VIVU cluster periodically reports the running state of the VIVU cluster (including whether the VIVU cluster runs normally, the situation of executing a video analysis task, the state values of a CPU, a memory, a hard disk, a network I/O and the like) to the IVAM;
step 602: the IVAM adaptively schedules the VIVU based on a BScheduler algorithm according to the load condition of the VIVU cluster, sends a task execution command Qk to the VIVU cluster, and starts the VIVU to execute a video analysis task;
BScheduler scheduling algorithm: and traversing each video analysis task j corresponding to each camera ci in the C, if the current VIVU can process j, allocating the task j to the current VIVU, and if the current VIVU cannot process the task j, selecting the next unoccupied VIVU from the VIVU cluster. And finally, obtaining a task execution command Qk of the VIVU cluster (wherein the Qk contains a task set which each VIVU should process).
Step 603: the IVAM returns the information of the VIVU cluster to the CS.
In the task processing stage, after receiving the vuu cluster information returned by the IVAM, the CS may monitor and receive a video analysis result returned by the vuu cluster, and a specific service interaction process is shown in fig. 7, and includes the following steps:
step 701: after receiving a task execution command Q1 (C, J) sent by the IVAM, the VIVU cluster sends a camera connection request to the PU set C;
step 702: the VIVU acquires and decodes a standard monitoring video stream from the camera, calls a video analysis algorithm required by an algorithm set J, and performs online analysis on the video stream;
step 703: the vuu returns the video analysis results to the CS.
In the task ending stage, when the time period T required in the task Q expires, the service interaction process is as shown in fig. 8, and includes the following steps:
step 801: the IVAM sends a stop video analytics task command S ═ Q1> (Q1 ═ { C, J }) to the VIVU;
step 802: the VIVU sends a video stream sending stopping command to a specified PU in the camera set C, the PU stops sending the video stream to the VIVU, and the VIVU stops a video analysis task Q1;
step 803: and the IVAM informs the CS of the expiration of the video analysis task Q and the stop of the video analysis work.
In the task ending stage, when the CS sends a request for revoking the vuu to the IVAM, the service interaction flow is as shown in fig. 9, and the method includes the following steps:
step 901: CS issues a cancel vuu request command P ═ < Q > (Q ═ { C, J, T }) to the IVAM;
step 902: the IVAM sends a stop video analytics task command S ═ Q1> (Q1 ═ { C, J }) to the VIVU;
step 903: the VIVU sends a video stream sending stopping command to a specified PU in the camera set C, the PU stops sending the video stream to the VIVU, and the VIVU stops a video analysis task Q1;
step 904: the method comprises the steps that the IVAM sends a computing resource revocation request to the CRMU to apply for revoking a virtual computing server cluster executing a Q task;
step 905: the CRMU reclaims the computing resources occupied by the VIVU executing task Q.
The above description is only a preferred embodiment of the present application and should not be taken as limiting the scope of the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the technical solution of the present application should be included in the scope of the present application.
Claims (10)
1. The utility model provides a surveillance video online processing task management system based on cloud calculates which characterized in that, surveillance video online processing task management system connects client and front end camera respectively, and this surveillance video online processing task management system includes: the system comprises an intelligent video analysis algorithm management module, a cloud resource management module, a cloud computing physical resource module and a virtual intelligent video analysis server;
the intelligent video analysis algorithm management module is used for managing video analysis tasks of the client, storing and managing related information of the virtual intelligent video analysis server, monitoring the running state of the virtual intelligent video analysis server, and deploying and starting the virtual intelligent video analysis server on the virtual computing server; sending resource application and revocation requests to a cloud computing physical resource module;
the cloud resource management module is used for dynamically creating, deleting and viewing the virtual intelligent video analysis server on the cloud computing physical resource module according to needs;
the cloud computing physical resource module is used for deploying a server virtualization environment and is provided with cloud computing physical resources for generating a virtual intelligent video analysis server;
the virtual intelligent video analysis servers are generated on the cloud computing physical resources provided by the cloud computing physical resource module, each virtual intelligent video analysis server comprises one or more video analysis algorithms and is used for receiving and decoding a video stream transmitted by the monitoring camera, taking charge of carrying out online analysis on the monitoring video stream and then sending the result of the video analysis to the client.
