KR20220096573A - Apparatus for efficient arrangement of rescue resources in use of the unmanned aerial vehicle, and method thereof, and computer recordable medium stroring program to perform the method - Google Patents

Abstract

Provided is a control device for efficient arrangement of rescue resources using an unmanned aerial vehicle. The control device comprises: an image collection unit which collects images on a plurality of zones in a disaster area through a wireless communication network from an unmanned aerial vehicle equipped with a photographing unit; a global image generation unit which extracts a plurality of feature points from the respective collected images on the plurality of zones, matches the plurality of feature points to calculate a relative distance of the feature points for the respective images, and generates a global image projected on the coordinate system for the entirety of the disaster area; a global image analysis unit which calculates a distribution chart of persons to be rescued, including geographical location information by each rescue area and the number of persons to be rescued by each rescue area, based on the global image; and a rescue resource allocation unit which arranges a plurality of rescue resource units based on the distribution chart of persons to be rescued.

Description

A control device for efficient arrangement of rescue resources using an unmanned aerial vehicle, a method for the same, and a computer readable recording medium on which a program for executing the method is recorded method thereof, and computer recordable medium storing program to perform the method}

The present invention relates to unmanned aerial vehicle (UAV) technology, and more particularly, to a control device for efficiently disposing rescue resources in a disaster area using an unmanned aerial vehicle and a method therefor.

Lifesaving activities using unmanned aerial vehicles such as drones are drawing attention in disaster situations that are difficult for humans to access, such as earthquakes, tsunamis, and fires. In particular, in a disaster situation, it is necessary to quickly identify the area and the number of people in need of rescue in a wide area (that is, the person in need) and to deploy the appropriate rescue resources quickly, so as not to miss the golden hour in a disaster environment that requires urgent wages and to be effective structure becomes possible. However, the conventional disaster relief system using an unmanned aerial vehicle merely captures the situation of the disaster area with an image using a drone, so there is a limit in quickly collecting information necessary for the effective arrangement of rescue resources.

Korean Patent Laid-Open Patent No. 2020-0002361 published on January 08, 2020 (Title: System and method for providing aerial image using autonomous driving drone)

An object of the present invention is to provide a control device for quickly and efficiently arranging rescue resources using an unmanned aerial vehicle when a disaster occurs in a wide area, and a method therefor.

The present invention for achieving the above object is a control device for the efficient arrangement of rescue resources using an unmanned aerial vehicle, and collects images for a plurality of areas of a disaster area from an unmanned aerial vehicle equipped with a photographing unit through a wireless communication network. and extracting a plurality of feature points from each image for the plurality of areas collected, matching the extracted feature points to calculate the relative distance of the feature points for each image, and the disaster A global image generation unit that generates a global image projected on the coordinate system for the entire region of the region, and a global image analysis that calculates a distribution map of users based on the global image including geographic location information for each structural area and the number of users for each structural region It can be achieved by including a rescue resource assignment unit for disposing a plurality of rescue resource units based on the distribution of the requesting person and the department.

Here, it may further include a disaster area setting unit that provides geographic location information of the disaster area to the unmanned aerial vehicle.

In addition, the global image analysis unit includes an object classification model that is an artificial neural network model trained to calculate and output coordinates of an area box indicating an area occupied by an object included in the image and a probability that an object is a human in the area box, The object classification model calculates and outputs the coordinates of the area box indicating the area occupied by the object included in the image through calculation and the probability that the object in the area box is a person, and if the output probability is greater than or equal to a preset threshold, the area box Recognizes that there is a requester within, and based on the coordinates and number of area boxes in which the requestor is present, a distribution map of users including geographic location information for each structural area within a certain range and the number of requesters for each structural area can be calculated. .

In addition, the rescue resource assignment unit may transmit geographic location information for each rescue area and information on the number of rescuers for each rescue area to a plurality of rescue resource units connected through a communication network based on the distribution of rescuers.

