CN115439997B - Fire early warning method, device, equipment and readable storage medium - Google Patents
Fire early warning method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN115439997B CN115439997B CN202211385472.4A CN202211385472A CN115439997B CN 115439997 B CN115439997 B CN 115439997B CN 202211385472 A CN202211385472 A CN 202211385472A CN 115439997 B CN115439997 B CN 115439997B
- Authority
- CN
- China
- Prior art keywords
- flame
- information
- image
- predicted
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention provides a fire early warning method, a fire early warning device, fire early warning equipment and a readable storage medium, which relate to the technical field of fire detection and comprise the steps of collecting flame images at a plurality of continuous moments and a plurality of groups of environment sample parameters related to the flame images; acquiring object information and flame information in each flame image; constructing a training set and a test set; building a neural network model, and training and testing the neural network model by using the training set and the testing set to obtain a flame prediction model; inputting the object information and the flame information of the flame image to be predicted and the environmental sample parameters into the flame prediction model to obtain predicted object information and flame information; the method and the device are used for solving the technical problems of large error, poor timeliness and high missing report rate of a fire monitoring mode in the prior art.
Description
Technical Field
The invention relates to the technical field of fire detection, in particular to a fire early warning method, a fire early warning device, fire early warning equipment and a readable storage medium.
Background
With the development of economic construction in China, various modern buildings put higher requirements on fire early warning and automatic fire extinguishing systems. A complete fire fighting system is required to be arranged in large hotels, shopping malls, libraries, museums, archives, office buildings and the like, so that the life and property safety of people is effectively guaranteed. At present, a fire early warning system mainly realizes signal transmission through a detector and a controller, and the system can monitor fire of each linkage device through various modules, but the monitoring mode has large error, poor timeliness and high missing report rate, so that a fire early warning method or device with high accuracy and low false alarm rate is urgently needed to be researched.
Disclosure of Invention
The present invention aims to provide a fire early warning method, a fire early warning device, a fire early warning equipment and a readable storage medium, so as to improve the problems. In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a fire early warning method, including:
acquiring flame images at a plurality of continuous moments and a plurality of groups of environment sample parameters related to the flame images;
acquiring object information and flame information in each flame image;
constructing a training set and a testing set by a plurality of groups of object information at continuous moments, the flame information and the environmental sample parameters;
building a neural network model, and training and testing the neural network model by using the training set and the testing set to obtain a flame prediction model;
acquiring a flame image to be predicted and an environment sample parameter of the flame image to be predicted, and inputting object information, flame information and the environment sample parameter of the flame image to be predicted into the flame prediction model to obtain predicted object information and flame information;
and calculating a total combustion index by utilizing the predicted object information and flame information, and judging to obtain a fire early warning grade based on the total combustion index.
Further, the acquiring flame images at a plurality of consecutive moments and a plurality of sets of environmental sample parameters related to the flame images specifically includes:
acquiring flame images at a plurality of moments in a flame development cycle, and forming a flame image set by the flame images;
and monitoring the environment characteristic change of the scene in the flame image acquisition process to obtain environment sample parameters corresponding to the flame image at the moment, wherein the environment sample parameters comprise smoke content, oxygen content, carbon dioxide content, humidity, temperature, pressure and light intensity.
Further, the acquiring of the object information and the flame information of each flame image specifically includes:
binaryzation processing the flame image to obtain a binary image;
performing flame edge detection on the binary image, and determining flame contour points to obtain flame information;
detecting the edge of the object in the binary image to determine the contour point of the object;
transferring the object contour points in the binary image to a flame image, and identifying the object in the flame image based on an image identification model to obtain object attribute information;
and forming object information by the object contour points and the object attribute information.
Further, the constructing a training set and a testing set by the object information, the flame information and the environmental sample parameters at a plurality of groups of continuous time includes:
acquiring object information, flame information and environmental sample parameters at multiple groups of continuous moments;
taking the object information, the flame information and the environmental sample parameters at the previous moment as input feature labels, and taking the object information and the flame information at the next moment as output feature labels to construct a data sample;
80% of the data samples were selected as the training set and 20% of the data samples were selected as the test set.
