KR102364020B1 - Fire analysis method using fire scene footage - Google Patents

Abstract

The present invention relates to a fire analysis method using an image of the scene of a fire. One aspect of the present invention includes the steps of: scanning the scene of a fire to acquire the image of the scene of a fire; acquiring an analysis image of an analysis target included in the scene of a fire; generating a processed image by processing the scene of a fire and the analysis image; storing the processed image; and reading the stored processed image by a user's input and providing it to a user through an image providing unit. Accordingly, various information is efficiently provided to the user.

Description

Fire analysis method using fire scene footage

The present invention relates to a fire analysis method using a fire scene image.

In modern society, various items such as various electronic products, firearms, products containing inflammable substances, and products containing explosive substances are being used. there is.

As such, fire is a disaster that can occur anytime and anywhere, but once it does occur, it often causes great human and economic damage.

To this end, in general, at the site where a fire occurs, various fire site inspections such as the cause of the fire and the spread of the fire are conducted after the firefighting operation is completed.

However, fire can be caused by a wide variety of causes, and the degree or rate of fire spread can be changed by various internal/external factors. There are many cases of damage, so fire analysis is very difficult.

Therefore, the development of a means that can easily and accurately analyze the causes and factors of the spread of damage for fires that occur for various reasons in various spaces such as apartments and commercial buildings, or in various spaces such as houses, mountains, and roads is required. the current situation.

An object of the present invention is to provide a fire analysis method that can easily obtain information for fire analysis and provide it to a user.

Another object of the present invention is to provide a fire analysis method that can efficiently provide various information for fire analysis to a user.

In addition, an object of the present invention is to provide a fire analysis method that can realistically provide a variety of information for fire analysis to a user.

However, these problems are exemplary and the problems to be solved by the present invention are not limited thereto.

In order to achieve the above object, one aspect of the present invention is to scan a fire scene to acquire a fire scene image, acquiring an analysis image of an analysis target included in the fire scene, the fire scene image and the analysis image It may include the steps of generating a processed image by processing, storing the processed image, and reading the stored processed image according to a user's input and providing the processed image to the user through an image providing unit.

In addition, the method may further include recognizing a region having a singularity or an object having a singularity at the fire site and selecting the region as an analysis target.

The method may further include inputting basic data of the analysis target to the analysis image.

Also, the processed image may include virtual reality data generated based on spatial data of the fire site.

The present invention can provide a fire analysis method for easily acquiring information for fire analysis and providing it to a user.

In addition, the present invention may provide a fire analysis method for efficiently providing various information for fire analysis to a user.

In addition, the present invention may provide a fire analysis method for providing a user with a variety of information for fire analysis realistically.

However, these effects are exemplary, and the effects of the present invention are not limited thereto.

1 is a diagram schematically illustrating an example of use of a fire analysis system.
FIG. 2 is a block diagram schematically illustrating an embodiment of the fire analysis system of FIG. 1 .
3 is a diagram schematically illustrating a state in which a user wears an image providing unit according to an embodiment.
4 is a diagram illustrating an embodiment of a screen provided to a user through an image providing unit.
FIG. 5 is a diagram for explaining a second analysis target of FIG. 4 .
6 is a diagram illustrating another embodiment of a screen provided to a user through an image providing unit.
7 is a diagram illustrating another embodiment of a screen provided to a user through an image providing unit.
8 is a view for explaining an embodiment of a fire analysis method using a fire scene image through a fire analysis system.
9 is a view for explaining another embodiment of a fire analysis method using a fire scene image through a fire analysis system.
FIG. 10 is a diagram for explaining an embodiment of a step of obtaining a fire analysis predicted value of FIG. 9 .

Since the present invention can apply various transformations and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. Effects and features of the present invention, and a method for achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and when described with reference to the drawings, the same or corresponding components are given the same reference numerals, and the overlapping description thereof will be omitted. .

In the following embodiments, terms such as first, second, etc. are used for the purpose of distinguishing one component from another, not in a limiting sense.

In the following examples, the singular expression includes the plural expression unless the context clearly dictates otherwise.

In the following embodiments, terms such as include or have means that the features or components described in the specification are present, and the possibility that one or more other features or components will be added is not excluded in advance.

In the drawings, the size of the components may be exaggerated or reduced for convenience of description. For example, since the size and thickness of each component shown in the drawings are arbitrarily indicated for convenience of description, the present invention is not necessarily limited to the illustrated bar.

In the following embodiments, the x-axis, the y-axis, and the z-axis are not limited to three axes on a Cartesian coordinate system, and may be interpreted in a broad sense including them. For example, the x-axis, y-axis, and z-axis may be orthogonal to each other, but may refer to different directions that are not orthogonal to each other.

In cases where certain embodiments may be implemented otherwise, a specific process sequence may be performed different from the described sequence. For example, two processes described in succession may be performed substantially simultaneously, or may be performed in an order opposite to the order described.

Hereinafter, the fire analysis system 10 according to the present invention will be described in detail in accordance with the above-described principle.

1 is a diagram schematically illustrating an example of use of the fire analysis system 10 .

Referring to FIG. 1 , a fire analysis system 10 according to an embodiment of the present invention may be used to analyze a fire from a fire scene. For example, the fire analysis system 10 may be used to conduct a fire scene detection by investigating and analyzing a fire site after the firefighting operation is finished.

