CN113286115B - Video monitoring guide library distribution control method and device and related equipment - Google Patents
Video monitoring guide library distribution control method and device and related equipment Download PDFInfo
- Publication number
- CN113286115B CN113286115B CN202010105223.XA CN202010105223A CN113286115B CN 113286115 B CN113286115 B CN 113286115B CN 202010105223 A CN202010105223 A CN 202010105223A CN 113286115 B CN113286115 B CN 113286115B
- Authority
- CN
- China
- Prior art keywords
- camera
- library
- model
- network
- monitoring algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The application discloses a video monitoring guide library distribution control method, which is applied to an analysis server and comprises the following steps: and issuing a library guiding task for a library corresponding to the model of the monitoring algorithm model used by the camera set to one network camera in the camera set aiming at each camera set, so that the network camera extracts the characteristic vector of the library, and sharing the characteristic vector of the library to other network cameras in the camera set, so that each network camera in the camera set carries out the library control based on the characteristic vector of the library to generate an alarm. By applying the technical scheme provided by the embodiment of the application, each camera group only needs to extract the feature vector of the distributed control library once, so that the library guiding time can be saved, and the video monitoring library guiding and controlling efficiency can be improved. The application also discloses another video monitoring guide library distribution control method, a video monitoring guide library distribution control device and related equipment, which have corresponding technical effects.
Description
Technical Field
The present disclosure relates to the field of video monitoring technologies, and in particular, to a method and an apparatus for managing and controlling a video monitoring database, and related devices.
Background
With the rapid development of computer technology and monitoring technology, video monitoring is required in many scenes such as highways, markets, parking lots and the like, and the application range of the video monitoring is wider and wider. A video monitoring system is mostly constructed by a front-end network camera and a rear-end analysis server. In the video monitoring process, police service can be distributed. The network camera at the front end and the analysis server at the back end have the function of guiding and controlling the library. However, the application scene is inconsistent with the hardware, so that the required monitoring algorithm model is various. Therefore, in the current video monitoring database guiding and controlling process, the front-end webcam and the rear-end analysis server are required to conduct database guiding operation. That is, each network camera and each analysis server need to conduct one-time database guiding operation, so that the database guiding and controlling efficiency of video monitoring is low.
Disclosure of Invention
The purpose of the application is to provide a video monitoring guide library distribution control method, a video monitoring guide library distribution control device and related equipment, so as to improve video monitoring guide library distribution control efficiency.
In order to solve the technical problems, the application provides the following technical scheme:
a video monitoring guide library distribution control method is applied to an analysis server, and the method comprises the following steps:
Obtaining the model of a monitoring algorithm model used by each network camera in the multicast network;
for each camera set, issuing a library guiding task for a library corresponding to the model of a monitoring algorithm model used by the camera set to one network camera in the camera set, so that after the network camera acquires the library, extracting a characteristic vector of the library, and sharing the extracted characteristic vector to other network cameras in the camera set, so that each network camera in the camera set carries out the library control based on the characteristic vector of the library to generate an alarm;
the model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same.
In a specific embodiment of the present application, further comprising:
receiving a library guiding task of a distributed library corresponding to the model of the monitoring algorithm model used by the analysis server;
acquiring the distributed control library according to the library guiding task;
extracting the characteristic vector of the control library;
and performing control based on the feature vector of the control library to generate an alarm.
In a specific embodiment of the present application, before the issuing, for each camera group, a library guiding task for a library corresponding to a model of a monitoring algorithm model used by the camera group to one network camera in the camera group, the method further includes:
For each camera group, determining whether the model of the monitoring algorithm model used by the camera group is the same as the model of the monitoring algorithm model used by the analysis server;
if the feature vectors are the same, the feature vectors of the distributed control library extracted by the analysis server are sent to each network camera in the camera group;
and if the monitoring algorithm models are different, executing the step of issuing a library guiding task for a distributed library corresponding to the model of the monitoring algorithm model used by the camera set to one network camera in the camera set.
In a specific embodiment of the present application, further comprising:
when a new network camera is added into the multicast network, the model of a monitoring algorithm model used by the new network camera is obtained;
and if the model of the monitoring algorithm model used by the new network camera is the same as the model of the existing monitoring algorithm model in the multicast network, synchronizing the feature vector of the distribution control library corresponding to the model of the monitoring algorithm model used by the new network camera to the new network camera so as to enable the new network camera to carry out distribution control based on the feature vector of the distribution control library to generate an alarm.
In a specific embodiment of the present application, further comprising:
If the model of the monitoring algorithm model used by the new network camera is different from the model of the existing monitoring algorithm model in the multicast network, a library guiding task of a library corresponding to the model of the monitoring algorithm model used by the new network camera is issued to the new network camera, so that after the new network camera acquires the library, the feature vector of the library is extracted, and the library is subjected to the library control based on the feature vector of the library to generate an alarm.
In a specific embodiment of the present application, further comprising:
creating a distribution task according to a distribution library corresponding to the model of the monitoring algorithm model used by each camera group in the multicast network;
and issuing each control task to each network camera in the corresponding camera group, so that each network camera carries out control based on the characteristic vector of the corresponding control library and the corresponding control task to generate an alarm.
A video monitoring database guiding and controlling method applied to a network camera, the method comprising:
receiving a library guiding task which is issued by an analysis server and aims at a distributed library corresponding to the model of the monitoring algorithm model used by the network camera;
extracting the characteristic vector of the control library;
Sharing the extracted feature vector to other network cameras in the camera group of the network camera so that each network camera in the camera group carries out control based on the feature vector of the control library to generate an alarm;
the model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the model numbers of the monitoring algorithm models used by the network cameras in different camera groups are different.