Further, the calculating the total combustion index by using the predicted object information and the flame information specifically includes:
acquiring an object contour point in the predicted object information, object attribute information and a flame contour point in the flame information;
determining the position relation of the object and the flame based on the object contour point and the flame contour point;
sequentially calculating the distance between the flame contour point and the object contour point and the area of the flame;
calculating a combustion index of the object based on the distance, the position relationship, the area of the flame and the object attribute information;
and accumulating the burning indexes of all the objects to obtain the total burning index.
In a second aspect, the present application further provides a fire early warning device, including:
a data acquisition module: the flame image acquisition device is used for acquiring flame images at a plurality of continuous moments and a plurality of groups of environment sample parameters related to the flame images;
a data acquisition module: the flame detector is used for acquiring object information and flame information in each flame image;
a parameter construction module: the system is used for constructing a training set and a testing set by a plurality of groups of object information, flame information and environment sample parameters at continuous time;
a training module: the system is used for building a neural network model, and training and testing the neural network model by using the training set and the testing set to obtain a flame prediction model;
a prediction module: the system comprises a flame prediction model, a flame prediction model and a controller, wherein the flame prediction model is used for acquiring a flame image to be predicted and an environment sample parameter of the flame image to be predicted, and inputting object information, flame information and the environment sample parameter of the flame image to be predicted into the flame prediction model to obtain predicted object information and flame information;
a judging module: and the system is used for calculating a total combustion index by utilizing the predicted object information and flame information, and judging to obtain a fire early warning grade based on the total combustion index.
Further, the data acquisition module comprises:
an image processing unit: the flame image is subjected to binarization processing to obtain a binary image;
a first detection unit: the flame edge detection module is used for detecting the flame edge in the binary image, determining flame contour points and obtaining flame information;
a second detection unit: the system is used for detecting the edge of an object in the binary image and determining the contour point of the object;
an identification unit: the system comprises a binary image, a flame image and an object recognition model, wherein the binary image is used for carrying out image recognition on the flame image;
a data construction unit: and the object information is composed of the object contour points and the object attribute information.
Further, the judging module comprises:
an acquisition unit: the system comprises a controller, a processor, a controller and a controller, wherein the controller is used for acquiring an object contour point in predicted object information, object attribute information and a flame contour point in flame information;
a position determination unit: the position relation of the object and the flame is determined based on the object contour point and the flame contour point;
the first calculation unit: the device is used for sequentially calculating the distance between the flame contour point and the object contour point and the area of the flame;
a second calculation unit: the combustion index of the object is obtained through calculation based on the distance, the position relation, the area of the flame and the object attribute information;
a third calculation unit: for summing the burn indexes of all objects to obtain a total burn index.
In a third aspect, the present application further provides a fire early warning device, including:
a memory for storing a computer program;
a processor for implementing the steps of the fire early warning method when executing the computer program.
In a fourth aspect, the present application further provides a readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the fire early warning method.
The invention has the beneficial effects that:
according to the method, the flame image sets under various scenes are collected, and the flame information in the flame development cycle and the object information in the scenes under various scenes are extracted. Meanwhile, a fire early warning model is established, and flame information and object information under various scenes are utilized to train the fire early warning model, so that the model can predict the state of flame to be developed according to the flame information and the object information under the current state, thereby realizing accurate fire prediction and fire early warning and providing reliable guarantee for a fire-fighting system.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart of a fire warning method according to an embodiment of the present invention;
FIG. 2 is a schematic illustration of flame contour points and object contour points in an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a fire warning device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a fire warning apparatus according to an embodiment of the present invention.
The labels in the figure are:
01. a data acquisition module; 02. a data acquisition module; 021. an image processing unit; 022. a first detection unit; 023. a second detection unit; 024. an identification unit; 025. a data construction unit; 03. a parameter construction module; 04. a training module; 05. a prediction module; 06. a judgment module; 061. an acquisition unit; 062. a position determination unit; 063. a first calculation unit; 064. a second calculation unit; 065. a third calculation unit;
800. fire early warning equipment; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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 invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not construed as indicating or implying relative importance.
Example 1:
the embodiment provides a fire early warning method.
Referring to fig. 1, the method is shown to include:
s1, collecting flame images at a plurality of continuous moments and a plurality of groups of environment sample parameters related to the flame images;
in this embodiment, one flame image set represents a flame development state diagram in one scene, preferably, the acquired flame image set should include all scenes that need to be predicted, and it should be noted that the usage scene of this embodiment is mainly in a city. The more the flame image set is selected, the more scenes the flame prediction model learns, and the more accurate the prediction is. The space in each scene is different in size, different in contained objects, different in placement mode of the objects and different in occupied space.