As an embodiment, the fire analysis system 10 may collect data for analyzing a fire from a fire site. That is, the fire analysis system 10 may collect data for analyzing a fire through the debris remaining at the fire site, the degree of deformation of the building or place where the fire occurred, the degree of dissipation, the remaining objects, and the like.

For example, the fire analysis system 10 may determine the cause of the fire from the fire site, the path of the spread of the fire, the time of the spread of the fire, the degree of spread of the fire, the degree of damage, the cause of the spread of damage or the reduction of the damage, the method for preventing a fire It is possible to collect various data related to fire, such as reasons attributable to fire occurrence or spread of fire.

Thereafter, the fire analysis system 10 determines the cause of the fire, the spread path of the fire, the spread time of the fire, the degree of spread of the fire, the degree of damage, the damage by the fire analysis agent etc. (hereinafter, the user) based on the collected data. It can help to perform analysis on the causes of spread or damage reduction, methods for fire prevention, and reasons attributable to the occurrence of fire or the spread of fire.

In addition, the fire analysis system 10 may provide various data related to fire to the user, or may provide the user with a result of analysis through fire related data. Accordingly, the user can easily and accurately perform fire analysis by receiving fire-related data or analysis results.

FIG. 2 is a block diagram schematically illustrating an embodiment of the fire analysis system 10 of FIG. 1 .

Referring to FIG. 2 , the fire analysis system 10 according to an embodiment of the present invention includes a scene image acquisition unit 110 that scans a fire scene to acquire a fire scene image, and an analysis target (AT) included in the fire scene. ), an analysis image acquisition unit 130 that acquires an analysis image of , an image processing unit 150 that processes the on-site image and the analysis image to generate a processed image P1, and a storage that stores the processed image P1 It may include a unit 160 and an image providing unit 170 that reads the processed image P1 stored in the storage unit 160 in response to a user's input and provides it to the user.

The on-site image acquisition unit 110 may be a means for acquiring a fire-site image by scanning a fire scene.

The fire site may be a place where a fire occurred, for example, a house where firefighting work is completed after a fire occurs, a multi-use facility such as a commercial building, or a place such as a detached house, a mountain, a road, etc.

The on-site image acquisition unit 110 may be a photographing device for scanning a fire scene. For example, the on-site image acquisition unit 110 may be one of a camera, a 3D scanner, an optical scanner, and a laser scanner. However, the present invention is not limited thereto and may be used as the on-site image acquisition unit 110 if it is a configuration that can scan the fire site to recognize the current state of the fire site and scan it.

The on-site image may be an image of the fire site obtained by the on-site image acquisition unit 110 . For example, the field image may be a static image or a dynamic image. Alternatively, the on-site image may be a panoramic image, or a continuous photo in which a plurality of static images are continuously captured for each frame. Alternatively, it may be a combination of a static image and a dynamic image.

As an embodiment, the on-site image may include a plurality of images. For example, when the fire site is a building, the scene image may include images of the outside and the inside of the building. Alternatively, when the fire site is an infrastructure such as a road or a bridge, images of the outside and the inside of the corresponding infrastructure may be included.

In detail, the field image may include a plurality of images in which a plurality of external surfaces are scanned, or at least two or more surfaces are continuously scanned. Also, a plurality of images obtained by scanning a plurality of inner surfaces or continuously scanning at least two or more surfaces may be included. In addition, when the building is divided into a plurality of spaces, that is, when the building is divided into a plurality of rooms, the on-site image is a plurality of scans of a plurality of inner surfaces for each partitioned space, or a plurality of continuously scanned at least two or more surfaces. May include video.

Accordingly, since the on-site image includes a plurality of images, the image of the place where the fire occurred may be implemented as a whole for each area. In addition, the user can select and check an image of a field area to be analyzed in the process of performing fire analysis through the acquired field image.

The analysis image acquisition unit 130 may be a means for acquiring an analysis image of the analysis target AT included in the fire scene.

The analysis target (AT) may mean an object or area requiring analysis for fire analysis.

For example, the target of analysis (AT) is the remains of structures remaining at the fire site, damaged areas of structures, soot, debris, objects remaining at the fire site, remnants or parts of objects at the fire site, electrical wiring, etc. It may mean that analysis is required for identification.

That is, the analysis target (AT) is the cause of the fire, the spread of the fire, the time of the spread of the fire, the degree of spread of the fire, the extent of the damage, the cause of the spread or reduction of the damage, the method for preventing the fire, the fire It may be a target that needs analysis for analysis related to fire, such as reasons attributable to the occurrence or spread of fire.

The analysis image acquisition unit 130 may be a device for photographing the analysis target AT. For example, the analysis image acquisition unit 130 may be one of a camera, a 3D scanner, an optical scanner, and a laser scanner. However, the present invention is not limited thereto, and may be used as the analysis image acquiring unit 130 if it is a configuration that can capture the analysis target AT and recognize the analysis target AT and acquire it as an image.

As an optional embodiment, the analysis image acquisition unit 130 may acquire a detailed image for each component constituting the analysis target AT. The detailed image may be an image of each component constituting the analysis target AT. For example, when the analysis target AT is an object, the analysis image acquisition unit 130 may disassemble the object into parts and photograph each part to obtain a detailed image. Alternatively, when the analysis target AT is an area, the analysis image acquisition unit 130 may divide the corresponding area into a plurality of areas and separately photograph each area to obtain a detailed image.

As will be described later, the detailed image acquired through the analysis image acquiring unit 130 may be provided to the user as detailed information on the corresponding analysis target AT according to the user's selection later.

