CN114241420A - Fire operation detection method and device - Google Patents
Fire operation detection method and device Download PDFInfo
- Publication number
- CN114241420A CN114241420A CN202111564698.6A CN202111564698A CN114241420A CN 114241420 A CN114241420 A CN 114241420A CN 202111564698 A CN202111564698 A CN 202111564698A CN 114241420 A CN114241420 A CN 114241420A
- Authority
- CN
- China
- Prior art keywords
- target detection
- layer
- fire
- image
- data
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Alarm Systems (AREA)
Abstract
The application discloses a fire operation detection method and device, belongs to the technical field of safety production, and is used for realizing high-precision and high-efficiency monitoring of power plant fire operation safety production. The method comprises the following steps: determining a target detection image through an application layer; and inputting the target detection image into a target detection model through an application layer, and outputting the target coordinates of the firing operation in the target detection image.
Description
Technical Field
The application belongs to the technical field of safety production, and particularly relates to a fire operation detection method and device.
Background
The sparking operation refers to welding and cutting operations in a forbidden zone and temporary operations on surfaces which may generate flame, spark and incandescence in flammable and explosive places using torches, electric drills, grinding wheels and the like. In order to ensure the safety of production, personnel and the like, the fire operation detection is required to be carried out on the construction process in different places.
At present, the detection method of the fire operation is realized by utilizing an image of a manual monitoring camera; and the second is to use image matching technology. Manual detection can achieve good results, but consumes human resources. The image matching technology depends on image similarity, but scenes in reality are often very different, images used for matching are not enough to cover all application scenes, so that the detection precision is not high, meanwhile, an image to be detected needs to be compared with each matched image, and the detection efficiency is low under the condition of very large data volume.
Disclosure of Invention
The embodiment of the application provides a method and a device for detecting a fire operation, which can quickly and accurately detect the target of the fire operation in a monitoring image and realize high-precision and high-efficiency monitoring on the safety production of the fire operation of a power plant.
In a first aspect, an embodiment of the present application provides a fire operation detection method, including: determining a target detection image through an application layer; and inputting the target detection image into a target detection model through an application layer, and outputting the target coordinates of the firing operation in the target detection image.
In a second aspect, the present application provides a device for detecting a fire operation, the device including: the determining module is used for determining a target detection image through an application layer; and the application module is used for inputting the target detection image into a target detection model through an application layer and outputting the target coordinates of the fire operation in the target detection image.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor, where the program or instructions, when executed by the processor, implement the steps of the method for detecting a fire.
In a fourth aspect, the present application provides a readable storage medium, on which a program or instructions are stored, which when executed by a processor implement the steps of the method for detecting a fire.
In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement the method for detecting a fire operation according to the first aspect.
In the embodiment of the application, a target detection image is determined through an application layer; the target detection image is input into a target detection model through an application layer, the target coordinate of the firing operation in the target detection image is output, the target of the firing operation in the monitoring image can be detected quickly and accurately, and the high-precision and high-efficiency monitoring of the safe production of the firing operation of the power plant is realized.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting a fire operation according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart of another method for detecting a fire in accordance with an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart of another method for detecting a fire in accordance with an embodiment of the present disclosure;
FIG. 4 is a schematic flow chart of another method for detecting a fire in accordance with an embodiment of the present disclosure;
FIG. 5 is a schematic flow chart of another method for detecting a fire in accordance with an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a fire work detection device according to an embodiment of the present application;
FIG. 7 is a schematic structural diagram of another fire detection device provided in the embodiments of the present application;
FIG. 8 is a schematic structural diagram of another fire detection device provided in an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.
The method for detecting a fire operation provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.
Fig. 1 illustrates a method for detecting a fire operation according to an embodiment of the present invention, which may be performed by an electronic device, and the electronic device may include at least one of the following: a server, a server cluster, a Network Attached Storage (NAS), a Personal Computer (PC), a Television (TV), a teller machine, and a self-service machine. In other words, the method may be performed by software or hardware installed in the electronic device, the method comprising the steps of:
s103: and determining a target detection image through the application layer.
The target detection image is an image of the construction process at different places shot by the camera. The application layer is used as one layer in a network system structure, is directly connected with an application program interface and provides common network application services, and is mainly used for preprocessing construction process images of different places shot by a camera to obtain the target detection image.
S104: and inputting the target detection image into a target detection model through an application layer, and outputting the target coordinates of the firing operation in the target detection image.