An image acquisition device is arranged in each scene, and can be a monitoring camera for monitoring object changes in the scene in real time. Meanwhile, an environment monitoring device is arranged in the scene, and environmental sample parameters such as smoke content, oxygen content, carbon dioxide content, humidity, temperature, pressure intensity and light intensity in the scene are measured in real time.
Specifically, the step S1 includes:
s11, acquiring flame images at a plurality of moments in a flame development cycle, and forming a flame image set by the flame images, specifically, acquiring the flame images in a preset time period, preferably, setting the preset time period to be 0.5S, acquiring the flame images at intervals of 0.5S, and forming a flame image set by all the flame images in the whole flame development cycle from the start of flame combustion to the end of combustion;
s12, monitoring the environment characteristic change of a scene in the flame image acquisition process to obtain environment sample parameters corresponding to the flame image at the moment, wherein the environment sample parameters comprise smoke content, oxygen content, carbon dioxide content, humidity, temperature, pressure and light intensity, and the environment sample parameters are expressed as an array [ P 2 O 5 ，O 2 ，CO 2 ，H，T，P，R]。
In this embodiment, the flame is different in the environmental sample at each combustion stage, so
Acquiring a group of environment sample parameters corresponding to the flame image acquisition time when acquiring one flame image;
s2, acquiring object information and flame information in each flame image;
specifically, the step S2 includes:
and S21, binaryzation processing the flame image to obtain a binary image, specifically,
obtaining a colour flame image I 0 For image I 0 Performing gray scale processing to obtain image I 1 Enhancing the image I 1 Obtaining an image I 2 For the image I 2 Carrying out binarization operation to obtain a binary image I 3 ；
S22, comparing the binary image I 3 Carrying out flame edge detection, and determining flame contour points to obtain flame information;
specifically, the binary image I is processed by a canny operator 3 Performing edge detection to obtain a binary image roi consisting of two edge points with the same size 0 And roi 1 ，roi 0 Image edge detection map, roi, composed of segmented pixels 1 The target area is cut from the original image edge detection graph; to roi 0 InRedundancy removal, namely removing internal points and redundant contour points to reduce the computation amount; traverse roi 0 Edge point in, at roi 1 In finding non-roi 0 Points within the edge contour region and closest to this point, from which the roi is formed 2 Region map, roi 2 The figure is a flame profile.
S23, carrying out object edge detection on the binary image to determine object contour points;
similarly, the method in step S22 is used to perform edge detection on the object.
S24, transferring the object contour points in the binary image to a flame image, and identifying the object in the flame image based on an image identification model to obtain object attribute information;
specifically, the construction method of the image recognition analysis model comprises the following steps:
s241, collecting an image set containing combustible objects;
s242, manually marking the outline of the combustible object in the image, and storing information such as the name, the material and the ignition point of the combustible object in object attribute information;
s243, constructing a training set and a testing set by using the image set and the object attribute information, wherein the image containing the combustible object is used as an input feature label, and the object attribute information is used as an output feature label;
and S244, training and testing the YOLOv3 model by using the training set and the testing set to obtain a trained image recognition model, wherein the image recognition model can automatically recognize objects in the image and object attribute information.
And S25, forming object information by the object contour points and the object attribute information.
S3, constructing a training set and a testing set by a plurality of groups of object information at continuous moments, the flame information and the environment sample parameters;
specifically, the step S3 includes:
s31, acquiring object information, flame information and environment sample parameters of a plurality of groups of continuous moments;
s32, enabling the last moment t n The object information, the flame information and the environmental sample parameters are used as input feature labels, and the next moment t n+1 The object information and the flame information are used as output characteristic labels to construct data samples;
and S33, selecting 80% of data samples as a training set and 20% of data samples as a testing set.
S4, building a neural network model, and training and testing the neural network model by using the training set and the testing set to obtain a flame prediction model;
in this embodiment, t is d Information in the flame image at the moment (namely object information and flame information) and environment sample parameters serve as input feature labels, t d+1 Information in the flame image at the moment is used as an output characteristic label to train the neural network model, and the obtained flame prediction model can realize accurate prediction of the flame development state, so that the flame prediction model is favorable for judgment and early warning of the fire behavior.