There may be objects or areas that cause fire, and objects or areas that affect the spread of fire or damage. On the other hand, not only this, but also objects or areas that are lost by simply transferring flames from other ignition sources may exist at the site of a fire.

Therefore, it may be inefficient in terms of cost and time to analyze all areas or objects existing at the fire scene. In order to solve this problem, it may be desirable to recognize the objects or areas that need analysis among the objects or areas existing at the fire site, and to analyze them intensively. That is, it may be required to select an area or object that needs to be analyzed among areas or objects existing at the fire site and select it as an analysis target (AT).

Based on this request, as an optional embodiment, the fire analysis system 10 further includes an analysis target selection unit 120 that recognizes an area with a singularity or an object with a singularity at the fire site and selects it as an analysis target (AT). can do.

For example, the analysis target selection unit 120 may be a means for recognizing a region or object having a singularity at the fire site, selecting it as an analysis target (AT), and providing it to the user.

As an embodiment, the analysis target selection unit 120 recognizes an area or object with a singularity located at the fire scene while the field image acquisition unit 110 acquires the field image, and the recognized area or object requires analysis It can be determined whether or not For example, while the on-site image acquisition unit 110 acquires the on-site image, the analysis target selection unit 120 determines the area with a singularity or the degree of damage to the object, the tendency of damage, the degree of fire, the direction of soot, and the surrounding area. The analysis target (AT) can be selected from areas or objects with singularities in consideration of the arrangement of objects, the weather on the day of the fire, the humidity on the day of the fire, the temperature or humidity of the building or facility on the day of the fire, and the power consumption on the day of the fire. there is.

As another embodiment, the analysis target selection unit 120 recognizes an area or object with a singularity located at the fire site after the field image acquisition unit 110 acquires the field image, and the recognized area or object requires analysis. It can be determined whether or not For example, after the on-site image acquisition unit 110 acquires the on-site image, the analysis target selection unit 120 uses the acquired on-site image to determine the degree of damage, the tendency of damage, and the degree of damage to the area or object having a singularity. , the direction of the soot, the arrangement of surrounding objects, the weather on the day of the fire, the humidity on the day of the fire, the temperature and humidity of the building or facility on the day of the fire, the power consumption on the day of the fire, etc. AT) can be selected.

As an optional embodiment, the analysis target selection unit 120 may select the analysis target AT through machine learning, as will be described later. Details will be described later.

As an embodiment, the fire analysis system 10 may include the data input unit 140 for inputting basic data ad of the analysis target AT to the analysis image.

The data input unit 140 may be a means for inputting matters related to fire with respect to the analysis target AT.

The basic data may be data stored in advance or data provided from a separate server provided outside, but is not limited thereto.

As an optional embodiment, the data input unit 140 may input data regarding the characteristics of the analysis target AT itself to the analysis image. For example, the data input unit 140 may input information such as the material of the analysis target AT, limited power, ignition point, explosion potential, defect rate, and fire vulnerability to the analysis image. Alternatively, when the corresponding analysis target AT is the direct cause of the utterance, the data input unit 140 may be information obtained by comparing the appearance before and after the utterance.

As another optional embodiment, the data input unit 140 may input reference data or statistical data regarding the analysis target AT to the analysis image. For example, the data input unit 140 may include a case, cause, frequency, probability, or cause, frequency, probability of the corresponding analysis target (AT) causing a fire or a factor causing the fire to spread at another fire site in the analysis image. , or information such as the number of reports of situations that may have caused a fire can be entered.

As another optional embodiment, the data input unit 140 may input data regarding the characteristics of each component constituting the analysis target AT in the detailed image. For example, the data input unit 140 may input information such as the defective rate of each part constituting the analysis target (AT), the fire possibility, the ignition point, the explosion possibility, the limited power, the material, and the degree of vulnerability to fire into the detailed image. there is. Alternatively, when the configuration constituting the corresponding analysis target AT is the direct cause of the utterance, the data input unit 140 may be information comparing the appearance before and after the utterance.

As another optional embodiment, the data input unit 140 may input reference data or statistical data regarding each component constituting the analysis target AT in the detailed image. For example, the data input unit 140 is a component constituting the corresponding analysis target (AT) in the detailed image, for example, a case, cause, frequency, probability, or factor that causes a fire in relation to parts or materials, etc. You can enter information such as cases, causes, frequency, probability, or reported cases or number of situations that may have caused a fire.

The basic data (ad) input to the analysis image or the detailed image may be provided to a user who performs a fire analysis later. For example, the basic data ad may be automatically provided to the user, or may be provided according to the user's selection. Details will be described later.

The image processing unit 150 may be a means for generating the processed image P1 by processing the field image and the analysis image.

As an embodiment, the image processing unit 150 may match the field image and the analysis image. For example, the image processing unit 150 matches the analysis image to the analysis target (AT) included in the on-site image so that the analysis image on the analysis target (AT) or information on the analysis target (AT) overlaps with the fire scene. A processed image P1 may be generated.

As an optional embodiment, the processed image P1 may include virtual reality data generated based on spatial data of a fire scene. For example, the processed image P1 may be implemented as an image of the actual scene of the fire based on the scene image and spatial data. In this case, the spatial data may include design drawings or specifications of the corresponding building or facility, satellite images, and other construction information. That is, the image processing unit 150 can visually implement the appearance of the actual fire site using the field image and spatial data, and gives the user a feeling of directly observing the scene at the fire site in a place other than the fire site. can provide

The spatial data may be data stored in advance or data provided from a separate server provided outside, but is not limited thereto.

