CN116343112A - Scene monitoring method, device, electronic equipment and storage medium - Google Patents
Scene monitoring method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116343112A CN116343112A CN202310197510.1A CN202310197510A CN116343112A CN 116343112 A CN116343112 A CN 116343112A CN 202310197510 A CN202310197510 A CN 202310197510A CN 116343112 A CN116343112 A CN 116343112A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- scene
- target
- monitor
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 531
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000007613 environmental effect Effects 0.000 claims abstract description 52
- 238000012806 monitoring device Methods 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims description 85
- 238000004422 calculation algorithm Methods 0.000 claims description 57
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 13
- 230000003044 adaptive effect Effects 0.000 abstract description 4
- 238000013507 mapping Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 230000004297 night vision Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000010223 real-time analysis Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000009970 fire resistant effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/36—Indoor scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a scene monitoring method, a scene monitoring device, electronic equipment and a storage medium, and relates to the technical field of intelligent monitoring, wherein the scene monitoring method comprises the following steps: comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result; according to the comparison result, determining a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task; according to the monitoring task, calling each monitor in the target monitoring component to monitor the current environmental information of the target scene; and detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene. The invention realizes the adaptive monitoring of the scene according to the computing power resource and the network bandwidth resource, thereby efficiently and accurately monitoring the scene.
Description
Technical Field
The present invention relates to the field of intelligent monitoring technologies, and in particular, to a scene monitoring method, a device, an electronic apparatus, and a storage medium.
Background
Real-time monitoring of important scenes is an important premise for effectively ensuring the safety and order of the scenes. If in a laboratory scene, a laboratory is used as an original innovation base, important tasks are carried out in national basic research, technical development and technical attack, and the laboratory is not monitored and managed in place, so that larger economic property loss can be caused, and serious casualties can be possibly caused. Therefore, how to realize laboratory scene monitoring is one of effective means for guaranteeing laboratory safety.
Traditional laboratory safety management, such as static clothes placement monitoring, is usually based on a single monitoring device, such as a camera, to complete the whole monitoring process of shooting, calculation, identification and the like. In general, network bandwidth resources and algorithm theory resources of a single monitoring device are limited, a laboratory scene is complex, monitoring contents are various, and laboratory scene monitoring cannot be efficiently and accurately realized through the single monitoring device.
Disclosure of Invention
The invention provides a scene monitoring method, a scene monitoring device, electronic equipment and a storage medium, which are used for solving the defects that single monitoring equipment is limited in monitoring efficiency and monitoring precision in the prior art and realizing efficient and accurate scene monitoring.
The invention provides a scene monitoring method, which comprises the following steps:
comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result;
according to the comparison result, determining a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task;
according to the monitoring task, calling each monitor in the target monitoring component to monitor the current environmental information of the target scene;
and detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene.
According to the scene monitoring method provided by the invention, the determining of the monitoring task corresponding to the target scene and the target monitoring component corresponding to the monitoring task according to the comparison result comprises the following steps:
under the condition that the comparison result is true, determining that the monitoring task corresponding to the target scene comprises an environment state monitoring task;
determining that the target monitoring component comprises at least one first monitor and at least one second monitor according to the environmental state monitoring task;
the environment state monitoring tasks comprise a light monitoring subtask and a person monitoring subtask, the first monitor is used for monitoring light information required by the light monitoring subtask in the current environment information, and the second monitor is used for monitoring person information required by the person monitoring subtask in the current environment information.
According to the scene monitoring method provided by the invention, according to the monitoring task, each monitor in the target monitoring component is called to monitor the current environmental information of the target scene, and the scene monitoring method comprises the following steps:
when the monitoring task comprises the environment state monitoring task, calling each first monitor to monitor the light information of the target scene according to the light monitoring subtask, and calling each second monitor to monitor the character information of the target scene according to the character monitoring subtask;
The step of detecting the current environmental information according to the monitoring task to obtain a monitoring result of the target scene comprises the following steps:
detecting the lamplight information of the target scene according to the lamplight monitoring subtask to obtain a lamplight detection result;
under the condition that the current lamplight state in the target scene is determined to be the lighting state according to the lamplight detection result, detecting the character information according to the character monitoring subtask to obtain a character detection result;
and determining the monitoring result of the target scene according to the person detection result.
According to the scene monitoring method provided by the invention, the monitoring result of the target scene is determined according to the person detection result, and the scene monitoring method comprises the following steps:
determining that the monitoring result is that the current environmental state of the target scene is in a normal state under the condition that the target scene contains the person according to the person detection result and the stay time of the person in the target scene reaches the preset time;
and under the condition that the target scene is determined to not contain the person according to the person detection result, determining that the monitoring result is that the current environment state is in an abnormal state.
According to the scene monitoring method provided by the invention, the determining of the monitoring task corresponding to the target scene and the target monitoring component corresponding to the monitoring task according to the comparison result comprises the following steps:
and if the comparison result is false, determining that the monitoring task comprises a safety protection monitoring task, and determining that the target monitoring component comprises at least one third monitor.
According to the scene monitoring method provided by the invention, according to the monitoring task, each monitor in the target monitoring component is called to monitor the current environmental information of the target scene, and the scene monitoring method comprises the following steps:
under the condition that the monitoring task comprises the safety protection monitoring task, calling each third monitor to monitor safety protection information in the target scene according to the safety protection monitoring task;
the step of detecting the current environmental information according to the monitoring task to obtain a monitoring result of the target scene comprises the following steps:
detecting safety protection information in the target scene according to the safety protection monitoring task to obtain a safety protection detection result;
determining that the current safety protection state is in an abnormal state according to the safety protection detection result when the target person in the target scene is not worn with special clothing and the stay time of the target person in the target scene reaches a preset time;
And under the condition that the target person wears the special clothing according to the safety protection detection result, determining that the monitoring result of the target scene is that the current safety protection state is in a normal state.
According to the scene monitoring method provided by the invention, the method further comprises the following steps:
resetting a timer corresponding to the monitoring task under the condition that the monitoring result determines that the target scene is a normal scene;
controlling the timer to continue to count under the condition that the target scene is determined to be an abnormal scene;
generating alarm information according to the monitoring result and pushing the alarm information under the condition that the timing time of the timer is larger than a time threshold value;
and resetting the timer under the condition that the alarm information pushing is determined to be successful.
According to the scene monitoring method provided by the invention, the current environment information is detected according to the monitoring task to obtain the monitoring result of the target scene, and the scene monitoring method comprises the following steps:
loading a scene detection algorithm corresponding to each monitor according to the monitoring task and the configuration information of each monitor;
and detecting the current environmental information obtained by monitoring each monitor based on a scene detection algorithm corresponding to each monitor to obtain a monitoring result of the target scene.
According to the scene monitoring method provided by the invention, the current scene information comprises a current time point, and the preset scene information comprises a time zone bit;
comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result, wherein the comparison result comprises:
comparing the current time point with the time zone bit;
under the condition that the current time point exceeds the time zone bit, determining that the comparison result is true;
and under the condition that the current time point does not exceed the time zone bit, determining that the comparison result is false.
The invention also provides a scene monitoring device, which comprises:
the comparison unit is used for comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result;
the determining unit is used for determining a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task according to the comparison result;
the calling unit is used for calling each monitor in the target monitoring assembly to monitor the current environment information of the target scene according to the monitoring task;
and the monitoring unit is used for detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the scene monitoring method as described in any of the above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a scene monitoring method as described in any of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements a scene monitoring method as described in any of the above.
According to the scene monitoring method, the device, the electronic equipment and the storage medium, provided by the embodiment, the current scene information of the target scene is compared with the preset scene information through the edge server, so that the monitoring task is divided and the target monitoring component is determined in a self-adaptive mode according to the comparison result, the current environment information of the target scene is monitored by using the computing power resources and the network bandwidth resources of each monitor in the target monitoring component, the current environment information is detected by using the computing power resources and the network bandwidth resources of the edge server, scene monitoring is realized, the computing power resources and the network bandwidth resources of the edge server and the computing power resources and the network bandwidth resources of each monitor in the target monitoring component are fully combined according to the monitoring task, the scene is monitored adaptively, the influence of the limited monitoring efficiency and the limited monitoring precision of the single monitoring equipment is avoided, and the scene monitoring is realized efficiently and accurately.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a scene monitoring method according to the present invention;
fig. 2 is a schematic structural diagram of a scene monitoring platform of the scene monitoring method provided by the invention;
FIG. 3 is a second flow chart of the scene monitoring method according to the present invention;
fig. 4 is a schematic structural diagram of a scene monitoring device provided by the invention;
fig. 5 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Traditional laboratory security management, such as static coat placement monitoring, is usually disposable and non-networked, i.e., the monitoring effect is poor by performing one-time detection report on passing persons through a single monitoring device, such as a front panel machine or other vertical device or camera placed in front of a laboratory door, so that laboratory monitoring becomes a form. In addition, as the calculation power of the single monitoring equipment has a bottleneck, the monitoring effect and efficiency are difficult to ensure for laboratory monitoring scenes needing complex reasoning logic; if special customization is performed for a complex scene, the monitoring cost is further increased. Therefore, in the prior art, complex scene monitoring cannot be efficiently and accurately realized through a single monitoring device.
In view of the above problems, the present embodiment provides a scene monitoring method and apparatus, which implement on-line full-flow scene monitoring by adopting a cooperative manner of a server and multiple monitors, specifically, by customizing scene reasoning by the server, perform real-time scheduling on the multiple monitors, so as to analyze data information collected by the monitors in real time, obtain a real-time scene monitoring result, and perform real-time pushing on the monitoring result, so that the operation and maintenance are simple, and efficient and accurate scene monitoring is implemented.
A scene monitoring method provided by the present invention is described below with reference to fig. 1.
As shown in fig. 1, one of the flow diagrams of the scene monitoring method provided by the embodiment of the present invention is that the scene monitoring method provided by the embodiment of the present invention can be applied to a scene monitoring platform, where the platform includes an edge server, a plurality of monitors, and other hardware devices for assisting scene monitoring, such as an entrance guard and a speaker, and specifically can be adaptively added and deleted according to the scene monitoring requirements.
In general, most of traditional intelligent monitoring frameworks rely on the computing power of a camera to perform some simple feature recognition, so that effective monitoring of complex scenes cannot be realized, and traditional NVRs (Network Video Recorder, network video recorders) cannot display and alarm specific recognition information, so that comprehensive monitoring cannot be realized, and the monitoring effect is poor. Compared with the prior art, the scene monitoring platform has the advantages that all the functional components in the scene monitoring platform are decoupled in compliance, the following adaptive addition and deletion of all the functional components are convenient, the scene monitoring platform is easy to expand and low in cost, the upper limit of the lower calculation force of the platform is determined by the calculation force limit of the edge server instead of the calculation force of a single monitoring device, and therefore the platform has higher efficiency and effect for effectively monitoring complex scenes. For example, the edge server 21T can support 16 paths of 1920x1080 camera codec, and support real-time reasoning of the neural network detection algorithm corresponding to the multiple paths of cameras, so as to realize efficient and accurate scene monitoring.
Fig. 2 is a schematic structural diagram of the scene monitoring platform. Wherein the edge server is in communication connection with a plurality of monitors and other hardware devices. The operation, deployment and operation and maintenance of the scene monitoring platform are realized based on an edge server.
The edge server comprises an algorithm engine, a rear end and a front end, so that the edge server can realize efficient and accurate scene monitoring according to communication interaction among the algorithm engine, the rear end and the front end and hardware equipment connected with the edge server.