S5, acquiring a flame image to be predicted and an environment sample parameter of the flame image to be predicted, and inputting object information, flame information and the environment sample parameter in the flame image to be predicted into the flame prediction model to obtain predicted object information and flame information;
in this embodiment, the monitoring device monitors each real scene in real time to obtain the photographed flame image to be predicted and the environmental sample parameters, the flame image to be predicted is processed in step S2, the flame contour points, the object contour points and the object attribute information in the flame image to be predicted are extracted, the flame is predicted by the flame prediction model based on the information of the flame image to be predicted, and it should be noted that the prediction time is longer than the actual combustion time of the flame, so that the flame can be predicted.
And S6, calculating a total combustion index by utilizing the predicted object information and flame information, and judging to obtain a fire early warning grade based on the total combustion index.
In this embodiment, one flame image includes one or more objects, the burning index of each object is sequentially calculated, and the total burning index in the current flame image can be obtained by accumulating all the burning indexes.
Specifically, the step S6 includes:
s61, acquiring an object contour point in the predicted object information, object attribute information and a flame contour point in the flame information;
s62, determining the position relation between the object and the flame based on the object contour point and the flame contour point;
in this embodiment, the positional relationship between the object and the flame includes: the object is to the side of the flame and the object is above the flame.
S63, sequentially calculating the distance between the flame contour point and the object contour point and the area of the flame;
in this embodiment, taking fig. 2 as an example, the distance between the flame contour point and the contour point of the object 1 is calculated from the contour points of the flame and the object 1 included in fig. 2:
the flame contour points are recorded as a coordinate array [ (x) according to the sequence from left to right/from top to bottom o 1 ，y o 1 ），（x o 2 ，y o 2 ），…，（x o m ，y o m ）]；
The contour points of the object 1 are recorded as a coordinate array [ (x) in left-to-right/top-to-bottom order 1 1 ，y 1 1 ），（x 1 2 ，y 1 2 ），…，（x 1 m ，y 1 m ）]；
Two contour points with the closest distance between the flame and the object 1 are determined, and the distance between the two contour points is calculated:
in the formula (x) o a ，y o a ) Represents the closest point to the object 1 among the flame contour points, (x) 1 b ，y 1 b ) Is represented by (x) o a ，y o a ) The closest point.
Calculating the area of flame based on the flame contour points, wherein the area of the graph calculated according to the image contour points can be quickly realized in drawing software, such as CAD (computer aided design) and the like, and is not repeated herein;
s64, calculating to obtain the combustion index of the object based on the distance, the position relation, the area of the flame and the object attribute information:
in the formula, F 1 Denotes the combustion index of the object 1, λ denotes the directional parameter; s represents the area of the flame in m 2 ，T 1 c Indicating the ignition point of the object 1 in c.
Wherein, the value of the direction parameter lambda is as follows:
and S65, accumulating the burning indexes of all the objects to obtain a total burning index.
In the formula, F General (1) Representing the total combustion index and n representing the total number of objects.
The more combustible objects contained in the image of flames indicates the more potential hazards in the scene and therefore the higher the overall burn index.
Based on the above embodiment, the method further comprises judging to obtain a fire early warning level based on the total combustion index;
performing early warning grade division on the combustion index to obtain an early warning grade reference table, as shown in table 1:
TABLE 1
In Table 1, F General (1) Higher warning level indicates more serious fire.
Example 2:
as shown in fig. 3, the present embodiment provides a fire early warning apparatus, including:
the data acquisition module 01: the flame image acquisition device is used for acquiring flame images at a plurality of continuous moments and a plurality of groups of environment sample parameters related to the flame images;
the data acquisition module 02: the flame detector is used for acquiring object information and flame information in each flame image;
the parameter construction module 03: the system is used for constructing a training set and a testing set by a plurality of groups of object information, flame information and environment sample parameters at continuous time;
the training module 04: the device is used for building a neural network model, and training and testing the neural network model by using the training set and the testing set to obtain a flame prediction model;
the prediction module 05: the system comprises a flame prediction model, a flame prediction model and a controller, wherein the flame prediction model is used for acquiring a flame image to be predicted and an environment sample parameter of the flame image to be predicted, and inputting object information, flame information and the environment sample parameter of the flame image to be predicted into the flame prediction model to obtain predicted object information and flame information;
the judgment module 06: and the system is used for calculating a total combustion index by utilizing the predicted object information and flame information, and judging to obtain a fire early warning grade based on the total combustion index.