As an embodiment, the image processing unit 150 may generate the processed image P1 such that the field image and the analysis image are matched, and the analysis image is selectively displayed. For example, the image processing unit 150 may generate the processed image P1 so that the analyzed image appears only when the user selects a specific analysis target AT.

As another embodiment, the image processing unit 150 may match the field image with the detailed image or basic data ad. Also, the image processing unit 150 may generate the processed image P1 so that the detailed image and the basic data ad are selectively displayed. For example, the image processing unit 150 may generate the processed image P1 so that a detailed image or basic data ad of the analysis target AT appears only when the user selects a specific option. Details on this will be described later.

The storage unit 160 may be a means for storing the processed image P1. For example, the processed image P1 generated by the image processing unit 150 may be stored in the storage 160 , and the processed image P1 may be read out according to a user's selection and provided to the user. .

The storage unit 160 may be implemented through a non-volatile storage medium capable of continuously storing arbitrary data. For example, storage 160 may include, but is not limited to, disks, optical disks, and magneto-optical storage devices, as well as storage devices based on flash memory and/or battery-backed memory. doesn't happen

Also, the storage unit 160 may include a memory. Memory is the main storage device directly accessed by the processor, such as random access memory (RAM), such as dynamic random access memory (DRAM) and static random access memory (SRAM). It may mean a volatile storage device that is erased by a , but is not limited thereto.

Meanwhile, the fire analysis system 10 according to the present embodiment may further include a control unit. The control unit may control the operation of the fire analysis system 10 . For example, the control unit includes the on-site image acquisition unit 110 , the analysis image acquisition unit 130 , the analysis target selection unit 120 , the data input unit 140 , the image processing unit 150 , the storage unit 160 , and the image. At least one operation of the providing unit 170 may be controlled.

The control unit may be implemented with one processor, or may be implemented with a plurality of processors. When the controller is implemented with a plurality of processors, at least some of the plurality of processors may be located at physically separated distances. Also, the control unit is not limited thereto and may be implemented in various ways.

For example, the control unit may correspond to one or a plurality of processors. The processor may be implemented as an array of a plurality of logic gates, or may be implemented as a combination of a general-purpose microprocessor and a memory in which a program executable in the microprocessor is stored. In addition, it can be understood by those skilled in the art that the present embodiment may be implemented in other types of hardware.

3 is a diagram schematically illustrating a state in which a user wears the image providing unit 170 according to an embodiment.

The image providing unit 170 may be a means for reading the processed image P1 stored in the storage 160 according to a user's input and providing it to the user.

As an embodiment, the image providing unit 170 may provide the processed image P1 to the user by using virtual reality (VR). For example, the image providing unit 170 may provide the user with a feeling of performing identification at an actual fire scene through VR.

As described above, VR may be a virtual reality implemented by including at least one of a field image, an analysis image, a processed image P1, a detailed image, basic data ad, and spatial data.

As an optional embodiment, the image providing unit 170 may include a display device 171 and an input device 172 .

The display device 171 may be a means for displaying the processed image P1 to the user. For example, the display device 171 may be a head mounted display (HMD). That is, the display device 171 may include a display mounted near the user's eyes to display the processed image P1 to the user.

However, the present invention is not limited thereto and may be used as the display device 171 as long as it is a means capable of providing a user with a virtual reality in which a fire scene is implemented.

The input device 172 may be a means for controlling the display device 171 by interworking with the display device 171 . For example, the user may control to display the processed image P1 on the display device 171 through the input device 172 , and control to display a detailed image or basic data ad on the processed image P1 . can do.

As an embodiment, the input device 172 may be any one of a joystick type, a keyboard type, a button type, a motion recognition type, a touch screen type, a voice recognition type, and a view recognition type.

However, the present invention is not limited thereto, and any means capable of controlling the processed image P1 displayed on the display device 171 may be used as the input device 172 .

Hereinafter, an example of use of the fire analysis system 10 will be described in detail with reference to FIGS. 4 to 7 . For convenience of description, the content overlapping with the above will be omitted or briefly described.

4 is a diagram illustrating an embodiment of a screen provided to a user through the image providing unit 170 .

Referring to FIG. 4 , the image providing unit 170 may provide a processed image P1 to the user.

As an embodiment, the processed image P1 may be an image in which an on-site image and an analysis image are registered, and as an optional embodiment, a detailed image or an image to which basic data ad is added.

As an embodiment, the processed image P1 may be an image of an actual fire site implemented as an image based on spatial data of the fire site.

The processed image P1 may be configured to include at least one analysis target AT. For example, the analysis target AT may be an area or an object having a singularity.

As an embodiment, the first analysis object AT1 may be soot, and the second analysis object AT2 , the third analysis object AT3 , and the fourth analysis object AT4 may be objects remaining at the fire site. There, the fifth analysis target (AT5) may be a damaged area of the structure, the sixth analysis target (AT6) may be an outlet disposed at the fire site, and the seventh analysis target (AT7) may be the remains of the structure there is.

FIG. 5 is a diagram for explaining the second analysis target AT2 of FIG. 4 .

Referring to FIG. 5 , the image providing unit 170 may provide a detailed image of each configuration constituting the second analysis target AT2 to the second analysis target AT2 to the user.

In addition, as an optional embodiment, the image providing unit 170 provides each basic data regarding each component constituting the second analysis target AT2 input through the data input unit 140 automatically or by the user's selection. (ad) can be indicated.

For example, when the user wants to view the detailed configuration of the second analysis object AT2, the user may select the second analysis object AT2, and the image providing unit 170 provides each of the second analysis objects AT2. A detailed image of the configuration may be provided to the user.

In addition, if the user wants to view the basic data ad of each configuration constituting the second analysis target AT2, each configuration or the entire configuration can be selected, and the image providing unit 170 provides the second analysis target AT2. The basic data (ad) of each configuration constituting the display may be provided to the user.

Although FIG. 5 is illustrated based on the second analysis object AT2, it goes without saying that the above-described process may be performed on the remaining analysis objects AT.

6 is a diagram illustrating another embodiment of a screen provided to a user through the image providing unit 170 .

Referring to FIG. 6 , the image providing unit 170 may display basic data ad related to at least one analysis target AT by the user's selection and provide it to the user.

As an optional embodiment, the analysis target AT may be a target selected by a user or a target selected by the analysis target selection unit 120 .

For example, when the user wants to view basic data ad regarding the first analysis object AT1, the second analysis object AT2, the fourth analysis object AT4, and the fifth analysis object AT5, the corresponding analysis The target AT may be selected, and the image providing unit 170 may display and provide basic data ad of the analysis target AT selected by the user to the user.

7 is a diagram illustrating another embodiment of a screen provided to a user through the image providing unit 170 .

Referring to FIG. 7 , the image providing unit 170 selects the corresponding analysis target (AT) to view detailed information on the specific analysis target (AT) in virtual reality in which a fire scene is implemented, and the corresponding analysis target (AT) is selected. ) can be provided by displaying the processed image P1 so that the detailed image and detailed information about it overlap the fire scene.

For example, when the user wants to view detailed information on the second analysis object AT2, the user may select the second analysis object AT2, and the image providing unit 170 configures the second analysis object AT2. The detailed image of the component and the basic data (ad) of each component may be overlapped and provided to the user. Here, the provided components and basic data ad may be those described with reference to FIG. 5 .

According to the fire analysis system 10 described above, a user can perform a fire scene detection operation in a virtual reality in which an actual fire scene is implemented.

In addition, in the virtual reality, information about objects or areas of the fire site are reflected in the virtual reality, and each object is implemented in a place corresponding to the location at the actual fire site, so users can more easily and accurately fire the fire. analysis can be performed.

In addition, when the user wants to view detailed information about a specific analysis target (AT), the analysis image or detailed image of the analysis target (AT) is displayed in front of them, so fire analysis can be performed intuitively, making it easier and more accurate can be done

In addition, the field image, the analysis image, the detailed image, and the processed image P1 reflecting the basic data ad are stored in the storage unit 160, so the user can read the processed image P1 at any time and perform fire analysis. there is.

8 is a view for explaining an embodiment of a fire analysis method using a fire scene image through a fire analysis system.

For convenience of description, the content overlapping with the fire analysis system 10 described with reference to FIGS. 1 to 7 will be omitted or briefly described.

Referring to FIG. 8 , a fire analysis method using a fire scene image according to an embodiment includes the steps of acquiring a fire scene image by scanning a fire site (S110), and analysis of an analysis target (AT) included in the fire scene Obtaining an image (S130), generating a processed image (P1) by processing the fire scene image and the analyzed image (S150), storing the processed image (P1) (S160), and the stored processing It may include a step (S170) of reading the image P1 according to the user's input and providing it to the user through the image providing unit 170 .

The step of obtaining the fire scene image (S110) may be the step of acquiring the fire site image by scanning the fire site (S110).

The fire site may be a place where a fire occurred, for example, a house where firefighting work is completed after a fire occurs, a multi-use facility such as a commercial building, or a place such as a detached house, a mountain, a road, etc.

The step of acquiring the fire scene image ( S110 ) may be performed through the on-site image acquisition unit 110 .

For example, the on-site image acquisition unit 110 may acquire an image of the fire site by scanning the fire site, and the on-site image may be a static image, a dynamic image, or a combination of a static image and a dynamic image. Alternatively, the on-site image may be a panoramic image, or a continuous photo in which a plurality of static images are continuously captured for each frame. Alternatively, it may be a combination of a static image and a dynamic image.

The fire analysis method using the fire scene image according to this embodiment can realize the fire scene as an image by acquiring the scene image, and the user can view the image of the field area that he wants to analyze in the process of performing fire analysis through the scene image. You can check it by selecting it.

As an optional embodiment, the fire analysis method using the fire scene image according to the present embodiment may further include the step (S120) of selecting an analysis target (AT). For example, the step of selecting the analysis target (AT) (S120) may include a step (S120) of recognizing an area having a singularity or an object with a singularity at the fire site and selecting the target for analysis AT (S120).

There may be objects or areas that cause fire, and objects or areas that affect the spread of fire or damage. On the other hand, not only this, but also objects or areas that are lost by simply transferring flames from other ignition sources may exist at the site of a fire.

Therefore, it may be inefficient in terms of cost and time to analyze all areas or objects existing at the fire scene.

To this end, it is possible to selectively analyze areas or objects that exist at the fire site by selecting those requiring analysis. In this way, the step (S120) of recognizing a region or object having a singularity and selecting it as an analysis target (AT) may be performed through the analysis target selection unit 120 .

For example, the analysis target selection unit 120 may recognize an area or object having a singularity at the fire site, select it as an analysis target (AT), and provide it to the user.

Specifically, the step of selecting the analysis target AT ( S120 ) may be performed simultaneously with the step of acquiring the on-site image ( S110 ), or may be performed after the step of acquiring the on-site image ( S110 ) is performed.

For example, while the on-site image acquisition unit 110 acquires the on-site image, the analysis image acquisition unit 130 detects the area with a singularity or the degree of damage to the object, the tendency of damage, the degree of loss, the direction of soot, and the surrounding area. The analysis target (AT) can be selected from areas or objects with singularities in consideration of the arrangement of objects, the weather on the day of the fire, the humidity on the day of the fire, the temperature or humidity of the building or facility on the day of the fire, and the power consumption on the day of the fire. and it can be provided to the user.

Alternatively, after the on-site image acquisition unit 110 acquires the on-site image, the analysis image acquisition unit 130 performs the analysis image acquisition unit 130 through the acquired on-site image to the degree of damage, the tendency of damage, the degree of loss, and soot in the area or object having a singularity. Analysis target (AT) among areas or objects with a singularity in consideration of the direction of can be selected, and can be provided to the user.

In this case, the user may select whether to acquire the analysis image for the provided analysis-necessary object. That is, the user may acquire an analysis image by selecting at least one of the analysis targets AT selected by the analysis target selection unit 120 .

As an optional embodiment, if there is an area or object that is not selected and provided by the analysis target selection unit 120 but is considered to be analyzed, the user may select it and obtain an analysis image for the region or object.

The step of acquiring the analysis image (S130) may be the step of acquiring the analysis image of the analysis target AT included in the fire scene (S130).

The analysis target (AT) may mean an object or area requiring analysis for fire analysis. For example, the target of analysis (AT) is the remains of structures remaining at the fire site, damaged areas of structures, soot, debris, objects remaining at the fire site, remnants or parts of objects at the fire site, electrical wiring, etc. It may mean that analysis is required for identification.

The step of acquiring the analysis image ( S130 ) may be performed through the analysis image acquisition unit 130 .

For example, the analysis image acquisition unit 130 may acquire the analysis image with respect to the analysis target AT provided by the analysis target selection unit 120 or selected by the user.

As an optional embodiment, the analysis image acquisition unit 130 may acquire a detailed image for each component constituting the analysis target AT. For example, when the analysis target AT is an object in which a plurality of components are combined, the analysis image acquisition unit 130 decomposes the analysis target AT into parts and takes pictures for each part to obtain a detailed image. can do. Alternatively, when the analysis target AT is an area, the analysis image acquisition unit 130 may divide the corresponding area into a plurality of areas and separately photograph each area to obtain a detailed image.

As an embodiment, the fire analysis method using the fire scene image according to the present embodiment may further include inputting basic data ad of the analysis target AT ( S140 ).

For example, the step of inputting the basic data ad ( S140 ) may be the step of inputting the basic data ad of the analysis target AT into the analysis image or the detailed image ( S140 ). The basic data ad may be data related to a fire for the analysis target AT.

The step of inputting the basic data ad ( S140 ) may be performed through the data input unit 140 .

As an embodiment, the data input unit 140 may input data regarding the characteristics of the analysis target AT itself to the analysis image.

As another embodiment, the data input unit 140 may input reference data or statistical data regarding the analysis target AT to the analysis image.

As another embodiment, the data input unit 140 may input data regarding the characteristics of each component constituting the analysis target AT in the detailed image.

As another embodiment, the data input unit 140 may input reference data or statistical data regarding each component constituting the analysis target AT in the detailed image.

The step of generating the processed image P1 ( S150 ) may be a step of generating the processed image P1 by processing the fire scene image and the analysis image ( S150 ).

The operation of generating the processed image P1 ( S150 ) may be performed through the image processing unit 150 .

As an embodiment, the image processing unit 150 may match the field image and the analysis image. For example, the image processing unit 150 may match the analysis image to the field image.

As an optional embodiment, the processed image P1 may include virtual reality data generated based on spatial data of a fire scene. For example, the processed image P1 may be implemented as an image of the actual scene of the fire based on the scene image and spatial data.

As an embodiment, the processed image P1 may be an image processed so that the field image and the analysis image are matched, and the analysis image is selectively displayed. For example, the image processing unit 150 may generate the processed image P1 so that the analyzed image appears only when the user selects a specific analysis target AT.

As another embodiment, the processed image P1 may be a combination of the detailed image and the basic data ad. In addition, the processed image P1 may be an image processed so that the detailed image and the basic data ad are selectively displayed. For example, the detailed image and basic data ad may appear only when the user selects a specific option.

The step of storing the processed image P1 ( S160 ) may be a step of storing the processed image P1 in the storage unit 160 . Accordingly, the processed image P1 stored in the storage 160 may be read out later according to the user's selection and provided to the user.

The step of providing the processed image P1 ( S170 ) may be a step ( S170 ) of reading the processed image P1 according to a user's input and providing the processed image P1 to the user through the image providing unit 170 .

As an embodiment, the step of providing the processed image P1 ( S170 ) may be performed through virtual reality technology (VR), for example, an image system including a display device 171 and an input device 172 . This can be done through the study 170 .

In the step of providing the processed image P1 ( S170 ), the processed image P1 is provided to the user through the display device 171 , and the user may control the processed image P1 through the input device 172 . . For example, the user may control to display the processed image P1 on the display device 171 , or to display a detailed image or basic data ad on the processed image P1 .

9 is a view for explaining another embodiment of a fire analysis method using a fire scene image through the fire analysis system 10, and FIG. 10 is an embodiment of the step of obtaining the fire analysis predicted value of FIG. It is a drawing for explanation.

