CN112885014A - Early warning method, device, system and computer readable storage medium - Google Patents
Early warning method, device, system and computer readable storage medium Download PDFInfo
- Publication number
- CN112885014A CN112885014A CN202110053568.XA CN202110053568A CN112885014A CN 112885014 A CN112885014 A CN 112885014A CN 202110053568 A CN202110053568 A CN 202110053568A CN 112885014 A CN112885014 A CN 112885014A
- Authority
- CN
- China
- Prior art keywords
- construction site
- power construction
- electric power
- early warning
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000010276 construction Methods 0.000 claims abstract description 177
- 238000012544 monitoring process Methods 0.000 claims abstract description 111
- 238000000605 extraction Methods 0.000 claims abstract description 34
- 238000012806 monitoring device Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims description 29
- 238000004891 communication Methods 0.000 claims description 14
- 238000003384 imaging method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 abstract description 13
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 7
- 231100001261 hazardous Toxicity 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000009545 invasion Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The application relates to an early warning method, an early warning device, an early warning system and a computer-readable storage medium. The method receives an image of an electric power construction site from a monitoring device of the electric power construction site through an early warning device, wherein the electric power construction site includes a dangerous area. And performing feature extraction on the image of the electric power construction site to obtain a monitoring object in the electric power construction site. And determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value. The early warning device in the early warning method can receive the images of the electric power construction site in real time, process the images and output early warning information, the early warning device can finish the whole process independently, manual participation is not needed, and the influence of subjective factors is avoided. Meanwhile, the method identifies the monitored object in a characteristic extraction mode, can more accurately determine the monitored object so as to determine the distance between the dangerous area and the monitored object, and improves the early warning effect.
Description
Technical Field
The present application relates to the field of wireless communication technologies, and in particular, to an early warning method, apparatus, system, and computer-readable storage medium.
Background
The areas with higher danger coefficients often exist in electric power construction sites such as construction sites of each electric power infrastructure, transformer substations and the like, and if the dangerous areas cannot be safely monitored, safety accidents can occur, and huge economic losses are caused. In order to reduce the occurrence of safety accidents, danger early warning needs to be performed at a power grid construction site.
At present, a method for performing danger early warning on a power grid construction site is to deploy a large number of video monitoring devices in the power grid construction site, the video monitoring devices can monitor a dangerous area of the power grid construction site and transmit monitoring information to a background server, an administrator can check whether a person invades the dangerous area in the power grid construction site through the background server, and if an invasion object is found, danger early warning is immediately performed on the invasion object.
However, the site construction environment of the power grid construction site is complex, the risk factors are numerous, the risk early warning method is greatly influenced by subjective factors, and due to the fact that the safety knowledge of constructors is deficient, warning boards and regional risk behavior signs in a dangerous region are often ignored, and the early warning effect is poor.
Disclosure of Invention
The embodiment of the application provides an early warning method, an early warning device, an early warning system and a computer-readable storage medium, which can improve the early warning effect of danger in a power grid construction site and effectively reduce the occurrence of safety accidents.
A first aspect of an embodiment of the present application provides an early warning method, including:
the early warning device receives an image of the electric power construction site from monitoring equipment of the electric power construction site; the electric power construction site includes a hazardous area;
performing feature extraction on the image of the electric power construction site to obtain a monitoring object in the electric power construction site;
and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
In one embodiment, the feature extraction of the image of the power construction site to obtain the monitoring object includes:
inputting an image of the electric power construction site into the monitoring object identification model to obtain a monitoring object in the electric power construction site; the monitoring object identification model is used for identifying monitoring objects in the electric power construction environment.
In one embodiment, inputting an image of the power construction site into the monitoring object recognition model to obtain the monitoring object in the power construction site includes:
inputting the image of the electric power construction site into a background processing module of the monitoring object identification model to obtain a foreground target of the image of the electric power construction site;
and inputting the foreground target of the image of the power construction site into a contour extraction module of the monitoring object identification model, extracting the contour of the foreground target, and determining the monitoring object according to the contour of the foreground target.
In one embodiment, before inputting the foreground target of the image of the power construction site into the contour extraction module of the monitoring object recognition model, the method further comprises:
and removing an imaging fuzzy area of the foreground target by using a shadow processing module of the monitoring object recognition model to obtain the foreground target with clear edges.
In one embodiment, the monitored object comprises a constructor.
A second aspect of an embodiment of the present application provides an early warning apparatus, including:
the communication module is used for receiving the image of the electric power construction site from the monitoring equipment of the electric power construction site; the electric power construction site comprises a dangerous area;
the processing module is used for extracting the characteristics of the image of the electric power construction site to obtain a monitoring object in the electric power construction site; and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
A third aspect of the embodiments of the present application provides an early warning apparatus, including: a transceiver and a processor, wherein the transceiver is connected to the processor,
a transceiver for receiving an image of the power construction site from a monitoring device of the power construction site; the electric power construction site comprises a dangerous area;
the processor is used for extracting the characteristics of the image of the electric power construction site to obtain a monitoring object in the electric power construction site; and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
A fourth aspect of an embodiment of the present application provides an early warning system, including: the early warning device is in communication connection with the monitoring equipment;
the early warning device is used for receiving an image of the electric power construction site from the monitoring equipment of the electric power construction site; the electric power construction site comprises a dangerous area; performing feature extraction on the image of the electric power construction site to obtain a monitoring object in the electric power construction site; determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value;
and the monitoring equipment is used for acquiring images of the electric power construction site.
In one embodiment, the early warning device is equipment deployed at the edge of an electric power construction site.
A fifth aspect of embodiments of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the warning method of any one of the above.
The embodiment of the application provides an early warning method, an early warning device, a system and a computer readable storage medium. And finally, determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value. The early warning device in the method can receive the images of the electric power construction site in real time, process the images and output early warning information, and the early warning device can finish the whole early warning process independently without manual participation, so that the influence of subjective factors is avoided. Meanwhile, the early warning method identifies the monitored object in a characteristic extraction mode, so that the distance between the dangerous area and the monitored object can be determined more accurately by determining the monitored object, and the early warning effect is improved.
Drawings
FIG. 1 is a diagram of an exemplary early warning system;
FIG. 2 is a flow diagram of an early warning method in one embodiment;
FIG. 3 is a flow diagram illustrating steps of a warning method in another embodiment;
FIG. 4 is a block diagram of an early warning device according to an embodiment;
fig. 5 is a block diagram of a hardware configuration of the warning device in one embodiment.
Description of reference numerals:
301. a communication module; 302. a processing module; 401. a transceiver; 402. a processor.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The early warning method provided by the embodiment of the application can be applied to the early warning system shown in fig. 1. The early warning system comprises a monitoring device 100 and an early warning device 300. The monitoring apparatus 100 communicates with the early warning device 300 through a network. For example, the monitoring apparatus 100 collects an image of the power construction site and transmits the image of the power construction site to the early warning device 300. The early warning device 300 may receive the image of the power construction site, process the image to generate early warning information, and perform early warning on the dangerous condition of the monitored object.
The network may be a wireless network, a local area network, or a wide area network. The monitoring apparatus 100 communicates with the early warning device 300 through a network.
The devices in the system shown in fig. 1 include, but are not limited to, the monitoring device 100 and the early warning apparatus 300, and may also include other devices, which are not limited in this embodiment of the present application. For example, although fig. 1 only shows one monitoring device 100 and one warning device 300, the number of the monitoring devices 100 and/or the warning devices 300 is not meant to be limited, and the system may include a plurality of monitoring devices 100 and/or a plurality of warning devices 300, and different warning devices may correspond to the same monitoring device 100 and acquire images of the power construction site from the monitoring device 100, or different warning devices 300 may correspond to different monitoring devices 100 and acquire images of the power construction site from the respective corresponding monitoring devices 100.
Fig. 2 is a schematic flow chart of an early warning method provided in an embodiment of the present application, and is described by taking the application of the method to the early warning device in fig. 1 as an example, where the method includes the following steps:
s202, receiving an image of the electric power construction site from monitoring equipment of the electric power construction site; the electric power construction site includes a hazardous area.