A video monitoring library director distribution device applied to an analysis server, the device comprising:
the model obtaining module is used for obtaining the model of the monitoring algorithm model used by each network camera in the multicast network;
the database guiding task issuing module is used for issuing a database guiding task of a database corresponding to the model of the monitoring algorithm model used by the camera set to one network camera in the camera set aiming at each camera set, so that after the network camera acquires the database, the network camera extracts the characteristic vector of the database, and shares the extracted characteristic vector to each other network camera in the camera set, so that each network camera in the camera set carries out the database allocation based on the characteristic vector of the database to generate an alarm;
The model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the model numbers of the monitoring algorithm models used by the network cameras in different camera groups are different.
A video surveillance guide library deployment and control device applied to a network camera, the device comprising:
the database guiding task receiving module is used for receiving database guiding tasks which are issued by the analysis server and are aimed at the distributed database corresponding to the model of the monitoring algorithm model used by the network camera;
the feature vector extraction module is used for extracting feature vectors of the distribution control library;
the feature vector sharing module is used for sharing the extracted feature vector to other network cameras in the camera group where the network cameras are located, so that each network camera in the camera group carries out control based on the feature vector of the control library to generate an alarm;
the model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the model numbers of the monitoring algorithm models used by the network cameras in different camera groups are different.
An analytics server, comprising:
a memory for storing a computer program;
and the processor is used for realizing the steps of the video monitoring guide library distribution control method when executing the computer program.
A network camera, comprising:
a camera;
a memory connected with the camera for storing a computer program;
and the processor is used for realizing the steps of the video monitoring guide library distribution control method when executing the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the video surveillance library director distribution method of any of the preceding claims.
By applying the technical scheme provided by the embodiment of the application, the analysis server obtains the model of the monitoring algorithm model used by each network camera in the multicast network, the network cameras using the monitoring algorithm model with the same model are classified into the same camera group, a library guiding task of a library corresponding to the model of the monitoring algorithm model used by the camera group is issued to one network camera in the camera group aiming at each camera group, after the network camera obtains the library, the feature vector of the library is extracted, and the extracted feature vector is shared to other network cameras in the camera group, so that each network camera in the camera group can carry out control based on the feature vector of the library to generate an alarm. The model of the monitoring algorithm model used by the network cameras in the same camera group is the same, the model of the monitoring algorithm model used by the network cameras in different camera groups is different, and for one camera group, only one network camera in the camera group is required to extract the feature vector of the distributed control library, and each network camera in the camera group is not required to extract the feature vector of the distributed control library, namely each camera group only needs to extract the feature vector of the distributed control library once, so that the library guiding time can be saved, and the video monitoring library guiding and controlling efficiency can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a multicast network according to an embodiment of the present application;
FIG. 2 is a flowchart of an implementation of a method for managing and controlling a video surveillance database according to an embodiment of the present application;
fig. 3 is a schematic diagram of a video monitoring library guiding process in an embodiment of the present application;
fig. 4 is a schematic diagram of a video monitoring and control process in an embodiment of the present application;
FIG. 5 is a flowchart illustrating another method for controlling a video surveillance database according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a video monitoring database guiding and controlling device in an embodiment of the present application;
fig. 7 is a schematic structural diagram of another video monitoring database guiding and controlling device in the embodiment of the present application;
FIG. 8 is a schematic structural diagram of an analysis server according to an embodiment of the present application;
Fig. 9 is a schematic structural diagram of a network camera according to an embodiment of the present application.
Detailed Description
The core of the application is to provide a video monitoring guide library distribution control method, which can be applied to an analysis server, wherein the analysis server can be in communication connection with a plurality of network cameras, the network cameras are deployed at the front end and used for image acquisition and analysis, and the analysis server is deployed at the rear end and can receive and analyze images acquired by each network camera connected with the analysis server. The analysis server may construct a multicast network with a plurality of network cameras. As shown in fig. 1, the multicast network includes an analysis server 110, a network camera 120, a network camera 130, and a network camera 140, and devices in the multicast network can communicate with each other.
In order to provide a better understanding of the present application, those skilled in the art will now make further details of the present application with reference to the drawings and detailed description. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Referring to fig. 2, a flowchart of an implementation of a method for controlling a video monitoring database, provided in an embodiment of the present application, may include the following steps:
s210: a model of a monitoring algorithm model used by each network camera in the multicast network is obtained.
The multicast network is constructed by an analysis server and a plurality of network cameras. When the monitoring task is to be executed initially or is changed or the library is updated, the analysis server and the network camera are required to conduct library guiding and controlling operation.
The library guide refers to a library guide. The distribution control library can store a plurality of reference images, is a large and full image set as much as possible, when a newly acquired image exists, the newly acquired image is required to be compared with each image in the distribution control library to obtain similarity, the similarity is compared with a threshold value set in a distribution control task, whether the newly acquired image hits a target is determined according to a comparison result, and if so, operations such as alarming and the like can be performed. The processes of comparing the acquired images, alarming when the acquired images are judged as a control process. The monitoring algorithm model obtained through neural network training under different scenes can be used in the image comparison process.
The analysis server and the plurality of network cameras are constructed to multicast the network. The devices in the multicast network may communicate with each other. The network camera in the present application refers to a camera with computing power. The analysis server and each web camera need to use some kind of monitoring algorithm model.