A fire analysis method using a fire scene image according to another embodiment will be described with reference to FIGS. 9 and 10 . However, for convenience of description, the content overlapping with the above will be briefly described or omitted.

The fire analysis method using the fire scene image according to the present embodiment may perform fire analysis using machine learning.

The fire analysis method using a fire scene image according to an embodiment is a fire analysis method using a fire scene image using machine learning, and includes the steps of scanning a fire scene and extracting fire characteristics (S210), the extracted fire It may include inputting the characteristics into the machine learning model to obtain a fire analysis predicted value (S220) and providing the obtained fire analysis predicted value to a user (S230).

In this case, the machine learning model may include machine learning model data learned to predict the cause of the fire, etc. according to the situation of the fire site. For example, the machine learning model recognizes the situation at the fire site, and based on this, predicts values for the cause of the fire, the spread of the fire, the degree of damage, the spread of the damage, the fire prevention measures, etc. can be derived and provided to the user. . In this case, the user may perform the fire analysis based on the provided predicted value, so that the fire analysis can be easily and accurately performed, and the time required for the analysis can be reduced by reducing trial and error.

The step of extracting fire characteristics by scanning the fire site (S210) is to extract the characteristics of the fire from the fire site, for example, the cause of the fire, the path of spread, the degree of spread of damage, and the prevention method of the fire to focus on a certain target. It can be a step to choose whether or not it should be analyzed.

As an embodiment, the step of extracting the fire characteristics ( S210 ) may be performed by scanning the fire scene through the scene image acquisition unit 110 . For example, the control unit can recognize information such as the degree of damage of facilities, the tendency of damage to facilities, the tendency of soot, the degree of soot, and the rate of burning while scanning the fire scene through the on-site image acquisition unit 110. And based on this, the characteristics of fire can be extracted.

As an optional embodiment, the control unit can recognize the degree of damage of the facility, the tendency of the damage of the facility, the tendency of the soot, the degree of soot, the burnout rate, etc. through the on-site image acquisition unit 110, and apply this to the machine learning model By inputting it, it is possible to extract the characteristics of the fire that match it. Thereafter, the control unit may provide the user with the characteristics of the extracted fire.

In this case, the user may predict the characteristics of the actual fire with reference to the provided characteristics of the fire and analyze the fire based on the characteristics of the fire.

The step of obtaining the fire analysis prediction value ( S220 ) may be a step of obtaining the fire analysis prediction value by inputting the extracted fire characteristics into the machine learning model.

For example, the step of obtaining a fire analysis prediction value (S220) is based on the extracted fire characteristics, the cause of the fire, the cause of the spread of the fire, the tendency of the fire to develop, the cause of the spread of damage, the method of preventing the fire, etc. It may be a step of obtaining an analysis prediction value related to the fire.

The predicted analysis prediction value may be provided to the user. In this case, the user may predict the analysis result of the actual fire with reference to the provided analysis prediction value, or perform additional analysis or in-depth analysis based on this.

As an embodiment, the step of obtaining the fire analysis predicted value ( S220 ) may include selecting an analysis target (AT) requiring analysis based on the extracted fire characteristics and providing the selected analysis target (AT) to the user ( S221 ).

For example, the step (S221) of selecting an analysis target (AT) and providing it to a user selects an analysis target (AT) requiring analysis for the topic analysis based on the extracted fire characteristics, and provides the selection result to the user It may be a step to provide

As an optional embodiment, the control unit may input the extracted fire characteristics to the machine learning model and select an analysis target (AT) matching the same.

For example, the control unit selects the analysis target (AT) that needs analysis among the areas or objects included in the on-site image to the user based on the matching result that a fire site having a specific fire characteristic is a trace of a fire caused by a specific factor. can be provided to users. To this end, the machine learning model may include machine learning data on what characteristics a fire caused by a specific factor leaves on the fire scene.

As another example, the control unit selects an analysis target (AT) that needs analysis among areas or objects included in the on-site image to the user based on the matching result that a fire site having a specific fire characteristic has a fire spread due to a specific cause can be provided to the user. To this end, the machine learning model may include machine learning data on what characteristics a fire spread by a specific factor leaves on a fire scene.

However, the machine learning model is not limited thereto, and the machine learning model is data that matches fire development and fire characteristics, data that matches the cause of damage and fire characteristics, data that matches fire detection and fire prevention methods, and fire It may further include data such that the signs of the fire and the characteristics of the fire are matched.

As another optional embodiment, the step (S220) of obtaining the predictive value of the fire analysis may further include the step (S222) of obtaining an analysis image of the analysis target (AT) selected by the user from among the selected analysis targets (AT) can

For example, the user may be provided with a list of analysis objects (ATs) that require analysis, and the analysis image acquisition unit 130 may acquire an analysis image by photographing the analysis objects (ATs) selected by the user's selection. .

As an embodiment, the user may control the controller to acquire all the analysis images of all the analysis objects (ATs) included in the provided analysis object (AT) list. Alternatively, the user may control the controller to select only the analysis subjects (ATs), which are considered to require acquisition of analysis images, from among the analysis subjects (ATs) included in the provided analysis target (AT) list to acquire only their analysis images. there is.

As another optional embodiment, in the step (S222) of obtaining a fire analysis prediction value, when an analysis target (AT) is selected and an analysis image is obtained, the selected analysis target (AT) and the analysis image are input to the machine learning model and analyzed The method may include obtaining a predicted value of the fire causality of the target AT and providing the obtained predicted value of the fire causality to the user ( S223 ).

For example, if the selected analysis target (AT) and the analysis image are input into the machine learning model, when a fire occurs by the analysis target (AT), the shape of the analysis target (AT) is derived, and it is actually acquired Compared with the analyzed image, it is possible to calculate what the probability of a fire occurring by the corresponding analysis target (AT) is, and provide it to the user. To this end, the machine learning model may further include data on how the specific analysis target (AT) will remain at the fire site when the specific analysis target (AT) is the cause of the fire.

As another example, if the selected analysis target (AT) and the analysis image are input to the machine learning model, if the fire is spread by the analysis target (AT), what shape the analysis target (AT) remains, and It is possible to calculate what the probability of a fire spreading by the corresponding analysis target (AT) is compared with the actually acquired analysis image and provide it to the user. To this end, the machine learning model may further include data on how the specific analysis target (AT) remains at the fire site when the specific analysis target (AT) is the cause of the fire spread.

However, the machine learning model is not limited thereto, and the machine learning model is data in which the development trend of fire and the analysis target (AT) are matched, the cause of damage spread and the analysis target (AT) are matched, and the signs of fire and the analysis target (AT) are matched. It may further include the matched data and the like.

Through this, the user can predict whether a fire occurs, spreads, or spreads damage by which analysis target (AT) in recognizing a fire site through this, and based on this, more quickly, easily and accurately A fire analysis can be performed.

The step of providing the fire analysis prediction value to the user ( S230 ) may be a step of providing the fire analysis prediction value extracted from the machine learning model to the user.

As an embodiment, the step (S230) of providing the fire analysis value may be performed simultaneously with the step (S170) of providing the processed image P1, as described above.

For example, the user may be provided with the processed image P1 through the image providing unit 170, and may be provided with an analysis image, detailed image, and basic data ad through the processed image P1, At the same time, a fire analysis prediction value may also be provided to the user.

As an optional embodiment, the obtained fire analysis prediction value is provided as one of the basic data (ad) for the configuration constituting the corresponding analysis target (AT) or the analysis target (AT), as described with reference to FIGS. 5 to 6 . it might be

For example, when a user selects a specific analysis target (AT) from among the processed images P1 and receives an analysis image for it, it is derived through a machine learning model as basic data (ad) for the corresponding analysis target (AT). A fire analysis predicted value may be provided to the user at the same time.

As such, the present invention has been described with reference to the embodiments shown in the drawings, which are merely exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. . Accordingly, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

The specific implementations described in the embodiment are only embodiments, and do not limit the scope of the embodiment in any way. For brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection or connection members of lines between the components shown in the drawings illustratively represent functional connections and/or physical or circuit connections, and in an actual device, various functional connections, physical connections that are replaceable or additional may be referred to as connections, or circuit connections. In addition, unless there is a specific reference such as "essential", "importantly", etc., it may not be a necessary component for the application of the present invention.

In the specification of embodiments (especially in the claims), the use of the term “the” and similar referential terms may be used in both the singular and the plural. In addition, when a range is described in the embodiment, it includes the invention to which individual values belonging to the range are applied (unless there is a description to the contrary), and each individual value constituting the range is described in the detailed description. . Finally, the steps constituting the method according to the embodiment may be performed in an appropriate order, unless the order is clearly stated or there is no description to the contrary. The embodiments are not necessarily limited according to the description order of the steps. The use of all examples or exemplary terms (eg, etc.) in the embodiment is merely for describing the embodiment in detail, and unless it is limited by the claims, the scope of the embodiment is limited by the examples or exemplary terminology. it is not In addition, those skilled in the art will appreciate that various modifications, combinations, and changes may be made in accordance with design conditions and factors within the scope of the appended claims or their equivalents.

10: fire analysis system
110: field image acquisition unit
120: analysis target selection unit
130: analysis image acquisition unit
140: data input unit
150: image processing unit
160: storage
170: video providing unit
P1: Machining video
AT: analysis target

Claims (4)

As a fire analysis method for identification of a fire site where firefighting work has been completed,
acquiring a fire scene image by scanning the fire scene;
An area having a singularity based on at least one of the degree of damage, the tendency of the fire, the degree of fire, the direction of soot, the arrangement of surrounding objects, the weather on the day of the fire, the humidity on the day of the fire, and the power consumption on the day of the fire or recognizing an object having a singularity and selecting the recognized area or object as an analysis target;
acquiring an analysis image of an analysis target included in the fire scene;
generating a processed image by processing the fire scene image and the analysis image;
storing the processed image; and
Including; reading the stored processed image by a user's input and providing it to the user through an image providing unit;
In the obtaining of the analysis image, when the analysis target is an object, the object is decomposed into parts to obtain a detailed image corresponding to each part, and when the analysis target is an area, the area is divided into a plurality of areas and each Including; acquiring a detailed image corresponding to the region;
The generating of the processed image includes matching the detailed image corresponding to the analysis target to the processed image; including, a fire analysis method using a fire scene image. According to claim 1,
The video providing unit,
When the user selects a specific analysis target, the detailed image corresponding to the selected analysis target is overlapped with the fire scene image and provided to the user. According to claim 1,
Inputting the basic data of the analysis target to the analysis image; further comprising, a fire analysis method using a fire scene image. According to claim 1,
The processed image includes virtual reality data generated based on spatial data of the fire site, a fire analysis method using a fire scene image.

Images