Based on the above embodiment, the data acquisition module 02 includes:
image processing unit 021: the flame image is subjected to binarization processing to obtain a binary image;
first detection unit 022: the flame edge detection module is used for detecting the flame edge in the binary image, determining flame contour points and obtaining flame information;
the second detecting unit 023: the binary image is used for carrying out object edge detection on the binary image and determining object contour points;
the recognition unit 024: the system comprises a binary image, a flame image and an object recognition model, wherein the binary image is used for carrying out image recognition on the flame image;
the data construction unit 025: and the object information is composed of the object contour points and the object attribute information.
Based on the above embodiment, the determination unit includes:
the acquisition unit 061: the system comprises a controller, a processor, a controller and a controller, wherein the controller is used for acquiring an object contour point in predicted object information, object attribute information and a flame contour point in flame information;
position determination unit 062: the position relation of the object and the flame is determined based on the object contour point and the flame contour point;
the first calculation unit 063: the device is used for sequentially calculating the distance between the flame contour point and the object contour point and the area of the flame;
second calculation unit 064: the combustion index of the object is calculated based on the distance, the position relation, the area of the flame and the object attribute information;
third calculation unit 065: for summing the burn indexes of all objects to obtain a total burn index.
It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated herein.
Example 3:
corresponding to the above method embodiments, a fire early warning device is also provided in this embodiment, and a fire early warning device described below and a fire early warning method described above may be referred to in correspondence.
Fig. 4 is a block diagram illustrating a fire early warning device 800 according to an exemplary embodiment. As shown in fig. 4, the fire early warning apparatus 800 may include: a processor 801, a memory 802. The fire early warning device 800 may further include one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the fire early warning apparatus 800 to complete all or part of the steps of the fire early warning method. The memory 802 is used to store various types of data to support the operation of the fire warning device 800, which may include, for example, instructions for any application or method operating on the fire warning device 800, as well as application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and so forth. The memory 802 may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable Read-only memory (EEPROM), erasable programmable Read-only memory (EPROM), programmable Read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia components 803 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 802 or transmitted through the communication component 805. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the fire early warning device 800 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding communication component 805 may include: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the fire warning apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the fire warning method described above.
In another exemplary embodiment, there is also provided a computer readable storage medium including program instructions which, when executed by a processor, implement the steps of the fire early warning method described above. For example, the computer readable storage medium may be the above-described memory 802 including program instructions that are executable by the processor 801 of the fire early warning device 800 to perform the above-described fire early warning method.
Example 4:
corresponding to the above method embodiments, a readable storage medium is also provided in this embodiment, and a readable storage medium described below and a fire early warning method described above may be referred to in correspondence.
A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the fire warning method of the above-mentioned method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and may store various program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A fire early warning method is characterized by comprising the following steps:
acquiring flame images at a plurality of continuous moments and a plurality of groups of environment sample parameters related to the flame images;
acquiring object information and flame information in each flame image:
carrying out binarization processing on the flame image to obtain a binary image;
performing flame edge detection on the binary image, and determining flame contour points to obtain flame information;
carrying out object edge detection on the binary image to determine object contour points;
transferring the object contour points in the binary image to a flame image, and identifying the object in the flame image based on an image identification model to obtain object attribute information;
forming object information by the object contour points and the object attribute information;
constructing a training set and a testing set by a plurality of groups of object information at continuous moments, the flame information and the environmental sample parameters;
building a neural network model, and training and testing the neural network model by using the training set and the testing set to obtain a flame prediction model;
acquiring a flame image to be predicted and an environment sample parameter of the flame image to be predicted, and inputting object information, flame information and the environment sample parameter of the flame image to be predicted into the flame prediction model to obtain predicted object information and flame information;
calculating a total combustion index by utilizing the predicted object information and flame information, and judging to obtain a fire early warning grade based on the total combustion index:
acquiring an object contour point in the predicted object information, object attribute information and a flame contour point in the flame information;
determining the position relation of the object and the flame based on the object contour point and the flame contour point;
sequentially calculating the distance between the flame contour point and the object contour point and the area of the flame;
calculating a combustion index of the object based on the distance, the positional relationship, the area of the flame, and the object attribute information:
in the formula, F 1 Representing the burning index of the object 1, d representing the distance between the flame contour point and the contour point of the object 1, and lambda representing a direction parameter; s denotes the area of the flame, T 1 c Represents the ignition point of the object 1;
and accumulating the burning indexes of all objects to obtain a total burning index:
in the formula, F General assembly Representing the total combustion index and n representing the total number of objects.
2. A fire warning method as claimed in claim 1, wherein the acquiring of the flame images at a plurality of successive times and the plurality of sets of environmental sample parameters related to the flame images comprises:
acquiring flame images at a plurality of moments in a flame development period, and forming a flame image set by the flame images at the plurality of moments;
and monitoring the environment characteristic change of a scene in the flame image acquisition process to obtain environment sample parameters corresponding to the flame image at the moment, wherein the environment sample parameters comprise smoke content, oxygen content, carbon dioxide content, humidity, temperature, pressure and light intensity.
3. A fire warning method as claimed in claim 1, wherein the constructing of training sets and testing sets from a plurality of sets of object information, flame information and environmental sample parameters at successive times comprises:
acquiring object information, flame information and environmental sample parameters at a plurality of groups of continuous moments;
taking the object information, the flame information and the environmental sample parameters at the previous moment as input feature labels, and taking the object information and the flame information at the next moment as output feature labels to construct a data sample;
80% of the data samples were selected as the training set and 20% of the data samples were selected as the test set.
4. A fire warning device, comprising:
a data acquisition module: the flame image acquisition device is used for acquiring flame images at a plurality of continuous moments and a plurality of groups of environment sample parameters related to the flame images;
a data acquisition module: for obtaining object information and flame information in each flame image:
binaryzation processing the flame image to obtain a binary image;
performing flame edge detection on the binary image, and determining flame contour points to obtain flame information;
performing object edge detection on the binary image to determine object contour points;
migrating the object contour points in the binary image to a flame image, and identifying the object in the flame image based on an image identification model to obtain object attribute information;
forming object information by the object contour points and the object attribute information;
a parameter construction module: the system is used for constructing a training set and a testing set by a plurality of groups of object information, flame information and environment sample parameters at continuous time;
a training module: the device is used for building a neural network model, and training and testing the neural network model by using the training set and the testing set to obtain a flame prediction model;
a prediction module: the flame prediction model is used for acquiring a flame image to be predicted and an environment sample parameter of the flame image to be predicted, and inputting object information, flame information and the environment sample parameter of the flame image to be predicted into the flame prediction model to obtain predicted object information and flame information;
a judging module: the system is used for calculating a total combustion index by utilizing the predicted object information and flame information, and judging to obtain a fire early warning grade based on the total combustion index:
acquiring an object contour point in the predicted object information, object attribute information and a flame contour point in the flame information;
determining the position relation of the object and the flame based on the object contour point and the flame contour point;
sequentially calculating the distance between the flame contour point and the object contour point and the area of the flame;
calculating a combustion index of the object based on the distance, the positional relationship, the area of the flame, and the object attribute information:
in the formula, F 1 Representing the combustion index of the object 1, d representing the distance between the flame contour point and the contour point of the object 1, and lambda representing a direction parameter; s denotes the area of the flame, T 1 c Represents the ignition point of the object 1;
and accumulating the burning indexes of all objects to obtain a total burning index:
in the formula, F General assembly Representing the total burn index and n representing the total number of objects.
5. The fire early warning device according to claim 4, wherein the data acquisition module comprises:
an image processing unit: the flame image is subjected to binarization processing to obtain a binary image;
a first detection unit: the flame edge detection module is used for detecting the flame edge in the binary image, determining flame contour points and obtaining flame information;
a second detection unit: the binary image is used for carrying out object edge detection on the binary image and determining object contour points;
an identification unit: the system comprises a binary image, a flame image and an object recognition model, wherein the binary image is used for carrying out image recognition on the flame image;
a data construction unit: and the object information is composed of the object contour points and the object attribute information.
6. A fire early warning device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the fire alerting method of any one of claims 1 to 3 when executing the computer program.
7. A readable storage medium, characterized by: the readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the fire alerting method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211385472.4A CN115439997B (en) | 2022-11-07 | 2022-11-07 | Fire early warning method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211385472.4A CN115439997B (en) | 2022-11-07 | 2022-11-07 | Fire early warning method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115439997A CN115439997A (en) | 2022-12-06 |
| CN115439997B true CN115439997B (en) | 2023-01-31 |
Family
ID=84252816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211385472.4A Active CN115439997B (en) | 2022-11-07 | 2022-11-07 | Fire early warning method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115439997B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115907241B (en) * | 2023-03-10 | 2023-06-20 | 广东广宇科技发展有限公司 | Building fire control resource investment prediction method and system |
| CN118887625B (en) * | 2024-09-29 | 2025-03-25 | 南京信息工程大学 | A method for predicting the fire situation in the early stage of a building fire |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5917417A (en) * | 1993-07-30 | 1999-06-29 | Girling; Christopher | Smoke detection system |
| US6111512A (en) * | 1997-03-13 | 2000-08-29 | Nippon Telegraph And Telephone Corporation | Fire detection method and fire detection apparatus |
| WO2001057819A2 (en) * | 2000-02-07 | 2001-08-09 | Vsd Limited | Smoke and flame detection |
| US20010020899A1 (en) * | 1999-12-08 | 2001-09-13 | Kadwell Brian J. | Smoke detector |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3363044B2 (en) * | 1996-11-07 | 2003-01-07 | 東海カーボン株式会社 | Fire detection method and apparatus in high temperature heat treatment process |
-
2022
- 2022-11-07 CN CN202211385472.4A patent/CN115439997B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5917417A (en) * | 1993-07-30 | 1999-06-29 | Girling; Christopher | Smoke detection system |
| US6111512A (en) * | 1997-03-13 | 2000-08-29 | Nippon Telegraph And Telephone Corporation | Fire detection method and fire detection apparatus |
| US20010020899A1 (en) * | 1999-12-08 | 2001-09-13 | Kadwell Brian J. | Smoke detector |
| WO2001057819A2 (en) * | 2000-02-07 | 2001-08-09 | Vsd Limited | Smoke and flame detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115439997A (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115439997B (en) | Fire early warning method, device, equipment and readable storage medium | |
| CN112767644B (en) | Method and device for early warning fire in highway tunnel based on video identification | |
| CN118015568B (en) | Driving risk detection method and system based on artificial intelligence | |
| CN114445780A (en) | Detection method and device for bare soil covering, and training method and device for recognition model | |
| CN115144548B (en) | Harmful gas composition real-time monitoring system and its monitoring method | |
| CN111125290B (en) | Intelligent river patrol method and device based on river growth system and storage medium | |
| CN116823232B (en) | A bridge apparent disease inspection method, inspection system and inspection device | |
| CN114913460A (en) | Electric vehicle elevator entering real-time detection method based on convolutional neural network | |
| CN113920673A (en) | Intelligent indoor fire monitoring method and system | |
| CN108629310B (en) | Engineering management supervision method and device | |
| CN117392591A (en) | Site security AI detection method and device | |
| CN118690255B (en) | Construction fire detection method and system based on Internet of Things | |
| CN116383937A (en) | Digital twin protection evaluation method for villages | |
| CN115311601A (en) | Fire detection analysis method based on video analysis technology | |
| CN114446002A (en) | Fire on-line monitoring method, device, medium and system | |
| CN118379844A (en) | Fire initial detection method and device, electronic equipment and medium | |
| CN113554364A (en) | Disaster emergency management method, device, equipment and computer storage medium | |
| CN117291430B (en) | Safety production detection method and device based on machine vision | |
| CN117292321B (en) | Motion detection method and device based on video monitoring and computer equipment | |
| CN112347874A (en) | Fire detection method, device, equipment and storage medium | |
| KR102602439B1 (en) | Method for detecting rip current using CCTV image based on artificial intelligence and apparatus thereof | |
| Ojelade et al. | Construction worker posture estimation using OpenPose | |
| CN114241212A (en) | Fire detection method, device, electronic device and storage medium | |
| CN115565123A (en) | Construction site fire monitoring method based on deep learning and multi-source image fusion perception | |
| CN117524354B (en) | Air pollution tracing method and device for chemical region |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |