WO2020057178A1 - 智能分析设备资源调整方法及装置 - Google Patents

智能分析设备资源调整方法及装置 Download PDF

Info

Publication number
WO2020057178A1
WO2020057178A1 PCT/CN2019/090274 CN2019090274W WO2020057178A1 WO 2020057178 A1 WO2020057178 A1 WO 2020057178A1 CN 2019090274 W CN2019090274 W CN 2019090274W WO 2020057178 A1 WO2020057178 A1 WO 2020057178A1
Authority
WO
WIPO (PCT)
Prior art keywords
analysis device
intelligent analysis
monitoring platform
camera
bound
Prior art date
Application number
PCT/CN2019/090274
Other languages
English (en)
French (fr)
Inventor
王震宇
Original Assignee
华为技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP19863081.6A priority Critical patent/EP3846459A4/en
Publication of WO2020057178A1 publication Critical patent/WO2020057178A1/zh
Priority to US17/206,609 priority patent/US11537810B2/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/181Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/285Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5011Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/52Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08Configuration management of networks or network elements
    • H04L41/0876Aspects of the degree of configuration automation
    • H04L41/0886Fully automatic configuration
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/70Admission control; Resource allocation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/1001Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004Server selection for load balancing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/12Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/66Remote control of cameras or camera parts, e.g. by remote control devices
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00Indexing scheme relating to G06F9/00
    • G06F2209/50Indexing scheme relating to G06F9/50
    • G06F2209/503Resource availability
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00Burglar, theft or intruder alarms
    • G08B13/18Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras

Definitions

  • the present application relates to the field of video surveillance, and in particular, to a method and device for adjusting resources of an intelligent analysis device.
  • Smart camera is a surveillance camera with independent intelligent processing functions (such as face recognition and license plate number recognition, etc.). With the rise of smart cameras, it solves the problem that video relies heavily on manual troubleshooting, and effectively guarantees intelligent identification and The timeliness of the response results in a wide range of applications in public safety, transportation, and industrial production.
  • smart cameras Compared with ordinary cameras, smart cameras also require complex intelligent processing, which requires more powerful hardware resources and deployment of software capable of intelligent processing. It is relatively expensive.
  • smart cameras are proposed.
  • the way that camera 1 drags N that is, the smart camera accesses the video streams of N ordinary cameras.
  • the smart camera In addition to processing the video streams collected by itself, it can also intelligently process the video streams of the accessed N ordinary cameras. Intelligent transformation of ordinary cameras.
  • the consumption of resources is highly correlated with the data collected by the camera. For example, when performing face analysis, there are no three different images of the face, one face, and a large number of faces.
  • the problem of imbalanced resource use is solved by manually adjusting the binding relationship between the smart camera and the ordinary camera.
  • the manual method has a slow response speed and low processing efficiency.
  • the application provides a method and device for adjusting resources of an intelligent analysis device, which can implement dynamic scheduling of the resources of an intelligent analysis device and improve processing efficiency.
  • the present application provides a method for adjusting resources of an intelligent analysis device, including:
  • the status information of the intelligent analysis device connected to the monitoring platform and the application information deployed on the intelligent analysis device are obtained through the monitoring platform.
  • the monitoring platform The status information and application information of the intelligent analysis device connected to the monitoring platform select the intelligent analysis device to be bound to the camera, send a command to bind the camera to the selected intelligent analysis device, and bind the camera to the intelligent analysis device.
  • the monitoring platform can dynamically bind the camera with only image acquisition function to the appropriate intelligent analysis device according to the resources of the intelligent analysis device connected to the monitoring platform.
  • the intelligent analysis device can analyze and process the video stream collected by the camera. The method allocates the resources of the intelligent analysis equipment, which improves the processing efficiency and avoids the inefficiency of manual processing.
  • a smart analysis device with the lowest resource occupancy is selected to be bound to the camera.
  • the smart analysis device is already bound to a camera, re-select the bound smart analysis device for one or more cameras bound to the smart analysis device;
  • a command to bind the one or more cameras is sent to the reselected bound intelligent analysis device.
  • the monitoring platform can dynamically bind a camera with only an image acquisition function to a suitable intelligent analysis device according to the resources of the intelligent analysis device connected to the monitoring platform.
  • load balancing processing is performed on the intelligent analysis device, and the binding relationship between the camera and the intelligent analysis device can be dynamically adjusted, thereby solving the intelligent Analyze the problem of imbalanced use of equipment resources, realize the balance of intelligent analysis equipment resources of the entire system, improve processing efficiency, and avoid the inefficiency of manual processing.
  • load balancing the intelligent analysis device includes:
  • the bound target smart analysis device is selected for the smart analysis device based on the status information and application information of other smart analysis devices connected to the monitoring platform;
  • the monitoring platform can dynamically bind a camera with only an image acquisition function to a suitable intelligent analysis device according to the resources of the intelligent analysis device connected to the monitoring platform.
  • load balancing processing is performed on the intelligent analysis device, and the video streams of some business applications on the intelligent analysis device can be transferred to the
  • the intelligent analysis device bound to the intelligent analysis device is processed on the intelligent analysis device to realize shunting, thereby solving the problem of imbalanced use of intelligent analysis device resources, realizing the balance of the intelligent analysis device resources of the entire system, improving the processing efficiency, and avoiding the inefficiency of manual processing. Sex.
  • the present application provides a method for adjusting resources of an intelligent analysis device, including:
  • the intelligent analysis device After the intelligent analysis device is connected to the monitoring platform, it sends status information of the intelligent analysis device and application information deployed on the intelligent analysis device to the monitoring platform.
  • the status information includes the resource occupancy rate and the number of cameras that are bound;
  • the intelligent analysis device receives the command from the monitoring platform to bind the target camera, and sends a video stream request to the target camera;
  • the intelligent analysis device receives the video stream sent by the target camera, and analyzes and processes the received video stream.
  • the intelligent analysis device After the intelligent analysis device is connected to the monitoring platform, it sends status information of the intelligent analysis device and application information deployed on the intelligent analysis device to the monitoring platform, and accesses the monitoring platform on any camera After that, the monitoring platform selects the bound intelligent analysis device for the camera according to the status information and application information of the intelligent analysis device connected to the monitoring platform, sends a command to bind the camera to the selected intelligent analysis device, and binds the camera to the intelligent On the analysis device, the intelligent analysis device receives the video stream sent by the target camera, and analyzes the received video stream.
  • the monitoring platform can dynamically bind a camera with only image acquisition function to a suitable intelligent analysis device according to the resources of the intelligent analysis device connected to the monitoring platform.
  • the intelligent analysis device can analyze and process the video stream collected by the camera, which can be automated through The method of allocating the resources of the intelligent analysis equipment improves the processing efficiency and avoids the inefficiency of manual processing.
  • the method further includes:
  • the intelligent analysis device receives the status information acquisition request sent by the monitoring platform;
  • the intelligent analysis device sends status information of the intelligent analysis device to the monitoring platform.
  • the method when the resource occupation rate of the intelligent analysis device is greater than the resource occupation rate threshold, the method further includes:
  • the smart analysis device receives a command sent by the monitoring platform to unbind one or more cameras on the smart analysis device;
  • the intelligent analysis device sends a command to stop sending video streams to the unbound camera or cameras.
  • the intelligent analysis device resource adjustment method if the monitoring platform finds that there is an intelligent analysis device with a resource occupation rate greater than a resource occupation threshold during the operation of the intelligent analysis device, load balancing processing is performed on the intelligent analysis device.
  • the binding relationship between the camera and the intelligent analysis device can be dynamically adjusted, thereby solving the problem of imbalanced use of intelligent analysis device resources, realizing the balance of the intelligent analysis device resources of the entire system, improving the processing efficiency, and avoiding the inefficiency of manual processing.
  • the method when the resource occupation rate of the intelligent analysis device is greater than the resource occupation rate threshold, the method further includes:
  • the intelligent analysis device receives the video stream request sent by the target intelligent analysis device bound to the intelligent analysis device.
  • the target intelligent analysis device is selected by the monitoring platform for the intelligent analysis device according to the status information and application information of other intelligent analysis devices connected to the monitoring platform;
  • the intelligent analysis device receives a command sent by the monitoring platform to stop processing of some business applications
  • the intelligent analysis device sends a video stream of some business applications to the target intelligent analysis device.
  • the monitoring platform finds that there is an intelligent analysis device whose resource occupation rate is greater than a resource occupation rate threshold during the operation of the intelligent analysis device, according to other intelligent analysis devices connected to the monitoring platform
  • the state information and application information of the intelligent analysis device select the target intelligent analysis device to be bound, and the video stream of some business applications on the intelligent analysis device is transferred to the target intelligent analysis device for processing, which realizes streaming, thereby solving the intelligent analysis device.
  • the problem of imbalanced use of resources realizes the balance of the intelligent analysis equipment resources of the entire system, improves the processing efficiency, and avoids the inefficiency of manual processing.
  • the acquisition module is used to obtain the status information of the intelligent analysis device connected to the monitoring platform and the application information deployed on the intelligent analysis device.
  • the status information includes the resource occupancy rate and the number of cameras that are bound.
  • the selection module is used to After accessing the monitoring platform, the intelligent analysis device to be bound is selected for the camera according to the status information and application information of the intelligent analysis device connected to the monitoring platform; a sending module is used to send a command to bind the camera to the selected intelligent analysis device.
  • the selection module is used to:
  • the processing module is configured to perform load balancing processing on the intelligent analysis device when the resource occupation rate of the intelligent analysis device connected to the monitoring platform is greater than the resource occupation rate threshold.
  • the processing module is used to:
  • the sending module is further configured to: send a command to the smart analysis device to unlink one or more cameras bound to the smart analysis device;
  • the sending module is further configured to send a command to bind the one or more cameras to the intelligent analysis device that reselects the binding.
  • the processing module is used to:
  • the bound target smart analysis device is selected for the smart analysis device based on the status information and application information of other smart analysis devices connected to the monitoring platform;
  • the present application provides an intelligent analysis device, including: a sending module, configured to send the intelligent analysis device to the monitoring platform after it is connected to the monitoring platform, and send the status information of the intelligent analysis device and the application information deployed on the intelligent analysis device.
  • the status information includes the resource occupancy rate and the number of cameras that have been bound;
  • the receiving module is used to receive the command to bind the target camera sent by the monitoring platform;
  • the sending module is also used to: send a video stream request to the target camera; the receiving module also Used for: receiving the video stream sent by the target camera; and a processing module for analyzing and processing the received video stream.
  • the receiving module is further configured to: receive a status information acquisition request sent by the monitoring platform;
  • the receiving module is further configured to: receive a command sent by the monitoring platform to unbind one or more cameras on the intelligent analysis device;
  • the sending module is further configured to send a command to stop sending video streams to the unbound camera or cameras.
  • the receiving module is further configured to: receive a command sent by the monitoring platform to stop processing of some business applications;
  • the sending module is further configured to send a video stream of some business applications to the target intelligent analysis device.
  • the present application provides a monitoring platform including: a memory and a processor;
  • Memory for storing program instructions
  • Memory for storing program instructions
  • the present application provides a readable storage medium that stores execution instructions.
  • the monitoring platform executes the execution instructions, executes any of the first aspect and the first aspect.
  • the present application provides a readable storage medium that stores execution instructions.
  • the smart analysis device executes the execution instructions, executes the second aspect and the second aspect. Any possible design of intelligent analysis equipment resource adjustment method.
  • the present application provides a method for adjusting resources of an intelligent analysis device, including:
  • the monitoring platform After the monitoring platform is connected to the monitoring platform, the monitoring platform selects a bound intelligent analysis device for the camera according to the status information and application information of the intelligent analysis device connected to the monitoring platform;
  • the intelligent analysis device sends status information of the intelligent analysis device to the monitoring platform.
  • the monitoring platform can dynamically bind a camera with only an image acquisition function to a suitable intelligent analysis device according to the resources of the intelligent analysis device connected to the monitoring platform.
  • load balancing processing is performed on the intelligent analysis device, and the binding relationship between the camera and the intelligent analysis device can be dynamically adjusted, thereby solving the intelligent Analyze the problem of imbalanced use of equipment resources, realize the balance of intelligent analysis equipment resources of the entire system, improve processing efficiency, and avoid the inefficiency of manual processing.
  • the monitoring platform is configured to: after the camera is connected to the monitoring platform, select a bound intelligent analysis device for the camera according to the status information and application information of the intelligent analysis device connected to the monitoring platform;
  • the intelligent analysis device that receives the command bound to the camera is configured to send a video stream request to the camera, receive a video stream sent by the camera, and analyze and process the received video stream.
  • the monitoring platform is specifically configured to:
  • the monitoring platform is further configured to: send a status information acquisition request to the intelligent analysis device;
  • the monitoring platform when the resource occupancy rate of the intelligent analysis device connected to the monitoring platform is greater than a resource occupancy threshold, the monitoring platform is further configured to perform load balancing processing on the intelligent analysis device.
  • the monitoring platform is specifically configured to:
  • the smart analysis device is not bound to a camera, selecting a bound target smart analysis device for the smart analysis device according to the status information and application information of other smart analysis devices connected to the monitoring platform;
  • the intelligent analysis device is further configured to receive a video stream request sent by the target intelligent analysis device, and send the video stream of the partial business application to the target intelligent analysis device.
  • FIG. 1 is a schematic structural diagram of a monitoring management system provided by the present application.
  • FIG. 2 is a flowchart of an embodiment of a method for adjusting resource of an intelligent analysis device provided by this application;
  • FIG. 4 is a flowchart of an embodiment of a method for adjusting resource of an intelligent analysis device provided by this application;
  • FIG. 6 is an interaction flowchart of an embodiment of a method for adjusting resource of an intelligent analysis device provided by this application;
  • FIG. 10 is a schematic structural diagram of an intelligent analysis device provided by the present application.
  • FIG. 11 is a schematic structural diagram of a monitoring platform provided by the present application.
  • FIG. 1 is a schematic structural diagram of a monitoring management system provided by this application, as shown in FIG. 1 It is shown that the network elements involved in the monitoring management system of this application are intelligent analysis equipment, cameras, and monitoring platforms.
  • the intelligent analysis equipment is a device with functions such as image analysis, image processing, video analysis, and video processing.
  • the intelligent analysis device can also It has image acquisition function.
  • the intelligent analysis device can be a smart camera.
  • the camera in this application only has an image acquisition function.
  • the camera in this application can be various types of cameras or cameras.
  • the monitoring platform is any one that can execute this application.
  • the software or hardware of the provided intelligent analysis equipment resource adjustment method In the monitoring management system shown in Figure 1, after the intelligent analysis equipment is connected to the monitoring platform, it reports its own status information and deployed application information to the monitoring platform. After connecting to the surveillance management system, select the camera Select the bound intelligent analysis device for binding. After the intelligent analysis device works, the monitoring platform can perform load balancing processing on the intelligent analysis device according to the resource occupation rate of the intelligent analysis device in the system.
  • FIG. 2 is a flowchart of an embodiment of a method for adjusting resource of an intelligent analysis device provided by this application.
  • the execution subject of this embodiment may be a monitoring platform.
  • the method of this embodiment may include:
  • S101 Obtain status information of an intelligent analysis device connected to a monitoring platform and application information deployed on the intelligent analysis device.
  • the status information includes a resource occupancy rate and a number of cameras that are bound.
  • the monitoring platform can directly obtain the application information deployed on the intelligent analysis device.
  • the application information is the application functions possessed by the intelligent analysis device, such as face recognition, license plate recognition, and parabolic recognition. , Intrusion detection, automatic tracking, and more.
  • the intelligent analysis device may actively report its own application information after being connected to the monitoring platform, or the monitoring platform requests the intelligent analysis device to report its application information after the intelligent analysis device is connected to the monitoring platform, and the monitoring platform obtains the application of the intelligent analysis device. After the information is stored.
  • the status information includes the resource usage rate and the number of cameras that are bound.
  • the resource usage rate can be the central processing unit (CPU) and memory usage rate.
  • the initial status information has been The number of bound cameras is 0.
  • the specific methods may be:
  • the status information acquisition request can be sent periodically, that is, the monitoring platform periodically triggers the intelligent analysis device to report its own status information; or it sends the status randomly.
  • An information acquisition request, or a status information acquisition request is sent after an event is triggered, or an artificial control sends a status information acquisition request.
  • it may specifically be: receiving status information sent by the intelligent analysis device connected to the monitoring platform when the status information is updated.
  • the intelligent analysis device actively reports to the monitoring platform when the status information is updated.
  • the application information and the initial status information may be reported to the monitoring platform at the same time, or may be separately reported to the monitoring platform, and the application information may be reported once.
  • the initial state information also includes the maximum number of cameras that the intelligent analysis device can bind.