In another aspect, the present invention includes the steps of: an image collection unit collecting images for a plurality of regions of a disaster area through a wireless communication network from an unmanned aerial vehicle equipped with a photographing unit; extracting a plurality of feature points from an image, matching the extracted feature points to calculate the relative distance of the feature points with respect to each image, and generating a global image projected on the coordinate system for the entire area of the disaster area; , calculating, by the global image analysis unit, a distribution map of persons requesting including geographic location information for each structure area and the number of persons requesting each structure area based on the global image; It provides a method for the efficient deployment of rescue resources using an unmanned aerial vehicle, comprising the step of deploying.

Here, the method may further include providing, by the disaster area setting unit, geographic location information of the disaster area to the unmanned aerial vehicle.

In addition, the global image analysis unit includes an object classification model that is an artificial neural network model trained to calculate and output coordinates of an area box indicating an area occupied by an object included in the image and a probability that an object is a human in the area box, The object classification model calculates and outputs the coordinates of the area box indicating the area occupied by the object included in the image through calculation and the probability that the object in the area box is a person, and if the output probability is greater than or equal to a preset threshold, the area box Recognizes that there is a requester within, and based on the coordinates and number of area boxes in which the requestor is present, a distribution map of users including geographic location information for each structural area within a certain range and the number of requesters for each structural area can be calculated. .

In addition, the rescue resource assignment unit may transmit geographic location information for each rescue area and information on the number of rescuers for each rescue area to a plurality of rescue resource units connected through a communication network based on the distribution of rescuers.

In another aspect, the present invention provides a computer-readable recording medium in which a program for executing the above-described method for efficient allocation of rescue resources using an unmanned aerial vehicle is recorded in a computer device.

According to the present invention, by analyzing the image taken by an unmanned aerial vehicle (UAV) through artificial intelligence and computer vision technology, the situation is recognized, and a global image of the disaster area is generated to calculate the distribution of the victims, so that the demanders density By arranging the necessary rescue resources efficiently and quickly according to

1 is a view for explaining a system for efficiently arranging rescue resources using an unmanned aerial vehicle according to an embodiment of the present invention.
2 is a block diagram for explaining the configuration of a control device according to an embodiment of the present invention.
3 is a block diagram for explaining the configuration of an unmanned aerial vehicle according to an embodiment of the present invention.
4 is a flowchart illustrating a method for efficiently arranging rescue resources using an unmanned aerial vehicle according to an embodiment of the present invention.
5 is a diagram for explaining an example of generating one global image for the entire disaster area from a plurality of images for each area of the disaster area according to an embodiment of the present invention.
6 is an exemplary diagram of a method for recognizing the presence of a requester from a global image through an object classification model according to an embodiment of the present invention.
7 is a diagram for explaining a method of arranging a rescue resource of an appropriate size according to a distribution diagram of users according to an embodiment of the present invention.

Prior to the detailed description of the present invention, the terms or words used in the present specification and claims described below should not be construed as being limited to their ordinary or dictionary meanings, and the inventors should develop their own inventions in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention based on the principle that it can be appropriately defined as a concept of a term for explanation. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are only the most preferred embodiments of the present invention, and do not represent all the technical spirit of the present invention, so various equivalents that can be substituted for them at the time of the present application It should be understood that there may be water and variations.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In this case, it should be noted that in the accompanying drawings, the same components are denoted by the same reference numerals as much as possible. In addition, detailed descriptions of well-known functions and configurations that may obscure the gist of the present invention will be omitted. For the same reason, some components are exaggerated, omitted, or schematically illustrated in the accompanying drawings, and the size of each component does not fully reflect the actual size.

First, a system for efficiently disposing rescue resources using an unmanned aerial vehicle according to an embodiment of the present invention will be described. 1 is a diagram for explaining a system according to an embodiment of the present invention according to an embodiment of the present invention. Referring to FIG. 1 , a system for efficient deployment of rescue resources using an unmanned aerial vehicle according to an embodiment of the present invention is basically a control device 100 , an unmanned aerial vehicle 200 , and the Ministry of Rescue Resources. (300).