The analysis server may obtain a model of the monitoring algorithm model used by each network camera in the multicast network. The monitoring algorithm model may be a different algorithm model that detects faces, human bodies, motor vehicles, non-motor vehicles, etc. Each network camera can report the model of the monitoring algorithm model used by itself in an active reporting mode, and can report the model of the monitoring algorithm model used by itself when receiving the acquisition instruction of the analysis server. Of course, the analysis server may obtain a camera code of each network camera to uniquely identify one network camera while obtaining a model of a monitoring algorithm model used by each network camera in the multicast network.
S220: and issuing a library guiding task for a library corresponding to the model of the monitoring algorithm model used by the camera set to one network camera in the camera set aiming at each camera set, so that after the network camera acquires the library, extracting the characteristic vector of the library, and sharing the extracted characteristic vector to other network cameras in the camera set, so that each network camera in the camera set carries out the library control based on the characteristic vector of the library to generate an alarm.
The model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the model numbers of the monitoring algorithm models used by the network cameras in different camera groups are different.
In the application, after the analysis server obtains the model of the monitoring algorithm model used by each network camera in the multicast network, the analysis server can know which network cameras use the monitoring algorithm model with the same model. Network cameras using the same model of monitoring algorithm model can be grouped into one camera group. That is, the types of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the types of the monitoring algorithm models used by the network cameras in different camera groups are different. Each camera group can contain one or more network cameras, each multicast network can contain a plurality of camera groups, and the model of the monitoring algorithm model used by one camera group is the model of the monitoring algorithm model used by each network camera contained in the camera group, and the models of the monitoring algorithm models used by different camera groups are different.
Different monitoring algorithm models have different models, the monitoring algorithm models of different models have different capacities and are more scattered, and the corresponding distribution library and the content and the mode of the feature vector to be extracted can be different. And creating a database guiding task according to the model of the monitoring algorithm model. The database guiding tasks corresponding to the monitoring algorithm models of different models can be different. The database guiding task can be created on the analysis server by a technician, and can also be automatically created by the analysis server according to the corresponding relation between the model of the monitoring algorithm model and the distributed database, which are obtained in advance.
For each camera set, a library-guiding task for a library corresponding to the model of the monitoring algorithm model used by the camera set can be issued to one network camera in the camera set. The network camera can be any one of the camera groups, and can also be one selected by the analysis server according to the processing capacity of the network camera in the camera groups.
After the network camera receives the database guiding task, the network camera can acquire the distributed database, so that the characteristic vector of the distributed database can be extracted by using a monitoring algorithm model. The extracted feature vector may then be shared to each of the other webcams in the camera set. Therefore, the extraction operation of the feature vector of the control library is not required to be carried out by each other network camera in the camera group, and the library guiding time of each other network camera is saved.
The feature vector extracted by the network camera is shared to other network cameras in the camera set, the network camera can directly send the feature vector to other network cameras in the camera set through a multicast network to achieve the purpose of sharing, or the network camera can send the extracted feature vector to an analysis server, and then the analysis server distributes the feature vector to other network cameras in the camera set to achieve the purpose of sharing.
For each network camera in the multicast network, after the network camera obtains the feature vector of the corresponding control library, the network camera can perform control based on the feature vector of the control library to generate an alarm.
By applying the method provided by the embodiment of the application, the analysis server obtains the model of the monitoring algorithm model used by each network camera in the multicast network, the network cameras using the monitoring algorithm model with the same model are classified into the same camera group, a library guiding task of a library corresponding to the model of the monitoring algorithm model used by the camera group is issued to one network camera in the camera group aiming at each camera group, after the network camera obtains the library, the feature vector of the library is extracted, and the extracted feature vector is shared to other network cameras in the camera group, so that each network camera in the camera group can carry out control based on the feature vector of the library to generate an alarm. The model of the monitoring algorithm model used by the network cameras in the same camera group is the same, the model of the monitoring algorithm model used by the network cameras in different camera groups is different, and for one camera group, only one network camera in the camera group is required to extract the feature vector of the distributed control library, and each network camera in the camera group is not required to extract the feature vector of the distributed control library, namely each camera group only needs to extract the feature vector of the distributed control library once, so that the library guiding time can be saved, and the video monitoring library guiding and controlling efficiency can be improved.
In one embodiment of the present application, the method may further comprise the steps of:
step one: receiving a library guiding task of a distributed library corresponding to the model of the monitoring algorithm model used by the analysis server;
step two: acquiring the distributed control library according to the library guiding task;
step three: extracting the characteristic vector of the control library;
step four: and performing control based on the feature vector of the control library to generate an alarm.
For ease of description, the four steps described above are combined.
In this application, the processing function of the analysis server is more powerful than that of the network camera. The analysis server can analyze the acquired images through the acquired network cameras, and the database guiding and controlling operation is needed.
The method comprises the steps that a library guiding task can be established for a library to be distributed corresponding to the model of a monitoring algorithm model used by an analysis server, after the analysis server receives the library guiding task, the library to be distributed can be obtained according to the library guiding task, the feature vector of the library to be distributed is extracted, and further, the library to be distributed is distributed based on the feature vector of the library to generate an alarm.
In one embodiment of the present application, before issuing, for each camera set, a library guiding task of a library corresponding to a model of a monitoring algorithm model used for the camera set to one network camera in the camera set in step S220, the method may further include the following steps:
The first step: for each camera group, determining whether the model of the monitoring algorithm model used by the camera group is the same as the model of the monitoring algorithm model used by the analysis server; if the same, the operation of the second step is performed, and if not, the operation of step S220 is performed;
and a second step of: and sending the feature vector of the control library extracted by the analysis server to each network camera in the camera group.
For ease of description, the two steps described above are combined.
In the application, after the analysis server obtains the model of the monitoring algorithm model used by each network camera in the multicast network, the network cameras using the monitoring algorithm model with the same model can be classified into the same camera group. The analysis server also has a monitoring algorithm model, and the processing capacity of the analysis server is stronger than that of the network camera, so that the analysis server can conduct library guiding operation more quickly and extract the feature vectors of the corresponding distributed libraries.
For each camera group, the analysis server may first determine whether the model of the monitoring algorithm model used by the camera group is the same as the model of the monitoring algorithm model used by itself. If the feature vectors of the distributed control libraries extracted by the user are the same, the feature vectors of the distributed control libraries extracted by the user can be sent to each network camera in the camera set, so that each network camera in the camera set does not need to extract the feature vectors of the corresponding distributed control libraries, and distributed control can be performed based on the obtained feature vectors to generate an alarm. And the video monitoring guide library distribution efficiency is improved. If the feature vectors are different, a library guiding task for a library corresponding to the model of the monitoring algorithm model used by the camera set can be issued to one network camera in the camera set, the feature vectors of the corresponding library are extracted by one network camera in the camera set and then shared into each other network camera in the camera set, so that each network camera can perform control based on the obtained feature vectors to generate an alarm.
In one embodiment of the present application, the method may further comprise the steps of:
step one: when a new network camera is added into a multicast network, obtaining the model of a monitoring algorithm model used by the new network camera;
step two: if the model of the monitoring algorithm model used by the new network camera is the same as the model of the existing monitoring algorithm model in the multicast network, the feature vector of the distribution control library corresponding to the model of the monitoring algorithm model used by the new network camera can be synchronized to the new network camera, so that the new network camera carries out distribution control based on the feature vector of the distribution control library to generate an alarm;
step three: if the model of the monitoring algorithm model used by the new network camera is different from the model of the existing monitoring algorithm model in the multicast network, a library guiding task of a library corresponding to the model of the monitoring algorithm model used by the new network camera is issued to the new network camera, so that after the new network camera acquires the library, the feature vector of the library is extracted, and the library is subjected to the library control based on the feature vector of the library to generate an alarm.
For ease of description, the three steps described above are combined.
In practical applications, new webcams may be added to the analysis server and webcams in the multicast network during operation.
When a new network camera is added into the multicast network, the analysis server can firstly obtain the model of the monitoring algorithm model used by the new network camera and check whether the model of the monitoring algorithm model exists in the multicast network.
If the model of the monitoring algorithm model used by the new network camera is the same as the model of the existing monitoring algorithm model in the multicast network, the method indicates that the extracted feature vector of the distributed control library corresponding to the model of the monitoring algorithm model exists currently, and the feature vector of the distributed control library corresponding to the model of the monitoring algorithm model used by the new network camera can be directly synchronized to the new network camera without the new network camera performing extraction operation. Therefore, the new network camera can perform control based on the feature vector of the control library to generate an alarm. Saving the database guiding time of the new network camera.
If the model of the monitoring algorithm model used by the new network camera is different from the model of the existing monitoring algorithm model in the multicast network, the characteristic vector of the distributed control library corresponding to the model of the monitoring algorithm model used by the new network camera does not exist currently, and the new network camera is required to extract the characteristic vector. In this case, a library-guiding task for the library to be distributed corresponding to the model of the monitoring algorithm model used by the new network camera may be issued to the new network camera. Thus, after the new network camera acquires the control library, the feature vector of the control library can be extracted, and control is performed based on the feature vector of the control library to generate an alarm.
For easy understanding, the embodiment of the present application will be described by taking the library guiding process shown in fig. 3 as an example.
The IPC4 is a network camera with computing power newly added into the multicast network, and after the IPC4 is added into the multicast network, the model and the camera code of the monitoring algorithm model used by the IPC4 are sent to the analysis server, and the analysis server can record the model and the camera code of the corresponding monitoring algorithm model in a key-value mode of a data structure. The analysis server can judge whether the network camera using the same model monitoring algorithm model previously or the network camera itself has extracted the feature vector of the corresponding control library. If so, the extracted corresponding feature vector can be directly sent to the IPC4, and the IPC4 can finish the library guiding operation without extracting the feature vector, thereby saving the library guiding time. If not, the database guiding task created according to the database management and control corresponding to the model of the monitoring algorithm model used by the IPC4 can be issued to the IPC4, the IPC4 acquires the corresponding database management and control, and the feature vector of the database management and control is extracted to complete the database guiding operation.
In the application, an analysis server issues a library guiding task of a library corresponding to a model of a monitoring algorithm model used by a camera set to one network camera in the camera set, and after the network camera acquires the library, the network camera extracts a feature vector of the library and shares the extracted feature vector to other network cameras in the camera set, so that each network camera in the camera set obtains the feature vector of the library. In practical application, each network camera can establish a control task by itself, and then perform control based on the obtained feature vector of the corresponding control library and the corresponding control task to generate an alarm.
In one embodiment of the present application, the method may further comprise the steps of:
the first step: creating a distribution task according to a distribution library corresponding to the model of the monitoring algorithm model used by each camera group in the multicast network;
and a second step of: and issuing each control task to each network camera in the corresponding camera group, so that each network camera carries out control based on the characteristic vector of the corresponding control library and the corresponding control task to generate an alarm.
For ease of description, the two steps described above are combined.
As described above, the processing power of the analysis server is stronger than that of the network camera. In the application, the analysis server can create the control task according to the control library corresponding to the model of the monitoring algorithm model used by each camera group in the multicast network. The network cameras using the same model of monitoring algorithm model have uniform control tasks.
The analysis server may issue each of the distributed tasks to each of the webcams in the respective camera group. Therefore, each network camera does not need to establish a control task, the control time can be saved, and the overall resource consumption is reduced. Each network camera can perform control based on the characteristic vector of the corresponding control library and the corresponding control task to generate an alarm.
For ease of understanding, the embodiment of the present application will be described by taking the control process shown in fig. 4 as an example.
The IPC5, the IPC6 and the IPC7 are network cameras in the multicast network, the types of the monitoring algorithm models used by the IPC5 and the IPC6 are the same, and the types of the monitoring algorithm models used by the IPC7 and the IPC5 and the IPC6 are different. The analysis server creates a distribution task according to the model of the monitoring algorithm model used by the IPC5 and the IPC7 respectively, and then distributes each distribution task (the distribution task 1 and the distribution task 2) to the corresponding network camera respectively through a multicast network. The network cameras using the same model monitoring algorithm model are issued with uniform control tasks, the IPC5, the IPC6 and the IPC7 do not need to independently create the control tasks, and the control can be carried out based on the obtained control tasks to generate alarms.
The analysis server and each network camera use different and more scattered monitoring algorithm model capability, and the feature vector of the distributed library is extracted by one network camera in one camera set and shared to other network cameras in the same camera set, so that the capability of the distributed library can be effectively utilized, meanwhile, the analysis server is used for creating the distributed task, each network camera is not required to be independently carried out, the distributed speed is improved, the overall distributed comparison speed is improved, and the waste of the calculation force of the overall hardware resources is reduced.
Referring to fig. 5, a flowchart of an implementation of a method for controlling a video monitoring database, provided in an embodiment of the present application, may be applied to a network camera, and includes the following steps:
s510: receiving a library guiding task which is issued by an analysis server and aims at a distributed library corresponding to the model of a monitoring algorithm model used by the network camera;
s520: extracting the characteristic vector of the control library;
s530: sharing the extracted characteristic vector to other network cameras in a camera group where the network cameras are located, so that each network camera in the camera group carries out control on the basis of the characteristic vector of the control library to generate an alarm;
the model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the model numbers of the monitoring algorithm models used by the network cameras in different camera groups are different.
For convenience of description, the above three steps are described in combination.
In this application, the analysis server may construct a multicast network with a plurality of network cameras. The analysis server may obtain the model of the monitoring algorithm model used by each network camera in the multicast network, and categorize the network cameras using the same model of monitoring algorithm model into one camera group. That is, the types of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the types of the monitoring algorithm models used by the network cameras in different camera groups are different. Each camera group can contain one or more network cameras, each multicast network can contain a plurality of camera groups, and the model of the monitoring algorithm model used by one camera group is the model of the monitoring algorithm model used by each network camera contained in the camera group, and the models of the monitoring algorithm models used by different camera groups are different.
For each camera set, the analysis server may issue a library-guiding task for a library corresponding to a model of a monitoring algorithm model used by the camera set to one of the network cameras in the camera set. The network camera can be any one of the camera groups, and can also be one selected by the analysis server according to the processing capacity of the network camera in the camera groups.
After the network camera receives the library guiding task which is issued by the analysis server and aims at the library corresponding to the model of the monitoring algorithm model used by the network camera, the feature vector of the library can be extracted, and then the extracted feature vector is shared with other network cameras in the camera group. Thus, each network camera in the camera group can obtain the characteristic vector of the control library, and can perform control based on the characteristic vector of the control library to generate an alarm.
By applying the method provided by the embodiment of the application, the model of the monitoring algorithm model used by the network cameras in the same camera group is the same, the model of the monitoring algorithm model used by the network cameras in different camera groups is different, and for one camera group, only one network camera in the camera group is required to extract the feature vector of the distributed control library, and each network camera in the camera group is not required to extract the feature vector of the distributed control library, namely each camera group only needs to extract the feature vector of the distributed control library once, so that the library guiding time can be saved, and the video monitoring library guiding and controlling efficiency is improved.
Corresponding to the method embodiment shown in fig. 2, the embodiment of the application also provides a video monitoring library guiding and controlling device, which is applied to the analysis server, and the video monitoring library guiding and controlling device and the video monitoring library guiding and controlling method described below can be correspondingly referred to each other.
Referring to fig. 6, the apparatus includes the following modules:
a model obtaining module 610, configured to obtain a model of a monitoring algorithm model used by each network camera in the multicast network;
a library-guiding task issuing module 620, configured to issue, for each camera group, a library-guiding task for a library corresponding to a model of a monitoring algorithm model used by the camera group to one network camera in the camera group, so that after the network camera acquires the library, extract a feature vector of the library, and share the extracted feature vector to each other network camera in the camera group, so that each network camera in the camera group performs a library control based on the feature vector of the library to generate an alarm;
the model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same.
By applying the device provided by the embodiment of the application, the analysis server obtains the model of the monitoring algorithm model used by each network camera in the multicast network, the network cameras using the monitoring algorithm model with the same model are classified into the same camera group, a library guiding task of a library corresponding to the model of the monitoring algorithm model used by the camera group is issued to one network camera in the camera group aiming at each camera group, after the network camera obtains the library, the feature vector of the library is extracted, and the extracted feature vector is shared to other network cameras in the camera group, so that each network camera in the camera group can carry out control based on the feature vector of the library to generate an alarm. The model of the monitoring algorithm model used by the network cameras in the same camera group is the same, the model of the monitoring algorithm model used by the network cameras in different camera groups is different, and for one camera group, only one network camera in the camera group is required to extract the feature vector of the distributed control library, and each network camera in the camera group is not required to extract the feature vector of the distributed control library, namely each camera group only needs to extract the feature vector of the distributed control library once, so that the library guiding time can be saved, and the video monitoring library guiding and controlling efficiency can be improved.
In a specific embodiment of the present application, the system further includes a database guiding and distributing module, configured to:
receiving a library guiding task of a distributed library corresponding to the model of the monitoring algorithm model used by the analysis server;
acquiring the distributed control library according to the library guiding task;
extracting the characteristic vector of the control library;
and performing control based on the feature vector of the control library to generate an alarm.
In a specific implementation manner of the application, the system further comprises a model determining module and a feature vector sending module;
the model determining module is used for determining whether the model of the monitoring algorithm model used by each camera set is the same as the model of the monitoring algorithm model used by the analysis server or not for each camera set before issuing a library guiding task for a distributed library corresponding to the model of the monitoring algorithm model used by the camera set to one network camera in the camera set; if the feature vectors are the same, triggering a feature vector sending module, and if the feature vectors are not the same, triggering a database guiding task issuing module 620;
and the characteristic vector sending module is used for sending the characteristic vector of the control library extracted by the analysis server to each network camera in the camera group.
In a specific embodiment of the present application, the model obtaining module 610 is further configured to:
when a new network camera is added into a multicast network, obtaining the model of a monitoring algorithm model used by the new network camera;
the device further comprises a feature vector synchronization module for:
and if the model of the monitoring algorithm model used by the new network camera is the same as the model of the existing monitoring algorithm model in the multicast network, synchronizing the feature vector of the distribution control library corresponding to the model of the monitoring algorithm model used by the new network camera to the new network camera so as to enable the new network camera to carry out distribution control based on the feature vector of the distribution control library to generate an alarm.
In a specific embodiment of the present application, the first database task issuing module is further configured to:
if the model of the monitoring algorithm model used by the new network camera is different from the model of the existing monitoring algorithm model in the multicast network, a library guiding task of a library corresponding to the model of the monitoring algorithm model used by the new network camera is issued to the new network camera, so that after the new network camera acquires the library, the feature vector of the library is extracted, and the library is subjected to the library control based on the feature vector of the library to generate an alarm.
In a specific embodiment of the present application, the system further includes a control module, configured to:
creating a distribution task according to a distribution library corresponding to the model of the monitoring algorithm model used by each camera group in the multicast network;
and issuing each control task to each network camera in the corresponding camera group, so that each network camera carries out control based on the characteristic vector of the corresponding control library and the corresponding control task to generate an alarm.
Corresponding to the method embodiment shown in fig. 5, the embodiment of the application also provides a video monitoring library guiding and controlling device, which is applied to the network camera, and the video monitoring library guiding and controlling device and the video monitoring library guiding and controlling method described below can be correspondingly referred to each other.
Referring to fig. 7, the apparatus includes the following modules:
the database guiding task receiving module 710 is configured to receive a database guiding task for a distributed database corresponding to a model of a monitoring algorithm model used by the webcam, which is issued by the analysis server;
the feature vector extraction module 720 is configured to extract a feature vector of the control library;
the feature vector sharing module 730 is configured to share the extracted feature vector to each other network camera in the camera group where the network camera is located, so that each network camera in the camera group performs control based on the feature vector of the control library to generate an alarm;
The model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the model numbers of the monitoring algorithm models used by the network cameras in different camera groups are different.
By applying the device provided by the embodiment of the application, the types of the monitoring algorithm models used by the network cameras in the same camera group are the same, the types of the monitoring algorithm models used by the network cameras in different camera groups are different, and for one camera group, only one network camera in the camera group is required to extract the feature vector of the distributed control library, and each network camera in the camera group is not required to extract the feature vector of the distributed control library, namely each camera group only needs to extract the feature vector of the distributed control library once, so that the library guiding time can be saved, and the video monitoring library guiding and controlling efficiency is improved. .
Corresponding to the method embodiment shown in fig. 2 above, the embodiment of the present application further provides an analysis server, including:
a memory for storing a computer program;
and the processor is used for realizing the steps of the video monitoring database guiding and controlling method when executing the computer program.
As shown in fig. 8, to illustrate a composition structure of the analysis server, the analysis server may include: a processor 10, a memory 11, a communication interface 12 and a communication bus 13. The processor 10, the memory 11 and the communication interface 12 all complete communication with each other through a communication bus 13.
In the present embodiment, the processor 10 may be a central processing unit (Central Processing Unit, CPU), an asic, a dsp, a field programmable gate array, or other programmable logic device, etc.
The processor 10 may call a program stored in the memory 11, and in particular, the processor 10 may perform operations in an embodiment of a video surveillance library distribution method.
The memory 11 is used for storing one or more programs, and the programs may include program codes, where the program codes include computer operation instructions, and in this embodiment, at least the programs for implementing the following functions are stored in the memory 11:
obtaining the model of a monitoring algorithm model used by each network camera in the multicast network;
for each camera set, issuing a library guiding task for a library corresponding to the model of a monitoring algorithm model used by the camera set to one network camera in the camera set, so that after the network camera acquires the library, extracting a characteristic vector of the library, and sharing the extracted characteristic vector to other network cameras in the camera set, so that each network camera in the camera set carries out the library control based on the characteristic vector of the library to generate an alarm;
The model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same, and the model numbers of the monitoring algorithm models used by the network cameras in different camera groups are different.
In one possible implementation, the memory 11 may include a storage program area and a storage data area, where the storage program area may store an operating system, and application programs required for at least one function (such as a sound playing function, an image playing function), and the like; the storage data area may store data created during use, such as model data, task data, and the like.
In addition, the memory 11 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device or other volatile solid-state storage device.
The communication interface 12 may be an interface of a communication module for interfacing with other devices or systems.