The algorithm engine is used for storing various detection algorithms and calling the detection algorithms to execute monitoring tasks when scene monitoring is carried out; the rear end is internally provided with a Spring Boot, service software, business logic, a database and the like, and is used for storing monitoring data, processing the monitoring data, scheduling hardware equipment, interacting with the front end and the like; the front end is used for content presentation and man-machine interaction through various software, and the software includes WEB (World Wide WEB) pages, applets, ngix (server software), VUE (video shooting and beautifying tool), which is not specifically limited in this embodiment.
It should be noted that, the edge server may be used as an execution body of the scene monitoring method provided in the embodiment; the following uses an edge server as an execution body, and a specific description is developed for a scene monitoring method in this embodiment, where the method includes the following steps:
the target scenario is a scenario that needs to be monitored, including but not limited to a laboratory, a factory shop, etc., which is not specifically limited in this embodiment.
The current scene information is information for characterizing the current state of the target scene, including time information or environment information, etc., which is not particularly limited in this embodiment.
The preset scene information is preconfigured by the edge server according to the monitoring requirement of the target scene.
Optionally, the edge server firstly collects current scene information of the target scene and loads preset scene information configured in advance; and comparing the current scene information with preset scene information to divide monitoring tasks according to the comparison result.
different comparison results correspond to different monitoring tasks, different monitoring tasks correspond to different monitoring components, namely, the environment information corresponding to different monitoring tasks is different, and the monitoring components for collecting different environment information are different.
The target monitoring component comprises one or more types of monitors, and the number of monitors contained in the target monitoring component, configuration information of each monitor and the like can be preconfigured, such as 5 monitors are configured according to the monitoring requirements of a target scene. The monitor in the target monitoring component can be a camera or other devices with monitoring functions. The configuration information includes basic information of the monitor, one or more monitoring algorithms, and a mapping relationship between the monitor and the scene detection algorithm, which is not specifically limited in this embodiment.
The monitoring task includes, but is not limited to, an environmental status monitoring task or a safety protection monitoring task, and may specifically be set according to a monitoring requirement, which is not specifically limited in this embodiment.
Optionally, after the comparison result is obtained, a monitoring task corresponding to the target scene may be determined according to the corresponding relationship between the comparison result and the monitoring task, and a monitor for implementing an environmental information collection function corresponding to the monitoring task may be determined, so as to construct the target monitoring component.
The monitoring tasks may include one or more sub-monitoring tasks, and the specific number of the sub-monitoring tasks is set according to actual monitoring requirements, for example, the monitoring tasks include a light monitoring sub-task and a person monitoring sub-task, or the monitoring tasks include only a safety protection monitoring sub-task.
Optionally, after the monitoring task is acquired, the number of subtasks included in the monitoring task may be determined, and under the condition that the monitoring task includes only one subtask, each monitor in the target monitoring component is directly called to synchronously monitor the target scene, so as to obtain current environmental information of the target scene. Under the condition that the monitoring task comprises a plurality of subtasks, each monitor in the target monitoring component can be directly called to monitor the target scene synchronously, the environment information corresponding to each subtask is obtained, and then the current environment information is obtained; or determining the execution sequence of each subtask, determining the monitoring sequence of each monitor in the target monitoring assembly according to the execution sequence of each subtask and the monitoring function of each monitor in the target monitoring assembly, and calling each monitor in the target monitoring assembly in turn to monitor a target scene based on the monitoring sequence to acquire the environment information corresponding to each subtask so as to acquire the current environment information, wherein the embodiment is not particularly limited.
And 104, detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene.
Optionally, after the current environmental information is acquired, a detection algorithm may be determined according to the monitoring task, so as to detect the current environmental information according to the detection algorithm, and determine whether the target scene is an abnormal scene or a normal scene according to the detection result, so that effective supervision on the target scene is facilitated.
The detection algorithm can be determined jointly according to configuration information of each monitor in the target monitoring component and the monitoring task; or may be determined directly according to a detection algorithm required for the monitoring task, which is not specifically limited in this embodiment.
It can be understood that compared with the conventional method in which a single monitoring device is used for monitoring, the problem of limited monitoring efficiency and monitoring accuracy exists, and the upper limit of calculation power and the network resource bandwidth in the scene monitoring method provided in the embodiment are determined by the calculation power limit of the edge server and the target monitor component together, and are not the calculation power and the network resource bandwidth of the single monitoring device, so that the method has higher calculation power upper limit and better monitoring effect for the algorithm customization of the complex scene, and further realizes efficient and accurate scene monitoring. In addition, the whole monitoring flow is realized by real-time scheduling of a plurality of monitors based on an edge server and real-time analysis, and the decoupling mode is followed, namely, all environment information required by a monitoring task is decoupled, so that in the execution process of the monitoring task, the corresponding monitors are adaptively selected (added or deleted) according to the function required by the monitoring task to realize the monitoring of the environment information, no additional physical hardware is needed, and the method has the characteristics of easiness in expansion, high flexibility and low cost.
It should be noted that, the above-mentioned scene monitoring method may be suitable for performing iterative monitoring on the target scene under each period, so as to perform real-time and efficient scene monitoring, and the scene monitoring step of each period may refer to steps 101 to 104, which are not repeated herein.
According to the scene monitoring method provided by the embodiment, the current scene information of the target scene is compared with the preset scene information which is configured in advance through the edge server, so that the monitoring task is divided and the target monitoring assembly is determined in a self-adaptive mode according to the comparison result, the current environment information of the target scene is monitored by utilizing the computing power resources and the network bandwidth resources of all monitors in the target monitoring assembly, the current environment information is detected by utilizing the computing power resources and the network bandwidth resources of the edge server, the scene monitoring is realized, and the scene is monitored in an adaptive mode by fully combining the computing power resources and the network bandwidth resources of the edge server and the computing power resources and the network bandwidth resources of all monitors in the target monitoring assembly according to the monitoring task, so that the influence of limited monitoring efficiency and limited monitoring precision of single monitoring equipment is avoided, and further the scene monitoring is realized efficiently and accurately.
In some embodiments, the step of determining, in step 102, the monitoring task corresponding to the target scene and the target monitoring component corresponding to the monitoring task according to the comparison result further includes:
under the condition that the comparison result is true, determining that the monitoring task corresponding to the target scene comprises an environment state monitoring task;
determining that the target monitoring component comprises at least one first monitor and at least one second monitor according to the environmental state monitoring task;
the environment state monitoring tasks comprise a light monitoring subtask and a person monitoring subtask, the first monitor is used for monitoring light information required by the light monitoring subtask in the current environment information, and the second monitor is used for monitoring person information required by the person monitoring subtask in the current environment information.
The comparison result is classified as true or false, so that the division of the monitoring task and the determination of the monitoring component are realized according to the true or false result.
The environmental state monitoring task is a task for detecting the environmental state of the target scene, including but not limited to a light monitoring subtask and a person monitoring subtask, and is specifically determined according to the monitoring requirement of the target scene. The light monitoring subtask is used for detecting the light state in the target environment, and the person monitoring subtask is used for detecting the person state in the target environment.
Optionally, after the comparison result is obtained, it is required to determine whether the comparison result is true or false; and under the condition that the comparison result is true, determining that the monitoring task corresponding to the target scene comprises a task for detecting the environment state of the target scene, namely an environment state monitoring task.
Therefore, the target monitoring component corresponding to the environment state monitoring task is determined to be a monitoring component for monitoring environment information required by the environment state monitoring task, wherein the component comprises at least one first monitor for monitoring lamplight information required by the lamplight monitoring subtask and at least one second monitor for monitoring character information required by the character monitoring subtask; the specific number of the first monitors and the second monitors can be set according to actual requirements, such as 1 first monitor and 4 second monitors.
In this embodiment, in the case that the comparison result is true, it may be determined that the monitoring task includes an environmental status monitoring task, so as to combine bandwidth resources and algorithm resources of at least one first monitor and at least one second monitor, to implement fast and accurate monitoring of environmental information required by the environmental status monitoring task, and further to implement target scene monitoring efficiently and accurately.
In some embodiments, the step of invoking each monitor in the target monitoring component to monitor the current environmental information of the target scene according to the monitoring task in step 103 further includes:
when the monitoring task comprises the environment state monitoring task, calling each first monitor to monitor the light information of the target scene according to the light monitoring subtask, and calling each second monitor to monitor the character information of the target scene according to the character monitoring subtask;
optionally, in the case that the monitoring task includes the environmental state monitoring task, the monitoring sequence of the first monitor and the monitoring sequence of the second monitor may be determined accordingly according to the execution sequence of the light monitoring subtask and the execution sequence of the person monitoring subtask, that is, the monitoring sequence of the first monitor is consistent with the execution sequence of the light monitoring subtask, and the monitoring sequence of the second monitor is consistent with the execution sequence of the person monitoring subtask.
And then, according to the monitoring sequence, sequentially calling the lamplight information of the monitored target scene of each first monitor and the character information of the monitored target scene of each second monitor.
The execution sequence of the light monitoring subtask is before the person monitoring subtask, and the monitoring sequence of the first monitors is before the second monitors, accordingly, the first monitors are called to monitor the light information of the target scene, and then the second monitors are called to monitor the person information of the target scene.
In step 104, the step of detecting the current environmental information according to the monitoring task to obtain the monitoring result of the target scene further includes:
detecting the lamplight information of the target scene according to the lamplight monitoring subtask to obtain a lamplight detection result;
under the condition that the current lamplight state in the target scene is determined to be the lighting state according to the lamplight detection result, detecting the character information according to the character monitoring subtask to obtain a character detection result;
and determining the monitoring result of the target scene according to the person detection result.
Optionally, under the condition that the lamplight information is obtained, a lamplight detection algorithm can be determined according to the lamplight monitoring subtask and the configuration information of the first monitor, so that lamplight information of the target scene is detected according to the lamplight detection algorithm, and whether the current lamplight state in the target scene is a lighting state or not is determined. If the target scene is in the unlit state, the process returns to step 101, and the target scene is monitored iteratively.
And under the condition of being in a lighting state, acquiring the character information of the target scene monitored by the second monitor, determining a character detection algorithm according to the character monitoring subtask and the configuration information of the second monitor, detecting the character information of the target scene according to the character detection algorithm to determine whether the character information in the target scene meets the condition or not, and further acquiring the monitoring result of the target scene according to the determination result.
In this embodiment, according to the environmental state monitoring task, the first monitor and the second monitor are adaptively invoked to collect light information and character information of the target scene to perform light detection and character detection, so that the environmental state monitoring of the target scene is flexibly implemented with low cost without additional update of hardware (monitor) version, and the environmental state monitoring of the target scene is efficiently and accurately performed.
In some embodiments, the determining the monitoring result of the target scene according to the person detection result includes:
determining that the monitoring result is that the current environmental state of the target scene is in a normal state under the condition that the target scene contains the person according to the person detection result and the stay time of the person in the target scene reaches the preset time;
And under the condition that the target scene is determined to not contain the person according to the person detection result, determining that the monitoring result is that the current environment state is in an abnormal state.
The person detection is used for detecting whether the person is contained in the target scene, and the stay time of the person needs to be determined under the condition that the person is contained, so that whether the person working normally exists in the target scene in the lighted state is determined.
The preset duration can be set according to the monitoring requirement and is used for limiting the effective tracking duration of the person.
Optionally, after the detection result is obtained, whether the target scene contains the person is determined according to the detection result, and if the target scene does not contain the person, the monitoring result is determined to be in an abnormal state, that is, the target scene is determined to be an abnormal scene.
Under the condition of containing the person, further determining that the stay time of the person in the target scene reaches the preset time according to the detection result, and further characterizing that the person is an effective person (namely a normal work person) in the target scene and further characterizing that the person working normally exists in the target scene in a lighting state, wherein the target scene is determined to be in a normal state at present; otherwise, the character is represented as an invalid character (namely, an invalid character generated by a monitoring error and an invalid character generated by non-work) in the target scene, and the character which does not normally work in the target scene is further represented in a lighting state, at the moment, the current abnormal state of the target scene is determined, and the abnormal state is alarmed, so that a manager can close the light in the target scene in time, and resource waste and laboratory safety influence are avoided.
In some embodiments, the step of determining, in step 102, the monitoring task corresponding to the target scene and the target monitoring component corresponding to the monitoring task according to the comparison result further includes:
and if the comparison result is false, determining that the monitoring task comprises a safety protection monitoring task, and determining that the target monitoring component comprises at least one third monitor.
Optionally, after the comparison result is obtained, it is required to determine whether the comparison result is true or false; and under the condition that the comparison result is false, determining that the monitoring task corresponding to the target scene comprises a task for detecting the safety protection state of the target scene, namely a safety protection monitoring task.
Therefore, the target monitoring component corresponding to the safety protection monitoring task is determined to be the monitoring component for monitoring the safety protection information required by the safety protection monitoring task, and the component comprises at least one third monitor; the at least one third monitor may include a first monitor and/or a second monitor, or may include other monitors except the first monitor and the second monitor, and may specifically be determined according to configuration information of the monitors, which is not specifically limited in this embodiment, for example, one first monitor and 4 second monitors.
It should be noted that, in the case where the at least one third monitor includes the first monitor and the second monitor, the first monitor needs to be configured with the light information monitoring function and the safety protection information monitoring function at the same time, and the second monitor needs to be configured with the character information monitoring function and the safety protection information monitoring function at the same time.
In this embodiment, in the case that the comparison result is false, it may be determined that the monitoring task includes a security protection monitoring task, so as to combine the bandwidth resource and the power management resource of at least one third monitor, to realize the fast and accurate monitoring of the environmental information required by the security protection monitoring task, and further to efficiently and accurately realize the target scene monitoring.
In some embodiments, the step of invoking each monitor in the target monitoring component to monitor the current environmental information of the target scene according to the monitoring task in step 103 further includes:
under the condition that the monitoring task comprises the safety protection monitoring task, calling each third monitor to monitor safety protection information in the target scene according to the safety protection monitoring task;
optionally, in the case that the monitoring task includes a security protection monitoring task, security protection information of the monitoring target scene of each third monitor may be synchronously invoked.
The safety protection information is information for ensuring safe operation of the target environment, including information of wearing a protection tool by the target person, and the like, and is not particularly limited in this embodiment.
In step 104, the step of detecting the current environmental information according to the monitoring task to obtain the monitoring result of the target scene further includes:
detecting safety protection information in the target scene according to the safety protection monitoring task to obtain a safety protection detection result;
detecting safety protection information in the target scene according to the safety protection monitoring task to obtain a safety protection detection result;
determining that the current safety protection state is in an abnormal state according to the safety protection detection result when the target person in the target scene is not worn with special clothing and the stay time of the target person in the target scene reaches a preset time;
and under the condition that the target person wears the special clothing according to the safety protection detection result, determining that the monitoring result of the target scene is that the current safety protection state is in a normal state.
The target person is a person needing to wear special clothing in the target scene. Specific garments include, but are not limited to, antistatic garments and fire-resistant garments, which are not specifically limited in this embodiment.
Optionally, under the condition that the safety protection information is obtained, a safety protection detection algorithm can be determined according to the safety protection monitoring task and the configuration information of the third monitor, so that the safety protection information of the target scene is detected according to the safety protection detection algorithm, whether the target person in the target scene wears special clothing and the stay time of the target person in the target scene are determined, and whether the current safety protection state is a safety state is further judged.
And under the condition that the target person in the target scene does not wear special clothing and the stay time of the target person in the target scene reaches the preset time, the current safety protection state is characterized as being in an abnormal state, at the moment, the current abnormal state of the target scene is determined, and the abnormal state is alarmed so as to prompt the target person to wear the special clothing in time, so that the influence on the safety of a laboratory is avoided.
Under the condition that the target person wearing special clothing in the target scene and the stay time of the target person in the target scene reaches the preset time, the current safety protection state is represented to be in a normal state, the method can continue to return to the step 101, and the target scene is monitored iteratively.
In this embodiment, according to the security protection monitoring task, the third monitor is adaptively invoked to collect security protection information of the target scene, so as to detect the security protection information, and under the condition that no additional update of the hardware version is ensured, the security protection state monitoring of the target scene is flexibly implemented with low cost, so as to efficiently and accurately implement the security protection of the target scene.
In some embodiments, the method further comprises:
resetting a timer corresponding to the monitoring task under the condition that the monitoring result determines that the target scene is a normal scene;
controlling the timer to continue to count under the condition that the target scene is determined to be an abnormal scene;
generating alarm information according to the monitoring result and pushing the alarm information under the condition that the timing time of the timer is larger than a time threshold value;
and resetting the timer under the condition that the alarm information pushing is determined to be successful.
Wherein the timer provides a time reference for alerting for the abnormal scene.
Optionally, according to the monitoring result, determining whether the target scene is a normal scene, so as to determine a control operation and an alarm operation to be executed on the timer according to the determination result.
For example, in executing the environmental state monitoring task, if the current environmental state of the target scene is determined to be a normal state according to the monitoring result, the target scene is determined to be a normal scene, the timing time of the timer can be initialized to 0, and the process returns to the step 101 again, and the target scene is monitored iteratively; if the current environmental state of the target scene is determined to be an abnormal state according to the monitoring result, the target scene is determined to be an abnormal scene, the timer can be controlled to continue to count, whether the count time of the timer is larger than a time threshold value or not is judged, and alarm information is generated according to the monitoring result under the condition that the timer is larger than the time threshold value; the alarm information at least includes a monitoring result, task information of a monitoring task, and the like, which is not specifically limited in this embodiment.
And synchronously pushing the alarm information to the rear end, and forwarding or operating the result according to different monitoring tasks after the rear end receives the alarm information pushed by the reasoning engine. In the process, the pushed alarm information is stored in a permanent storage space of the edge server and added to front-end calling of the edge server, and meanwhile, the alarm information can be synchronized to the cloud server. In addition, the back end can call physical resources under the target scene in a script form, such as a loudspeaker and a loudspeaker, to give an alarm according to alarm information, so that a manager can timely process abnormal conditions of the target scene, the target scene can be conveniently and timely restored to a normal state, and the safety of the target scene is improved.
In addition, under the condition that the alarm information is successfully pushed to the rear end, the timer is filtered, namely, the timer is reset, and secondary timing is continuously carried out on the timer, so that the alarm information is prevented from being continuously pushed to the rear end, the interference to staff in a target scene is avoided, and the user experience is influenced.
In some embodiments, in step 104, detecting the current environmental information according to the monitoring task to obtain a monitoring result of the target scene includes:
loading a scene detection algorithm corresponding to each monitor according to the monitoring task and the configuration information of each monitor;
and detecting the current environmental information obtained by monitoring each monitor based on a scene detection algorithm corresponding to each monitor to obtain a monitoring result of the target scene.
It should be noted that, before performing scene monitoring, the edge server pre-configures configuration information of each camera according to the monitoring requirement of the target scene, where the configuration information includes, but is not limited to, basic information of the monitor, one or more monitoring algorithms, and a mapping relationship between the monitor and the scene detection algorithm, and this embodiment is not specifically limited. Illustratively, configuring the first monitor includes a light monitoring algorithm and a safety protection monitoring algorithm, a mapping relationship between the first monitor and a light detection algorithm, a mapping relationship between the first monitor and a safety protection detection algorithm, and the like.
Optionally, when executing step 104, a scene detection algorithm corresponding to each monitor required for implementing the monitoring task is loaded in the algorithm database according to the mapping relation in the configuration information of each monitor and the monitoring task;
and then, detecting the current environment information obtained by monitoring each monitor based on a scene detection algorithm corresponding to each monitor so as to obtain a monitoring result of the target scene.
In an exemplary embodiment, when the monitoring task includes a light detection subtask, the scene detection algorithm corresponding to the first monitor is a light detection algorithm, and the light information is detected based on the light detection algorithm to obtain a light detection result, so as to obtain a monitoring result of the target scene according to the light detection result.
Compared with the traditional scene monitoring mode, the method adopts the edge server to realize real-time scheduling of multiple monitors, carries out real-time analysis on the current environment information monitored by each monitor based on the detection algorithm corresponding to each monitor, carries out real-time pushing, is simple in operation and maintenance, and improves the integrity and the real-time performance of the scene monitoring while improving the efficiency of the scene monitoring.
In some embodiments, the current scene information includes a current point in time, and the preset scene information includes a time flag bit;
Comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result, wherein the comparison result comprises:
comparing the current time point with the time zone bit;
under the condition that the current time point exceeds the time zone bit, determining that the comparison result is true;
and under the condition that the current time point does not exceed the time zone bit, determining that the comparison result is false.
The time zone bit can be preconfigured according to the monitoring requirement of the target scene and is used for dividing tasks so as to reasonably utilize bandwidth resources and algorithm processing resources of each monitor, realize real-time scheduling of different algorithm logics of a laboratory in different time periods, analyze in real time and infer in real time.
Optionally, acquiring a current time point of the target scene in real time, judging whether the current time point exceeds a time zone bit, if so, determining that the comparison result is true, namely, representing that the current time is at night, and carrying out an environment state monitoring task; otherwise, determining that the comparison result is false, namely, representing that the current time is daytime, and carrying out a safety protection monitoring task.
The current time of the target scene is compared with the time zone bit, so that the tasks can be reasonably divided, the safety protection monitoring task is realized during the daytime, the environment state monitoring task is performed at night, the monitoring range of the target scene is improved, the monitoring integrity is improved, and further, the scene monitoring is ensured to be more effective.
The scene monitoring method in the present embodiment is described below with specific examples.
As shown in fig. 3, a second flowchart of a scene monitoring method according to the present embodiment is shown, where the method includes:
and under the condition that the comparison result is true, performing an environmental state monitoring task, wherein the specific steps are as follows:
and polling to perform light detection according to the light information collected by the monitor 1.
It should be noted that, in the case where the monitor 1 is a night vision camera, the light detection is performed using the saturation in the color model (abbreviated as HSV); in the case where the monitor 1 is an night vision camera, light detection is performed correspondingly using the average luminance.
Under the condition that the light state of the target scene is the lighting state according to the light detection result, collecting character information based on the monitor 2, the monitor 3, the monitor 4 and the monitor 5, detecting the character information collected by each second monitor in the monitors 2, 3, 4 and 5 based on a character detection algorithm corresponding to each second monitor, such as a general YOLOX model, to determine whether the character is contained in the target scene, and when the character is contained in the target scene, determining that the stay time of the character in the target scene reaches the preset time length, namely the minimum tracking time length of the character is met, characterizing that the character still works normally under the target scene, not needing to alarm, and returning to step 302 again after refreshing a reset timer, continuing the next round of scene monitoring;
If the target scene does not contain the person, the timer continues to count, and returns to the step 302 again to continue the next scene monitoring when the count time of the timer does not meet the condition that the count time is greater than the time threshold; under the condition that the timing time of the timer is greater than the time threshold, alarm information generated according to the monitoring result is pushed to the rear end, and the timer is filtered at the same time, so that the timer is clocked for the second time, and the alarm information is prevented from being pushed continuously, and interference is caused to staff.
And under the condition that the comparison result is false, performing a security mode monitoring task, wherein the method comprises the following specific steps of:
the control monitor 1, the monitor 2, the monitor 3, the monitor 4 and the monitor 5 collect the safety protection information under the target environment, and based on the corresponding safety protection detection algorithm of each monitor, such as a special clothing YOLOX model, the safety protection detection is carried out on the safety protection information collected by each monitor, when it is determined that the target person under the target scene is not wearing the antistatic clothing according to the detection result, and the stay time of the target person in the target scene reaches the preset time, the alarm information is generated, and after the alarm information is pushed to the rear end, the step 302 is returned again.
In summary, according to the scene monitoring method provided by the embodiment, on-line scene monitoring is realized under the monitoring framework based on the combination of the edge server and the multi-monitor, because the upper limit of the computing power under the framework is determined by the computing power limit of the edge server (instead of the computing power of a single monitor), compared with the traditional mode, the framework has higher upper limit and better reasoning effect for the algorithm customization of a complex scene, in addition, the operation, deployment and operation and maintenance under the framework are all based on the application layer of the edge server, the hardware structure is not required to be updated, the deployment end is more convenient and efficient, the self-adaptive high-efficiency switching of the multi-monitor task can be realized, namely, the safety protection task is carried out in daytime based on the current environment information, and the alarm picture uploading and the voice broadcasting are carried out when the safety protection state is abnormal; sensing people and light detection at night so as to realize light control or alarm under the unmanned condition; in addition, under the condition that normal operation of the service is not affected, the addition of an additional algorithm module can be performed based on the existing monitor (without purchasing a panel machine or a standing camera) in a target scene, so that the self-adaptive high-efficiency switching of multiple monitoring tasks can be realized, and the operation and maintenance cost is effectively reduced; in addition, the method conforms to the decoupling modes of the front end, the back end and the algorithm engine, realizes the separation of the reasoning, pushing and displaying results of the algorithm, and facilitates the addition and correction of various data processing modules and pushing and displaying modules so as to realize efficient, accurate and comprehensive scene monitoring.
The scene monitoring device provided by the invention is described below, and the scene monitoring device described below and the scene monitoring method described above can be referred to correspondingly.
As shown in fig. 4, a scene monitoring device provided in this embodiment includes:
the comparing unit 401 is configured to compare the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result;
the determining unit 402 is configured to determine, according to the comparison result, a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task;
the calling unit 403 is configured to call each monitor in the target monitoring component to monitor the current environmental information of the target scene according to the monitoring task;
the monitoring unit 404 is configured to detect the current environmental information according to the monitoring task, and obtain a monitoring result of the target scene.
According to the scene monitoring device provided by the embodiment, the current scene information of the target scene is compared with the preset scene information which is configured in advance through the edge server, so that the monitoring task is divided and the target monitoring assembly is determined in a self-adaptive mode according to the comparison result, the current environment information of the target scene is monitored by utilizing the computing power resources and the network bandwidth resources of all monitors in the target monitoring assembly, the current environment information is detected by utilizing the computing power resources and the network bandwidth resources of the edge server, the scene monitoring is realized, and the scene is monitored in an adaptive mode by fully combining the computing power resources and the network bandwidth resources of the edge server and the computing power resources and the network bandwidth resources of all monitors in the target monitoring assembly according to the monitoring task, so that the influence of limited monitoring efficiency and limited monitoring precision of single monitoring equipment is avoided, and further the scene monitoring is realized efficiently and accurately.
Fig. 5 illustrates a physical schematic diagram of an electronic device, as shown in fig. 5, which may include: a processor (processor) 501, a communication interface (Communications Interface) 502, a memory (memory) 503 and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 communicate with each other via the communication bus 504. The processor 501 may invoke logic instructions in the memory 503 to perform a scene monitoring method comprising: comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result; according to the comparison result, determining a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task; according to the monitoring task, calling each monitor in the target monitoring component to monitor the current environmental information of the target scene; and detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene.
Further, the logic instructions in the memory 503 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the scene monitoring method provided by the above methods, the method comprising: comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result; according to the comparison result, determining a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task; according to the monitoring task, calling each monitor in the target monitoring component to monitor the current environmental information of the target scene; and detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform a scene monitoring method provided by the above methods, the method comprising: comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result; according to the comparison result, determining a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task; according to the monitoring task, calling each monitor in the target monitoring component to monitor the current environmental information of the target scene; and detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (12)
1. A scene monitoring method, comprising:
comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result;
according to the comparison result, determining a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task;
according to the monitoring task, calling each monitor in the target monitoring component to monitor the current environmental information of the target scene;
and detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene.
2. The scene monitoring method according to claim 1, wherein the determining, according to the comparison result, the monitoring task corresponding to the target scene and the target monitoring component corresponding to the monitoring task includes:
Under the condition that the comparison result is true, determining that the monitoring task corresponding to the target scene comprises an environment state monitoring task;
determining that the target monitoring component comprises at least one first monitor and at least one second monitor according to the environmental state monitoring task;
the environment state monitoring tasks comprise a light monitoring subtask and a person monitoring subtask, the first monitor is used for monitoring light information required by the light monitoring subtask in the current environment information, and the second monitor is used for monitoring person information required by the person monitoring subtask in the current environment information.
3. The scene monitoring method according to claim 2, wherein the invoking each monitor in the target monitoring component to monitor the current environmental information of the target scene according to the monitoring task comprises:
when the monitoring task comprises the environment state monitoring task, calling each first monitor to monitor the light information of the target scene according to the light monitoring subtask, and calling each second monitor to monitor the character information of the target scene according to the character monitoring subtask;
The step of detecting the current environmental information according to the monitoring task to obtain a monitoring result of the target scene comprises the following steps:
detecting the lamplight information of the target scene according to the lamplight monitoring subtask to obtain a lamplight detection result;
under the condition that the current lamplight state in the target scene is determined to be the lighting state according to the lamplight detection result, detecting the character information according to the character monitoring subtask to obtain a character detection result;
and determining the monitoring result of the target scene according to the person detection result.
4. The scene monitoring method according to claim 3, wherein the determining the monitoring result of the target scene based on the person detection result includes:
determining that the monitoring result is that the current environmental state of the target scene is in a normal state under the condition that the target scene contains the person according to the person detection result and the stay time of the person in the target scene reaches the preset time;
and under the condition that the target scene is determined to not contain the person according to the person detection result, determining that the monitoring result is that the current environment state is in an abnormal state.
5. The scene monitoring method according to claim 1, wherein the determining, according to the comparison result, the monitoring task corresponding to the target scene and the target monitoring component corresponding to the monitoring task includes:
and if the comparison result is false, determining that the monitoring task comprises a safety protection monitoring task, and determining that the target monitoring component comprises at least one third monitor.
6. The scene monitoring method according to claim 5, wherein the invoking each monitor in the target monitoring component to monitor the current environmental information of the target scene according to the monitoring task comprises:
under the condition that the monitoring task comprises the safety protection monitoring task, calling each third monitor to monitor safety protection information in the target scene according to the safety protection monitoring task;
the step of detecting the current environmental information according to the monitoring task to obtain a monitoring result of the target scene comprises the following steps:
detecting safety protection information in the target scene according to the safety protection monitoring task to obtain a safety protection detection result;
Determining that the current safety protection state is in an abnormal state according to the safety protection detection result when the target person in the target scene is not worn with special clothing and the stay time of the target person in the target scene reaches a preset time;
and under the condition that the target person wears the special clothing according to the safety protection detection result, determining that the monitoring result of the target scene is that the current safety protection state is in a normal state.
7. The scene monitoring method according to any of claims 1-6, characterized in that the method further comprises:
resetting a timer corresponding to the monitoring task under the condition that the monitoring result determines that the target scene is a normal scene;
controlling the timer to continue to count under the condition that the target scene is determined to be an abnormal scene;
generating alarm information according to the monitoring result and pushing the alarm information under the condition that the timing time of the timer is larger than a time threshold value;
and resetting the timer under the condition that the alarm information pushing is determined to be successful.
8. The scene monitoring method according to any one of claims 1 to 6, wherein the detecting the current environmental information according to the monitoring task to obtain the monitoring result of the target scene includes:
loading a scene detection algorithm corresponding to each monitor according to the monitoring task and the configuration information of each monitor;
and detecting the current environmental information obtained by monitoring each monitor based on a scene detection algorithm corresponding to each monitor to obtain a monitoring result of the target scene.
9. The scene monitoring method according to any one of claims 1 to 6, wherein the current scene information includes a current time point, and the preset scene information includes a time-stamp bit;
comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result, wherein the comparison result comprises:
comparing the current time point with the time zone bit;
under the condition that the current time point exceeds the time zone bit, determining that the comparison result is true;
and under the condition that the current time point does not exceed the time zone bit, determining that the comparison result is false.
10. A scene monitoring device, comprising:
the comparison unit is used for comparing the current scene information of the target scene with preset scene information configured in advance to obtain a comparison result;
the determining unit is used for determining a monitoring task corresponding to the target scene and a target monitoring component corresponding to the monitoring task according to the comparison result;
the calling unit is used for calling each monitor in the target monitoring assembly to monitor the current environment information of the target scene according to the monitoring task;
and the monitoring unit is used for detecting the current environment information according to the monitoring task to obtain a monitoring result of the target scene.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the scene monitoring method of any of claims 1 to 9 when the program is executed by the processor.
12. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the scene monitoring method according to any of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310197510.1A CN116343112A (en) | 2023-03-03 | 2023-03-03 | Scene monitoring method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310197510.1A CN116343112A (en) | 2023-03-03 | 2023-03-03 | Scene monitoring method, device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116343112A true CN116343112A (en) | 2023-06-27 |
Family
ID=86881483
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310197510.1A Pending CN116343112A (en) | 2023-03-03 | 2023-03-03 | Scene monitoring method, device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116343112A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118135507A (en) * | 2024-05-07 | 2024-06-04 | 山东汉鑫科技股份有限公司 | Tunnel traffic event processing system, method, medium and equipment |
-
2023
- 2023-03-03 CN CN202310197510.1A patent/CN116343112A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118135507A (en) * | 2024-05-07 | 2024-06-04 | 山东汉鑫科技股份有限公司 | Tunnel traffic event processing system, method, medium and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109039740A (en) | A kind of method and apparatus handling O&M monitoring alarm | |
Colom et al. | Scheduling framework for distributed intrusion detection systems over heterogeneous network architectures | |
EP2871553A1 (en) | Systems and methods for protecting virtualized assets | |
CN110784628A (en) | Image data acquisition processing method and system, intelligent camera and server | |
CN102740121B (en) | Be applied to video quality diagnostic control system and the method for video surveillance network | |
US20170288979A1 (en) | Blue print graphs for fusing of heterogeneous alerts | |
CN112269640A (en) | Method for realizing life cycle management of container cloud component | |
CN116343112A (en) | Scene monitoring method, device, electronic equipment and storage medium | |
CN111737075A (en) | Execution sequence determination method and device, storage medium and electronic device | |
WO2015192664A1 (en) | Device monitoring method and apparatus | |
CN110708316A (en) | Method and system architecture for enterprise network security operation management | |
CN111813497A (en) | Container environment anomaly detection method, device, medium and computer equipment | |
CN113949652B (en) | User abnormal behavior detection method and device based on artificial intelligence and related equipment | |
CN116015819A (en) | SOAR-based attack behavior response method, device and processing equipment | |
CN112035839B (en) | Method and device for detecting competitive condition vulnerability exploitation | |
CN109218286B (en) | Method and device for realizing agent-free EDR (enhanced data Rate) in virtualization environment | |
CN114168951B (en) | Abnormality detection method and apparatus | |
CN106230666B (en) | A kind of monitoring method and monitoring system of service availability | |
CN112416530B (en) | Method and device for elastically managing cluster physical machine nodes and electronic equipment | |
CN114895609A (en) | Machine room monitoring method, device, equipment and medium | |
Lys et al. | Development of a Video Surveillance System for Motion Detection and Object Recognition | |
CN110874303B (en) | Data acquisition method, device and equipment | |
CN113055743A (en) | Method and system for intelligently pushing video | |
CN109327433A (en) | Threat cognitive method and system based on Run-time scenario analysis | |
CN116798204B (en) | Security method, security device, security equipment and storage medium |
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 |