2. The monitored video on-line processing task management system according to claim 1, wherein the intelligent video analysis algorithm management module comprises the following functional units:
the intelligent video analysis algorithm management unit is used for storing a plurality of intelligent video analysis algorithm images, and the client side manages the video analysis algorithm images; the management operation at least comprises adding, deleting and searching;
the intelligent video analysis task management unit is used for managing video analysis tasks of the client, and comprises the steps of monitoring and responding task requests, storing and managing task information and controlling the execution process of the tasks;
the virtual intelligent video analysis server management unit is used for storing and managing relevant information of the virtual intelligent video analysis server and monitoring the running state of the virtual intelligent video analysis server; the cloud resource management module is also used for sending a virtual computing server resource application and revocation request to the cloud resource management module, deploying and starting the virtual intelligent video analysis server on the virtual computing server;
and the system task scheduling unit is used for adaptively scheduling the intelligent video analysis tasks to the corresponding virtual intelligent video analysis servers for video analysis according to the running state of the current virtual intelligent video analysis server cluster.
3. The monitored video online processing task management system according to claim 1, wherein the cloud resource management module comprises:
the cloud host management unit is used for dynamically managing the virtual intelligent video analysis server of the virtual intelligent video analysis server as required, remotely starting, closing, restarting and logging in the virtual intelligent video analysis server of the virtual intelligent video analysis server, and performing heat migration on the virtual intelligent video analysis server of the virtual intelligent video analysis server; the management operation at least comprises creation, deletion and viewing;
the mirror image management unit is used for creating, deleting and inquiring mirror image files, and realizing the rapid configuration of a software environment and the rapid deployment of services;
and the cloud host state monitoring unit is used for monitoring the running state of the cloud host of the cloud computing physical resource module in real time, and collecting, storing and graphically displaying the state value of the cloud host.
4. A surveillance video on-line processing task management method based on cloud computing, which is implemented based on the surveillance video on-line processing task management system according to any one of claims 1 to 3, and comprises the following steps:
a task request stage: the client sends a monitoring video online processing task request Q ═ C, J, T to the intelligent video analysis algorithm management module, and then waits for a task deployment result of the intelligent video analysis algorithm management module; c ═ C1, C2, …, cn } is a camera set, J ═ { J1, J2, …, J3} is a video analysis algorithm set, and T ═ T1, T2] is a task execution time period;
a task deployment stage: after receiving the task request Q, the intelligent video analysis algorithm management module judges: if no virtual intelligent video analysis server capable of meeting the task request Q exists in the current cloud computing physical resource module, a virtual computing server meeting the resource configuration required by the task request Q is dynamically generated through a cloud resource management module, then a required intelligent video analysis algorithm application mirror image is deployed to the virtual computing server, so that a virtual intelligent video analysis server meeting the task requirement is generated, the virtual intelligent video analysis server is started to execute a video analysis task, and relevant information of the virtual intelligent video analysis server is returned to a client; if the current cloud computing physical resource module is provided with a virtual intelligent video analysis server capable of meeting the task request Q, the virtual intelligent video analysis server is adaptively scheduled according to the load condition of the virtual intelligent video analysis server cluster, the virtual intelligent video analysis server is started to execute a video analysis task, and corresponding virtual intelligent video analysis server cluster information is returned to the client;
and a task processing stage: after receiving the virtual intelligent video analysis server information returned by the intelligent video analysis algorithm management module, the client can monitor and receive the video analysis result returned by the virtual intelligent video analysis server. The virtual intelligent video analysis server acquires and decodes the standard monitoring video stream from the front-end camera, calls a J-demand video analysis algorithm, performs online analysis on the video stream, and returns an analysis result to the client.
5. The method of claim 4, wherein the task deployment phase further comprises: after the intelligent video analysis algorithm management module sends a computing resource application to the cloud resource management module, the cloud resource management module generates a virtual computing server with corresponding resource configuration on the cloud computing physical resource module according to the load condition of the current cloud computing physical resource module, and returns the relevant information of the virtual computing server to the intelligent video analysis algorithm management module.
6. The method according to claim 5, wherein in the task deployment phase, if there is no virtual intelligent video analysis server capable of satisfying the task request Q in the current cloud computing physical resource module, dynamically generating a virtual computing server satisfying the resource configuration required by the task request Q through the cloud resource management module, then deploying the required intelligent video analysis algorithm application mirror image to the virtual computing server, thereby generating a virtual intelligent video analysis server satisfying the task requirement, starting the virtual intelligent video analysis server to execute the video analysis task, and returning the relevant information of the virtual intelligent video analysis server to the client comprises:
step 501: the intelligent video analysis algorithm management module logs in the cloud resource management module, and the cloud resource management module verifies the identity of the intelligent video analysis algorithm management module;
step 502: the intelligent video analysis algorithm management module sends a request for generating a virtual machine to the cloud resource management module, and dynamically generates a virtual computing server meeting the resource configuration required by the task request Q;
step 503: the cloud resource management module selects a physical server set in the cloud computing physical resource module based on a first scheduling algorithm according to the load condition of the current physical basic resource cloud computing physical resource module, sends a virtual machine mirror image to the selected physical server set, and generates a virtual computing server cluster with corresponding resource configuration on the physical server set;
step 504: the cloud resource management module returns the information of the virtual computing server cluster to the intelligent video analysis algorithm management module;
step 505: the intelligent video analysis algorithm management module deploys an intelligent video analysis algorithm application mirror image required by the Q to the virtual computing server cluster, so that a virtual intelligent video analysis server cluster meeting task requirements is generated;
step 506: the virtual intelligent video analysis server cluster reports the running state of the virtual intelligent video analysis server cluster to an intelligent video analysis algorithm management module;
step 507: the intelligent video analysis algorithm management module sends a task execution command Q1 to the virtual intelligent video analysis server cluster, wherein the command is { C, J }, and the virtual intelligent video analysis server is started to execute a video analysis task;
step 508: and the intelligent video analysis algorithm management module returns the information of the virtual intelligent video analysis server cluster to the client.
7. The method of claim 6, wherein the first scheduling algorithm comprises: setting the processing capacity of each virtual computing server to be the same, and processing Nk video analysis tasks at least in parallel, so that N cloud computing physical resource modules are required to be created, wherein Nc is the number of cameras in C, and Nj is the number of tasks in J;
for each virtual computing server, acquiring the virtual computing environment states of the physical servers in all the cloud computing physical resource modules, and then filtering out physical servers which do not meet the Q required resources; and then, carrying out weight value scoring on all the remaining physical servers, finally extracting a plurality of hosts with the highest score, and randomly selecting one from the plurality of physical servers as a candidate virtual computing server.
8. The method according to claim 4, wherein in the step of deployment, if there are virtual intelligent video analysis servers capable of satisfying the task request Q in the current cloud computing physical resource module, adaptively scheduling the virtual intelligent video analysis servers according to the load condition of the virtual intelligent video analysis server cluster, starting the virtual intelligent video analysis servers to execute the video analysis task, and returning the corresponding virtual intelligent video analysis server cluster information to the client comprises:
step 601: the virtual intelligent video analysis server cluster periodically reports the running state of the virtual intelligent video analysis server cluster to the intelligent video analysis algorithm management module;
step 602: the intelligent video analysis algorithm management module adaptively schedules the virtual intelligent video analysis server based on a second scheduling algorithm according to the load condition of the virtual intelligent video analysis server cluster, sends a task execution command Qk to the virtual intelligent video analysis server cluster, and starts the virtual intelligent video analysis server to execute a video analysis task;
step 603: and the intelligent video analysis algorithm management module returns the information of the virtual intelligent video analysis server cluster to the client.
9. The method of claim 8, wherein the second scheduling algorithm comprises: traversing each video analysis task j corresponding to each camera ci in the C, if the current virtual intelligent video analysis server can process j, allocating the task j to the current virtual intelligent video analysis server, and if the current virtual intelligent video analysis server cannot process the task j, selecting the next unoccupied virtual intelligent video analysis server from the virtual intelligent video analysis server cluster; finally, a task execution command Qk of the virtual intelligent video analysis server cluster is obtained; where Qk contains the set of tasks that each virtual intelligent video analytics server should handle.
10. The method of any of claims 4 to 9, wherein the task processing stage is further followed by:
the first type of task ending stage: when the task is finished, namely the time period T required in the task Q is cut off, the intelligent video analysis algorithm management module stops the video analysis work of the virtual intelligent video analysis server;
or,
and a second type of task ending stage: or when the client sends a request for canceling the virtual intelligent video analysis server to the intelligent video analysis algorithm management module, the intelligent video analysis algorithm management module sends a computing resource canceling request to the cloud resource management module, and then the cloud resource management module withdraws the computing resources occupied by the corresponding virtual intelligent video analysis server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510065491.2A CN104618693B (en) | 2015-02-09 | 2015-02-09 | A kind of monitor video based on cloud computing handles task management method and system online |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510065491.2A CN104618693B (en) | 2015-02-09 | 2015-02-09 | A kind of monitor video based on cloud computing handles task management method and system online |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104618693A true CN104618693A (en) | 2015-05-13 |
| CN104618693B CN104618693B (en) | 2017-07-28 |
Family
ID=53152952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510065491.2A Expired - Fee Related CN104618693B (en) | 2015-02-09 | 2015-02-09 | A kind of monitor video based on cloud computing handles task management method and system online |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104618693B (en) |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105491329A (en) * | 2015-11-24 | 2016-04-13 | 上海君是信息科技有限公司 | Large-scale monitoring video stream converging method based on stream-oriented computation |
| CN105554591A (en) * | 2015-12-02 | 2016-05-04 | 蓝海大数据科技有限公司 | Video analysis method and device |
| CN105704458A (en) * | 2016-03-22 | 2016-06-22 | 北京邮电大学 | Container-technology-based video monitoring cloud service platform realization method and system |
| CN106101196A (en) * | 2016-06-01 | 2016-11-09 | 上海上大海润信息系统有限公司 | A kind of cloud rendering platform task scheduling system based on probabilistic model and method |
| CN106817562A (en) * | 2015-12-01 | 2017-06-09 | 欧阳卓明 | A kind of platform software with video monitoring image intellectual analysis function |
| CN106851215A (en) * | 2017-03-10 | 2017-06-13 | 深圳市博信诺达经贸咨询有限公司 | The method and device that safety monitoring based on cloud is realized |
| CN106851227A (en) * | 2017-03-30 | 2017-06-13 | 安徽四创电子股份有限公司 | The system and its addition digital watermark method of monitor video addition digital watermarking |
| CN107391031A (en) * | 2017-06-27 | 2017-11-24 | 北京邮电大学 | Data migration method and device in a kind of computing system based on mixing storage |
| CN105554444B (en) * | 2015-12-03 | 2018-07-24 | 深圳市泛海三江电子股份有限公司 | security monitoring system and method |
| CN109005433A (en) * | 2018-09-04 | 2018-12-14 | 北京邮电大学 | A kind of video cloud service platform architecture and implementation method |
| CN109040686A (en) * | 2018-08-22 | 2018-12-18 | 苏宁易购集团股份有限公司 | Software deployment method and Internet of Things camera system in a kind of Internet of Things camera system |
| CN110192393A (en) * | 2016-11-06 | 2019-08-30 | 微软技术许可有限责任公司 | Large-scale real-time video analysis |
| CN110417831A (en) * | 2018-04-27 | 2019-11-05 | 杭州海康威视数字技术股份有限公司 | Smart machine computational resource allocation method, apparatus and system |
| CN110830759A (en) * | 2018-08-09 | 2020-02-21 | 华为技术有限公司 | Intelligent application deployment method, device and system |
| CN110895464A (en) * | 2018-09-13 | 2020-03-20 | 华为技术有限公司 | Application deployment method, device and system |
| CN110944146A (en) * | 2018-09-21 | 2020-03-31 | 华为技术有限公司 | Intelligent analysis equipment resource adjusting method and device |
| CN111158894A (en) * | 2018-11-08 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Task monitoring method and device in cloud analysis system |
| CN111800514A (en) * | 2020-07-13 | 2020-10-20 | 华侨大学 | Cloud management system based on application and location awareness |
| CN111885350A (en) * | 2020-06-10 | 2020-11-03 | 北京旷视科技有限公司 | Image processing method, system, server and storage medium |
| CN112165603A (en) * | 2020-09-01 | 2021-01-01 | 北京都是科技有限公司 | Artificial intelligence management system and management method of artificial intelligence processing device |
| CN112423041A (en) * | 2020-11-19 | 2021-02-26 | 湖南大学 | Video stream processing method and system based on QoS constraint under distributed computing platform |
| CN112559128A (en) * | 2020-12-15 | 2021-03-26 | 跬云(上海)信息科技有限公司 | Apache Kylin hosting system and method based on cloud computing |
| CN112583922A (en) * | 2020-12-16 | 2021-03-30 | 罗普特科技集团股份有限公司 | Intelligent scheduling system for video monitoring service |
| CN112860426A (en) * | 2019-11-28 | 2021-05-28 | 杭州海康消防科技有限公司 | Intelligent analysis method and device, electronic equipment and readable storage medium |
| CN113194281A (en) * | 2021-01-27 | 2021-07-30 | 广东建邦计算机软件股份有限公司 | Video analysis method and device, computer equipment and storage medium |
| CN113259451A (en) * | 2021-05-31 | 2021-08-13 | 长沙鹏阳信息技术有限公司 | Cluster processing architecture and method for intelligent analysis of large-scale monitoring nodes |
| CN113703973A (en) * | 2021-08-26 | 2021-11-26 | 北京百度网讯科技有限公司 | Cloud task processing method, system, device, equipment and storage medium |
| CN114301816A (en) * | 2022-01-11 | 2022-04-08 | 浪潮软件集团有限公司 | Multipath analysis method and device |
| CN115866417A (en) * | 2023-02-28 | 2023-03-28 | 中国人民解放军军事科学院战争研究院 | Video service method and system based on edge calculation |
| CN115951974A (en) * | 2023-03-10 | 2023-04-11 | 浙江宇视科技有限公司 | Management method, system, device and medium for GPU virtual machine |
| CN116915786A (en) * | 2023-09-13 | 2023-10-20 | 杭州立方控股股份有限公司 | License plate recognition and vehicle management system with cooperation of multiple servers |
| CN118072259A (en) * | 2024-04-17 | 2024-05-24 | 安徽博微广成信息科技有限公司 | Slag car identification flow method based on AI intelligent detection and intelligent monitoring equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103067514A (en) * | 2012-12-29 | 2013-04-24 | 深圳先进技术研究院 | Cloud computing resource optimization method and cloud computing resource optimization system used for video mointoring and analysis system |
| CN103096030A (en) * | 2011-11-03 | 2013-05-08 | 中国移动通信集团江苏有限公司 | Video monitoring multi-service convergence platform and solution |
| CN103595574A (en) * | 2013-12-02 | 2014-02-19 | 重庆市三文盾科技有限责任公司 | Computer network cloud start-up system |
| WO2014179749A1 (en) * | 2013-05-02 | 2014-11-06 | Pribula Alexis Juri | Interactive real-time video editor and recorder |
-
2015
- 2015-02-09 CN CN201510065491.2A patent/CN104618693B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103096030A (en) * | 2011-11-03 | 2013-05-08 | 中国移动通信集团江苏有限公司 | Video monitoring multi-service convergence platform and solution |
| CN103067514A (en) * | 2012-12-29 | 2013-04-24 | 深圳先进技术研究院 | Cloud computing resource optimization method and cloud computing resource optimization system used for video mointoring and analysis system |
| WO2014179749A1 (en) * | 2013-05-02 | 2014-11-06 | Pribula Alexis Juri | Interactive real-time video editor and recorder |
| CN103595574A (en) * | 2013-12-02 | 2014-02-19 | 重庆市三文盾科技有限责任公司 | Computer network cloud start-up system |
Cited By (48)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105491329A (en) * | 2015-11-24 | 2016-04-13 | 上海君是信息科技有限公司 | Large-scale monitoring video stream converging method based on stream-oriented computation |
| CN105491329B (en) * | 2015-11-24 | 2018-09-14 | 上海君是信息科技有限公司 | A kind of extensive monitoring video flow assemblage method based on streaming computing |
| CN106817562A (en) * | 2015-12-01 | 2017-06-09 | 欧阳卓明 | A kind of platform software with video monitoring image intellectual analysis function |
| CN105554591A (en) * | 2015-12-02 | 2016-05-04 | 蓝海大数据科技有限公司 | Video analysis method and device |
| CN105554444B (en) * | 2015-12-03 | 2018-07-24 | 深圳市泛海三江电子股份有限公司 | security monitoring system and method |
| CN105704458A (en) * | 2016-03-22 | 2016-06-22 | 北京邮电大学 | Container-technology-based video monitoring cloud service platform realization method and system |
| CN106101196B (en) * | 2016-06-01 | 2019-04-30 | 上海上大海润信息系统有限公司 | A kind of cloud rendering platform task scheduling system based on probabilistic model |
| CN106101196A (en) * | 2016-06-01 | 2016-11-09 | 上海上大海润信息系统有限公司 | A kind of cloud rendering platform task scheduling system based on probabilistic model and method |
| CN110192393A (en) * | 2016-11-06 | 2019-08-30 | 微软技术许可有限责任公司 | Large-scale real-time video analysis |
| CN106851215A (en) * | 2017-03-10 | 2017-06-13 | 深圳市博信诺达经贸咨询有限公司 | The method and device that safety monitoring based on cloud is realized |
| CN106851227A (en) * | 2017-03-30 | 2017-06-13 | 安徽四创电子股份有限公司 | The system and its addition digital watermark method of monitor video addition digital watermarking |
| CN107391031A (en) * | 2017-06-27 | 2017-11-24 | 北京邮电大学 | Data migration method and device in a kind of computing system based on mixing storage |
| CN107391031B (en) * | 2017-06-27 | 2020-05-08 | 北京邮电大学 | Data migration method and device in computing system based on hybrid storage |
| CN110417831A (en) * | 2018-04-27 | 2019-11-05 | 杭州海康威视数字技术股份有限公司 | Smart machine computational resource allocation method, apparatus and system |
| CN110417831B (en) * | 2018-04-27 | 2022-07-29 | 杭州海康威视数字技术股份有限公司 | Intelligent equipment computing resource allocation method, device and system |
| CN110830759A (en) * | 2018-08-09 | 2020-02-21 | 华为技术有限公司 | Intelligent application deployment method, device and system |
| CN110830759B (en) * | 2018-08-09 | 2021-09-07 | 华为技术有限公司 | Intelligent application deployment method, device and system |
| CN109040686A (en) * | 2018-08-22 | 2018-12-18 | 苏宁易购集团股份有限公司 | Software deployment method and Internet of Things camera system in a kind of Internet of Things camera system |
| CN109005433B (en) * | 2018-09-04 | 2019-05-21 | 北京邮电大学 | A kind of video cloud service platform architecture and implementation method |
| CN109005433A (en) * | 2018-09-04 | 2018-12-14 | 北京邮电大学 | A kind of video cloud service platform architecture and implementation method |
| CN110895464A (en) * | 2018-09-13 | 2020-03-20 | 华为技术有限公司 | Application deployment method, device and system |
| CN110895464B (en) * | 2018-09-13 | 2021-12-14 | 华为技术有限公司 | Application deployment method, device and system |
| US11537810B2 (en) | 2018-09-21 | 2022-12-27 | Huawei Technologies Co., Ltd. | Method for adjusting resource of intelligent analysis device and apparatus |
| CN110944146A (en) * | 2018-09-21 | 2020-03-31 | 华为技术有限公司 | Intelligent analysis equipment resource adjusting method and device |
| CN111158894B (en) * | 2018-11-08 | 2023-04-07 | 杭州海康威视数字技术股份有限公司 | Task monitoring method and device in cloud analysis system |
| CN111158894A (en) * | 2018-11-08 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Task monitoring method and device in cloud analysis system |
| CN112860426B (en) * | 2019-11-28 | 2024-03-01 | 杭州海康消防科技有限公司 | Intelligent analysis method, intelligent analysis device, electronic equipment and readable storage medium |
| CN112860426A (en) * | 2019-11-28 | 2021-05-28 | 杭州海康消防科技有限公司 | Intelligent analysis method and device, electronic equipment and readable storage medium |
| CN111885350A (en) * | 2020-06-10 | 2020-11-03 | 北京旷视科技有限公司 | Image processing method, system, server and storage medium |
| CN111800514B (en) * | 2020-07-13 | 2022-04-15 | 华侨大学 | Cloud management system based on application and location awareness |
| CN111800514A (en) * | 2020-07-13 | 2020-10-20 | 华侨大学 | Cloud management system based on application and location awareness |
| CN112165603A (en) * | 2020-09-01 | 2021-01-01 | 北京都是科技有限公司 | Artificial intelligence management system and management method of artificial intelligence processing device |
| CN112165603B (en) * | 2020-09-01 | 2023-04-25 | 北京都是科技有限公司 | Artificial intelligence management system and management method of artificial intelligence processing equipment |
| CN112423041A (en) * | 2020-11-19 | 2021-02-26 | 湖南大学 | Video stream processing method and system based on QoS constraint under distributed computing platform |
| CN112423041B (en) * | 2020-11-19 | 2021-10-29 | 湖南大学 | Video stream processing method and system based on QoS constraint under distributed computing platform |
| CN112559128A (en) * | 2020-12-15 | 2021-03-26 | 跬云(上海)信息科技有限公司 | Apache Kylin hosting system and method based on cloud computing |
| CN112583922A (en) * | 2020-12-16 | 2021-03-30 | 罗普特科技集团股份有限公司 | Intelligent scheduling system for video monitoring service |
| CN113194281B (en) * | 2021-01-27 | 2024-04-26 | 广东建邦计算机软件股份有限公司 | Video parsing method, device, computer equipment and storage medium |
| CN113194281A (en) * | 2021-01-27 | 2021-07-30 | 广东建邦计算机软件股份有限公司 | Video analysis method and device, computer equipment and storage medium |
| CN113259451A (en) * | 2021-05-31 | 2021-08-13 | 长沙鹏阳信息技术有限公司 | Cluster processing architecture and method for intelligent analysis of large-scale monitoring nodes |
| CN113259451B (en) * | 2021-05-31 | 2021-09-21 | 长沙鹏阳信息技术有限公司 | Cluster processing architecture and method for intelligent analysis of large-scale monitoring nodes |
| CN113703973A (en) * | 2021-08-26 | 2021-11-26 | 北京百度网讯科技有限公司 | Cloud task processing method, system, device, equipment and storage medium |
| CN114301816A (en) * | 2022-01-11 | 2022-04-08 | 浪潮软件集团有限公司 | Multipath analysis method and device |
| CN115866417A (en) * | 2023-02-28 | 2023-03-28 | 中国人民解放军军事科学院战争研究院 | Video service method and system based on edge calculation |
| CN115951974A (en) * | 2023-03-10 | 2023-04-11 | 浙江宇视科技有限公司 | Management method, system, device and medium for GPU virtual machine |
| CN116915786A (en) * | 2023-09-13 | 2023-10-20 | 杭州立方控股股份有限公司 | License plate recognition and vehicle management system with cooperation of multiple servers |
| CN116915786B (en) * | 2023-09-13 | 2023-12-01 | 杭州立方控股股份有限公司 | License plate recognition and vehicle management system with cooperation of multiple servers |
| CN118072259A (en) * | 2024-04-17 | 2024-05-24 | 安徽博微广成信息科技有限公司 | Slag car identification flow method based on AI intelligent detection and intelligent monitoring equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104618693B (en) | 2017-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104618693B (en) | A kind of monitor video based on cloud computing handles task management method and system online | |
| CN105049268B (en) | Distributed computing resource distribution system and task processing method | |
| CN103197968A (en) | Thread pool processing method and system capable of fusing synchronous and asynchronous features | |
| CN103795804A (en) | Storage resource scheduling method and storage calculation system | |
| CN108920153A (en) | A kind of Docker container dynamic dispatching method based on load estimation | |
| CN103458055A (en) | Clout competing platform | |
| CN202918339U (en) | Ground test-launch-control system of carrier rocket based on cloud computing | |
| CN107967175B (en) | Resource scheduling system and method based on multi-objective optimization | |
| CN105786603B (en) | Distributed high-concurrency service processing system and method | |
| CN107645410A (en) | A kind of virtual machine management system and method based on OpenStack cloud platforms | |
| Xiong et al. | Design and implementation of a prototype cloud video surveillance system | |
| CN110706148B (en) | Face image processing method, device, equipment and storage medium | |
| CN112437129B (en) | Cluster management method and cluster management device | |
| CN104021029B (en) | Spatial information cloud computing system and implementing method thereof | |
| WO2015192664A1 (en) | Device monitoring method and apparatus | |
| CN111679911A (en) | Management method, device, equipment and medium for GPU (graphics processing Unit) card in cloud environment | |
| CN112988344A (en) | Distributed batch task scheduling method, device, equipment and storage medium | |
| CN104881749A (en) | Data management method and data storage system for multiple tenants | |
| CN115576684A (en) | Task processing method and device, electronic equipment and storage medium | |
| CN114528104A (en) | Task processing method and device | |
| CN114296891A (en) | Task scheduling method, system, computing device, storage medium and program product | |
| CN107528871A (en) | Data analysis in storage system | |
| WO2018188607A1 (en) | Stream processing method and device | |
| CN112039985A (en) | Heterogeneous cloud management method and system | |
| CN116510312A (en) | Cloud game multi-opening implementation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170728 |