  • the intelligent analysis device provides an application programming interface (API) for media processing control to the monitoring platform, and the two communicate with each other through a standard protocol.
  • the standard protocol may be, for example, OVIF or T28181.
  • Intelligent analysis equipment can access the monitoring platform through the API interface.
  • the camera also provides an API interface to the monitoring platform, and the two communicate with each other through a standard protocol.
  • the standard protocol can be, for example, OVIF or T28181, and the camera can access the monitoring platform through the API interface.
  • the intelligent analysis equipment connected to the monitoring platform constitutes a resource pool of intelligent analysis equipment.
  • Figure 3 is a schematic diagram of the binding of the monitoring platform after the camera is connected to the monitoring platform. As shown in Figure 3, after the camera is connected to the monitoring platform, the monitoring platform switches from the intelligent Select an intelligent analysis device from the analysis device resource pool, and bind the camera to the intelligent analysis device.
  • the monitoring platform selects the intelligent analysis device to be bound for the camera according to the status information, application information, and the maximum number of cameras that can be bound to the intelligent analysis device in the system.
  • Method 1 From a smart analysis device whose resource occupancy is less than the resource occupancy threshold and the application information matches the camera, poll to select a smart analysis device to bind to the camera.
  • all intelligent analysis devices in the access monitoring platform may have the same or different resource occupancy thresholds.
  • Each intelligent analysis device corresponds to its resource occupancy threshold.
  • the resource occupancy threshold is, for example, 85% or 90%. Wait.
  • the matching of the application information with the camera means that the selected intelligent analysis device to be bound can process the video stream of the camera.
  • Manner 2 From the intelligent analysis device whose resource occupancy is less than the resource occupancy threshold and the application information matches the camera, a smart analysis device closest to the camera location is selected to be bound to the camera.
  • the nearest location may refer to the nearest geographical location.
  • Method 3 From the intelligent analysis device whose resource occupancy is less than the resource occupancy threshold and the application information matches the camera, a smart analysis device with the lowest resource occupancy rate is selected to be bound to the camera.
  • the command to bind a camera can also be a binding request, a binding instruction, a binding notification, etc.
  • the command to bind a camera can be in restful or rpc format, and the command to bind a camera can include the IP of the camera to be bound Address, port, authentication information, identification number, and type of service to be performed (such as face recognition).
  • the selected intelligent analysis device after receiving the command to bind the camera sent by the monitoring platform, it sends a video stream request to the camera, receives the video stream sent by the camera, and analyzes the received video stream.
  • the intelligent analysis device resource adjustment method obtains the status information of the intelligent analysis device connected to the monitoring platform and the application information deployed on the intelligent analysis device through the monitoring platform. After any camera is connected to the monitoring platform, the monitoring platform The status information and application information of the intelligent analysis device entering the monitoring platform select the intelligent analysis device to be bound to the camera, send the command to bind the camera to the selected intelligent analysis device, and bind the camera to the intelligent analysis device.
  • the monitoring platform can dynamically bind a camera with only image acquisition function to a suitable intelligent analysis device according to the resources of the intelligent analysis device connected to the monitoring platform.
  • the intelligent analysis device can analyze and process the video stream collected by the camera, and it can be automated. Allocating the resources of the intelligent analysis equipment improves the processing efficiency and avoids the inefficiency of manual processing.
  • FIG. 4 is a flowchart of an embodiment of a method for adjusting resources of an intelligent analysis device provided in this application.
  • the execution subject of this embodiment may be a monitoring platform.
  • the method of this implementation is based on the method shown in FIG. 2.
  • it may further include:
  • the monitoring platform finds that the system has an imbalanced resource allocation, that is, there is an intelligent analysis device with a resource occupation rate greater than the resource occupation rate threshold, it performs load balancing processing on the intelligent analysis device.
  • load balancing processing of the intelligent analysis device There are two specific implementation methods for load balancing processing of the intelligent analysis device in S103:
  • the unbinding command may include the IP address and port of the camera to be unbound.
  • the original intelligent analysis device received the unbinding in the intelligent analysis issued by the monitoring platform. After the command of one or more cameras on the device is released, the corresponding cameras are unbound, and a command to stop sending video streams is sent to the unbound camera or cameras. Then, after reselecting the bound intelligent analysis device to receive the command of the bound camera, it sends a video stream to the bound camera, and analyzes the received video stream.
  • Method 2 If the smart analysis device is not bound to a camera, the monitoring platform performs load balancing processing on the smart analysis device. Specifically, the smart analysis device may be selected for the smart analysis device based on the status information and application information of other smart analysis devices connected to the monitoring platform.
  • the bound target intelligent analysis device sends a command to the target intelligent analysis device to bind the intelligent analysis device for the target intelligent analysis device to bind the intelligent analysis device to the target intelligent analysis device.
  • the command to bind the intelligent analysis device can Contains the IP address and port of the intelligent analysis device to be bound, and sends a command to the intelligent analysis device to stop processing of some business applications. This command is used by the intelligent analysis device to stop processing of video streams of some business applications. That is, the video streams of some business applications on the intelligent analysis device are transferred to a target intelligent analysis device bound to the intelligent analysis device.
  • the target smart analysis device is selected for the smart analysis device based on the status information and application information of other smart analysis devices connected to the monitoring platform.
  • the bound target intelligent analysis device replaces the intelligent analysis device for partial application processing.
  • the application selection for processing can be performed according to predefined rules, such as polling, selecting the application with the smallest resource consumption, and selecting the resource occupation. The largest application or the application that chooses to occupy the center.
  • the target intelligent analysis device receives a command sent by the monitoring platform to bind the intelligent analysis device, the target intelligent analysis device sends a video stream request to the intelligent analysis device, and performs a video stream of a part of the business application sent by the received intelligent analysis device. Analysis and processing.
  • the monitoring platform can dynamically bind a camera with only an image acquisition function to a suitable intelligent analysis device according to the resources of the intelligent analysis device connected to the monitoring platform, and work on the intelligent analysis device.
  • the monitoring platform finds that there is an intelligent analysis device with a resource occupancy rate greater than the resource occupancy threshold, load balancing processing is performed on the intelligent analysis device, and the binding relationship between the camera and the intelligent analysis device can be dynamically adjusted.
  • the video stream of some business applications on the analysis device is transferred to the intelligent analysis device bound to the intelligent analysis device for processing and streaming, thereby solving the problem of imbalanced use of intelligent analysis device resources and realizing the entire system of intelligent analysis device resources. Equilibrium improves processing efficiency and avoids the inefficiency of manual processing.
  • FIG. 5 is an interaction flowchart of an embodiment of a method for adjusting resource of an intelligent analysis device provided in this application. As shown in FIG. 5, in this embodiment, three intelligent analysis devices in an access monitoring platform are taken as an example. Example methods can include:
  • the monitoring platform obtains status information of the intelligent analysis device A, intelligent analysis device B, and intelligent analysis device C in the access monitoring platform, and application information and status of the intelligent analysis device A, intelligent analysis device B, and intelligent analysis device C.
  • the information includes the resource occupancy rate and the number of cameras that have been bound.
  • Method 1 The monitoring platform sends a status information acquisition request to the intelligent analysis device. After the intelligent analysis device receives the status information acquisition request, it sends its status information to the monitoring platform.
  • Method 2 The intelligent analysis device sends the updated status information to the monitoring platform when the status information is updated.
  • the camera is connected to a monitoring platform.
  • the monitoring platform determines an application corresponding to the intelligent analysis processing required by the camera, and determines an intelligent analysis device matching the camera according to the application information deployed on the intelligent analysis device.
  • the intelligent analysis device A, the intelligent analysis device B, and the intelligent analysis device C can all process the video stream of the camera.
  • the monitoring platform selects the bound intelligent analysis for the camera according to the status information of the intelligent analysis device A, the intelligent analysis device B, and the intelligent analysis device C and the application information deployed on the intelligent analysis device A, the intelligent analysis device B, and the intelligent analysis device C.
  • the device sends a command to bind the camera to the intelligent analysis device.
  • it may be selected from a smart analysis device whose resource occupancy rate is less than the resource occupancy threshold, and polling to select a smart analysis device to be bound to the camera, or a smart analysis device whose resource occupancy rate is less than the resource occupancy threshold.
  • a smart analysis device closest to the camera position is bound to the camera, or from a smart analysis device whose resource occupancy is less than a resource occupancy threshold, a smart analysis device with the lowest resource occupancy is selected to be bound to the camera.
  • the monitoring platform obtains status information of the intelligent analysis device A, the intelligent analysis device B, and the intelligent analysis device C in the access monitoring platform.
  • the camera sends a video stream to the intelligent analysis device C.
  • the intelligent analysis device C analyzes and processes the received video stream.
  • FIG. 7 is an interaction flowchart of an embodiment of a method for adjusting resource of an intelligent analysis device provided in this application.
  • three intelligent analysis devices in an access monitoring platform are taken as an example.
  • a part of the business application on the intelligent analysis device that is overloaded is switched to the intelligent analysis device bound to the intelligent analysis device for load balancing processing.
  • the method in this embodiment is described in the method shown in FIG. 5. On the basis, it can also include:
  • the monitoring platform obtains status information of the intelligent analysis device A, the intelligent analysis device B, and the intelligent analysis device C in the access monitoring platform.
  • the monitoring platform determines that the resource occupation rate of the intelligent analysis device B is greater than the resource occupation threshold, that is, the intelligent analysis device B is overloaded.
  • the business applications being processed on the intelligent analysis device B are face recognition and license plate recognition.
  • the monitoring platform forwards the video stream of the business application on the intelligent analysis device B—the license plate recognition to the intelligent analysis device C.
  • Analysis device B only deals with face recognition, and intelligent analysis device C deals with license plate recognition and face recognition.
  • the selection module 12 is configured to select a bound intelligent analysis device for the camera according to the status information and application information of the intelligent analysis device connected to the monitoring platform after the camera is connected to the monitoring platform.
  • the selection module 12 is used for:
  • the device in this embodiment may be a monitoring platform, and may be used to execute the technical solution of the method embodiment shown in FIG. 1.
  • the implementation principle is similar, and details are not described herein again.
  • the monitoring platform obtained in this embodiment obtains the status information of the intelligent analysis device and the application information deployed on the intelligent analysis device through the acquisition module.
  • the selection module is based on the access monitoring platform's The status information and application information of the intelligent analysis device select the intelligent analysis device to be bound to the camera.
  • the sending module sends a command to bind the camera to the selected intelligent analysis device, and binds the camera to the intelligent analysis device, thereby monitoring the platform.
  • the camera with only image acquisition function can be dynamically bound to the appropriate intelligent analysis equipment.
  • the intelligent analysis equipment can analyze and process the video stream collected by the camera, and can allocate intelligence by automatic means. Analyzing the resources of the equipment improves the processing efficiency and avoids the inefficiency of manual processing.
  • the bound smart analysis device is reselected for one or more cameras bound to the smart analysis device.
  • processing module 14 is configured to:
  • the smart analysis device is not bound to a camera, selecting a bound target smart analysis device for the smart analysis device according to the state information and application information of other smart analysis devices connected to the monitoring platform;
  • the receiving module 22 is further configured to: receive a video stream sent by the target camera;
  • the sending module 21 is further configured to send status information of the intelligent analysis device to the monitoring platform.
  • the receiving module 22 is further configured to receive a video stream request sent by a target intelligent analysis device bound to the intelligent analysis device, and the target intelligent analysis device is another intelligent analysis that the monitoring platform accesses according to the monitoring platform. Device status information and application information are selected by the intelligent analysis device;
  • the receiving module 22 is further configured to: receive a command sent by the monitoring platform to stop processing of some service applications;
  • the intelligent analysis device provided by this embodiment. After the intelligent analysis device accesses the monitoring platform, the sending module sends the status information of the intelligent analysis device and the application information deployed on the intelligent analysis device to the monitoring platform, and the receiving module receives the binding sent by the monitoring platform.
  • This application may divide the functional modules of the sending device according to the above method examples.
  • each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module.
  • the above integrated modules may be implemented in the form of hardware or software functional modules. It should be noted that the division of the modules in the embodiments of the present application is schematic, and is only a logical function division. In actual implementation, there may be another division manner.
  • FIG. 11 is a schematic structural diagram of a monitoring platform provided by this application.
  • the monitoring platform 700 includes:
  • the processor 702 is configured to call and execute program instructions in the memory to implement each step in the method for adjusting resources of the intelligent analysis device in FIG. 1 or FIG. 4. For details, refer to related descriptions in the foregoing method embodiments.
  • An input / output interface 703 may also be included.
  • the input / output interface 703 may include an independent output interface and an input interface, or may be an integrated interface that integrates input and output.
  • the output interface is used to output data, and the input interface is used to obtain input data.
  • the output data is the collective name of the output in the method embodiment, and the input data is the collective name of the input in the method embodiment.
  • the monitoring platform may be used to execute each step and / or process corresponding to the monitoring platform in the foregoing method embodiment.
  • FIG. 12 is a schematic structural diagram of an intelligent analysis device provided by the present application.
  • the intelligent analysis device 800 includes:
  • the memory 801 is configured to store program instructions, and the memory 801 may be a flash (flash memory).
  • the processor 802 is configured to call and execute program instructions in the memory to implement each step in the method for adjusting resources of the intelligent analysis device of FIG. 1 or FIG. 4. For details, refer to related descriptions in the foregoing method embodiments.
  • An input / output interface 803 may also be included.
  • the input / output interface 803 may include an independent output interface and an input interface, or may be an integrated interface that integrates input and output.
  • the output interface is used to output data, and the input interface is used to obtain input data.
  • the output data is the collective name of the output in the method embodiment, and the input data is the collective name of the input in the method embodiment.
  • the intelligent analysis device may be configured to execute each step and / or process corresponding to the intelligent analysis device in the foregoing method embodiment.
  • the present application also provides a readable storage medium that stores execution instructions.
  • the monitoring platform executes the intelligent analysis device resource adjustment method in the foregoing method embodiment. .
  • the present application also provides a readable storage medium that stores execution instructions.
  • the smart analysis device executes the smart analysis device resources in the foregoing method embodiments. Adjustment method.
  • the present application also provides a chip, where the chip is connected to a memory, or a memory is integrated on the chip, and when a software program stored in the memory is executed, a method for adjusting an intelligent analysis device resource in the foregoing method embodiment is implemented. .
  • the application also provides a program product including an execution instruction, and the execution instruction is stored in a readable storage medium.
  • At least one processor of the monitoring platform may read the execution instruction from a readable storage medium, and the execution of the execution instruction by the at least one processor causes the monitoring platform to implement the intelligent analysis device resource adjustment method in the foregoing method embodiment.
  • the application also provides a program product including an execution instruction, and the execution instruction is stored in a readable storage medium.
  • At least one processor of the intelligent analysis device may read the execution instruction from a readable storage medium, and the execution of the execution instruction by the at least one processor causes the intelligent analysis device to implement the method for adjusting resources of the intelligent analysis device in the foregoing method embodiment.
  • the present application also provides a monitoring management system, including the monitoring platform shown in FIG. 8 or FIG. 9 and the intelligent analysis device shown in FIG. 10, or the monitoring platform shown in FIG. 11 and the intelligent analysis device shown in FIG. .
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be from a website site, computer, server, or data center Transmission by wire (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) to another website site, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, and the like that includes one or more available medium integration.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Automation & Control Theory (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Alarm Systems (AREA)
  • Studio Devices (AREA)

Abstract

本申请提供一种智能分析设备资源调整方法及装置。该方法包括:获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,状态信息包括资源占用率和已绑定的摄像机的个数;在摄像机接入监控平台后,根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备;向所选择的智能分析设备发送绑定摄像机的命令。从而,可以通过自动化的方式分配智能分析设备的资源,提高了处理效率,避免人工处理的低效性。

Description

智能分析设备资源调整方法及装置 技术领域
本申请涉及视频监控领域,尤其涉及一种智能分析设备资源调整方法及装置。
背景技术
智能摄像机是一种具备独立智能处理功能(如人脸识别和车牌号识别等)的监控摄像机,随着智能摄像机的兴起,解决了视频严重依赖于人工排查的问题,且有效保障了智能识别和结果响应的及时性,因而在公共安全、交通和工业生产等各个领域都有着非常广阔的应用前景。
相比于普通摄像机,智能摄像机还需要进行复杂的智能处理,因而需要更强大的硬件资源以及部署能够进行智能处理的软件,比较昂贵,为充分使用智能摄像机的硬件资源和软件资源,提出了智能摄像机1拖N的方式,即智能摄像机接入N个普通摄像机的视频流,除了处理自身采集的视频流之外,同时还能够对接入的N个普通摄像机的视频流进行智能处理,实现了对普通摄像机的智能化改造。在智能摄像机的智能处理过程中,资源的消耗与摄像机采集的数据相关性比较强,比如进行人脸分析时,没有人脸、一个人脸和大量人脸这三种不同的图像,对于资源的消耗迥然不同,因而摄像机会因为部署的位置不同,导致资源使用不平衡,例如,可能一些位置智能摄像机的资源已经过载,但是另一些位置则长期低负荷工作,采用智能摄像机1拖N方式,则加大了资源使用不平衡的可能性。
相关技术中,通过人工调整智能摄像机与普通摄像机的绑定关系的方式来解决资源使用不平衡的问题,但是,人工方式响应速度慢,处理效率不高。
发明内容
本申请提供一种智能分析设备资源调整方法及装置,可实现智能分析设备资源的动态调度,提高处理效率。
第一方面,本申请提供一种智能分析设备资源调整方法,包括:
获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,状态信息包括资源占用率和已绑定的摄像机的个数,在摄像机接入监控平台后,根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备,向所选择的智能分析设备发送绑定摄像机的命令。
通过第一方面提供的智能分析设备资源调整方法,通过监控平台获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,在任一摄像机接入监控平台后,监控平台根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备,向所选择的智能分析设备发送绑定该摄像机的命令,将摄像机绑定在智能分析设备上,从而,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,智能分析设备可以分析处理摄像机采集的视频流,可以通过自动化的方式分配智能分析设备的资源,提高了处理效率,避免人工处理的低效性。
在一种可能的设计中,根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备,包括:
从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,轮询 选择一个智能分析设备与摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,选择距摄像机位置最近的一个智能分析设备与摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,选择资源占用率最低的一个智能分析设备与摄像机绑定。
在一种可能的设计中,上述方法还包括:
向接入监控平台的智能分析设备发送状态信息获取请求;
接收接入监控平台的智能分析设备发送的状态信息。
在一种可能的设计中,上述方法还包括:
当接入监控平台的智能分析设备的资源占用率大于资源占用率阈值,则对智能分析设备进行负载均衡处理。
在一种可能的设计中,对智能分析设备进行负载均衡处理,包括:
若智能分析设备已绑定摄像机,则为绑定在智能分析设备上的一个或多个摄像机重新选择绑定的智能分析设备;
向所述智能分析设备发送解除绑定在所述智能分析设备上的一个或多个摄像机的命令;
向重新选择绑定的智能分析设备发送绑定所述一个或多个摄像机的命令。
通过该实施方式提供的智能分析设备资源调整方法,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,在智能分析设备工作过程中,若监控平台发现存在资源占用率大于资源占用率阈值的智能分析设备,则对该智能分析设备进行负载均衡处理,可以动态调整摄像机与智能分析设备的绑定关系,从而解决了智能分析设备资源使用不平衡的问题,实现整个***智能分析设备资源的均衡,提高了处理效率,避免人工处理的低效性。
在一种可能的设计中,对智能分析设备进行负载均衡处理,包括:
若智能分析设备未绑定摄像机,则根据监控平台接入的其他智能分析设备的状态信息和应用信息为智能分析设备选择绑定的目标智能分析设备;
向目标智能分析设备发送绑定智能分析设备的命令;
向智能分析设备发送停止部分业务应用处理的命令。
通过该实施方式提供的智能分析设备资源调整方法,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,在智能分析设备工作过程中,若监控平台发现存在资源占用率大于资源占用率阈值的智能分析设备,则对该智能分析设备进行负载均衡处理,可以将该智能分析设备上的部分业务应用的视频流转移到与该智能分析设备绑定的智能分析设备上处理,实现分流,从而解决了智能分析设备资源使用不平衡的问题,实现整个***智能分析设备资源的均衡,提高了处理效率,避免人工处理的低效性。
第二方面,本申请提供一种智能分析设备资源调整方法,包括:
智能分析设备在接入监控平台后,向监控平台发送智能分析设备的状态信息和智能分析设备上部署的应用信息,状态信息包括资源占用率和已绑定的摄像机的个数;
智能分析设备接收监控平台发送的绑定目标摄像机的命令,向目标摄像机发送视频流 请求;
智能分析设备接收目标摄像机发送的视频流,对接收到的视频流进行分析处理。
通过第二方面提供的智能分析设备资源调整方法,智能分析设备在接入监控平台后,向监控平台发送智能分析设备的状态信息和智能分析设备上部署的应用信息,在任一摄像机接入监控平台后,监控平台根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备,向所选择的智能分析设备发送绑定该摄像机的命令,将摄像机绑定在智能分析设备上,智能分析设备接收目标摄像机发送的视频流,对接收到的视频流进行分析处理。从而,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,智能分析设备可以分析处理摄像机采集的视频流,可以通过自动化的方式分配智能分析设备的资源,提高了处理效率,避免人工处理的低效性。
在一种可能的设计中,方法还包括:
智能分析设备接收监控平台发送的状态信息获取请求;
智能分析设备向监控平台发送智能分析设备的状态信息。
在一种可能的设计中,智能分析设备的资源占用率大于资源占用率阈值时,方法还包括:
智能分析设备接收监控平台发送的解除绑定在智能分析设备上的一个或多个摄像机的命令;
智能分析设备向解除绑定的一个或多个摄像机发送停止发送视频流的命令。
通过该实施方式提供的智能分析设备资源调整方法,在智能分析设备工作过程中,若监控平台发现存在资源占用率大于资源占用率阈值的智能分析设备,则对该智能分析设备进行负载均衡处理,可以动态调整摄像机与智能分析设备的绑定关系,从而解决了智能分析设备资源使用不平衡的问题,实现整个***智能分析设备资源的均衡,提高了处理效率,避免人工处理的低效性。
在一种可能的设计中,智能分析设备的资源占用率大于资源占用率阈值时,方法还包括:
智能分析设备接收绑定智能分析设备的目标智能分析设备发送的视频流请求,目标智能分析设备为监控平台根据监控平台接入的其他智能分析设备的状态信息和应用信息为智能分析设备选择的;
智能分析设备接收监控平台发送的停止部分业务应用处理的命令;
智能分析设备向目标智能分析设备发送部分业务应用的视频流。
通过该实施方式提供的智能分析设备资源调整方法,在智能分析设备工作过程中,若监控平台发现存在资源占用率大于资源占用率阈值的智能分析设备,则根据监控平台接入的其他智能分析设备的状态信息和应用信息为智能分析设备选择绑定的目标智能分析设备,将该智能分析设备上的部分业务应用的视频流转移到目标智能分析设备上处理,实现分流,从而解决了智能分析设备资源使用不平衡的问题,实现整个***智能分析设备资源的均衡,提高了处理效率,避免人工处理的低效性。
第三方面,本申请提供一种监控平台,包括:
获取模块,用于获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署 的应用信息,状态信息包括资源占用率和已绑定的摄像机的个数;选择模块,用于在摄像机接入监控平台后,根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备;发送模块,用于向所选择的智能分析设备发送绑定摄像机的命令。
在一种可能的设计中,选择模块用于:
从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,轮询选择一个智能分析设备与摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,选择距摄像机位置最近的一个智能分析设备与摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,选择资源占用率最低的一个智能分析设备与摄像机绑定。
在一种可能的设计中,获取模块用于:
向接入监控平台的智能分析设备发送状态信息获取请求;
接收接入监控平台的智能分析设备发送的状态信息。
在一种可能的设计中,监控平台还包括:
处理模块,用于当接入监控平台的智能分析设备的资源占用率大于资源占用率阈值,则对智能分析设备进行负载均衡处理。
在一种可能的设计中,处理模块用于:
若智能分析设备已绑定摄像机,则为绑定在智能分析设备上的一个或多个摄像机重新选择绑定的智能分析设备;
发送模块还用于:向智能分析设备发送解除绑定在智能分析设备上的一个或多个摄像机的命令;
发送模块还用于:向重新选择绑定的智能分析设备发送绑定所述一个或多个摄像机的命令。
在一种可能的设计中,处理模块用于:
若智能分析设备未绑定摄像机,则根据监控平台接入的其他智能分析设备的状态信息和应用信息为智能分析设备选择绑定的目标智能分析设备;
向目标智能分析设备发送绑定智能分析设备的命令;
向智能分析设备发送停止部分业务应用处理的命令。
上述第三方面以及上述第三方面的各可能的设计中所提供的装置,其有益效果可以参见上述第一方面和第一方面的各可能的实施方式所带来的有益效果,在此不再赘述。
第四方面,本申请提供一种智能分析设备,包括:发送模块,用于智能分析设备在接入监控平台后,向监控平台发送智能分析设备的状态信息和智能分析设备上部署的应用信息,状态信息包括资源占用率和已绑定的摄像机的个数;接收模块,用于接收监控平台发送的绑定目标摄像机的命令;发送模块还用于:向目标摄像机发送视频流请求;接收模块还用于:接收目标摄像机发送的视频流;处理模块,用于对接收到的视频流进行分析处理。
在一种可能的设计中,接收模块还用于:接收监控平台发送的状态信息获取请求;
发送模块还用于:向监控平台发送智能分析设备的状态信息。
在一种可能的设计中,智能分析设备的资源占用率大于资源占用率阈值时,
接收模块还用于:接收监控平台发送的解除绑定在智能分析设备上的一个或多个摄像 机的命令;
发送模块还用于:向解除绑定的一个或多个摄像机发送停止发送视频流的命令。
在一种可能的设计中,智能分析设备的资源占用率大于资源占用率阈值时,
接收模块还用于:接收绑定智能分析设备的目标智能分析设备发送的视频流请求,目标智能分析设备为监控平台根据监控平台接入的其他智能分析设备的状态信息和应用信息为智能分析设备选择的;
接收模块还用于:接收监控平台发送的停止部分业务应用处理的命令;
发送模块还用于:向目标智能分析设备发送部分业务应用的视频流。
上述第四方面以及上述第四方面的各可能的设计中所提供的装置,其有益效果可以参见上述第二方面和第二方面的各可能的实施方式所带来的有益效果,在此不再赘述。
第五方面,本申请提供一种监控平台,包括:存储器和处理器;
存储器用于存储程序指令;
处理器用于调用存储器中的程序指令执行第一方面及第一方面任一种可能的设计中的智能分析设备资源调整方法。
第六方面,本申请提供一种智能分析设备,包括:存储器和处理器;
存储器用于存储程序指令;
处理器用于调用存储器中的程序指令执行第二方面及第二方面任一种可能的设计中的智能分析设备资源调整方法。
第七方面,本申请提供一种可读存储介质,可读存储介质中存储有执行指令,当监控平台的至少一个处理器执行该执行指令时,监控平台执行第一方面及第一方面任一种可能的设计中的智能分析设备资源调整方法。
第八方面,本申请提供一种可读存储介质,可读存储介质中存储有执行指令,当智能分析设备的至少一个处理器执行该执行指令时,智能分析设备执行第二方面及第二方面任一种可能的设计中的智能分析设备资源调整方法。
第九方面,本申请提供一种程序产品,该程序产品包括执行指令,该执行指令存储在可读存储介质中。监控平台的至少一个处理器可以从可读存储介质读取该执行指令,至少一个处理器执行该执行指令使得监控平台实施第一方面及第一方面任一种可能的设计中的智能分析设备资源调整方法。
第十方面,本申请提供一种程序产品,该程序产品包括执行指令,该执行指令存储在可读存储介质中。智能分析设备的至少一个处理器可以从可读存储介质读取该执行指令,至少一个处理器执行该执行指令使得智能分析设备实施第二方面及第二方面任一种可能的设计中的智能分析设备资源调整方法。
第十一方面,本申请提供一种芯片,所述芯片与存储器相连,或者所述芯片上集成有存储器,当所述存储器中存储的软件程序被执行时,实现第一方面及第一方面任一种可能的设计中或者第二方面及第二方面任一种可能的设计中的智能分析设备资源调整方法。
第十二方面,本申请提供一种智能分析设备资源调整方法,包括:
智能分析设备在接入监控平台后,向所述监控平台发送所述智能分析设备的状态信息 和所述智能分析设备上部署的应用信息,所述状态信息包括资源占用率和已绑定的摄像机的个数;
所述监控平台在摄像机接入所述监控平台后,根据接入所述监控平台的智能分析设备的状态信息和应用信息为所述摄像机选择绑定的智能分析设备;
所述监控平台向所选择的智能分析设备发送绑定所述摄像机的命令;
接收到绑定所述摄像机的命令的智能分析设备向所述摄像机发送视频流请求,并接收所述摄像机发送的视频流,对接收到的视频流进行分析处理。
通过第十二方面提供的智能分析设备资源调整方法,通过智能分析设备在接入监控平台后,向监控平台发送智能分析设备的状态信息和智能分析设备上部署的应用信息,在任一摄像机接入监控平台后,监控平台根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备,向所选择的智能分析设备发送绑定该摄像机的命令,将摄像机绑定在智能分析设备上,从而,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,智能分析设备可以分析处理摄像机采集的视频流,可以通过自动化的方式分配智能分析设备的资源,提高了处理效率,避免人工处理的低效性。
在一种可能的设计中,所述根据接入所述监控平台的智能分析设备的状态信息和应用信息为所述摄像机选择绑定的智能分析设备,包括:
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,轮询选择一个智能分析设备与所述摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择距所述摄像机位置最近的一个智能分析设备与所述摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择资源占用率最低的一个智能分析设备与所述摄像机绑定。
在一种可能的设计中,所述方法还包括:
所述监控平台向所述智能分析设备发送状态信息获取请求;
所述智能分析设备向所述监控平台发送所述智能分析设备的状态信息。
在一种可能的设计中,所述方法还包括:
当接入所述监控平台的智能分析设备的资源占用率大于资源占用率阈值,则所述监控平台对所述智能分析设备进行负载均衡处理。
在一种可能的设计中,所述监控平台对所述智能分析设备进行负载均衡处理,包括:
若所述智能分析设备已绑定摄像机,则所述监控平台为绑定在所述智能分析设备上的一个或多个摄像机重新选择绑定的智能分析设备;
所述监控平台向所述智能分析设备发送解除绑定在所述智能分析设备上的一个或多个摄像机的命令;
所述监控平台向重新选择绑定的智能分析设备发送绑定所述一个或多个摄像机的命令;
所述智能分析设备向解除绑定的一个或多个摄像机发送停止发送视频流的命令。
通过该实施方式提供的智能分析设备资源调整方法,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,在 智能分析设备工作过程中,若监控平台发现存在资源占用率大于资源占用率阈值的智能分析设备,则对该智能分析设备进行负载均衡处理,可以动态调整摄像机与智能分析设备的绑定关系,从而解决了智能分析设备资源使用不平衡的问题,实现整个***智能分析设备资源的均衡,提高了处理效率,避免人工处理的低效性。
在一种可能的设计中,所述监控平台对所述智能分析设备进行负载均衡处理,包括:
若所述智能分析设备未绑定摄像机,则所述监控平台根据接入所述监控平台的其他智能分析设备的状态信息和应用信息为所述智能分析设备选择绑定的目标智能分析设备;
所述监控平台向所述目标智能分析设备发送绑定所述智能分析设备的命令;
所述监控平台向所述智能分析设备发送停止部分业务应用处理的命令;
所述智能分析设备接收所述目标智能分析设备发送的视频流请求,向所述目标智能分析设备发送所述部分业务应用的视频流。
通过该实施方式提供的智能分析设备资源调整方法,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,在智能分析设备工作过程中,若监控平台发现存在资源占用率大于资源占用率阈值的智能分析设备,则对该智能分析设备进行负载均衡处理,可以将该智能分析设备上的部分业务应用的视频流转移到与该智能分析设备绑定的智能分析设备上处理,实现分流,从而解决了智能分析设备资源使用不平衡的问题,实现整个***智能分析设备资源的均衡,提高了处理效率,避免人工处理的低效性。
第十三方面,本申请提供一种监控管理***,包括监控平台和智能分析设备,
所述智能分析设备用于:在接入监控平台后,向所述监控平台发送所述智能分析设备的状态信息和所述智能分析设备上部署的应用信息,所述状态信息包括资源占用率和已绑定的摄像机的个数;
所述监控平台用于:在摄像机接入所述监控平台后,根据接入所述监控平台的智能分析设备的状态信息和应用信息为所述摄像机选择绑定的智能分析设备;
所述监控平台还用于:向所选择的智能分析设备发送绑定所述摄像机的命令;
接收到绑定所述摄像机的命令的智能分析设备用于:向所述摄像机发送视频流请求,并接收所述摄像机发送的视频流,对接收到的视频流进行分析处理。
在一种可能的设计中,所述监控平台具体用于:
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,轮询选择一个智能分析设备与所述摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择距所述摄像机位置最近的一个智能分析设备与所述摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择资源占用率最低的一个智能分析设备与所述摄像机绑定。
在一种可能的设计中,所述监控平台还用于:向所述智能分析设备发送状态信息获取请求;
所述智能分析设备还用于:向所述监控平台发送所述智能分析设备的状态信息。
在一种可能的设计中,当接入所述监控平台的智能分析设备的资源占用率大于资源占用率阈值,所述监控平台还用于:对所述智能分析设备进行负载均衡处理。
在一种可能的设计中,所述监控平台具体用于:
若所述智能分析设备已绑定摄像机,则为绑定在所述智能分析设备上的一个或多个摄像机重新选择绑定的智能分析设备;
向所述智能分析设备发送解除绑定在所述智能分析设备上的一个或多个摄像机的命令;
向重新选择绑定的智能分析设备发送绑定所述一个或多个摄像机的命令;
所述智能分析设备还用于:向解除绑定的一个或多个摄像机发送停止发送视频流的命令。
在一种可能的设计中,所述监控平台具体用于:
若所述智能分析设备未绑定摄像机,则根据接入所述监控平台的其他智能分析设备的状态信息和应用信息为所述智能分析设备选择绑定的目标智能分析设备;
向所述目标智能分析设备发送绑定所述智能分析设备的命令;
向所述智能分析设备发送停止部分业务应用处理的命令;
所述智能分析设备还用于:接收所述目标智能分析设备发送的视频流请求,向所述目标智能分析设备发送所述部分业务应用的视频流。
上述第十三方面以及上述第十三方面的各可能的设计中所提供的***,其有益效果可以参见上述第十二方面和第十二方面的各可能的实施方式所带来的有益效果,在此不再赘述。
附图说明
图1为本申请提供的一种监控管理***的结构示意图;
图2为本申请提供的一种智能分析设备资源调整方法实施例的流程图;
图3为摄像机接入监控平台后监控平台进行绑定的示意图;
图4为本申请提供的一种智能分析设备资源调整方法实施例的流程图;
图5为本申请提供的一种智能分析设备资源调整方法实施例的交互流程图;
图6为本申请提供的一种智能分析设备资源调整方法实施例的交互流程图;
图7为本申请提供的一种智能分析设备资源调整方法实施例的交互流程图;
图8为本申请提供的一种监控平台的结构示意图;
图9为本申请提供的一种监控平台的结构示意图;
图10为本申请提供的一种智能分析设备的结构示意图;
图11为本申请提供的一种监控平台结构示意图;
图12为本申请提供的一种智能分析设备结构示意图。
具体实施方式
本申请提供的智能分析设备资源调整方法及装置,可应用于由监控平台和智能分析设备组成的监控管理***中,图1为本申请提供的一种监控管理***的结构示意图,如图1所示,本申请的监控管理***涉及的网元为智能分析设备、摄像机和监控平台,其中,智能分析设备为具有图像分析、图像处理、视频分析、视频处理等功能的设备,智能分析设备还可以具有图像采集功能,例如智能分析设备可以为智能摄像机,本申请中的摄像机仅有图像采集功能,本申请中摄像机可以是各类摄像机,还可以是摄像头,监控平台为任一具有可执行本申请提供的智能分析设备资源调整方法的软件或硬件,图1 所示的监控管理***中,智能分析设备接入监控平台后,向监控平台上报自身的状态信息和部署的应用信息,监控平台在摄像机接入监控管理***后,为摄像机选择绑定的智能分析设备进行绑定,之后在智能分析设备工作后,监控平台可根据***中智能分析设备的资源占用率变化情况对智能分析设备进行负载均衡处理。下面结合附图详细说明本申请的技术方案。
图2为本申请提供的一种智能分析设备资源调整方法实施例的流程图,本实施例的执行主体可以为监控平台,如图2所示,本实施例的方法可以包括:
S101、获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,状态信息包括资源占用率和已绑定的摄像机的个数。
具体地,智能分析设备接入监控平台后,监控平台可直接获取智能分析设备上部署的应用信息,应用信息为智能分析设备所具备的应用功能,如可进行人脸识别、车牌识别、抛物识别、入侵检测、自动跟踪等。具体可以是智能分析设备接入监控平台后主动上报自身的应用信息,也可以是智能分析设备接入监控平台后监控平台请求智能分析设备上报自身的应用信息,监控平台获取到智能分析设备的应用信息后存储。
状态信息包括资源占用率和已绑定的摄像机的个数,其中资源占用率可以是中央处理器(CPU)和内存的占用率,在智能分析设备接入监控平台后,初始的状态信息中已绑定的摄像机的个数为0。可选的,S101中监控平台获取接入监控平台中的智能分析设备的状态信息有两种可实施的方式,作为一种可实施的方式,具体可以为:
向接入监控平台的智能分析设备发送状态信息获取请求,可选的,可以是周期性发送状态信息获取请求,即就是监控平台周期性触发智能分析设备上报自身的状态信息;或者随机性发送状态信息获取请求,或者事件触发后发送状态信息获取请求,或者人为控制发送状态信息获取请求等。
接收接入监控平台的智能分析设备发送的状态信息。
作为另一种可实施的方式,具体可以为:接收接入监控平台的智能分析设备在状态信息更新时发送的状态信息。该方式为智能分析设备在状态信息更新时主动上报给监控平台。
需要说明的是,智能分析设备接入监控平台后,应用信息和初始的状态信息可以是同时上报给监控平台,也可以是分开上报给监控平台,应用信息上报一次即可。可选的,初始状态信息中还包括智能分析设备可绑定的摄像机的最大个数。
本实施例中,智能分析设备向监控平台提供媒体处理控制的应用程序编程接口(Application programming interface,API),二者通过标准协议互通,标准协议例如可以为OVIF或T28181。智能分析设备可通过API接口接入监控平台。
S102、在摄像机接入监控平台后,根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备。
具体地,摄像机也向监控平台提供API接口,二者通过标准协议互通,标准协议例如可以为OVIF或T28181,摄像机可通过API接口接入监控平台。接入监控平台的 智能分析设备构成一智能分析设备资源池,图3为摄像机接入监控平台后监控平台进行绑定的示意图,如图3所示,摄像机接入监控平台后,监控平台从智能分析设备资源池中选择智能分析设备,将摄像机绑定在智能分析设备上。
本实施例中,具体地,监控平台根据***中智能分析设备的状态信息、应用信息和可绑定的摄像机的最大个数,为摄像机选择绑定的智能分析设备,首先监控平台先根据智能分析设备已绑定的摄像机的个数和该智能分析设备可绑定的摄像机的最大个数判定是否可再绑定摄像机,若可以,则监控平台根据***中每一智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备,具体地,有三种可实施的方式:
方式一、从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,轮询选择一个智能分析设备与摄像机绑定。
其中,接入监控平台中的所有智能分析设备可以是资源占用率阈值均相同,也可以是不同,每一智能分析设备对应有其资源占用率阈值,资源占用率阈值例如为85%或90%等。其中的应用信息与摄像机匹配是指所选的要绑定的智能分析设备可以处理该摄像机的视频流。
方式二、从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,选择距所述摄像机位置最近的一个智能分析设备与摄像机绑定。
其中,位置最近可以是指地理位置最近。
方式三、从资源占用率小于资源占用率阈值且应用信息与摄像机匹配的智能分析设备中,选择资源占用率最低的一个智能分析设备与摄像机绑定。
S103、向所选择的智能分析设备发送绑定所述摄像机的命令。
具体地,绑定摄像机的命令还可以是绑定请求、绑定指示、绑定通知等,绑定摄像机的命令可以采用restful或rpc格式,绑定摄像机的命令可以包含要绑定的摄像机的IP地址、端口、认证信息、识别号以及要进行的业务类型(如进行人脸识别)。对于所选择的智能分析设备而言,接收到监控平台发送的绑定摄像机的命令后,向该摄像机发送视频流请求,接收该摄像机发送的视频流,对接收到的视频流进行分析处理。
本实施例提供的智能分析设备资源调整方法,通过监控平台获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,在任一摄像机接入监控平台后,监控平台根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备,向所选择的智能分析设备发送绑定该摄像机的命令,将摄像机绑定在智能分析设备上,从而,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,智能分析设备可以分析处理摄像机采集的视频流,可以通过自动化的方式分配智能分析设备的资源,提高了处理效率,避免人工处理的低效性。
图4为本申请提供的一种智能分析设备资源调整方法实施例的流程图,本实施例的执行主体可以为监控平台,如图4所示,本实施的方法在图2所示方法的基础上,进一步地,还可以包括:
S104、当接入监控平台的智能分析设备的资源占用率大于资源占用率阈值,则对智能分析设备进行负载均衡处理。
具体地,在智能分析设备工作过程中,若监控平台发现***中出现资源分配不均衡,即存在资源占用率大于资源占用率阈值的智能分析设备,则对该智能分析设备进行负载均衡处理。S103中对智能分析设备进行负载均衡处理有两种可具体实施的方式:
方式一、若智能分析设备已绑定摄像机,则监控平台对该智能分析设备进行负载均衡处理具体可以为:为绑定在该智能分析设备上的一个或多个摄像机重新选择绑定的智能分析设备,向所述智能分析设备发送解除绑定在所述智能分析设备上的一个或多个摄像机的命令,向重新选择绑定的智能分析设备发送绑定所述一个或多个摄像机的命令。
具体地,解除绑定命令中可以包含要解除绑定的摄像机的IP地址和端口等,对于原智能分析设备而言,相应地,原智能分析设备接收监控平台下发的解除绑定在智能分析设备上的一个或多个摄像机的命令后,解除相应摄像机的绑定,向解除绑定的一个或多个摄像机发送停止发送视频流的命令。然后,重新选择绑定的智能分析设备接收绑定摄像机的命令后,向绑定的摄像机发送视频流,对接收到的视频流进行分析处理。
方式二、若智能分析设备未绑定摄像机,则监控平台对该智能分析设备进行负载均衡处理具体可以为:根据监控平台接入的其他智能分析设备的状态信息和应用信息为该智能分析设备选择绑定的目标智能分析设备,向目标智能分析设备发送绑定智能分析设备的命令,用于目标智能分析设备将该智能分析设备绑定在目标智能分析设备上,绑定智能分析设备的命令可以包含要绑定的智能分析设备的IP地址和端口等,向智能分析设备发送停止部分业务应用处理的命令,该命令用于智能分析设备停止对部分业务应用的视频流的处理。即,将该智能分析设备上的部分业务应用的视频流转移到绑定该智能分析设备的目标智能分析设备上。
具体来说,若智能分析设备未绑定摄像机,但是运行了多个应用,则根据监控平台接入的其他智能分析设备的状态信息和应用信息为该智能分析设备选择绑定的目标智能分析设备,由绑定的目标智能分析设备代替该智能分析设备进行部分应用处理,其中,代为处理的应用选择可以根据预定义规则进行,预定义规则如轮询、选择资源占用最小的应用、选择资源占用最大的应用或者选择资源占用居中的应用等。
对于资源占用率大于资源占用率阈值的智能分析设备而言,相应地,智能分析设备接收绑定智能分析设备的目标智能分析设备发送的视频流请求,目标智能分析设备为监控平台根据监控平台接入的其他智能分析设备的状态信息和应用信息为智能分析设备选择的,智能分析设备接收监控平台发送的停止部分业务应用处理的命令,智能分析设备向目标智能分析设备发送部分业务应用的视频流。相应地,目标智能分析设备接收监控平台发送的绑定该智能分析设备的命令,目标智能分析设备向智能分析设备发送视频流请求,对接收到的智能分析设备发送的部分业务应用的视频流进行分析处理。
本实施例提供的智能分析设备资源调整方法,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,在智能分析设备工作过程中,若监控平台发现存在资源占用率大于资源占用率阈值的智能分析设备,则对该智能分析设备进行负载均衡处理,可以动态调整摄像机与智能分析设备的绑定关系,还可以将该智能分析设备上的部分业务应用的视频流转移到与该智能分析设备绑定的智能 分析设备上处理,实现分流,从而解决了智能分析设备资源使用不平衡的问题,实现整个***智能分析设备资源的均衡,提高了处理效率,避免人工处理的低效性。
下面采用2个具体的实施例,对图1和图3所示方法实施例的技术方案进行详细说明。
图5为本申请提供的一种智能分析设备资源调整方法实施例的交互流程图,如图5所示,本实施例中以接入监控平台中的智能分析设备为3个为例,本实施例的方法可以包括:
S201、监控平台获取接入监控平台中的智能分析设备A、智能分析设备B和智能分析设备C的状态信息和智能分析设备A、智能分析设备B和智能分析设备C上部署的应用信息,状态信息包括资源占用率和已绑定的摄像机的个数。
具体地,有两种可实施的方式:
方式一、监控平台向智能分析设备发送状态信息获取请求,智能分析设备接收到状态信息获取请求后,向监控平台发送自身的状态信息。
方式二、智能分析设备在状态信息更新时向监控平台发送更新后的状态信息。
S202、摄像机接入监控平台。
S203、监控平台确定摄像机所需的智能分析处理对应的应用,根据智能分析设备上部署的应用信息确定与摄像机匹配的智能分析设备。
本实施例中,例如智能分析设备A、智能分析设备B和智能分析设备C均可以处理该摄像机的视频流。
S204、监控平台根据智能分析设备A、智能分析设备B和智能分析设备C的状态信息和智能分析设备A、智能分析设备B和智能分析设备C上部署的应用信息为摄像机选择绑定的智能分析设备,向该智能分析设备发送绑定摄像机的命令。
具体地,可以是从资源占用率小于资源占用率阈值的智能分析设备中,轮询选择一个智能分析设备与摄像机绑定,或者,从资源占用率小于资源占用率阈值的智能分析设备中,选择距所述摄像机位置最近的一个智能分析设备与摄像机绑定,或者,从资源占用率小于资源占用率阈值的智能分析设备中,选择资源占用率最低的一个智能分析设备与摄像机绑定。
本实施例,例如选择智能分析设备B,将摄像机与智能分析设备B绑定,则向智能分析设备B发送绑定该摄像机的命令。
S205、智能分析设备B向摄像机发送视频流请求。
S206、摄像机向智能分析设备B发送视频流。
S207、智能分析设备B对接收到的视频流进行分析处理。
图6为本申请提供的一种智能分析设备资源调整方法实施例的交互流程图,如图5所示,本实施例中以接入监控平台中的智能分析设备为3个为例,本实施例中以动态调 整摄像机与智能分析设备的绑定关系来进行负载均衡处理为例进行说明,本实施例的方法在图5所示方法的基础上,还可以包括:
S301、监控平台获取接入监控平台中的智能分析设备A、智能分析设备B和智能分析设备C的状态信息。
具体可以是采用图5所示实施例中的两种可实施的方式中的一种方式。
S302、监控平台根据智能分析设备A、智能分析设备B和智能分析设备C的状态信息,确定出智能分析设备B的资源占用率大于资源占用率阈值,即智能分析设备B过载。
S303、若智能分析设备B绑定了摄像机,监控平台为绑定在智能分析设备B上的一个或多个摄像机重新选择绑定的智能分析设备。例如,如图6所示,以一个摄像机为例,监控平台解除智能分析设备B与该摄像机的绑定,选择智能分析设备C与该摄像机绑定,则向智能分析设备C发送绑定该摄像机的命令,并向智能分析设备B发送解除绑定该摄像机的命令,一般地,解除绑定命令中包含索要解除的摄像机的IP地址和端口。
S304、智能分析设备B向解除绑定的该摄像机发送停止发送视频流的命令。
S305、智能分析设备C向摄像机发送视频流请求。
S306、摄像机向智能分析设备C发送视频流。
S307、智能分析设备C对接收到的视频流进行分析处理。
图7为本申请提供的一种智能分析设备资源调整方法实施例的交互流程图,如图7所示,本实施例中以接入监控平台中的智能分析设备为3个为例,本实施例中以将出现过载的智能分析设备上的部分业务应用切换到与该智能分析设备绑定的智能分析设备上来进行负载均衡处理为例进行说明,本实施例的方法在图5所示方法的基础上,还可以包括:
S401、监控平台获取接入监控平台中的智能分析设备A、智能分析设备B和智能分析设备C的状态信息。
具体可以是采用图5所示实施例中的两种可实施的方式中的一种方式。
S402、监控平台根据智能分析设备A、智能分析设备B和智能分析设备C的状态信息,确定出智能分析设备B的资源占用率大于资源占用率阈值,即智能分析设备B过载。
S403、若智能分析设备B未绑定摄像机,则监控平台根据智能分析设备A和智能分析设备C的状态信息和应用信息为智能分析设备B选择绑定的智能分析设备。
例如选择的绑定的智能分析设备为智能分析设备C,则监控平台向智能分析设备C发送绑定智能分析设备B的命令,智能分析设备C向智能分析设备B发送视频流请求。
监控平台将智能分析设备B上的部分业务应用的视频流转移到与智能分析设备B 绑定的智能分析设备C上。
如图7所示,例如智能分析设备B上正在处理的业务应用为人脸识别和车牌识别,监控平台将智能分析设备B上的业务应用—车牌识别的视频流转发到智能分析设备C上,智能分析设备B只处理人脸识别,智能分析设备C处理车牌识别和人脸识别。
S404、监控平台向智能分析设备B发送停止部分业务应用处理的命令。
S405、智能分析设备C向智能分析设备B发送视频流请求。
S406、智能分析设备B向智能分析设备C发送视频流。
S407、智能分析设备C对接收到的视频流进行分析处理。
图8为本申请提供的一种监控平台的结构示意图,如图8所示,本实施例的装置可以包括:获取模块11、选择模块12和发送模块13,其中,
获取模块11用于获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,所述状态信息包括资源占用率和已绑定的摄像机的个数。
选择模块12用于在摄像机接入所述监控平台后,根据接入所述监控平台的智能分析设备的状态信息和应用信息为所述摄像机选择绑定的智能分析设备。
发送模块13用于向所选择的智能分析设备发送绑定所述摄像机的命令。
可选的,选择模块12用于:
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,轮询选择一个智能分析设备与所述摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择距所述摄像机位置最近的一个智能分析设备与所述摄像机绑定;或者,
从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择资源占用率最低的一个智能分析设备与所述摄像机绑定。
可选的,获取模块11用于:
向接入所述监控平台的智能分析设备发送状态信息获取请求;
接收接入所述监控平台的智能分析设备发送的状态信息。
本实施例的装置,可以为监控平台,可以用于执行图1所示方法实施例的技术方案,其实现原理类似,此处不再赘述。
本实施例提供的监控平台,通过获取模块获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,在任一摄像机接入监控平台后,选择模块根据接入监控平台的智能分析设备的状态信息和应用信息为摄像机选择绑定的智能分析设备,发送模块向所选择的智能分析设备发送绑定该摄像机的命令,将摄像机绑定在智能分析设备上,从而,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,智能分析设备可以分析处理摄像机采集的视频流,可以通过自动化的方式分配智能分析设备的资源,提高了处理效率,避免人工处理的低效性。
图9为本申请提供的一种监控平台的结构示意图,如图9所示,本实施例的装置在 图8所示装置结构的基础上,进一步地,还可以包括:处理模块14,该处理模块14用于当接入所述监控平台的智能分析设备的资源占用率大于资源占用率阈值,则对所述智能分析设备进行负载均衡处理。
可选的,处理模块14用于:
若所述智能分析设备已绑定摄像机,则为绑定在所述智能分析设备上的一个或多个摄像机重新选择绑定的智能分析设备。
发送模块13还用于:向所述智能分析设备发送解除绑定在所述智能分析设备上的一个或多个摄像机的命令。
发送模块13还用于:向重新选择绑定的智能分析设备发送绑定所述一个或多个摄像机的命令。
可选的,处理模块14用于:
若所述智能分析设备未绑定摄像机,则根据所述监控平台接入的其他智能分析设备的状态信息和应用信息为所述智能分析设备选择绑定的目标智能分析设备;
向所述目标智能分析设备发送绑定所述智能分析设备的命令;
向所述智能分析设备发送停止部分业务应用处理的命令。
本实施例的装置,可以用于执行图4所示方法实施例的技术方案,其实现原理类似,此处不再赘述。
本实施例提供的监控平台,监控平台可根据接入监控平台的智能分析设备的资源,动态绑定仅有图像采集功能的摄像机到合适的智能分析设备上,在智能分析设备工作过程中,若监控平台发现存在资源占用率大于资源占用率阈值的智能分析设备,则对该智能分析设备进行负载均衡处理,可以动态调整摄像机与智能分析设备的绑定关系,还可以将该智能分析设备上的部分业务应用的视频流转移到与该智能分析设备绑定的智能分析设备上处理,实现分流,从而解决了智能分析设备资源使用不平衡的问题,实现整个***智能分析设备资源的均衡,提高了处理效率,避免人工处理的低效性。
图10为本申请提供的一种智能分析设备的结构示意图,如图10所示,本实施例的智能分析设备可以包括:发送模块21、接收模块22和处理模块23,其中,发送模块21用于智能分析设备在接入监控平台后,向监控平台发送所述智能分析设备的状态信息和所述智能分析设备上部署的应用信息,所述状态信息包括资源占用率和已绑定的摄像机的个数;
接收模块22用于接收所述监控平台发送的绑定目标摄像机的命令;
所述发送模块21还用于:向所述目标摄像机发送视频流请求;
所述接收模块22还用于:接收所述目标摄像机发送的视频流;
处理模块23用于对接收到的视频流进行分析处理。
进一步地,所述接收模块22还用于:接收所述监控平台发送的状态信息获取请求;
所述发送模块21还用于:向所述监控平台发送所述智能分析设备的状态信息。
进一步地,智能分析设备的资源占用率大于资源占用率阈值时,
所述接收模块22还用于:接收绑定所述智能分析设备的目标智能分析设备发送的视频流请求,所述目标智能分析设备为所述监控平台根据所述监控平台接入的其他智能分析设备的状态信息和应用信息为所述智能分析设备选择的;
所述接收模块22还用于:接收所述监控平台发送的停止部分业务应用处理的命令;
所述发送模块21还用于:向所述目标智能分析设备发送所述部分业务应用的视频流。
本实施例的装置,可以用于执行图1或图4所示方法实施例的技术方案,其实现原理类似,此处不再赘述。
本实施例提供的智能分析设备,智能分析设备在接入监控平台后,发送模块向监控平台发送智能分析设备的状态信息和智能分析设备上部署的应用信息,接收模块接收监控平台发送的绑定目标摄像机的命令,发送模块向目标摄像机发送视频流请求,接收模块接收目标摄像机发送的视频流,最后处理模块对接收到的视频流进行分析处理。从而,可以通过自动化的方式分配智能分析设备的资源,提高了处理效率,避免人工处理的低效性。
本申请可以根据上述方法示例对发送设备进行功能模块的划分,例如,可以对应各个功能划分各个功能模块,也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现,也可以采用软件功能模块的形式实现。需要说明的是,本申请各实施例中对模块的划分是示意性的,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
图11为本申请提供的一种监控平台结构示意图,该一种监控平台700包括:
存储器701,用于存储程序指令,该存储器701可以是flash(闪存)。
处理器702,用于调用并执行存储器中的程序指令,以实现图1或图4的智能分析设备资源调整方法中的各个步骤。具体可以参见前面方法实施例中的相关描述。
还可以包括输入/输出接口703。输入/输出接口703可以包括独立的输出接口和输入接口,也可以为集成输入和输出的集成接口。其中,输出接口用于输出数据,输入接口用于获取输入的数据,上述输出的数据为上述方法实施例中输出的统称,输入的数据为上述方法实施例中输入的统称。
该监控平台可以用于执行上述方法实施例中监控平台对应的各个步骤和/或流程。
图12为本申请提供的一种智能分析设备结构示意图,该一种智能分析设备800包括:
存储器801,用于存储程序指令,该存储器801可以是flash(闪存)。
处理器802,用于调用并执行存储器中的程序指令,以实现图1或图4的智能分析设备资源调整方法中的各个步骤。具体可以参见前面方法实施例中的相关描述。
还可以包括输入/输出接口803。输入/输出接口803可以包括独立的输出接口和输入接口,也可以为集成输入和输出的集成接口。其中,输出接口用于输出数据,输入接口用于获取输入的数据,上述输出的数据为上述方法实施例中输出的统称,输入的数据为上述方法实施例中输入的统称。
该智能分析设备可以用于执行上述方法实施例中智能分析设备对应的各个步骤和/ 或流程。
本申请还提供一种可读存储介质,可读存储介质中存储有执行指令,当监控平台的至少一个处理器执行该执行指令时,监控平台执行上述方法实施例中的智能分析设备资源调整方法。
本申请还提供一种可读存储介质,可读存储介质中存储有执行指令,当智能分析设备的至少一个处理器执行该执行指令时,智能分析设备执行上述方法实施例中的智能分析设备资源调整方法。
本申请还提供一种芯片,所述芯片与存储器相连,或者所述芯片上集成有存储器,当所述存储器中存储的软件程序被执行时,实现上述方法实施例中的智能分析设备资源调整方法。
本申请还提供一种程序产品,该程序产品包括执行指令,该执行指令存储在可读存储介质中。监控平台的至少一个处理器可以从可读存储介质读取该执行指令,至少一个处理器执行该执行指令使得监控平台实施上述方法实施例中的智能分析设备资源调整方法。
本申请还提供一种程序产品,该程序产品包括执行指令,该执行指令存储在可读存储介质中。智能分析设备的至少一个处理器可以从可读存储介质读取该执行指令,至少一个处理器执行该执行指令使得智能分析设备实施上述方法实施例中的智能分析设备资源调整方法。
本申请还提供一种监控管理***,包括图8或图9所示的监控平台和图10所示的智能分析设备,或者,包括图11所示的监控平台和图12所示的智能分析设备。
本领域普通技术人员可以理解:在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时,全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如固态硬盘Solid State Disk(SSD))等。

Claims (22)

  1. 一种智能分析设备资源调整方法,其特征在于,包括:
    获取接入监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,所述状态信息包括资源占用率和已绑定的摄像机的个数;
    在摄像机接入所述监控平台后,根据接入所述监控平台的智能分析设备的状态信息和应用信息为所述摄像机选择绑定的智能分析设备;
    向所选择的智能分析设备发送绑定所述摄像机的命令。
  2. 根据权利要求1所述的方法,其特征在于,所述根据接入所述监控平台的智能分析设备的状态信息和应用信息为所述摄像机选择绑定的智能分析设备,包括:
    从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,轮询选择一个智能分析设备与所述摄像机绑定;或者,
    从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择距所述摄像机位置最近的一个智能分析设备与所述摄像机绑定;或者,
    从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择资源占用率最低的一个智能分析设备与所述摄像机绑定。
  3. 根据权利要求1或2所述的方法,其特征在于,所述方法还包括:
    向接入所述监控平台的智能分析设备发送状态信息获取请求;
    接收接入所述监控平台的智能分析设备发送的状态信息。
  4. 根据权利要求1-3任一项所述的方法,其特征在于,所述方法还包括:
    当接入所述监控平台的智能分析设备的资源占用率大于资源占用率阈值,则对所述智能分析设备进行负载均衡处理。
  5. 根据权利要求4所述的方法,其特征在于,所述对所述智能分析设备进行负载均衡处理,包括:
    若所述智能分析设备已绑定摄像机,则为绑定在所述智能分析设备上的一个或多个摄像机重新选择绑定的智能分析设备;
    向所述智能分析设备发送解除绑定在所述智能分析设备上的一个或多个摄像机的命令;
    向重新选择绑定的智能分析设备发送绑定所述一个或多个摄像机的命令。
  6. 根据权利要求4所述的方法,其特征在于,所述对所述智能分析设备进行负载均衡处理,包括:
    若所述智能分析设备未绑定摄像机,则根据接入所述监控平台的其他智能分析设备的状态信息和应用信息为所述智能分析设备选择绑定的目标智能分析设备;
    向所述目标智能分析设备发送绑定所述智能分析设备的命令;
    向所述智能分析设备发送停止部分业务应用处理的命令。
  7. 一种智能分析设备资源调整方法,其特征在于,包括:
    智能分析设备在接入监控平台后,向所述监控平台发送所述智能分析设备的状态信息和所述智能分析设备上部署的应用信息,所述状态信息包括资源占用率和已绑定的摄像机的个数;
    所述智能分析设备接收所述监控平台发送的绑定目标摄像机的命令,向所述目标摄 像机发送视频流请求;
    所述智能分析设备接收所述目标摄像机发送的视频流,对接收到的视频流进行分析处理。
  8. 根据权利要求7所述的方法,其特征在于,所述方法还包括:
    所述智能分析设备接收所述监控平台发送的状态信息获取请求;
    所述智能分析设备向所述监控平台发送所述智能分析设备的状态信息。
  9. 根据权利要求7或8所述的方法,其特征在于,所述智能分析设备的资源占用率大于资源占用率阈值时,所述方法还包括:
    所述智能分析设备接收所述监控平台发送的解除绑定在所述智能分析设备上的一个或多个摄像机的命令;
    所述智能分析设备向解除绑定的一个或多个摄像机发送停止发送视频流的命令。
  10. 根据权利要求7或8所述的方法,其特征在于,所述智能分析设备的资源占用率大于资源占用率阈值时,所述方法还包括:
    所述智能分析设备接收绑定所述智能分析设备的目标智能分析设备发送的视频流请求,所述目标智能分析设备为所述监控平台根据所述监控平台接入的其他智能分析设备的状态信息和应用信息为所述智能分析设备选择的;
    所述智能分析设备接收所述监控平台发送的停止部分业务应用处理的命令;
    所述智能分析设备向所述目标智能分析设备发送所述部分业务应用的视频流。
  11. 一种监控平台,其特征在于,包括:
    获取模块,用于获取接入所述监控平台的智能分析设备的状态信息和智能分析设备上部署的应用信息,所述状态信息包括资源占用率和已绑定的摄像机的个数;
    选择模块,用于在摄像机接入所述监控平台后,根据接入所述监控平台的智能分析设备的状态信息和应用信息为所述摄像机选择绑定的智能分析设备;
    发送模块,用于向所选择的智能分析设备发送绑定所述摄像机的命令。
  12. 根据权利要求11所述的监控平台,其特征在于,所述选择模块用于:
    从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,轮询选择一个智能分析设备与所述摄像机绑定;或者,
    从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择距所述摄像机位置最近的一个智能分析设备与所述摄像机绑定;或者,
    从资源占用率小于资源占用率阈值且应用信息与所述摄像机匹配的智能分析设备中,选择资源占用率最低的一个智能分析设备与所述摄像机绑定。
  13. 根据权利要求11或12所述的监控平台,其特征在于,所述获取模块用于:
    向接入所述监控平台的智能分析设备发送状态信息获取请求;
    接收接入所述监控平台的智能分析设备发送的状态信息。
  14. 根据权利要求11-13任一项所述的监控平台,其特征在于,所述监控平台还包括:
    处理模块,用于当接入所述监控平台的智能分析设备的资源占用率大于资源占用率阈值,则对所述智能分析设备进行负载均衡处理。
  15. 根据权利要求14所述的监控平台,其特征在于,所述处理模块用于:
    若所述智能分析设备已绑定摄像机,则为绑定在所述智能分析设备上的一个或多个摄像机重新选择绑定的智能分析设备;
    所述发送模块还用于:向所述智能分析设备发送解除绑定在所述智能分析设备上的一个或多个摄像机的命令;
    所述发送模块还用于:向重新选择绑定的智能分析设备发送绑定所述一个或多个摄像机的命令。
  16. 根据权利要求14所述的监控平台,其特征在于,所述处理模块用于:
    若所述智能分析设备未绑定摄像机,则根据接入所述监控平台的其他智能分析设备的状态信息和应用信息为所述智能分析设备选择绑定的目标智能分析设备;
    向所述目标智能分析设备发送绑定所述智能分析设备的命令;
    向所述智能分析设备发送停止部分业务应用处理的命令。
  17. 一种智能分析设备,其特征在于,包括:
    发送模块,用于所述智能分析设备在接入监控平台后,向所述监控平台发送所述智能分析设备的状态信息和所述智能分析设备上部署的应用信息,所述状态信息包括资源占用率和已绑定的摄像机的个数;
    接收模块,用于接收所述监控平台发送的绑定目标摄像机的命令;
    所述发送模块还用于:向所述目标摄像机发送视频流请求;
    所述接收模块还用于:接收所述目标摄像机发送的视频流;
    处理模块,用于对接收到的视频流进行分析处理。
  18. 根据权利要求17所述的智能分析设备,其特征在于,
    所述接收模块还用于:接收所述监控平台发送的状态信息获取请求;
    所述发送模块还用于:向所述监控平台发送所述智能分析设备的状态信息。
  19. 根据权利要求17或18所述的智能分析设备,其特征在于,所述智能分析设备的资源占用率大于资源占用率阈值时,
    所述接收模块还用于:接收所述监控平台发送的解除绑定在所述智能分析设备上的一个或多个摄像机的命令;
    所述发送模块还用于:向解除绑定的一个或多个摄像机发送停止发送视频流的命令。
  20. 根据权利要求17或18所述的智能分析设备,其特征在于,所述智能分析设备的资源占用率大于资源占用率阈值时,
    所述接收模块还用于:接收绑定所述智能分析设备的目标智能分析设备发送的视频流请求,所述目标智能分析设备为所述监控平台根据所述监控平台接入的其他智能分析设备的状态信息和应用信息为所述智能分析设备选择的;
    所述接收模块还用于:接收所述监控平台发送的停止部分业务应用处理的命令;
    所述发送模块还用于:向所述目标智能分析设备发送所述部分业务应用的视频流。
  21. 一种可读存储介质,其特征在于,可读存储介质中存储有执行指令,当监控平台的至少一个处理器执行该执行指令时,所述监控平台执行权利要求1-6任一项所述的智能分析设备资源调整方法。
  22. 一种可读存储介质,其特征在于,可读存储介质中存储有执行指令,当智能分析设备的至少一个处理器执行该执行指令时,所述智能分析设备执行权利要求7-10任一项所述的智能分析设备资源调整方法。
PCT/CN2019/090274 2018-09-21 2019-06-06 智能分析设备资源调整方法及装置 WO2020057178A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP19863081.6A EP3846459A4 (en) 2018-09-21 2019-06-06 METHOD AND APPARATUS FOR ADJUSTING THE RESOURCES OF INTELLIGENT ANALYSIS DEVICES
US17/206,609 US11537810B2 (en) 2018-09-21 2021-03-19 Method for adjusting resource of intelligent analysis device and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811110372.4A CN110944146B (zh) 2018-09-21 2018-09-21 智能分析设备资源调整方法及装置
CN201811110372.4 2018-09-21

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/206,609 Continuation US11537810B2 (en) 2018-09-21 2021-03-19 Method for adjusting resource of intelligent analysis device and apparatus

Publications (1)

Publication Number Publication Date
WO2020057178A1 true WO2020057178A1 (zh) 2020-03-26

Family

ID=69888218

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/090274 WO2020057178A1 (zh) 2018-09-21 2019-06-06 智能分析设备资源调整方法及装置

Country Status (4)

Country Link
US (1) US11537810B2 (zh)
EP (1) EP3846459A4 (zh)
CN (1) CN110944146B (zh)
WO (1) WO2020057178A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110248156B (zh) * 2019-05-17 2020-11-10 浙江大华技术股份有限公司 视频分析方法、平台设备、智能相机和智能监控***
CN111479048A (zh) * 2020-04-22 2020-07-31 安徽大学 一种基于边缘计算的智能视频图像处理设备
CN111625358B (zh) * 2020-05-25 2023-06-20 浙江大华技术股份有限公司 一种资源分配方法、装置、电子设备及存储介质
CN112165603B (zh) * 2020-09-01 2023-04-25 北京都是科技有限公司 人工智能管理***以及人工智能处理设备的管理方法
CN113194298B (zh) * 2021-05-07 2023-04-07 浙江宇视科技有限公司 实现非智能相机图像结构化的方法、装置、***及介质
CN113687947A (zh) * 2021-08-25 2021-11-23 京东方科技集团股份有限公司 边缘盒子的优化方法及装置、存储介质、电子设备
CN117041534B (zh) * 2023-10-08 2024-01-02 天津华来科技股份有限公司 一种智能摄像机的绑定性能测试方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104363300A (zh) * 2014-11-26 2015-02-18 浙江宇视科技有限公司 一种服务器集群中计算任务分布式调度装置
CN104581423A (zh) * 2013-10-12 2015-04-29 北京航天长峰科技工业集团有限公司 一种海量视频智能分析***的综合调度和负载均衡方法
CN104917836A (zh) * 2015-06-10 2015-09-16 北京奇虎科技有限公司 基于集群监控分析计算设备可用性的方法及装置
US20170078626A1 (en) * 2015-09-16 2017-03-16 Microsoft Technology Licensing, Llc Bandwidth efficient video surveillance system

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060171453A1 (en) * 2005-01-04 2006-08-03 Rohlfing Thomas R Video surveillance system
US20070177023A1 (en) * 2006-01-31 2007-08-02 Beuhler Allyson J System and method to provide an adaptive camera network
US20090031381A1 (en) * 2007-07-24 2009-01-29 Honeywell International, Inc. Proxy video server for video surveillance
CN101808126B (zh) * 2010-03-12 2012-11-14 清华大学 一种用于实时视频处理的分布式计算***和方法
CN102547250B (zh) * 2012-02-09 2015-05-20 中兴通讯股份有限公司 一种视频处理方法和***、ivm和ivu
US9858052B2 (en) * 2013-03-21 2018-01-02 Razer (Asia-Pacific) Pte. Ltd. Decentralized operating system
US9736349B2 (en) * 2014-12-24 2017-08-15 Intel Corporation Adaptive video end-to-end network with local abstraction
CN104618693B (zh) * 2015-02-09 2017-07-28 北京邮电大学 一种基于云计算的监控视频在线处理任务管理方法及***
CN106455115B (zh) * 2015-08-13 2019-08-16 电信科学技术研究院 一种数据发送方法及装置
US10097795B2 (en) * 2015-10-01 2018-10-09 Sensormatic Electronics, LLC Network video recorder cluster and method of operation
US20210208949A1 (en) * 2016-01-29 2021-07-08 Nec Corporation Centralized control server, local terminal, distributed surveillance system, surveillance method and storage medium
US10778600B2 (en) * 2016-03-30 2020-09-15 Intel Corporation Adaptive workload distribution for network of video processors
CN107026900B (zh) * 2017-03-06 2020-02-14 浙江大华技术股份有限公司 一种拍摄任务分配方法及装置
CN108122246A (zh) * 2017-12-07 2018-06-05 中国石油大学(华东) 视频监控智能识别***

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104581423A (zh) * 2013-10-12 2015-04-29 北京航天长峰科技工业集团有限公司 一种海量视频智能分析***的综合调度和负载均衡方法
CN104363300A (zh) * 2014-11-26 2015-02-18 浙江宇视科技有限公司 一种服务器集群中计算任务分布式调度装置
CN104917836A (zh) * 2015-06-10 2015-09-16 北京奇虎科技有限公司 基于集群监控分析计算设备可用性的方法及装置
US20170078626A1 (en) * 2015-09-16 2017-03-16 Microsoft Technology Licensing, Llc Bandwidth efficient video surveillance system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3846459A4 *

Also Published As

Publication number Publication date
US20210209411A1 (en) 2021-07-08
EP3846459A1 (en) 2021-07-07
EP3846459A4 (en) 2021-11-03
CN110944146B (zh) 2022-04-12
CN110944146A (zh) 2020-03-31
US11537810B2 (en) 2022-12-27

Similar Documents

Publication Publication Date Title
WO2020057178A1 (zh) 智能分析设备资源调整方法及装置
CN110795244B (zh) 一种任务分配方法、装置、设备及介质
WO2022222755A1 (zh) 业务处理方法、装置及存储介质
WO2018072687A1 (zh) 一种资源调度的方法、装置和过滤式调度器
WO2018157836A1 (zh) 一种可编程硬件的资源管理方法、可编程硬件设备及存储介质
US10469805B2 (en) Load balancing method, and related apparatus and system
KR20160073409A (ko) 서비스 처리 방법, 시스템 및 장치
WO2016197628A1 (zh) 终端会议负载均衡方法、装置及***
CN102970379A (zh) 在多个服务器之间实现负载均衡的方法
US20110173319A1 (en) Apparatus and method for operating server using virtualization technique
US20170353854A1 (en) Wireless Communication Device
US20160164828A1 (en) Adjusting virtual machine resources
US11316916B2 (en) Packet processing method, related device, and computer storage medium
CN113934545A (zh) 一种视频数据调度方法、***、电子设备及可读介质
US20230236896A1 (en) Method for scheduling compute instance, apparatus, and system
US10884781B2 (en) Method and apparatus for a virtual machine
JP2014107802A (ja) 優先制御方法、サーバ、および優先制御プログラム
US9531764B1 (en) History inclusive connection management
CN109831467B (zh) 数据传输方法、设备及***
CN109391663B (zh) 一种访问请求的处理方法与设备
WO2018127013A1 (zh) 一种流数据的并发传输方法和装置
US11106680B2 (en) System, method of real-time processing under resource constraint at edge
US20210004308A1 (en) Data processing method and system
US9467661B2 (en) Method of operating camera, camera, and surveillance system having the same
WO2021012974A1 (zh) 基于云平台的容器化应用网络流控方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19863081

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019863081

Country of ref document: EP

Effective date: 20210401