In this step, a target detection model for detecting a fire operation in an image is stored in the application layer, the input of the target detection model is a picture, and the output of the target detection model is a target coordinate of the fire operation in the picture. Inputting the target detection image into the target detection model, carrying out target detection on the target detection image in the fire operation, and outputting the target coordinate of the fire operation in the target detection image.
In one implementation, the target detection model in step S104 includes a target detection algorithm model based on a deep neural network, and optionally, the target detection algorithm may include a YOLOv4 (young Only Look Once version 4, YOLOv4) algorithm, an SSD (SSD) algorithm, and the like. The target detection algorithm model based on the deep neural network can be used for detecting target detection images covering more different types of application scenes, and targets of fire operation in the images can be quickly and accurately detected.
According to the method for detecting the operation of the fire, provided by the embodiment of the invention, a target detection image is determined through an application layer; the target detection image is input into a target detection model through an application layer, the target coordinate of the firing operation in the target detection image is output, the target of the firing operation in the monitoring image can be detected quickly and accurately, and the high-precision and high-efficiency monitoring of the safe production of the firing operation of the power plant is realized.
Fig. 2 illustrates a method for detecting a fire operation according to another embodiment of the present invention, which may be performed by an electronic device, and the electronic device may include at least one of the following: server, server cluster, NAS, PC, TV, teller machine, self-service machine. In other words, the method may be performed by software or hardware installed in the electronic device, the method comprising the steps of:
s203: and sampling the image data in the data layer at a preset sampling frequency to obtain a plurality of target detection images.
The method comprises the steps of receiving a preset sampling frequency input by a user through a display layer, sampling pictures from a data layer in which image data are stored at the preset sampling frequency, and outputting a plurality of target detection images at the output frequency which is the same as the sampling frequency, so that automatic and ordered monitoring of safety production within a period of time is realized. The data layer is used as one layer of a network architecture, and is mainly used for storing a large amount of video image data acquired by the camera and providing computing resources in the step. The display layer is used as the uppermost layer in the network architecture and is mainly used for being connected with an input control terminal in the step to realize interaction with a user, such as receiving the opening and closing operations of the target detection model by the user, receiving the parameter setting of the target detection model by the user, receiving the setting of the preset sampling frequency by the user and the like.
S204: and inputting the target detection images into the target detection model, and outputting a plurality of target coordinates of a plurality of fire jobs in the target detection images.
Wherein the target detection model is trained from training data. This step outputs a plurality of target coordinates of a plurality of firing jobs in the plurality of target detection images by sequentially inputting the plurality of target detection images into the target detection model at the same frequency as the frequency output in step S204. The training process of the target detection model comprises the steps of selecting a model optimization target, determining an optimization strategy and the like.
In one implementation, the target detection model in step S204 may include a deep neural network-based target detection algorithm model. The step may be described in step S104 in the embodiment of fig. 1, and repeated descriptions of the repeated parts are omitted here.
According to the method for detecting the operation of the fire, provided by the embodiment of the invention, a target detection image is determined through an application layer; the target detection image is input into a target detection model through an application layer, the target coordinate of the firing operation in the target detection image is output, the target of the firing operation in the monitoring image can be detected quickly and accurately, and the high-precision and high-efficiency monitoring of the safe production of the firing operation of the power plant is realized.
According to the detection method for the fire operation, provided by the embodiment of the invention, a plurality of target detection images are obtained by sampling image data in a data layer at a preset sampling frequency, wherein the preset sampling frequency is determined by receiving input of a user through a display layer, and the image data are stored in the data layer; and inputting the target detection images into the target detection model, and outputting a plurality of target coordinates of a plurality of fire operations in the target detection images, wherein the target detection model is obtained by training data, so that the targets of the fire operations in the monitoring images can be quickly and accurately detected, and the high-precision, high-efficiency and orderly monitoring of the safety production of the fire operations of the power plant is realized.
Fig. 3 illustrates a method for detecting a fire operation according to another embodiment of the present invention, which may be performed by an electronic device, and the electronic device may include at least one of the following: server, server cluster, NAS, PC, TV, teller machine, self-service machine. In other words, the method may be performed by software or hardware installed in the electronic device, the method comprising the steps of:
s301: and extracting image data from a video stream through a perception layer, wherein the video stream is from different monitoring equipment and/or different servers, and the image data is used for obtaining the training data and/or the target detection image.
Extracting each frame of picture from video streams from different types of monitoring equipment such as cameras and the like and/or different servers through a perception layer to obtain a large amount of image data with wide coverage, wherein the image data is used for obtaining the training data and/or the target detection image, the perception layer is used as the lowest layer in a network architecture and is a key part of information acquisition, and the perception layer is mainly used for connecting different monitoring equipment and/or different servers and acquiring image data.
By extracting image data from video streams from different monitoring devices and/or different servers, wherein the image data is used for obtaining the training data and/or the target detection image, on one hand, when the image data is used for training the target detection model, the obtained target detection model has more accurate detection effect, more robust model and strong migratory capability, and on the other hand, when the image data is used for obtaining the target detection image, the detection range is wider and the detection is more accurate.
S302: and transmitting the image data to the data layer through a transmission device, and storing the image data through the data layer.
In the step, the image data is transmitted to the data layer through the transmission equipment, the data layer stores the image data, the transmission and the storage can be separated, the detection can be more flexible, the unified deployment and scheduling can be realized, meanwhile, the mobility is strong, and the detection efficiency is improved.
In one implementation, the transmission device includes a switch. Optionally, the switch includes an enterprise-level gigabit switch, and the switch supports not less than 44 port gigabit optical port switching and 4 gigabit optical port upstream.
In one implementation, the data layer may include at least one of the following hardware devices: 1) the GPU server needs to: the model is as follows: a rack-mounted 4U server; GPU: the single machine needs to support 8 GPUs; GPU single card: the CUDA core number is greater than 5000, the single-precision floating point performance is not lower than 14TFlops, the video memory is not less than 10GB, and the video memory Bit width is not lower than 300 bits; a CPU: the single machine configuration is not lower than 2 Intel Zhiqiangyin 421010 cores 20 threads x2, 2.2 GHz; memory: the single machine configuration is not less than 128GB, DDR 4; hard disk: the single machine configuration SSD hard disk is more than or equal to 1TB, and the SATA hard disk is more than or equal to 8 TB; power supply: the single machine configuration is not lower than 2KW, and 1+1 redundancy; network card: not less than 1 10G network card (ten-gigabit network card); operating the system: CentOS 7.4 and above or ubuntu18.04 and above. 2) The storage facility requirements are as follows: and configuring the storage capacity of at least 1TB according to the video path number and the storage market. 3) The requirements of the switch are as follows: the enterprise-level gigabit switch supports switching of gigabit optical ports of not less than 44 ports and uplink of 4 gigabit optical ports. 4) The database requirements are as follows: the analytic database meets the requirement of real-time query of video big data.
S303: and determining a target detection image through the application layer.
The step may be described in step S103 in the embodiment of fig. 1, and repeated descriptions of the repeated parts are omitted here.
S304: and inputting the target detection image into a target detection model through an application layer, and outputting the target coordinates of the firing operation in the target detection image.
The step may be described in step S104 in the embodiment of fig. 1, and repeated descriptions of the repeated parts are omitted here.
In an implementation manner, the step S303 may implement the step described as S203 in the embodiment of fig. 2, and repeated descriptions of the repeated parts are omitted here.
In an implementation manner, the step S304 may implement the step described as S204 in the embodiment of fig. 2, and repeated descriptions for repeated parts are omitted here.
According to the method for detecting the operation of the fire, provided by the embodiment of the invention, a target detection image is determined through an application layer; the target detection image is input into a target detection model through an application layer, the target coordinate of the firing operation in the target detection image is output, the target of the firing operation in the monitoring image can be detected quickly and accurately, and the high-precision and high-efficiency monitoring of the safe production of the firing operation of the power plant is realized.
According to the method for detecting the fire operation, provided by the embodiment of the invention, image data are extracted from video streams through a sensing layer, wherein the video streams come from different monitoring equipment and/or different servers, and the image data are used for obtaining the training data and/or the target detection image; transmitting the image data to the data layer through a transmission device, storing the image data through the data layer, and determining a target detection image through an application layer; the target detection image is input into the target detection model through the application layer, the target coordinate of the firing operation in the target detection image is output, a target detection algorithm which is more accurate in detection, wider in detection range, more robust in model and stronger in migratory ability can be obtained and used for quickly and accurately detecting the firing operation target in the monitoring image, high-precision, high-efficiency and orderly monitoring of power plant firing operation safety production is achieved, and meanwhile unified deployment of power plant firing operation detection is achieved.
Fig. 4 illustrates a method for detecting a fire operation according to an embodiment of the present invention, which may be performed by an electronic device, and the electronic device may include at least one of the following: server, server cluster, NAS, PC, TV, teller machine, self-service machine. In other words, the method may be performed by software or hardware installed in the electronic device, the method comprising the steps of:
s401: and extracting image data from a video stream through a perception layer, wherein the video stream is from different monitoring equipment and/or different servers, and the image data is used for obtaining the training data and/or the target detection image.
The step may be the description of step S301 in the embodiment of fig. 3, and repeated descriptions of the repeated parts are omitted here.
S402: and transmitting the image data to the data layer through a transmission device, and storing the image data through the data layer.
The step may be the description of step S302 in the embodiment of fig. 3, and repeated descriptions of the repeated parts are omitted here.
S403: and sampling image data in a data layer at a preset sampling frequency to obtain a plurality of target detection images, wherein the preset sampling frequency is determined by receiving input of a user through a display layer, and the image data is stored in the data layer.
The step may be described in step S203 in the embodiment of fig. 2, and repeated descriptions of the repeated parts are omitted here.
In an implementation manner, step S403 may also implement the step described as S103 in the embodiment of fig. 1, and repeated descriptions of the repeated parts are omitted here.
S404: and inputting the target detection images into the target detection model, and outputting a plurality of target coordinates of a plurality of fire jobs in the target detection images, wherein the target detection model is trained by training data.
The step may be described in step S204 in the embodiment of fig. 2, and repeated descriptions of the repeated parts are omitted here.
In an implementation manner, step S404 may also implement the step described as S104 in the embodiment of fig. 1, and repeated descriptions for repeated parts are omitted here.
S405: displaying the plurality of target detection images through a display layer, wherein the plurality of target detection images are marked with the plurality of firing operations.
The display layer is mainly used for being connected with the output control terminal in the step and displaying information such as the detection result. Specifically, after receiving a plurality of target coordinates of a plurality of firing jobs in the plurality of target detection images output by the application layer, marking the plurality of target coordinates on the corresponding plurality of target detection images through the display layer, and displaying the plurality of target detection images.
In one implementation, step S405 in this embodiment includes: displaying statistical data of the plurality of fire works through a display layer, wherein the statistical data comprises the time of the plurality of fire works and the frequency of the fire works in a preset time period.
In another implementation manner, step S405 in this embodiment includes: controlling, by a presentation layer, playback of a video over a first time period, wherein the first time period includes at least one of the times of the plurality of fire jobs, the video over the first time period being obtained from the data layer.
According to the method for detecting the operation of the fire, provided by the embodiment of the invention, a target detection image is determined through an application layer; the target detection image is input into a target detection model through an application layer, the target coordinate of the firing operation in the target detection image is output, the target of the firing operation in the monitoring image can be detected quickly and accurately, and the high-precision and high-efficiency monitoring of the safe production of the firing operation of the power plant is realized.
According to the fire operation detection method provided by the embodiment of the invention, image data are extracted from a video stream through a sensing layer, wherein the video stream is from different monitoring equipment and/or different servers, the image data are used for obtaining the training data and/or the target detection image, and a target detection algorithm with more accurate detection, wider detection range, more robust model and stronger migratable capability can be obtained.
According to the method for detecting the dynamic fire operation, the image data are transmitted to the data layer through the transmission equipment, the image data are stored through the data layer, the target detection image is determined through the application layer, the target detection image is input into the target detection model through the application layer, the target coordinate of the dynamic fire operation in the target detection image is output, the uniform deployment and scheduling of the dynamic fire operation detection of the power plant are achieved, and the control is flexible.
According to the method for detecting the sparking operation, provided by the embodiment of the invention, after the target coordinates of the sparking operations in the target detection images are obtained, the target detection images are displayed through a display layer, wherein the target detection images are marked with the sparking operations; and/or displaying statistical data of the plurality of fire jobs through a display layer, wherein the statistical data comprises the time of the plurality of fire jobs and the frequency of the fire jobs within a predetermined time period; and/or through the broadcast of video in the first time quantum of show layer control, wherein the first time quantum contains at least one in a plurality of time of the operation of starting a fire, the video is followed in the first time quantum the data layer is obtained, can integrate the show of operation of starting a fire testing result, data summary analysis, video playback, algorithm configuration to show layer unified management and dispatch, realize the visual and unified management of operation of starting a fire control monitoring.
It should be noted that in the method for detecting a fire operation provided in the embodiment of the present application, the execution subject may be a fire operation detection management system, and the fire operation detection management system may use multiple layers in a network architecture when executing the method for detecting a fire operation, and specifically may include the sensing layer, the data layer, the application layer, the presentation layer, and the like.
In the method for detecting a fire work according to the embodiment of the present application, the executing body may be a fire work detecting device or a control module for executing the fire work detecting method in the fire work detecting device. In the embodiment of the present application, a method for detecting a fire operation performed by a fire operation detection device is taken as an example, and a fire operation detection device provided in the embodiment of the present application is described.
Fig. 5 is a schematic structural diagram illustrating a fire detection device according to an embodiment of the present invention. As shown in fig. 5, the fire work detection device 500 includes: a determination module 503 and an application module 504.
A determining module 503, configured to determine a target detection image through an application layer;
the application module 504 is configured to input the target detection image into a target detection model through an application layer, and output target coordinates of a fire operation in the target detection image.
In one implementation, the determining module 503: the target detection device is used for sampling image data in the data layer at a predetermined sampling frequency to obtain a plurality of target detection images, wherein the predetermined sampling frequency is determined by receiving input of a user through the display layer.
In one implementation, the application module 504 is configured to input the target detection images into the target detection model, and obtain a plurality of target coordinates of a plurality of fire jobs in the target detection images, where the target detection model is trained by training data.
The fire operation detection device provided by the embodiment of the invention is characterized in that the determination module is used for determining a target detection image through an application layer; and the application module is used for inputting the target detection image into a target detection model through an application layer, outputting the target coordinate of the firing operation in the target detection image, quickly and accurately detecting the target of the firing operation in the monitoring image, and realizing high-precision and high-efficiency monitoring on the safety production of the firing operation of the power plant.
According to the detection device for the fire operation, provided by the embodiment of the invention, the determination module is used for sampling image data in the data layer at a preset sampling frequency to obtain a plurality of target detection images, wherein the preset sampling frequency is determined by receiving input of a user through the display layer; and the application module is used for inputting the target detection images into the target detection model to obtain a plurality of target coordinates of a plurality of fire operations in the target detection images, wherein the target detection model is obtained by training data, so that the targets of the fire operations in the monitoring images can be quickly and accurately detected, and the high-precision, high-efficiency and wide-range and orderly monitoring of the safety production of the fire operations of the power plant is realized.
Fig. 6 is a schematic structural diagram illustrating a fire detection device according to an embodiment of the present invention. As shown in fig. 6, the fire work detection device 600 includes: a perception module 601, a data module 602, a determination module 603, and an application module 604.
A sensing module 601, configured to extract image data from a video stream through a sensing layer, where the video stream is from the different monitoring device and/or the different server, and the image data is used to obtain the training data and/or the target detection image.
And the data module 602 is configured to receive, through the transmission device, the image data transmitted by the sensing module and store the image data.
A determining module 603, configured to determine a target detection image through an application layer;
the application module 604 is configured to input the target detection image into a target detection model through an application layer, and output a target coordinate of a fire operation in the target detection image.
In one implementation, the determining module 603: the target detection device is used for sampling image data in the data layer at a predetermined sampling frequency to obtain a plurality of target detection images, wherein the predetermined sampling frequency is determined by receiving input of a user through the display layer.
In one implementation, the application module 604 is configured to input the target detection images into the target detection model, and obtain a plurality of target coordinates of a plurality of fire jobs in the target detection images, where the target detection model is trained by training data.
The fire operation detection device provided by the embodiment of the invention is characterized in that the determination module is used for determining a target detection image through an application layer; and the application module is used for inputting the target detection image into a target detection model through an application layer, outputting the target coordinate of the firing operation in the target detection image, quickly and accurately detecting the target of the firing operation in the monitoring image, and realizing high-precision and high-efficiency monitoring on the safety production of the firing operation of the power plant.
The detection device for the fire operation provided by the embodiment of the invention is used for extracting image data from a video stream through a sensing layer through a sensing module, wherein the video stream is from different monitoring equipment and/or different servers, and the image data is used for obtaining the training data and/or the target detection image; and the data module is used for receiving the image data transmitted by the sensing module through the transmission equipment, storing the image data, obtaining a target detection algorithm with more accurate detection, wider detection range, more robust model and stronger migratory capability, realizing the unified deployment and scheduling of the power plant fire operation detection, and having flexible control and strong migratory capability.
Fig. 7 is a schematic structural diagram illustrating a fire detection device according to an embodiment of the present invention. As shown in fig. 7, the fire work detection device 700 includes: a perception module 701, a data module 702, a determination module 703, an application module 704, and a first display module 705.
A sensing module 701, configured to extract image data from a video stream through a sensing layer, where the video stream is from the different monitoring device and/or the different server, and the image data is used to obtain the training data and/or the target detection image.
And a data module 702, configured to receive, through the transmission device, the image data transmitted by the sensing module, and store the image data.
A determining module 703, configured to sample image data in the data layer at a predetermined sampling frequency to obtain a plurality of the target detection images, where the predetermined sampling frequency is determined by receiving an input from a user through the presentation layer.
An application module 704, configured to input the multiple target detection images into the target detection model, and obtain multiple target coordinates of multiple fire jobs in the multiple target detection images, where the target detection model is trained from training data.
A first display module 705, configured to display the plurality of target detection images through a display layer, where the plurality of target detection images are marked with the plurality of firing jobs.
In one implementation, the fire activity detection device further includes: and the second display module is used for displaying the statistical data of the plurality of fire operations through a display layer, wherein the statistical data comprises the time of the plurality of fire operations and the frequency of the fire operations in a preset time period.
In another implementation, the fire activity detection device further includes: and the third display module is used for controlling the playing of the video in a first time period through the display layer, wherein the first time period comprises at least one of the time of the plurality of fire jobs, and the video in the first time period is obtained from the data layer.
The fire operation detection device provided by the embodiment of the invention is characterized in that the determination module is used for determining a target detection image through an application layer; and the application module is used for inputting the target detection image into a target detection model through an application layer, outputting the target coordinate of the firing operation in the target detection image, quickly and accurately detecting the target of the firing operation in the monitoring image, and realizing high-precision and high-efficiency monitoring on the safety production of the firing operation of the power plant.
The detection device for the fire operation provided by the embodiment of the invention is used for extracting image data from a video stream through a sensing layer through a sensing module, wherein the video stream is from different monitoring equipment and/or different servers, and the image data is used for obtaining the training data and/or the target detection image; and the data module is used for receiving the image data transmitted by the sensing module through the transmission equipment, storing the image data, obtaining a target detection algorithm with more accurate detection, wider detection range, more robust model and stronger migratory capability, and realizing the unified deployment and flexible control of the power plant fire operation detection.
The fire operation detection device provided by the embodiment of the invention is used for displaying a plurality of target detection images through a display layer through a first display module, wherein the plurality of target detection images are marked with a plurality of fire operations; and/or a second display module for displaying the statistical data of the plurality of fire works through a display layer, wherein the statistical data comprises the time of the plurality of fire works and the frequency of the fire works in a preset time period; and/or the third display module is used for controlling the playing of the video in the first time period through the display layer, wherein the first time period comprises at least one of the time of the plurality of fire operation, the video in the first time period is obtained from the data layer, the display, data summarization analysis, video playback and algorithm configuration of the fire operation detection result can be integrated into the display layer for unified management, and the visualization and unified management of the fire operation monitoring are realized.
It should be noted that the embodiment of the fire work detection device in this specification and the embodiment of the fire work detection method in this specification are based on the same inventive concept, and therefore, for specific implementation of the embodiment of the fire work detection device, reference may be made to the implementation of the foregoing corresponding embodiment of the fire work detection method, and repeated details are not described here.
The fire work detection device in the embodiment of the application can be a device, and can also be a component, an integrated circuit or a chip in a terminal. The device may be a server, a server cluster, or the like, and the embodiment of the present application is not particularly limited.
One type of fire detection device in the embodiments of the present application may be a device having an operating system. The operating system may be a CentOS 7.4 or above or an ubuntu18.04 or above, or may be other possible operating systems, and the embodiment of the present application is not particularly limited.
The detection device for the operation of fire provided by the embodiment of the application can realize each process realized in the method embodiments of fig. 1 to fig. 4, and is not repeated here for avoiding repetition.
Optionally, as shown in fig. 8, an electronic device 800 is further provided in this embodiment of the present application, and includes a processor 801, a memory 802, and a program or an instruction stored in the memory 802 and executable on the processor 801, where the program or the instruction is executed by the processor 801 to implement the processes of the foregoing fire operation detection method embodiment, and can achieve the same technical effects, and in order to avoid repetition, details are not repeated here.
It should be noted that the electronic device in the embodiment of the present application includes the server and/or the server cluster described above.
Fig. 9 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.
The electronic device 900 includes, but is not limited to: a radio frequency unit 901, a network module 902, an audio output unit 903, an input unit 904, a sensor 905, a display unit 906, a user input unit 907, an interface unit 908, a memory 909, and a processor 910.
Those skilled in the art will appreciate that the electronic device 900 may further include a power source (e.g., a battery) for supplying power to various components, and the power source may be logically connected to the processor 910 through a power management system, so as to manage charging, discharging, and power consumption management functions through the power management system. The electronic device structures shown in the figures do not constitute limitations of the electronic device, and the electronic device may include more or less components than those shown, or combine some components, or arrange different components, and thus, the description is not repeated here.
Wherein the input unit 904 is configured to extract image data from a video stream through a sensing layer, wherein the video stream is from a different monitoring device and/or a different server, and the image data is used to obtain the training data and/or the target detection image.
A display unit 906 configured to display the plurality of target detection images through a display layer, wherein the plurality of target detection images are marked with the plurality of firing jobs; and/or displaying statistical data of the plurality of fire jobs through a display layer, wherein the statistical data comprises the time of the plurality of fire jobs and the frequency of the fire jobs within a predetermined time period; and/or controlling the playing of the video within a first time period by the presentation layer, wherein the first time period comprises at least one of the time of the plurality of fire jobs, and the video within the first time period is obtained from the data layer.
A memory 909 for transferring the image data to the data layer by a transfer device; and saving the image data through the data layer.
A processor 910 configured to determine a target detection image through an application layer; and inputting the target detection image into a target detection model through an application layer, and outputting the target coordinates of the firing operation in the target detection image.
In one implementation, the processor 910 is configured to sample image data in a data layer at a predetermined sampling frequency to obtain a plurality of the target detection images, where the predetermined sampling frequency is determined by receiving user input through a presentation layer, and the image data is stored in the data layer; and inputting the target detection images into the target detection model, and outputting a plurality of target coordinates of a plurality of fire jobs in the target detection images, wherein the target detection model is trained by training data.
The embodiment can realize each process of the above-mentioned fire operation detection method embodiment, and can achieve the same technical effect, and for avoiding repetition, the details are not described here.
It should be understood that, in the embodiment of the present application, the input Unit 904 may include a Graphics Processing Unit (GPU) 9041, and the Graphics Processing Unit 9041 processes image data of a still picture or a video obtained by an image capturing device (such as a camera) in a video capturing mode or an image capturing mode. The display unit 906 may include a display panel 9061, and the display panel 9061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 907 includes a touch panel 9071 and other input devices 9072. A touch panel 9071 also referred to as a touch screen. The touch panel 9071 may include two parts, a touch detection device and a touch controller. Other input devices 9072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail herein. Memory 909 can be used to store software programs as well as various data including, but not limited to, application programs and operating systems. The processor 910 may integrate an application processor, which primarily handles operating systems, user interfaces, applications, etc., and a modem processor, which primarily handles wireless communications. It is to be appreciated that the modem processor described above may not be integrated into processor 910.
The embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the method implements each process of the foregoing method for detecting a fire operation, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and so on.
The embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, the processor is configured to run a program or an instruction, implement each process of the foregoing fire operation detection method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
It should be understood that the chips mentioned in the embodiments of the present application may also be referred to as system-on-chip, system-on-chip or system-on-chip, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method of firestopping detection, the method comprising:
determining a target detection image through an application layer;
and inputting the target detection image into a target detection model through an application layer, and outputting the target coordinates of the firing operation in the target detection image.
2. The method of claim 1, wherein determining the object detection image by the application layer comprises:
sampling image data in a data layer at a predetermined sampling frequency to obtain a plurality of target detection images, wherein the predetermined sampling frequency is determined by receiving input of a user through a display layer;
the inputting the target detection image into a target detection model through an application layer and outputting the target coordinates of the firing operation in the target detection image comprises the following steps:
and inputting the target detection images into the target detection model to obtain a plurality of target coordinates of a plurality of fire jobs in the target detection images, wherein the target detection model is trained by training data.
3. The method of claim 1, further comprising, prior to said determining a target detection image by an application layer:
and extracting image data from a video stream through a perception layer, wherein the video stream is from different monitoring equipment and/or different servers, and the image data is used for obtaining the training data and/or the target detection image.
4. The method of claim 3, further comprising, after said extracting image data from the video stream through the perceptual layer:
transmitting the image data to the data layer by a transmission device;
and saving the image data through the data layer.
5. The method of claim 2, further comprising, after said obtaining a plurality of target coordinates for a plurality of sparking events in said plurality of target detection images:
displaying the plurality of target detection images through a display layer, wherein the plurality of target detection images are marked with the plurality of firing operations;
and/or
Displaying statistical data of the plurality of fire works through a display layer, wherein the statistical data comprises the time of the plurality of fire works and the frequency of the fire works in a preset time period;
and/or
Controlling, by a presentation layer, playback of a video over a first time period, wherein the first time period includes at least one of the times of the plurality of fire jobs, the video over the first time period being obtained from the data layer.
6. A fire activity detection device, the device comprising:
the determining module is used for determining a target detection image through an application layer;
and the application module is used for inputting the target detection image into a target detection model through an application layer and outputting the target coordinates of the fire operation in the target detection image.
7. The apparatus of claim 6, wherein the determining module is configured to:
sampling image data in a data layer at a predetermined sampling frequency to obtain a plurality of target detection images, wherein the predetermined sampling frequency is determined by receiving input of a user through a display layer;
the application module is configured to:
and inputting the target detection images into the target detection model, and outputting a plurality of target coordinates of a plurality of fire jobs in the target detection images, wherein the target detection model is trained by training data.
8. The apparatus of claim 6, further comprising:
and the perception module is used for extracting image data from a video stream through a perception layer, wherein the video stream is from different monitoring equipment and/or different servers, and the image data is used for obtaining the training data and/or the target detection image.
9. The apparatus of claim 6, further comprising:
and the data module is connected with the sensing module and used for receiving the image data transmitted by the sensing module through the transmission equipment and storing the image data.
10. The apparatus of claim 6, further comprising at least one of:
the first display module is used for displaying the target detection images through a display layer, wherein the target detection images are marked with the fire operation tasks;
the second display module is used for displaying the statistical data of the plurality of fire operations through a display layer, wherein the statistical data comprises the time of the plurality of fire operations and the frequency of the fire operations in a preset time period;
and the third display module is used for controlling the playing of the video in a first time period through the display layer, wherein the first time period comprises at least one of the time of the plurality of fire jobs, and the video in the first time period is obtained from the data layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111564698.6A CN114241420A (en) | 2021-12-20 | 2021-12-20 | Fire operation detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111564698.6A CN114241420A (en) | 2021-12-20 | 2021-12-20 | Fire operation detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114241420A true CN114241420A (en) | 2022-03-25 |
Family
ID=80759541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111564698.6A Pending CN114241420A (en) | 2021-12-20 | 2021-12-20 | Fire operation detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114241420A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116863252A (en) * | 2023-09-04 | 2023-10-10 | 四川泓宝润业工程技术有限公司 | Method, device, equipment and storage medium for detecting inflammable substances in live fire operation site |
-
2021
- 2021-12-20 CN CN202111564698.6A patent/CN114241420A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116863252A (en) * | 2023-09-04 | 2023-10-10 | 四川泓宝润业工程技术有限公司 | Method, device, equipment and storage medium for detecting inflammable substances in live fire operation site |
| CN116863252B (en) * | 2023-09-04 | 2023-11-21 | 四川泓宝润业工程技术有限公司 | Method, device, equipment and storage medium for detecting inflammable substances in live fire operation site |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11138216B2 (en) | Automatically invoked unified visualization interface | |
| US20130014028A1 (en) | Method and system for drawing | |
| CN106201265B (en) | A kind of mobile terminal control method, apparatus and system based on WEB | |
| CN110727572A (en) | Buried point data processing method, device, equipment and storage medium | |
| WO2022268024A1 (en) | Video playback method and apparatus, and electronic device | |
| CN105141878B (en) | Content share method and instant communication client when video interactive | |
| CN112115224B (en) | Auxiliary quality inspection method and device for map data, electronic equipment and storage medium | |
| CN112486444A (en) | Screen projection method, device, equipment and readable storage medium | |
| CN114241420A (en) | Fire operation detection method and device | |
| CN112949172A (en) | Data processing method and device, machine readable medium and equipment | |
| CN107346274A (en) | Touch-screen response performance test platform and method | |
| CN111651106A (en) | Unread message prompting method, unread message prompting device, unread message prompting equipment and readable storage medium | |
| CN112929494B (en) | Information processing method, information processing apparatus, information processing medium, and electronic device | |
| CN112783406B (en) | Operation execution method and device and electronic equipment | |
| CN112929734A (en) | Screen projection method and device and electronic equipment | |
| CN104158696B (en) | A kind of determination method, apparatus and terminal for measuring operation delay | |
| CN108829329B (en) | Operation object display method and device and readable medium | |
| CN112328155B (en) | Input device control method and device and electronic device | |
| CN112565597A (en) | Display method and device | |
| CN113610327A (en) | Pepper disease prediction method and device, electronic device and storage medium | |
| CN105577888A (en) | Data interaction method adopting non-contact between cell phone and computer | |
| CN112966484B (en) | Chart typesetting method, device, electronic equipment and readable storage medium | |
| CN110750193A (en) | Scene topology determination method and device based on artificial intelligence | |
| CN113221010B (en) | Event propagation state display method and device and electronic equipment | |
| CN217741832U (en) | Multi-channel data acquisition device and system |
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 |