Of course, it should be noted that the structure shown in fig. 8 is not limited to the analysis server in the embodiment of the present application, and the analysis server may include more or fewer components than those shown in fig. 8, or may combine some components in practical applications.
Corresponding to the method embodiment shown in fig. 5 above, the embodiment of the present application further provides a network camera, as shown in fig. 9, including:
A camera 910;
a memory 920 connected to the camera 910 for storing a computer program;
the processor 930 is configured to implement the steps of the video surveillance database management method shown in fig. 5 when executing the computer program.
Corresponding to the above method embodiment, the embodiment of the application further provides a computer readable storage medium, where a computer program is stored, and when the computer program is executed by the processor, the steps of the video monitoring database guiding and controlling method are implemented.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Specific examples are used herein to illustrate the principles and embodiments of the present application, and the description of the above examples is only for aiding in understanding the technical solution of the present application and its core ideas. It should be noted that it would be obvious to those skilled in the art that various improvements and modifications can be made to the present application without departing from the principles of the present application, and such improvements and modifications fall within the scope of the claims of the present application.
Claims (11)
1. The method is characterized by being applied to an analysis server, and comprises the following steps:
obtaining the model of a monitoring algorithm model used by each network camera in the multicast network;
for each camera group, determining whether the model of the monitoring algorithm model used by the camera group is the same as the model of the monitoring algorithm model used by the analysis server;
If the feature vectors are the same, the feature vectors of the distributed control library extracted by the analysis server are sent to each network camera in the camera group;
if the feature vectors are different, issuing a library guiding task of a library corresponding to the model of the monitoring algorithm model used by the camera set to one network camera in the camera set, so that after the network camera acquires the library, extracting the feature vector of the library, and sharing the extracted feature vector to other network cameras in the camera set, so that each network camera in the camera set carries out the library control based on the feature vector of the library to generate an alarm;
the model numbers of the monitoring algorithm models used by the network cameras in the same camera group are the same.
2. The method as recited in claim 1, further comprising:
receiving a library guiding task of a distributed library corresponding to the model of the monitoring algorithm model used by the analysis server;
acquiring the distributed control library according to the library guiding task;
extracting the characteristic vector of the control library;
and performing control based on the feature vector of the control library to generate an alarm.
3. The method as recited in claim 1, further comprising:
when a new network camera is added into the multicast network, the model of a monitoring algorithm model used by the new network camera is obtained;
and if the model of the monitoring algorithm model used by the new network camera is the same as the model of the existing monitoring algorithm model in the multicast network, synchronizing the feature vector of the distribution control library corresponding to the model of the monitoring algorithm model used by the new network camera to the new network camera so as to enable the new network camera to carry out distribution control based on the feature vector of the distribution control library to generate an alarm.
4. A method according to claim 3, further comprising:
if the model of the monitoring algorithm model used by the new network camera is different from the model of the existing monitoring algorithm model in the multicast network, a library guiding task of a library corresponding to the model of the monitoring algorithm model used by the new network camera is issued to the new network camera, so that after the new network camera acquires the library, the feature vector of the library is extracted, and the library is subjected to the library control based on the feature vector of the library to generate an alarm.
5. The method according to any one of claims 1 to 4, further comprising:
creating a distribution task according to a distribution library corresponding to the model of the monitoring algorithm model used by each camera group in the multicast network;
and issuing each control task to each network camera in the corresponding camera group, so that each network camera carries out control based on the characteristic vector of the corresponding control library and the corresponding control task to generate an alarm.
6. The method is characterized by being applied to a network camera, and comprises the following steps:
receiving a library guiding task which is issued by an analysis server and aims at a distributed control library corresponding to the model of a monitoring algorithm model used by a camera group where the network camera is located;
extracting the characteristic vector of the control library;
sharing the extracted feature vector to other network cameras in the camera group of the network camera so that each network camera in the camera group carries out control based on the feature vector of the control library to generate an alarm;
the monitoring algorithm models used by the network cameras in the same camera group are the same in model, and the monitoring algorithm models used by the network cameras in different camera groups are different in model;
Before receiving the library guiding task of the distributed library corresponding to the model of the monitoring algorithm model used by the camera group where the network camera is located and issued by the analysis server, the method further comprises:
determining, for each camera group, whether a model of a monitoring algorithm model used by the camera group is the same as a model of a monitoring algorithm model used by the analysis server;
if the feature vectors are the same, the feature vectors of the distributed control library extracted by the analysis server are sent to each network camera in the camera group;
and if the monitoring algorithm models are different, the step of issuing a library guiding task for the distributed library corresponding to the model of the monitoring algorithm model used by the camera group of the network camera to one network camera in the camera group is executed.
7. A video monitoring library director distribution device, which is applied to an analysis server, the device comprising:
the model obtaining module is used for obtaining the model of the monitoring algorithm model used by each network camera in the multicast network;
the database guiding task issuing module is used for issuing a database guiding task of a database corresponding to the model of the monitoring algorithm model used by the camera set to one network camera in the camera set aiming at each camera set, so that after the network camera acquires the database, the network camera extracts the characteristic vector of the database, and shares the extracted characteristic vector to each other network camera in the camera set, so that each network camera in the camera set carries out the database allocation based on the characteristic vector of the database to generate an alarm;
The monitoring algorithm models used by the network cameras in the same camera group are the same in model, and the monitoring algorithm models used by the network cameras in different camera groups are different in model;
the device also comprises a model determining module and a feature vector sending module;
the model determining module is used for determining whether the model of the monitoring algorithm model used by each camera set is the same as the model of the monitoring algorithm model used by the analysis server or not for each camera set before issuing a library guiding task for a library corresponding to the model of the monitoring algorithm model used by the camera set to one network camera in the camera set; if the feature vectors are the same, triggering the feature vector sending module, and if the feature vectors are different, triggering the database guiding task issuing module;
and the characteristic vector sending module is used for sending the characteristic vector of the control library extracted by the analysis server to each network camera in the camera group.