Specifically, the monitoring device may be a camera, a video camera, or the like, which is disposed at a preset position of the electric power construction site, where the preset position of the electric power construction site may be a position of an edge area of the electric power construction site, and the number of the monitoring devices is at least one. Illustratively, the monitoring device may be an electronic eye device. The monitoring equipment is used for shooting images of the electric power construction site in real time, the images can reflect the field condition of the electric power construction site, and the early warning device can acquire the distribution condition of constructors in the electric power construction site through the images, so that subsequent danger early warning is facilitated. The image may be captured by one monitoring device, or each monitoring device may have its own capture range, and the image may be captured by a plurality of images captured by a plurality of monitoring devices. It should be noted that there are some areas with higher risk coefficients in the electric power construction site, that is, the dangerous areas described in the embodiments of the present application. When a person is in a dangerous area, the person can be injured, so that the dangerous area needs to be pre-warned for example by constructors or other external personnel, and personal injury of the constructors or other external personnel is avoided. The danger zone is a certain zone or a zone area, for example, the danger zone may be a zone where a high voltage device is installed or a zone where a radius is at a preset value centered on a location where a high voltage device is installed.
And S204, extracting the characteristics of the image of the electric power construction site to obtain a monitoring object in the electric power construction site.
Specifically, based on the image of the electric power construction site collected by the monitoring device, the monitoring device uploads the image to the early warning device, so that the early warning device performs feature extraction on the image, where the feature extraction may be, for example: and carrying out influence analysis, transformation and other processing on the image. The extracted features may be, for example, features having a human body image attribute or the like. The image is subjected to feature extraction to output a monitoring object in the electric power construction site, and optionally, the monitoring object can be a constructor.
S206, determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is smaller than or equal to a preset threshold value.
Specifically, the early warning device obtains the monitored object in the electric power construction site based on the steps, the obtained monitored object is mainly used for determining whether the monitored object is the target monitored object, and under the condition that the monitored object is the target monitored object, the early warning device carries out danger early warning on the monitored object. The determination may be by: and carrying out equal-proportion conversion according to the image distance between the monitored object and the dangerous area on the image of the electric power construction site to obtain the actual distance between the monitored object and the dangerous area, and if the actual distance is smaller than or equal to a preset threshold value, outputting early warning information by the early warning device. Optionally, the early warning device may output the early warning information in a manner of auditory stimulation to the target constructor, for example, an alarm module on the early warning device is used to play music, warning words, buzzing sounds and the like to the target constructor; the warning device on the early warning device can be used for sending a warning signal to the target constructor, and the warning signal can be sent to the target constructor. When the alarm module is a buzzer, the early warning information can be output in the form of intermittent buzzing sounds of 'click, click and click'; when the alarm module is a loudspeaker, the early warning information can be output in an audio mode of playing continuous 'danger ahead, do not approach'; when the alarm module is a light-emitting alarm device, the early warning information can be output in the form of continuous flashing red light. It should be noted that the alarm device may also have other external expression forms, and the early warning information may also be output in other forms, which are only examples and cannot cover all implementation manners, and further description of other implementation manners is not repeated here.
According to the early warning method provided by the embodiment of the application, the image of the electric power construction site is received from the monitoring equipment of the electric power construction site through the early warning device, wherein the electric power construction site comprises a dangerous area, the image of the electric power construction site is subjected to feature extraction, and a monitored object in the electric power construction site is obtained. And finally, determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value. The early warning device in the method can receive the images of the electric power construction site in real time, process the images and output early warning information, and the early warning device can finish the whole early warning process independently without manual participation, so that the influence of subjective factors is avoided. Meanwhile, the early warning method identifies the monitored object in a characteristic extraction mode, so that the distance between the dangerous area and the monitored object can be determined more accurately by determining the monitored object, and the early warning effect is improved.
In an optional embodiment, the embodiment relates to an optional process of how the early warning device performs feature extraction on an image of an electric power construction site to obtain a monitored object. On the basis of the foregoing embodiment, the foregoing S204 may include the following steps:
inputting an image of the electric power construction site into the monitoring object identification model to obtain a monitoring object in the electric power construction site; the monitoring object identification model is used for identifying monitoring objects in the electric power construction environment.
Specifically, the monitoring object recognition model may be constructed based on a deep learning neural network by performing big data supervised learning on features of human body images of a large number of constructors or human body images of non-constructors to extract target feature information. For field data with high collection difficulty, a monitoring object recognition model can be constructed in a mode of small sample training, reinforcement learning and self-confrontation learning. Since the monitoring object recognition model is used for recognizing the monitoring object in the electric power construction environment, the monitoring object can be output by inputting the image of the electric power construction site to the monitoring object recognition model.
According to the early warning method provided by the embodiment of the application, the monitoring object recognition model is used for recognizing the monitoring object of the image of the electric power construction site, and the monitoring object recognition model is obtained through training of a large amount of real data according to the particularity of the electric power environment. The identification range is expanded, so that the obtained monitored object is more accurate, and further, the accuracy of early warning can be improved.
In an optional embodiment, fig. 3 is a schematic flow chart of another early warning method provided in an embodiment of the present application, and this embodiment relates to an optional process of how the above-mentioned early warning device inputs an image of an electric power construction site into a monitored object identification model to obtain a monitored object in the electric power construction site. On the basis of the foregoing embodiment, the foregoing S204 may include the following steps:
s2041, inputting the image of the electric power construction site into a background processing module of the monitoring object identification model, and obtaining a foreground target of the image of the electric power construction site.
Specifically, when an image of an electric power construction site is input into a monitoring object recognition model, a background processing module of the monitoring object recognition model can segment a foreground target in the image from a background, establish a background analysis model, perform differential operation on the background model and a current image, and subtract consistent background information to obtain the foreground target, wherein the background analysis model comprises a static background analysis model and a dynamic background analysis model. The static background analysis model is used for analyzing clear input images of the edge imaging area, and the dynamic background analysis model is used for analyzing fuzzy input images of the edge imaging area.
S2042, inputting the foreground target of the image of the power construction site into the contour extraction module of the monitoring object recognition model, extracting the contour of the foreground target, and determining the monitoring object according to the contour of the foreground target.
Specifically, based on the foreground target output by the background processing module of the monitored object identification model, the contour extraction module of the monitored object identification model extracts the contour of the foreground target to obtain the contour of the foreground target, wherein the contour of the foreground target can be the contour of an animal or the contour of a person, and then the early warning device can judge whether the monitored object exists in the image according to the contour. It should be noted that the method provided by the embodiment of the present application is mainly used for human risk early warning, so that when the early warning device determines that the contour of the foreground target is the contour of one person, it is determined that the monitored object exists in the image.
According to the early warning method provided by the embodiment of the application, the image is processed through the multiple modules to obtain an identification result, a reliable basis is provided for the early warning device to judge whether the image has the monitored object, and the accuracy of early warning is further improved.
In an optional embodiment, the present embodiment provides an optional process of processing an image before inputting a foreground target of the image of the power construction site into the contour extraction module of the monitoring object recognition model, and on the basis of the above embodiment, before the step S2042, the following steps may be included:
and removing an imaging fuzzy area of the foreground target by using a shadow processing module of the monitoring object recognition model to obtain the foreground target with clear edges.
Specifically, because the moving target always appears along with its shadow, the image that monitoring equipment gathered is the image of monitoring object when moving, then can make monitoring object's physical shape change, if directly carry out the profile extraction to this monitoring object, the condition that can cause the erroneous judgement appears, then will be unfavorable for early warning device and carry out danger early warning. Therefore, before contour extraction is performed on the foreground target, processing for removing an imaging fuzzy region of the foreground target needs to be performed on the foreground target to obtain a foreground target image with clear contour, so that contour extraction is performed on the foreground target in the following process.
According to the early warning method provided by the embodiment of the application, before the contour of the foreground target is extracted, the operation of removing the imaging fuzzy area of the foreground target is carried out on the foreground target, so that the contour of the foreground target is clear, a follow-up contour extraction module can conveniently carry out contour extraction operation on the foreground target, the image quality of the foreground target is improved, a reliable basis is provided for the early warning device to judge whether a monitored object exists in the image, and the accuracy of early warning is further improved.
In an alternative embodiment, the monitored object comprises a construction worker.
Specifically, the monitoring object can be external personnel, also can be the constructor in electric power construction place, because the probability that external personnel invade electric power construction place danger area is less, so this application embodiment mainly provides early warning information for the constructor in electric power construction place, ensures constructor's personal safety, can reduce economic loss simultaneously.
The embodiment of the present application provides an early warning device, and fig. 4 is a block diagram of a structure of the early warning device provided in the embodiment of the present application, where the device includes: a communication module 301 and a processing module 302, the communication module 301 being communicatively coupled to the processing module 302,
a communication module 301 for receiving an image of the power construction site from a monitoring device of the power construction site; the electric power construction site comprises a dangerous area;
the processing module 302 is configured to perform feature extraction on an image of an electric power construction site to obtain a monitoring object in the electric power construction site; and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
Specifically, the communication module 301 may implement wireless communication or wired communication between the early warning apparatus and the monitoring device. The processing module 302 may be a single chip.
In one embodiment, the processing module 302 is specifically configured to input an image of the electric power construction site into the monitoring object identification model, and obtain a monitoring object in the electric power construction site; the monitoring object identification model is used for identifying monitoring objects in the electric power construction environment.
In one embodiment, the processing module 302 is specifically configured to input the image of the electric power construction site into the background processing module 302 of the monitored object identification model, and obtain a foreground target of the image of the electric power construction site; and inputting the foreground target of the image of the electric power construction site into a contour extraction module of the monitoring object identification model, extracting the contour of the foreground target, and determining the monitoring object according to the contour of the foreground target.
In an embodiment, the processing module 302 is specifically configured to remove an imaging blur area of the foreground object by using the shadow processing module 302 of the monitored object recognition model, so as to obtain the foreground object with a clear edge.
In one embodiment, the monitored objects include construction personnel.
The embodiment of the present application provides an early warning device, and fig. 5 is a hardware structure block diagram of the early warning device provided in the embodiment of the present application, where the early warning device includes: a transceiver 401 and a processor 402, the transceiver 401 communicatively coupled to the processor 402,
a transceiver 401 for receiving an image of the power construction site from a monitoring device of the power construction site; the electric power construction site comprises a dangerous area;
a processor 402, configured to perform feature extraction on an image of an electric power construction site, to obtain a monitoring object in the electric power construction site; and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
In one embodiment, the processor 402 is specifically configured to input an image of the power construction site into the monitoring object identification model, and obtain a monitoring object in the power construction site; the monitoring object identification model is used for identifying monitoring objects in the electric power construction environment.
In one embodiment, the processor 402 is specifically configured to input the image of the electric power construction site into the background processing module 302 of the monitored object identification model, and obtain a foreground target of the image of the electric power construction site; and inputting the foreground target of the image of the electric power construction site into a contour extraction module of the monitoring object identification model, extracting the contour of the foreground target, and determining the monitoring object according to the contour of the foreground target.
In an embodiment, the processor 402 is specifically configured to remove an imaging blur area of a foreground object by using the shadow processing module 302 for monitoring an object recognition model, so as to obtain the foreground object with a clear edge.
In one embodiment, the monitored objects include construction personnel.
An embodiment of the present application provides an early warning system, see fig. 1, the system includes: the early warning device is in communication connection with the monitoring equipment;
the early warning device is used for receiving an image of the electric power construction site from the monitoring equipment of the electric power construction site; the electric power construction site comprises a dangerous area; performing feature extraction on the image of the electric power construction site to obtain a monitoring object in the electric power construction site; determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value;
and the monitoring equipment is used for acquiring images of the electric power construction site.
In one embodiment, the early warning device is specifically configured to input an image of the power construction site into the monitored object identification model to obtain a monitored object in the power construction site; the monitoring object identification model is used for identifying monitoring objects in the electric power construction environment.
In one embodiment, the early warning device is specifically configured to input an image of the electric power construction site into a background processing module of the monitored object identification model, and obtain a foreground target of the image of the electric power construction site; and inputting the foreground target of the image of the electric power construction site into a contour extraction module of the monitoring object identification model, extracting the contour of the foreground target, and determining the monitoring object according to the contour of the foreground target.
In one embodiment, the early warning device is specifically configured to remove an imaging blur area of a foreground target by using a shadow processing module of the monitored object recognition model, and obtain the foreground target with clear edges.
In one embodiment, the early warning device is equipment deployed at the edge of a power construction site.
In one embodiment, the monitored objects include construction personnel.
An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the following steps:
the early warning device receives an image of the electric power construction site from monitoring equipment of the electric power construction site; the electric power construction site includes a hazardous area;
performing feature extraction on the image of the electric power construction site to obtain a monitoring object in the electric power construction site;
and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
In one embodiment, the computer program when executed by the processor further performs the steps of: inputting an image of the electric power construction site into the monitoring object identification model to obtain a monitoring object in the electric power construction site; the monitoring object identification model is used for identifying monitoring objects in the electric power construction environment.
In one embodiment, the computer program when executed by the processor further performs the steps of: inputting the image of the electric power construction site into a background processing module of the monitoring object identification model to obtain a foreground target of the image of the electric power construction site; and inputting the foreground target of the image of the electric power construction site into a contour extraction module of the monitoring object identification model, extracting the contour of the foreground target, and determining the monitoring object according to the contour of the foreground target.
In one embodiment, the computer program when executed by the processor further performs the steps of: and removing an imaging fuzzy area of the foreground target by using a shadow processing module of the monitoring object recognition model to obtain the foreground target with clear edges.
In one embodiment, the monitored objects include construction personnel.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An early warning method, characterized in that the method comprises:
the method comprises the steps that an early warning device receives an image of an electric power construction site from monitoring equipment of the electric power construction site; the electric power construction site comprises a dangerous area;
performing feature extraction on the image of the electric power construction site to obtain a monitoring object in the electric power construction site;
and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
2. The method according to claim 1, wherein the extracting features of the image of the power construction site to obtain the monitoring object comprises:
inputting the image of the electric power construction site into a monitoring object identification model to obtain a monitoring object in the electric power construction site; the monitoring object identification model is used for identifying monitoring objects in the electric power construction environment.
3. The method according to claim 2, wherein the inputting the image of the power construction site into a monitoring object recognition model to obtain the monitoring object in the power construction site comprises:
inputting the image of the electric power construction site into a background processing module of the monitoring object identification model to obtain a foreground target of the image of the electric power construction site;
inputting a foreground target of the image of the electric power construction site into a contour extraction module of the monitoring object identification model, extracting a contour of the foreground target, and determining the monitoring object according to the contour of the foreground target.
4. The method of claim 3, wherein before inputting the foreground target of the image of the power construction site into the contour extraction module of the monitored object recognition model, the method further comprises:
and removing the imaging fuzzy area of the foreground target by utilizing a shadow processing module of the monitoring object recognition model to obtain the foreground target with clear edges.
5. The method of any one of claims 1-4, wherein the monitored object comprises a construction worker.
6. An early warning device, the device comprising:
the system comprises a communication module, a monitoring module and a display module, wherein the communication module is used for receiving an image of an electric power construction site from monitoring equipment of the electric power construction site; the electric power construction site comprises a dangerous area;
the processing module is used for extracting the characteristics of the image of the electric power construction site to obtain a monitoring object in the electric power construction site; and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
7. The early warning device is characterized by comprising a transceiver and a processor,
the transceiver is used for receiving an image of the electric power construction site from a monitoring device of the electric power construction site; the electric power construction site comprises a dangerous area;
the processor is used for extracting features of the image of the electric power construction site to obtain a monitoring object in the electric power construction site; and determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value.
8. An early warning system, the system comprising: the early warning device is in communication connection with the monitoring equipment;
the early warning device is used for receiving an image of the electric power construction site from monitoring equipment of the electric power construction site; the electric power construction site comprises a dangerous area; performing feature extraction on the image of the electric power construction site to obtain a monitoring object in the electric power construction site; determining the distance between the monitored object and the dangerous area, and outputting early warning information if the distance between the monitored object and the dangerous area is less than or equal to a preset threshold value;
the monitoring equipment is used for acquiring images of the electric power construction site.
9. The system of claim 8, wherein the pre-warning device is equipment deployed at the edge of the power construction site.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the warning method of one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110053568.XA CN112885014A (en) | 2021-01-15 | 2021-01-15 | Early warning method, device, system and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110053568.XA CN112885014A (en) | 2021-01-15 | 2021-01-15 | Early warning method, device, system and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112885014A true CN112885014A (en) | 2021-06-01 |
Family
ID=76048030
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110053568.XA Pending CN112885014A (en) | 2021-01-15 | 2021-01-15 | Early warning method, device, system and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112885014A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113627405A (en) * | 2021-10-12 | 2021-11-09 | 环球数科集团有限公司 | Scenic spot danger monitoring method and device and computer equipment |
CN115082545A (en) * | 2022-06-08 | 2022-09-20 | 国网黑龙江省电力有限公司大庆供电公司 | Safety system applied to electric power field |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102147869A (en) * | 2011-03-31 | 2011-08-10 | 上海交通大学 | Pedestrian detection method based on foreground analysis and pattern recognition |
CN104063692A (en) * | 2014-06-30 | 2014-09-24 | 武汉烽火众智数字技术有限责任公司 | Method and system for pedestrian positioning detection |
JP6206627B1 (en) * | 2016-12-05 | 2017-10-04 | 日本電気株式会社 | Information processing apparatus, control method, and program |
CN110110657A (en) * | 2019-05-07 | 2019-08-09 | 中冶赛迪重庆信息技术有限公司 | Method for early warning, device, equipment and the storage medium of visual identity danger |
CN111083435A (en) * | 2019-10-27 | 2020-04-28 | 恒大智慧科技有限公司 | Security monitoring method and device and computer readable storage medium |
-
2021
- 2021-01-15 CN CN202110053568.XA patent/CN112885014A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102147869A (en) * | 2011-03-31 | 2011-08-10 | 上海交通大学 | Pedestrian detection method based on foreground analysis and pattern recognition |
CN104063692A (en) * | 2014-06-30 | 2014-09-24 | 武汉烽火众智数字技术有限责任公司 | Method and system for pedestrian positioning detection |
JP6206627B1 (en) * | 2016-12-05 | 2017-10-04 | 日本電気株式会社 | Information processing apparatus, control method, and program |
CN110110657A (en) * | 2019-05-07 | 2019-08-09 | 中冶赛迪重庆信息技术有限公司 | Method for early warning, device, equipment and the storage medium of visual identity danger |
CN111083435A (en) * | 2019-10-27 | 2020-04-28 | 恒大智慧科技有限公司 | Security monitoring method and device and computer readable storage medium |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113627405A (en) * | 2021-10-12 | 2021-11-09 | 环球数科集团有限公司 | Scenic spot danger monitoring method and device and computer equipment |
CN115082545A (en) * | 2022-06-08 | 2022-09-20 | 国网黑龙江省电力有限公司大庆供电公司 | Safety system applied to electric power field |
CN115082545B (en) * | 2022-06-08 | 2023-02-07 | 国网黑龙江省电力有限公司大庆供电公司 | Safety system applied to electric power field |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111797890A (en) | Method and system for detecting defects of power transmission line equipment | |
CN113191699A (en) | Power distribution construction site safety supervision method | |
CN112885014A (en) | Early warning method, device, system and computer readable storage medium | |
CN111898581A (en) | Animal detection method, device, electronic equipment and readable storage medium | |
CN111062303A (en) | Image processing method, system and computer storage medium | |
CN112257500A (en) | Intelligent image recognition system and method for power equipment based on cloud edge cooperation technology | |
CN114782897A (en) | Dangerous behavior detection method and system based on machine vision and deep learning | |
CN114360209B (en) | Video behavior recognition security system based on deep learning | |
CN111126411B (en) | Abnormal behavior identification method and device | |
CN111860187A (en) | High-precision worn mask identification method and system | |
CN113627321A (en) | Image identification method and device based on artificial intelligence and computer equipment | |
KR20200123324A (en) | A method for pig segmentation using connected component analysis and yolo algorithm | |
CN111695404B (en) | Pedestrian falling detection method and device, electronic equipment and storage medium | |
CN111325708B (en) | Transmission line detection method and server | |
CN106803937B (en) | Double-camera video monitoring method, system and monitoring device with text log | |
CN116433029A (en) | Power operation risk assessment method, system, equipment and storage medium | |
CN114821486B (en) | Personnel identification method in power operation scene | |
CN113536842A (en) | Electric power operator safety dressing identification method and device | |
CN111461655A (en) | Personnel management system | |
CN113762115B (en) | Distribution network operator behavior detection method based on key point detection | |
CN115909212A (en) | Real-time early warning method for typical violation behaviors of power operation | |
CN113609937B (en) | Emergency processing method, system and storage medium for urban rail transit | |
CN116933002A (en) | Action detection method and device, terminal equipment and storage medium | |
CN115205747A (en) | Automatic road detection system based on image recognition | |
CN112861711A (en) | Regional intrusion detection method and device, electronic 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 | ||
CB02 | Change of applicant information |
Address after: 510802 5-1, Hongzhu Road, Xinhua Street, Huadu District, Guangzhou City, Guangdong Province Applicant after: China Southern Power Grid Big Data Service Co.,Ltd. Address before: 510800 5-1, Hongzhu Road, Xinhua Street, Huadu District, Guangzhou City, Guangdong Province Applicant before: Guangzhou suinengtong Energy Technology Co.,Ltd. |
|
CB02 | Change of applicant information | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210601 |
|
RJ01 | Rejection of invention patent application after publication |