The control device 100 controls the unmanned aerial vehicle 200 through a wireless communication network, and collects images of the disaster area photographed by the unmanned aerial vehicle 200 .

The unmanned aerial vehicle 200 receives geographic location information on the disaster area A from the control device 100 and flies around the disaster site, and transmits an image of the disaster area to the control device 100 .

The rescue resource unit 300 receives from the control device 100 geographic location information on the rescue area for which a rescue is requested and information on the number of rescuers existing in the rescue zone. Rescue resource unit 300 may be provided with various types of rescue resources, and information on the size of rescue workers for types of vehicles, rescue workers, etc. is registered in the control device 100 .

Then, the control device 100 according to the embodiment of the present invention will be described in more detail. 2 is a block diagram for explaining the configuration of a control device according to an embodiment of the present invention. Referring to FIG. 2 , the control device 100 according to an embodiment of the present invention includes a communication module 110 , a storage module 120 , and a control module 130 .

The communication module 110 is for communication with the unmanned aerial vehicle 200 and the rescue resource unit 300 . The communication module 110 may include an RF (Radio Frequency) transmitter (Tx) for up-converting and amplifying the frequency of a transmitted signal, and an RF receiver (Rx) for low-noise amplifying a received signal and down-converting the frequency. have. In addition, the communication module 110 may include a modem that modulates a transmitted signal and demodulates a received signal. The communication module 110 may receive various control commands for controlling the unmanned aerial vehicle 200 received from the control module 130 and transmit it to the unmanned aerial vehicle 200 . In particular, when a disaster situation occurs, a geographic location indicating the location of the disaster site, ie, GPS coordinates, may be transmitted to the unmanned aerial vehicle 200 so that the unmanned aerial vehicle 200 moves to the disaster site. In addition, the communication module 110 may receive various data, images, etc. from the unmanned aerial vehicle 200 and transmit it to the control module 130 .

The storage module 120 stores various data necessary for the operation of the control device 100 , applications, and various data generated according to the operation of the control device 100 . The storage module 120 may be storage, memory, or the like. In particular, the storage module 120 may selectively store an operating system (OS) for booting and operation of the control device 100 and an application according to an embodiment of the present invention. Various data stored in the storage module 120 may be deleted, changed, or added according to a user's operation. In addition, the storage module 120 may receive or input geographic location information on an area where a disaster occurs from the outside and store it, and also an image of the disaster area A received from the unmanned aerial vehicle 200 is stored. In addition, information on the number of people available for rescue may be received from the rescue resource unit 300 , and may be identified and stored according to each rescue resource unit 300 .

The control module 130 may control the overall operation of the control device 100 and the signal flow between internal blocks of the control device 100 , and may perform a data processing function of processing data. The control module 130 may be a central processing unit (CPU), an application processor, a graphic processing unit (GPU), or the like. The control module 130 includes a disaster area setting unit 131 that provides geographic location information on the disaster area to the unmanned aerial vehicle 200 for each function, and a plurality of areas of the disaster area received from the unmanned aerial vehicle 200 . An image collection unit 132 that collects images of A global image analysis unit 134 that calculates a distribution map of persons in need including geographic location information and the number of persons in need, and a rescue resource allocation unit 135 that arranges a plurality of rescue resources based on the calculated distribution map of persons in need. can Each configuration constituting the control module 130 will be described in more detail below.

Next, the unmanned aerial vehicle 200 according to an embodiment of the present invention will be described. 3 is a block diagram for explaining the configuration of an unmanned aerial vehicle according to an embodiment of the present invention.

Referring to FIG. 3 , the unmanned aerial vehicle 200 according to an embodiment of the present invention includes a control unit 210 , a photographing unit 220 , a navigation unit 230 , a driving unit 240 , a communication unit 250 , and a storage unit 260 . ) may be included.

The photographing unit 220 is for photographing an image of the disaster site. The photographing unit 220 generates a plurality of images through photographing. The photographing unit 220 includes a lens, an image sensor, and a converter. In addition, a predetermined filter and the like may be further included in the configuration of the photographing unit 220 , and mechanically, the lens, the image sensor, and the converter are mounted in a housing including an actuator, and a driver that drives the actuator and the like may be included in the photographing unit 220 . The lens allows visible light incident on the photographing unit 220 to be focused on the image sensor. The image sensor is a photoelectric conversion device integrated using a semiconductor device manufacturing technology. The image sensor may be, for example, a charge-coupled device (CCD) image sensor or a complementary metal-oxide semiconductor (CMOS) image sensor. Such an image sensor detects visible light and outputs an analog image signal that is an analog signal constituting an image. Then, the converter converts the analog image signal into a digital image signal that is a digital signal constituting the image and transmits it to the controller 210 . In particular, the photographing unit 220 according to an embodiment of the present invention may include a 3D sensor (depth sensor). The 3D sensor is a sensor for acquiring 3D coordinates for each pixel of an image in a non-contact manner. The photographing unit 220 may detect the coordinate values (eg, x, y, and z values) of the three-dimensional coordinates for each pixel of the image photographed through the 3D sensor while photographing the object. In this case, the coordinate values of the three-dimensional coordinates are coordinate values when the focus of the image sensor of the photographing unit 220 is set to zero. As the 3D sensor, various types of sensors using laser, infrared, or visible light may be used. These 3D sensors are a laser type 3D scanner using any one of TOP (Time of Flight), phase-shift, and online waveform analysis, a laser type 3D scanner using optical triangulation, and white light. Alternatively, optical 3D scanner using modulated light, Handheld Real Time PHOTO, optical 3D scanner, Pattern Projection or Line Scanning method, a laser-type full-body scanner, a photographic scanner using photogrammetry, a real-time scanner using Kinect Fusion, and the like can be exemplified. Accordingly, the photographing unit 220 may extract three-dimensional coordinates from the captured image, and accordingly, the current location of the photographing unit 220 , that is, the current geographic location (GPS coordinates) of the unmanned aerial vehicle 200 . ) can measure the actual distance from the captured image. The current geographic location (GPS coordinates) of the unmanned aerial vehicle 200 may be acquired by the navigation unit 230 .

The navigation unit 230 is for measuring the current geographical position (latitude, longitude, altitude) and posture (yaw, roll, pitch) of the unmanned aerial vehicle 200 . The navigation unit 250 includes a GPS signal receiving module for receiving a GPS signal from a GPS satellite, a gyro sensor for measuring motion, and sensors such as angular velocity and acceleration. The navigation unit 230 measures the current geographic position and attitude by using the GPS signal and the sensor values measured by the sensors, and transmits the measured current geographical position and attitude to the controller 210 .

The driving unit 240 is for generating lift so that the unmanned aerial vehicle 200 can fly. The driving unit 240 includes a propeller, a motor, and the like. The driving unit 240 allows the unmanned aerial vehicle 200 to fly in a direction and speed according to the control of the control unit 210 . In particular, the driving unit 240 may adjust the rotation speed of the propeller so that the unmanned aerial vehicle 200 can hover within a predetermined area according to the control of the controller 210 . In particular, the driving unit 240 may drive a propeller, a motor, or the like, so that the unmanned aerial vehicle 200 flies along a path set from the current location to the location of the disaster site under the control of the controller 210 . The driving unit 240 may move the unmanned aerial vehicle 200 by driving a propeller, a motor, etc. so that the photographing unit 220 may photograph each area of the disaster area A under the control of the control unit 210 .

The communication unit 250 is for communicating with the control device 100 . The communication unit 250 may include a radio frequency (RF) transmitter (Tx) for up-converting and amplifying the frequency of a signal for transmission, and an RF receiver (Rx) for low-noise amplifying a received signal and down-converting the frequency. . In addition, the communication unit 250 may include a modem that modulates a transmitted signal and demodulates a received signal. The communication unit 250 transmits an image of the disaster area to the control device 100 under the control of the control unit 290 .

The storage unit 260 stores various types of data required for the operation of the unmanned aerial vehicle 200 , applications, and various types of data generated according to the operation of the unmanned aerial vehicle 200 . The storage unit 260 may be storage, memory, or the like. In particular, the storage unit 260 selectively stores data such as an operating system (OS) for booting and operation of the unmanned aerial vehicle 200, and an image of a disaster site according to an embodiment of the present invention. can be saved. Various types of data stored in the storage unit 260 may be deleted, changed, or added according to a user's manipulation.

The controller 210 may control the overall operation of the unmanned aerial vehicle 200 and the signal flow between internal blocks of the unmanned aerial vehicle 200 , and may perform a data processing function of processing data. The control unit 290 may be a central processing unit (CPU), an application processor, a graphic processing unit (GPU), or the like. The controller 210 may control the flight direction of the unmanned aerial vehicle 200 through the driving unit 240 according to the geographic location information of the disaster area A received from the control device 100 . At this time, the control unit 210 moves the unmanned aerial vehicle 200 by controlling the driving unit 240 so that the photographing unit 220 can capture an image of each area according to a plurality of areas dividing the disaster area.

Next, a method for efficiently arranging rescue resources using an unmanned aerial vehicle according to an embodiment of the present invention will be described. 4 is a flowchart illustrating a method for efficiently arranging rescue resources using an unmanned aerial vehicle according to an embodiment of the present invention.

Referring to FIG. 4 , when a disaster occurs, geographic information on the disaster area transmitted or input to the control device 100 is transmitted to the unmanned aerial vehicle 200 through the disaster area setting unit 131 . The control unit 210 of the unmanned aerial vehicle 200 receives location information about the target location from the control device 100 as a geographic location (GPS coordinates) through the communication unit 250 in step S110, and through the navigation unit 230 It sets a route from the current location to the received target location and controls the driving unit 240 to fly along the corresponding route to move to the received target location. Here, the target location received from the control device 100 may be the location of the disaster site.

Upon arrival at the target location, the control unit 210 captures the scene through the photographing unit 220 . In this case, a plurality of unmanned aerial vehicles 200 may be used according to the range of the disaster area. Since the photographing unit 220 installed in the unmanned aerial vehicle 200 can cover a certain area, if the disaster area is wide, sliding windowing a plurality of areas of the disaster area A set by the disaster area setting unit 131 (Sliding windowing) can be taken sequentially. When a plurality of unmanned aerial vehicles 200 are used, an area covered by each unmanned aerial vehicle 200 may be set differently.

In this way, the image for each area photographed by the unmanned aerial vehicle 200 is transmitted to the control device 100 , and the image collection unit 132 provides information on a plurality of areas photographed by one or two or more unmanned aerial vehicle 200 . collect images. In the images collected in this way, the photographed areas are different, and the angle photographed by the unmanned aerial vehicle 100 is also not constant. The image collection unit 132 stores the plurality of collected images P1, P2, ..., Pn as images for the disaster area A in the storage module 120 as shown in FIG. 5 .

Next, in step S120 , the global image generation unit 133 generates a global image for the entire disaster area based on a plurality of images collected for the corresponding disaster area A stored in the storage module 120 . The global image generator 133 extracts a plurality of feature points from the collected images for each domain, matches the extracted feature points to calculate the relative distances of the feature points for each image, Creates a global image projected on the coordinate system.

That is, as shown in FIG. 5 , feature points are first extracted from each of the plurality of images P1, P2, ..., Pn for each area of the disaster area. For example, homography is a model for explaining a 2D image transformation relationship of a flat object, and refers to a transformation matrix that can know the transformation relationship of an object in two dimensions. For example, when there are two quadrilaterals lying in two dimensions, a transformation matrix that can move all points from one quadrangle to the other is called a homography matrix. In order to calculate the homography, it is necessary to know the correspondence between the points constituting the two quadrilaterals. Using this, if it is known that there is a correspondence between two image frames, a homography matrix can be calculated, and the calculated transformation matrix represents camera motion information. Accordingly, corresponding points are found for each frame constituting the plurality of images P1, P2, ..., Pn, and feature point extraction is performed, and camera homography is calculated by matching them. Through this, a camera-centered coordinate system can be created by fixing the camera to a specific viewpoint and then re-transforming the image. In this way, the global image generation unit 133 sets the coordinates for the entire disaster area by integrating the plurality of images P1, P2, ..., Pn (FIG. 5 (b)), One global image (FIG. 5(c)) projected on the global coordinate system is generated.

Next, in step S130 , the global image analysis unit 134 detects a person existing in the global image. For example, as shown in FIG. 6 , the global image analysis unit 134 includes coordinates (x, y, w, h) and An artificial neural network trained to output the probability (eg, Person = 0.88, Car = 0.01, Person = 0.11) that the corresponding object obj belongs to at least one preset class (eg, Person class, Car class, Tree class, etc.) It may include an object classification model, which is a model. Such object classification models can be exemplified by YOLO, YOLOv2, YOLO9000, YOLOv3, and the like. Among the coordinates of the area box (B), x, y, are the center coordinates of the area box (B) in the image, w represents the width, and h represents the height.

The global image analysis unit 134 inputs the global image generated by the global image generation unit 133 to the object classification model, and the object classification model calculates the coordinates (x, y, w, h) of the area box B. And if the output probability that the object in the area box B is a person is greater than or equal to a preset threshold (eg, 0.80 = 80%), it is recognized that the requestor is present in the area box B, and it is detected can do.

Also, the global image analysis unit 134 may convert the center coordinates (x, y) of the area box B into geographic coordinates, that is, GPS coordinates. That is, the global image analysis unit 220 calculates, based on the global image projected on the global coordinate system, the coordinates (GPS location) of the area box where the requestor exists and the number of area boxes recognized as the presence of the requester, A distribution map of users including geographic location information for each area and the number of users for each rescue area is generated (S140). By integrating the coordinates of a plurality of area boxes (B) set as the structure area, geographic location information (GPS location) for the structure area is calculated. In addition, by counting the number of area boxes (B) included in one structure area, the number of requesters existing in the structure area is calculated. The calculated geographical location information and the number of people for each structural area can be calculated as the density of people who need them, and based on this, the distribution of people can be calculated.

Next, the rescue resource allocation unit 135 arranges according to the type of the rescue resource unit connected through a communication network based on the calculated distribution of rescuers and requests to perform the rescue (S150). That is, as shown in FIG. 7 , depending on the type of the plurality of rescue resource units 300 stored in the storage module 120 of the control device 100 (ie, the number of rescuers), the rescuer requesting the rescue resource 3 with a large number of rescuers Priority is given to areas with high density, and Rescue Resource 1 with a relatively small number of rescuers is placed in areas with low density of rescuers. Through this, in case of a disaster in a wide area, rescue resources can be efficiently deployed, and thus, the efficiency of lifesaving can be doubled. The rescue resource allocation unit 135 may transmit geographic location information for each rescue area and information on the number of rescuers for each rescue area to a plurality of rescue resource units connected through a communication network based on the distribution of rescuers.

Meanwhile, the method according to the embodiment of the present invention described above may be implemented in the form of a program readable by various computer means and recorded in a computer readable recording medium. Here, the recording medium may include a program command, a data file, a data structure, etc. alone or in combination. The program instructions recorded on the recording medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. For example, the recording medium includes magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floppy disks ( magneto-optical media), and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions may include not only machine language wires such as those generated by a compiler, but also high-level language wires that can be executed by a computer using an interpreter or the like.

Although the present invention has been described above using several preferred embodiments, these examples are illustrative and not restrictive. As such, those of ordinary skill in the art to which the present invention pertains will understand that various changes and modifications can be made in accordance with the doctrine of equivalents without departing from the spirit of the present invention and the scope of rights set forth in the appended claims.

Claims (9)

As a control device for efficient deployment of rescue resources using unmanned aerial vehicles,
An image collection unit that collects images of a plurality of areas of a disaster area through a wireless communication network from an unmanned aerial vehicle equipped with a photographing unit;
A plurality of feature points are extracted from each image for the plurality of areas collected, and a relative distance of the feature points for each image is calculated by matching the plurality of extracted feature points, and a coordinate system for the entire disaster area A global image generation unit for generating a global image projected on the
a global image analysis unit that calculates a distribution map of demanded persons including geographic location information for each structural area and the number of requestors for each structural area based on the global image;
A control device comprising a rescue resource assignment unit for arranging a plurality of rescue resource units based on the distribution map of the person in need.
The method of claim 1,
The control device, characterized in that it further comprises a disaster area setting unit for providing the geographical location information of the disaster area to the unmanned aerial vehicle.
The method of claim 1,
The global image analysis unit,
and an object classification model, which is an artificial neural network model trained to calculate and output the coordinates of the area box indicating the area occupied by the object included in the image and the probability that the object is a person in the area box,
The object classification model calculates and outputs the coordinates of the area box indicating the area occupied by the object included in the image through calculation and the probability that the object in the area box is a person, and if the output probability is greater than or equal to a preset threshold, the area box Recognizing that the requestor exists within,
Rescue resources using an unmanned aerial vehicle, characterized in that based on the coordinates and number of area boxes in which the persons in need are present, a distribution map of persons in need including geographic location information for each structure area within a certain range and the number of persons requesting persons per structure area is calculated. device for the efficient deployment of
The method of claim 1,
The rescue resource allocation unit transmits geographic location information for each rescue area and information on the number of people requesting for each rescue area to a plurality of rescue resource units connected through a communication network based on the distribution of rescuers.
A step of collecting images for a plurality of areas in a disaster area through a wireless communication network from an unmanned aerial vehicle equipped with a photographing unit by an image collecting unit;
The global image generator extracts a plurality of feature points from each image for the plurality of areas collected, matches the extracted feature points to calculate the relative distance of the feature points for each image, generating a global image projected on a coordinate system for the global;
calculating, by a global image analysis unit, a distribution map of claimants including geographic location information for each structural area and the number of people requesting for each structural area based on the global image;
A method for efficient deployment of rescue resources using an unmanned aerial vehicle, comprising the step of disposing a plurality of rescue resource units based on the distribution map of the rescuers by the rescue resource assignment unit.
6. The method of claim 5,
The method for efficient deployment of rescue resources using an unmanned aerial vehicle, characterized in that it further comprises the step of providing the disaster area setting unit geographical location information of the disaster area to the unmanned aerial vehicle.
6. The method of claim 5,
The global image analysis unit includes an object classification model that is an artificial neural network model trained to calculate and output coordinates of an area box indicating an area occupied by an object included in the image and a probability that an object is a human in the area box,
The object classification model calculates and outputs the coordinates of the area box indicating the area occupied by the object included in the image through calculation and the probability that the object in the area box is a person, and if the output probability is greater than or equal to a preset threshold, the area box Recognizing that the requestor exists within,
Rescue resources using an unmanned aerial vehicle, characterized in that based on the coordinates and number of area boxes in which the persons in need are present, a distribution map of persons in need including geographic location information for each structure area within a certain range and the number of persons requesting persons per structure area is calculated. method for the efficient deployment of
6. The method of claim 5,
Efficient use of rescue resources using unmanned aerial vehicles, characterized in that the rescue resource allocation unit transmits geographic location information for each rescue area and information on the number of rescuers for each rescue area to a plurality of rescue resource units connected through a communication network based on the distribution map of rescuers method for placement.
A computer-readable recording medium in which a program for executing the method for efficient allocation of rescue resources using an unmanned aerial vehicle according to claim 5 to 8 in a computer device is recorded.

Images