8. A video surveillance guide library deployment and control device, characterized in that it is applied to a network camera, the device comprising:
the database guiding task receiving module is used for receiving database guiding tasks which are issued by the analysis server and are aimed at the distributed database corresponding to the model of the monitoring algorithm model used by the camera group where the network camera is located;
The feature vector extraction module is used for extracting feature vectors of the distribution control library;
the feature vector sharing module is used for sharing the extracted feature vector to other network cameras in the camera group where the network cameras are located, so that each network camera in the camera group carries out control based on the feature vector of the control library to generate an alarm;
the monitoring algorithm models used by the network cameras in the same camera group are the same in model, and the monitoring algorithm models used by the network cameras in different camera groups are different in model;
before receiving the library guiding task of the distributed library corresponding to the model of the monitoring algorithm model used by the camera group where the network camera is located and issued by the analysis server, the method further comprises:
determining, for each camera group, whether a model of a monitoring algorithm model used by the camera group is the same as a model of a monitoring algorithm model used by the analysis server;
if the feature vectors are the same, the feature vectors of the distributed control library extracted by the analysis server are sent to each network camera in the camera group;
and if the monitoring algorithm models are different, the step of issuing a library guiding task for the distributed library corresponding to the model of the monitoring algorithm model used by the camera group of the network camera to one network camera in the camera group is executed.
9. An analytics server, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the video surveillance library management method according to any one of claims 1 to 5 when executing the computer program.
10. A network camera, characterized by comprising:
a camera;
a memory connected with the camera for storing a computer program;
a processor for implementing the steps of the video surveillance library deployment method of claim 6 when executing the computer program.
11. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, the computer program implementing the steps of the video surveillance library director distribution method according to any of claims 1 to 6 when being executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010105223.XA CN113286115B (en) | 2020-02-20 | 2020-02-20 | Video monitoring guide library distribution control method and device and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010105223.XA CN113286115B (en) | 2020-02-20 | 2020-02-20 | Video monitoring guide library distribution control method and device and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113286115A CN113286115A (en) | 2021-08-20 |
| CN113286115B true CN113286115B (en) | 2023-05-16 |
Family
ID=77275149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010105223.XA Active CN113286115B (en) | 2020-02-20 | 2020-02-20 | Video monitoring guide library distribution control method and device and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113286115B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102510478A (en) * | 2011-10-28 | 2012-06-20 | 唐玉勇 | Intelligent distribution control system and method used for 'Safe City' project |
| CN104200466B (en) * | 2014-08-20 | 2017-05-31 | 深圳市中控生物识别技术有限公司 | A kind of method for early warning and video camera |
| CN104349143A (en) * | 2014-11-11 | 2015-02-11 | 广东中星电子有限公司 | Video monitoring method, video monitoring device and video monitoring system |
| US10051343B2 (en) * | 2016-11-22 | 2018-08-14 | Sap Se | Match video marking |
| CN110147759A (en) * | 2019-05-17 | 2019-08-20 | 北京迈格威科技有限公司 | Target identification method, system, target identification management method and storage medium |
| CN110266999A (en) * | 2019-06-05 | 2019-09-20 | 长沙年余信息科技有限公司 | A kind of system and method for garden place security control |
-
2020
- 2020-02-20 CN CN202010105223.XA patent/CN113286115B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113286115A (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109410278B (en) | Target positioning method, device and system | |
| JP6909829B2 (en) | Information processing methods, devices, systems and storage media | |
| CN110457974B (en) | Image superposition method and device, electronic equipment and readable storage medium | |
| CN111951313A (en) | Image registration method, device, equipment and medium | |
| CN113870613B (en) | Parking space determination method and device, electronic equipment and storage medium | |
| CN113014623B (en) | Method and device for processing real-time streaming data of embedded point, computer equipment and storage medium | |
| CN111586432B (en) | Method and device for determining air-broadcast live broadcast room, server and storage medium | |
| CN111479095B (en) | Service processing control system, method and device | |
| CN111429476A (en) | Method and device for determining action track of target person | |
| CN111091106A (en) | Image clustering method and device, storage medium and electronic device | |
| CN110516738B (en) | Distributed comparison clustering method and device, electronic equipment and storage medium | |
| CN111160201B (en) | Face image uploading method and device, electronic equipment and storage medium | |
| CN113286115B (en) | Video monitoring guide library distribution control method and device and related equipment | |
| CN110855947B (en) | Image snapshot processing method and device | |
| CN111147603A (en) | Method and device for networking reasoning service | |
| CN111339949A (en) | License plate recognition method and device and inspection vehicle | |
| CN110162666A (en) | A kind of the execution method and executive device of retrieval tasks | |
| CN114205632A (en) | Video preview method and device, electronic equipment and computer readable storage medium | |
| CN114422776A (en) | Detection method and device for camera equipment, storage medium and electronic device | |
| CN114513681A (en) | Video processing system, method, device, electronic equipment and storage medium | |
| CN109874036B (en) | Video analysis method and device, equipment and storage medium | |
| CN111782483A (en) | Cloud computing monitoring platform capable of elastically stretching | |
| CN112882787A (en) | Data visualization processing method, device, medium and electronic equipment | |
| US10564601B2 (en) | Method and system for image processing and data transmission in network-based multi-camera environment | |
| CN116662645B (en) | Video event tracing analysis method and system, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |