CN111079614A

CN111079614A - Fire identification method, fire identification device, storage medium and electronic equipment

Info

Publication number: CN111079614A
Application number: CN201911255312.6A
Authority: CN
Inventors: 杨学政; 张美娜; 汪浩; 杨耀威; 梁超
Original assignee: Shuzhi Beijing Wulian Technology Co ltd
Current assignee: Shuzhi Beijing Wulian Technology Co ltd
Priority date: 2019-12-10
Filing date: 2019-12-10
Publication date: 2020-04-28

Abstract

The embodiment of the invention relates to a fire disaster identification method, a fire disaster identification device, a storage medium and electronic equipment, wherein the method comprises the following steps: determining image acquisition equipment in the current environment, and calling the image acquisition equipment to acquire images in the current environment; inputting the image into a preset fire recognition model; and if the output result of the fire identification model meets the preset condition, identifying that the fire exists in the current environment. Therefore, based on the image in the current environment, the fire in the current environment is identified, the fire can be found in time, and personal and property losses are avoided.

Description

Fire identification method, fire identification device, storage medium and electronic equipment

Technical Field

The embodiment of the invention relates to the technical field of fire identification, in particular to a fire identification method, a fire identification device, a storage medium and electronic equipment.

Background

A fire refers to a catastrophic combustion phenomenon that loses control over time or space. Among the various disasters, fire is one of the main disasters that threaten public safety and social development most often and most generally. The history of using fire by human beings and the history of fighting with fire by human beings are concomitant, people continuously summarize the rule of fire occurrence while using fire, reduce fire and the harm to human beings as far as possible, thereby the recognition of fire as early as possible has great significance for public safety and social development.

In the related art, identification of a fire is mostly based on a temperature sensor or a smoke sensor, and information sent by the temperature sensor or the smoke sensor is received and fire alarm information is sent. Because the temperature sensor or the smoke sensor for sensing the fire is basically arranged at the key position, key equipment or a position with higher fire occurrence probability and has lower sensitivity, although the key position, the key equipment and the position with higher fire occurrence probability can be found, the fire at other positions can not be found in time, and personal and property loss is caused.

Disclosure of Invention

In view of the above, embodiments of the present invention provide a fire identification method, a fire identification device, a storage medium, and an electronic device to solve the above technical problems or some technical problems.

In a first aspect, an embodiment of the present invention provides a fire identification method, where the method includes:

determining image acquisition equipment in the current environment, and calling the image acquisition equipment to acquire images in the current environment;

inputting the image into a preset fire recognition model;

and if the output result of the fire identification model meets the preset condition, identifying that the fire exists in the current environment.

In one possible embodiment, the method further comprises:

segmenting the image by utilizing a preset CIE LAB color model to obtain a color component corresponding to the image;

and forming the flame corresponding to the fire by the color components.

In one possible embodiment, the method further comprises:

determining target image acquisition equipment for identifying the fire;

and determining the position information of the fire according to the position information of the target image acquisition equipment.

In one possible embodiment, the determining the location information of the fire according to the location information of the target image capturing device includes:

determining the height of the target image acquisition equipment from a horizontal plane and an included angle formed by the target image acquisition equipment and the fire;

calculating the distance between the target image acquisition equipment and the fire in the horizontal direction according to the height and the included angle;

and determining the position information of the fire according to the position information of the target image acquisition equipment and the distance.

In one possible embodiment, the method further comprises:

determining the fire category according to the mapping relation between the preset position information and the fire category;

and linking the fire extinguishing equipment corresponding to the fire category in the current environment to extinguish the fire.

In a second aspect, an embodiment of the present invention provides a fire recognition apparatus, including:

the device determination module is used for determining the image acquisition device in the current environment;

the image acquisition module is used for calling the image acquisition equipment to acquire images in the current environment;

the image input module is used for inputting the image into a preset fire recognition model;

and the fire identification module is used for identifying that a fire exists in the current environment if the output result of the fire identification model meets a preset condition.

In one possible embodiment, the apparatus further comprises:

the flame segmentation module is used for segmenting the image by utilizing a preset CIE LAB color model to obtain a color component corresponding to the image;

and forming the flame corresponding to the fire by the color components.

In one possible embodiment, the apparatus further comprises:

the information determining module is used for determining target image acquisition equipment for identifying the fire;

In a third aspect, embodiments of the present invention provide a storage medium storing one or more programs, which are executable by one or more processors to implement the foregoing fire identification method.

In a fourth aspect, an embodiment of the present invention provides an electronic device, including: a processor and a memory, the processor being configured to execute the fire identification program stored in the memory to implement the aforementioned fire identification method.

According to the technical scheme provided by the embodiment of the invention, the image acquisition equipment in the current environment is called to acquire the image in the current environment and input the image into the fire identification model, and if the output result of the fire identification model meets the preset condition, the fire in the current environment is identified. Therefore, based on the image in the current environment, the fire in the current environment is identified, the fire can be found in time, and personal and property losses are avoided.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present specification, and other drawings can be obtained by those skilled in the art according to the drawings.

FIG. 1 is a schematic flow chart illustrating a method for fire identification according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a CIE LAB color model according to an embodiment of the present invention;

FIG. 3 is a schematic illustration of a flame segmented using a CIE LAB color model according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating a method for calculating fire location information according to an embodiment of the present invention;

FIG. 5 is a schematic view of a fire recognition device according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

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. 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.

For the convenience of understanding of the embodiments of the present invention, the following description will be further explained with reference to specific embodiments, which are not to be construed as limiting the embodiments of the present invention.

As shown in fig. 1, an implementation flow diagram of a fire identification method according to an embodiment of the present invention is shown, and the method may specifically include the following steps:

s101, determining image acquisition equipment in the current environment, and calling the image acquisition equipment to acquire images in the current environment;

in the embodiment of the present invention, the image capturing device may be a camera, and the category of the camera may be a dome camera, or may be other image capturing devices.

The ball machine can be used in different occasions, an integrated camera (including a zoom lens), a tripod head structure and a decoder are arranged in the ball machine, and an integrated front-end imaging device adopting a spherical shield is called an integrated ball camera. It has the characteristics of small volume, beautiful appearance, powerful function, convenient installation, simple use, easy maintenance and the like, and is also commonly called as a 'fast ball' or 'ball machine' by people.

In a specific fire monitoring environment, such as a mall, a school, a park and the like, in order to ensure that a recognizable range has no dead angle, the deployment requirements of the camera are as follows:

1. the monitoring pictures of the plurality of cameras can restore the universe in the monitoring environment;

2. a camera needs to be specially deployed in a whole area in a monitored environment and an occluded area;

3. in order to ensure that the time delay is controlled within a certain range (for example, not more than 3 seconds), all the cameras are required to be deployed in the same local area network, and the network bandwidth is the maximum value of the instant flow of each camera;

4. in order to ensure that the monitoring picture can be reviewed and used as a machine learning training sample, the storage space of the monitoring image should be reserved for more than 7 days.

After the deployment, it is possible to determine the image capturing devices in the current environment, i.e. the cameras, such as camera 1, camera 2, and camera 3 … …, and call these cameras to capture the images in the current environment, i.e. capture the pictures in the current environment by using these cameras, identify the smoke and flame in the pictures, and determine whether a fire occurs.

S102, inputting the image into a preset fire recognition model;

in the embodiment of the present invention, M1, M2, M3, M4, M5, M6 and presence/absence of fire are used to indicate 6 flame characteristics such as circularity, number of sharp corners, area ratio of red and green components, and area change rate, and the domain U is { x1, x2, …, x200}, the condition attribute M is { M1, M2, M3, M4, M5, M6}, and the decision attribute D is { D }, where D is 1 and D is 0, indicating a fire condition, and no fire condition.

The 6 flame features are discretized through a feature quantity classification table, detected data are counted, initial parameter values are respectively 100 iteration times N, 500 population scale N, 0.85 pc1, 0.1 pm1, 0.7 β and 1.8, the scattered fire/interference data set is trained through 4 algorithms of 6 flame features and Support Vector Machine (SVM), image-based fire detection algorithm based on the support vector Machine, rough set and SVM (RS + SVM), genetic algorithm, rough set and SVM (GA + RS + SVM), training samples are selected from 5000 data sets, 100 fire and interference samples are randomly selected, and part of data is selected from the rest as test samples.

The fire identification model can be obtained through the processing, the collected images are input into the fire identification model, and whether a fire disaster occurs in the current environment can be judged.

S103, if the output result of the fire identification model meets a preset condition, identifying that a fire exists in the current environment.

For the output result of the fire identification model, if the preset condition is met, if d is 1, the preset condition is met, and the fire in the current environment can be identified, otherwise, the fire does not exist.

For the images, the fire disaster in the current environment is identified, and flame segmentation can be performed, and the method specifically comprises the following steps: segmenting the image by utilizing a preset CIE LAB color model to obtain a color component corresponding to the image; and forming the flame corresponding to the fire by the color components.

For the CIE LAB color model, the basic features are: any color in nature can be expressed in the Lab model, and the application is the most extensive. The model can represent all human visible colors and is independent of equipment. The Lab model consists of luminance L and a, b2 color channels, as shown in FIG. 2.

In the CIE LAB color model shown in FIG. 2, the L threshold is 0-100, and when L is 80%, the color is 80% black; the threshold value of a is from +127 to-128, and when a is +127, the color is red.

For a given RGB channel image, we can switch to Lab space as follows:

wherein the content of the first and second substances,

the average of the pixel values of three channels, which contain important information, can be expressed as:

BR1 ∩ BR2 ∩ BR3 ∩ BR4 ∩ BR5, which is the final suspected flame region.

And segmenting the image by using a CIE LAB color model to obtain an L component, an a component and a b component corresponding to the image, and forming flames corresponding to the fire by the L component, the a component and the b component, as shown in figure 3.

In addition, in the embodiment of the present invention, a fire in the current environmental memory is identified, a target image capturing device that identifies the fire may be determined, and the location information of the fire is determined according to the location information of the target image capturing device. Wherein, the optional implementation of specifically determining the location information of the fire is as follows:

determining the height of the target image acquisition equipment from a horizontal plane and an included angle formed by the target image acquisition equipment and the fire; calculating the distance between the target image acquisition equipment and the fire in the horizontal direction according to the height and the included angle; and determining the position information of the fire according to the position information of the target image acquisition equipment and the distance.

As shown in fig. 4, P2 is a location of a fire, P1 is location information of the target image capturing device, b is a distance between the target image capturing device and the fire in a horizontal direction, θ is an included angle between the target image capturing device and the fire, a1 is a height of a rod, and a2 is a height of the camera itself, so that a is 1+ a2/2, b is tan (θ) a, and P2 is P1+ b. P2 is the location of the fire, which is a point b away from P1, and the direction of the fire coincides with the direction of the camera.

Furthermore, after the fire location information is determined, the fire category may be determined according to a mapping relationship between preset location information and the fire category, and fire extinguishing equipment corresponding to the fire category in the current environment is linked to perform fire extinguishing processing on the fire.

In the embodiment of the invention, the fire extinguishing devices corresponding to different types of fire are different, and the recognizable fire types are as follows:

the type A fire refers to a solid matter fire. Such materials are generally organic in nature and generally produce a glowing ember upon combustion. Such as fire, wood, coal, cotton, wool, hemp, paper, etc.

Class B fires refer to liquid or meltable solid matter fires. Such as kerosene, diesel oil, crude oil, methanol, ethanol, asphalt, paraffin and the like.

Type C fires refer to gas fires. Such as coal gas, natural gas, methane, ethane, propane, hydrogen, etc.

The D-type fire refers to metal fire. Such as potassium, sodium, magnesium, aluminum magnesium alloy and the like.

Class E fires, live fires. The object is burnt in a charged manner.

Class F fires, fires in cooking items (e.g., animal and vegetable fats) within the cooking appliance.

The types of the above-mentioned fires are shown in the following table 1 in the corresponding types of fire extinguishing equipment.

Fire category	Processing apparatus
		Class A fire	Water sprinkling irrigation
Class B fire	Dry powder
		Class C fire	Dry powder
Class D fire	Dry powder
		Class E fire	Dry powder
Class F fire	Dry powder

TABLE 1

In the process of linking the fire extinguishing equipment corresponding to the fire category in the current environment and carrying out fire extinguishing treatment on the fire, taking the A-type fire as an example, the fire extinguishing by the water spraying and irrigating equipment follows the following principle:

the equipment is aligned with the flame position for continuous irrigation

The irrigation process is continued until no flame is seen in the video

After no flame is seen, the water is kept for 10 minutes

During irrigation, if the water irrigation equipment has automatic control capability, the water irrigation equipment is communicated with the video recognition algorithm process, namely the water irrigation equipment stops irrigation, which is determined by the algorithm.

If the water irrigation equipment does not have the automatic control capability, a clock device linked with a video recognition algorithm is established, and the device has a time reporting function and a voice broadcasting function so as to inform a worker to control the on-off of the equipment.

Other types of fires, which employ dry powder fire extinguishing apparatus, should follow the following principles:

for example, in the case of a throwable dry powder fire extinguishing apparatus (e.g., a fire extinguishing ball), an automatic throwing device is provided which can throw the apparatus to the point of fire; under the precondition that the fire extinguishing equipment is not limited, the throwing process is continued until no flame is seen

Such as fire extinguishing equipment not equipped with an automatic throwing device or non-throwing fire extinguishing equipment (such as a portable dry chemical extinguisher), the operator should be informed of the location of the fire extinguishing equipment spray until no flames are visible.

After the fire is extinguished, the cause of the fire can be marked to facilitate fire review and prevention. The fire cause marks can be classified into the following two types:

automatic estimation

The fire monitoring system is built, automatic estimation can be carried out, and the estimation content comprises the following components:

and automatically marking and estimating the fire occurrence time according to the time for identifying the flame in the camera picture.

And identifying whether a person goes to a fire point before the fire according to a video clip before the time of identifying the flame in the camera picture (a common video identification algorithm with face identification capability is sufficient).

And identifying whether other flame ignition points exist or not according to the video clip before the actual flame is identified in the camera picture.

Hand operated presumption

If a fire monitoring system is not in resume, a camera monitoring picture is required to automatically capture video clips during and half an hour before a fire occurs so as to be checked by workers and manually marked.

Through the above description of the technical solution provided by the embodiment of the present invention, the image acquisition device in the current environment is called to acquire the image in the current environment and input the image into the fire identification model, and if the output result of the fire identification model meets the preset condition, the fire existing in the current environment is identified. Therefore, based on the image in the current environment, the fire in the current environment is identified, the fire can be found in time, and personal and property losses are avoided.

In addition, in the stage of fire treatment, the accurate starting of the fire extinguishing equipment is realized by combining the type of combustible substances in the fire occurrence area, so that the fire intensity aggravation caused by the improper use of the fire extinguishing equipment can be prevented (for example, the chemical reaction of explosion between chemicals or between chemicals and water can be caused by the use of water spraying and filling equipment for dangerous chemical equipment), and the larger loss (for example, the further damage of the equipment can be caused by the use of water spraying and filling equipment for electrical equipment) can also be prevented.

Moreover, based on a space-time calculation mode, the flame position can be accurately identified. The identified position is used as the fire extinguishing position of the fire extinguishing equipment, so that the time for determining the fire point can be reduced, and the risk of fire spreading is effectively reduced

Embodiments of the present invention also provide, with respect to method embodiments, an embodiment of a fire recognition apparatus, as shown in fig. 5, the apparatus may include: a device determination module 510, an image acquisition module 520, an image input module 530, a fire identification module 540.

A device determination module 510 for determining image capture devices within the current environment;

an image acquisition module 520, configured to invoke the image acquisition device to acquire an image in a current environment;

an image input module 530, configured to input the image into a preset fire recognition model;

and a fire recognition module 540, configured to recognize that a fire exists in the current environment if an output result of the fire recognition model meets a preset condition.

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 600 shown in fig. 6 includes: at least one processor 601, memory 602, at least one network interface 604, and other user interfaces 603. The various components in the mobile terminal 600 are coupled together by a bus system 605. It is understood that the bus system 605 is used to enable communications among the components. The bus system 605 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 605 in fig. 6.

The user interface 603 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball, touch pad, or touch screen, among others.

It will be appreciated that the memory 602 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a programmable Read-only memory (PROM), an erasable programmable Read-only memory (erasabprom, EPROM), an electrically erasable programmable Read-only memory (EEPROM), or a flash memory. The volatile memory may be a Random Access Memory (RAM) which functions as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (staticiram, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (syncronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), enhanced synchronous dynamic random access memory (EnhancedSDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM), and direct memory bus random access memory (DRRAM). The memory 602 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In some embodiments, memory 602 stores the following elements, executable units or data structures, or a subset thereof, or an expanded set thereof: an operating system 6021 and application programs 6022.

The operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application program 6022 includes various application programs such as a media player (MediaPlayer), a Browser (Browser), and the like, and is used to implement various application services. A program implementing the method of an embodiment of the invention can be included in the application program 6022.

In the embodiment of the present invention, by calling a program or an instruction stored in the memory 602, specifically, a program or an instruction stored in the application program 6022, the processor 601 is configured to execute the method steps provided by the method embodiments, for example, including: determining image acquisition equipment in the current environment, and calling the image acquisition equipment to acquire images in the current environment; inputting the image into a preset fire recognition model; and if the output result of the fire identification model meets the preset condition, identifying that the fire exists in the current environment.

The method disclosed by the above-mentioned embodiment of the present invention can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 601. The processor 601 may be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the method in combination with the hardware thereof.

It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the processing units may be implemented within 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), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.

For a software implementation, the techniques described herein may be implemented by means of units performing the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.

The electronic device provided in this embodiment may be the electronic device shown in fig. 6, and may perform all the steps of the fire identification method shown in fig. 1, so as to achieve the technical effect of the fire identification method shown in fig. 1, please refer to the related description of fig. 1 for brevity, which is not described herein again.

The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium herein stores one or more programs. Among others, the storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.

When one or more programs in the storage medium are executable by one or more processors to implement the above-described fire recognition method performed at the fire recognition device side.

The processor is used for executing the fire identification program stored in the memory so as to realize the following steps of the fire identification method executed on the fire identification device side:

determining image acquisition equipment in the current environment, and calling the image acquisition equipment to acquire images in the current environment; inputting the image into a preset fire recognition model; and if the output result of the fire identification model meets the preset condition, identifying that the fire exists in the current environment.

Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims

1. A method of fire identification, the method comprising:

inputting the image into a preset fire recognition model;

2. The method of claim 1, further comprising:

and forming the flame corresponding to the fire by the color components.

3. The method of claim 1, further comprising:

determining target image acquisition equipment for identifying the fire;

4. The method of claim 3, wherein determining the location information of the fire from the location information of the target image capture device comprises:

5. The method according to any one of claims 3-4, further comprising:

6. A fire identification device, the device comprising:

7. The apparatus of claim 6, further comprising:

and forming the flame corresponding to the fire by the color components.

8. The apparatus of claim 6, further comprising:

9. An electronic device, comprising: a processor and a memory, the processor being configured to execute a fire identification program stored in the memory to implement the fire identification method of any one of claims 1 to 5.

10. A storage medium storing one or more programs executable by one or more processors to implement the fire recognition method of any one of claims 1 to 5.