KR102533928B1 - Method and System for Automatically Detecting Reservoirs Using the 3D Spatial Imagery Datasets - Google Patents

Abstract

The present invention relates to an automated method and a system for reservoir detection using 3D spatial image data. The automated system for reservoir detection using 3D spatial image data according to an embodiment of the present invention comprises: an external device that provides 3D spatial image data including satellite images of a random area; and a reservoir detection device that uses provided 3D spatial image data and a terrain model that analyzes the data to determine the location of reservoirs in a random area and detect boundaries of the reservoirs, calculates the area of the reservoir according to time changes using time series satellite images, and converts and outputs the calculated area data into a GIS shape file with a vector-type file structure, thereby capable of automating reservoir detection using high-resolution satellite images and digital terrain models (DEM), which are 3D spatial image data.

Description

Method and System for Automatically Detecting Reservoirs Using the 3D Spatial Imagery Datasets}

The present invention relates to an automated method and system for detecting a reservoir using 3D spatial image data, and more particularly, utilizes 3D spatial image data, such as high-resolution satellite images and a digital terrain model (Digital Elevation Model, DEM) It relates to an automated method and system for reservoir detection using 3D spatial image data, which automates reservoir detection by

A reservoir is a type of man-made pond, a large pond created by damming a stream or valley for irrigation, water supply, hydroelectric power, flood control, and agricultural water supply. Reservoir In general, it is an artificial facility for confining or managing water in river areas to supply agricultural water. Water storage rate, water level, water storage volume, etc.) are provided. Figure 1 shows this.

By the way, the reservoir status information provided by RAWRIS is information measured by measurement data installed in some areas of the reservoir, which is useful for accurately locating large and small reservoirs scattered across the country, precise boundary surveying of large-scale reservoirs, and accurate measurement of seasonal reservoir areas. There are technical limitations.

Korean Registered Patent Publication No. 10-1782868 (2017.09.22) Korea Patent Registration No. 10-2399089 (2022.05.12) Korean Patent Publication No. 10-2022-0106639 (2022.07.29)

An embodiment of the present invention is an automated method and system for detecting a reservoir using 3D spatial image data, which automates the detection of a reservoir by utilizing, for example, a high-resolution satellite image and a digital terrain model (DEM), which are 3D spatial image data. Its purpose is to provide

An automated system for detecting a reservoir using 3D spatial image data according to an embodiment of the present invention includes an external device providing 3D spatial image data including a satellite image of an arbitrary area, and the 3D spatial image provided above. Using the data and a terrain model that analyzes the data, the position of the reservoirs in the arbitrary area is determined, the boundary of the reservoir is detected, and the area of the reservoir according to the change in time is calculated using time-series satellite images, and the calculation It includes a reservoir detection device that converts data of one area into a Geographic Information System (GIS) shape file having a vector file structure and outputs the output.

The reservoir detection device generates a binary image using the satellite image, analyzes the size and boundary of a water body using the generated binary image, and as a result of the analysis, sets a water body of a predetermined size in the reservoir. It is judged as , and a GIS shape file of the reservoir according to the above judgment can be generated and output.

The reservoir detection device generates a normalized difference water index (NIR) image by using a visible light green band and a near infrared (NIR) band of a multispectral satellite image, and the normalized water index is generated. The binarized image for dividing the water body and a region excluding the water body may be generated using the index image and the terrain model.

The reservoir detection device may remove an error included in the water body in the binarized image by applying an expansion algorithm of geomorphology operations when analyzing the size and boundary of the water body.

The reservoir detection device may calculate the area of each reservoir by analyzing the satellite images captured at different times or dates, and calculate a change in area of each reservoir by comparing the calculated areas of the reservoir.

In addition, an automated method for detecting a reservoir using 3D spatial image data according to an embodiment of the present invention includes a step of providing 3D spatial image data including a satellite image of an area by an external device, and a reservoir detection device. A, using the provided 3D spatial image data and a terrain model that analyzes the data, the position of the reservoirs in the arbitrary area is determined, the boundary of the reservoir is detected, and time-series satellite images are used to determine the location of the reservoirs according to time changes Calculating the area of the reservoir, and converting and outputting data of the calculated area into a GIS shape file having a vector file structure.

The outputting may include generating a binary image using the satellite image, analyzing the size and boundary of the water body using the generated binary image, and determining a water body having a predetermined size as a reservoir as a result of the analysis. It may include generating and outputting data of the GIS shape file of the reservoir according to the judgment.

The generating of the binarized image may include generating a normal moisture index image obtained by normalizing the moisture index using the visible green band and the near infrared (NIR) band of the multispectral satellite image, and the generated normal moisture index image. The method may include generating the binarized image for dividing the water body and a region excluding the water body using the image and the terrain model.

The outputting may further include removing an error included in the water body in the binarized image by applying a dilatation algorithm of morphological operation when analyzing the size and boundary of the water body.

The outputting step may include calculating the area of each reservoir by analyzing the satellite images captured at different times or dates, and calculating a change in area of each reservoir by comparing the calculated areas of the reservoir. may further include.

An embodiment of the present invention can check the agricultural and industrial water supply status in the area adjacent to the reservoir by checking the area of individual reservoirs scattered over a vast area in the event of a drought without visiting the site, thereby providing efficient drought through systematic management of agricultural and industrial water It can be used for response work.

In addition, embodiments of the present invention can be used for efficient flood control in areas adjacent to reservoirs by estimating unmeasured inflows through area change information of reservoirs scattered over a vast area.

Furthermore, the automated method and system for detecting a reservoir based on 3D spatial image data according to an embodiment of the present invention can be used to establish a disaster response policy, and can be used to calculate insurance premiums for storm and flood damage and crop disasters.

1 is a view showing reservoir status information provided to a conventional agricultural water comprehensive information system;
2 is a diagram illustrating an automated system for performing reservoir detection using 3D spatial image data according to an embodiment of the present invention;
3 to 6 are diagrams for explaining an automated operation of reservoir detection performed in the reservoir detection device of FIG. 2;
Figure 7 is a block diagram illustrating the detailed structure of the reservoir detection device of Figure 2, and
8 is a flowchart illustrating an automated method for performing reservoir detection using 3D spatial image data according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

2 is a diagram illustrating an automated system for performing reservoir detection using 3D spatial image data according to an embodiment of the present invention.

As shown in FIG. 2, an automated system (hereinafter, an automated system) 90 for performing reservoir detection using 3D spatial image data according to an embodiment of the present invention includes a satellite 200, a communication network 210, Some or all of the reservoir detection device 220 and the third party device 230 are included.

Here, "including some or all" means that the automation system 90 is configured by omitting some components such as the third party device 230, or some or all of the components such as the reservoir detection device 220 It means something that can be integrated and configured in a network device (eg, a wireless switching device, etc.) constituting the communication network 210, and will be described as including all of them to help a sufficient understanding of the present invention.

The artificial satellite 200 is equipped with a satellite camera for observing the earth in outer space. The satellite camera may be composed of or include an optical sensor for acquiring multispectral satellite images (landsat imagery). The satellite 200 according to an embodiment of the present invention may be referred to as an external device when considering the reservoir detection device 220 as a standard. A satellite camera, referred to as the 'eye of the satellite', is divided into an optical camera, an infrared camera, and a radar.

The artificial satellite 200 in FIG. 2 may include various types of satellite devices for acquiring satellite images according to an embodiment of the present invention. For example, in an embodiment of the present invention, in order to collect satellite images related to reservoir detection, images may be collected by accessing a server such as the National Meteorological Satellite Center. For example, the reservoir detection device 220 of FIG. 2 may be linked to a server of the National Center for Meteorological and Physics through API (Application Programming Interface) to receive satellite images related to reservoir detection in real time. Of course, the satellite 200 periodically transmits captured images through communication with the National Weather Service Center. Therefore, according to an embodiment of the present invention, the reservoir detection device 220 can connect to a server operated by the National Center for Meteorological and Physics and receive and use the multi-spectral image taken by the satellite 200 as 3D space image data.

The artificial satellite 200 may include an optical camera for observing the earth or various types of sensors (eg, R, G, B sensors constituting a CCD camera, etc.), and depending on the performance of these parts, Characteristics may be somewhat different. Therefore, in the embodiment of the present invention, it is possible to determine whether the same product is used in the sensor of the satellite 200 in order to detect changes in the location of the reservoir, the boundary of the reservoir, and the area of the reservoir by season. This can be done by previously storing spec information related to the performance of the satellite 200 in the reservoir detection device 220 and checking it. Above all, the artificial satellite 200 according to an embodiment of the present invention can provide multispectral images.

Here, the multispectral (or multispectral) image is an image obtained by acquiring image data belonging to a specific wavelength range of the electromagnetic spectrum. Wavelengths can be separated using filters or instruments sensitive to specific wavelengths, including light from frequencies outside the range of visible light, such as microwave, infrared, ultraviolet, and X-rays. That is, the multispectral image is a collection of several monochromatic images of the same scene, which were taken with different sensors. Here, each monochromatic image is called a band. A well-known multispectral (or multiband image) is an RGB color image composed of red, green, and blue images, which are captured by sensors sensitive to different wavelengths. Such spectral imaging may allow extraction of additional information that the human eye cannot capture with the receptors for red, green and blue colors. Multispectral imaging typically measures light in 3 to 15 spectral bands (or bands). However, imaging with higher radiant resolution and fine spectra including hundreds or thousands of bands in multispectral imaging is called hyperspectral. Therefore, in the embodiment of the present invention, there will be no particular limitation on what kind of spectroscopic imaging is performed.

The communication network 210 performs satellite communication with the satellite 200 . It may include a ground station for communicating with the satellite 200. Since satellite communication uses microwaves, high-speed and large-capacity communication is possible, and a wide area (eg, the whole of a specific country) can be covered as a communication area. In addition, even communication is possible regardless of terrain, and communication is not restricted even in the event of a disaster. However, there are disadvantages in that the round-trip time (about 0.24 seconds) of the radio wave is delayed during voice communication, and there is no security of information. In addition, since solar cells are used as a power source, a momentary loss of communication may occur when the satellite is in the shadow of the earth or when heavy rain falls.

The communication network 210 includes both wired and wireless communication networks. For example, as the communication network 210, a wired or wireless Internet network may be used or interlocked. Here, the wired network includes an Internet network such as a cable network or a public switched telephone network (PSTN), and the wireless communication network includes CDMA, WCDMA, GSM, Evolved Packet Core (EPC), Long Term Evolution (LTE), and Wibro networks. meaning to include Of course, the communication network according to the embodiment of the present invention is not limited thereto, and can be used as an access network of a next-generation mobile communication system to be implemented in the future, for example, a cloud computing network under a cloud computing environment, a 5G network, and the like. For example, when the communication network is a wired communication network, the access point within the communication network 210 can access an exchange center of a telephone company, but in the case of a wireless communication network, access to an SGSN or GGSN (Gateway GPRS Support Node) operated by a communication company to process data, Data can be processed by connecting to various repeaters such as BTS (Base Transceiver Station), NodeB, and e-NodeB.

The communication network 210 may include an access point. Access points include small base stations such as femto or pico base stations that are often installed in buildings. Here, the femto or pico base station is classified according to the maximum number of units of the reservoir detection device 220 or the third party device 230 that can be connected to the small base station. Of course, the access point includes a short-range communication module for performing short-range communication such as ZigBee and Wi-Fi with the reservoir detection device 220 or the third party device 230. The access point may use TCP/IP or Real-Time Streaming Protocol (RTSP) for wireless communication. Here, short-range communication may be performed in various standards such as Bluetooth, ZigBee, infrared (IrDA), RF (Radio Frequency) such as UHF (Ultra High Frequency) and VHF (Very High Frequency), and ultra-wideband communication (UWB) in addition to Wi-Fi. can Accordingly, the access point can extract the location of the data packet, designate the best communication path for the extracted location, and forward the data packet to the next device, such as the reservoir detection device 220, along the designated communication path. An access point may share several lines in a general network environment, and includes, for example, a router, a repeater, and a repeater.

The reservoir detection device 220 uses 3D spatial image data such as satellite images and digital terrain models (DEMs) to determine the location of the reservoir, detects the boundary of the reservoir, and calculates the area of the reservoir for each season using time-series satellite images. and run an automation method that outputs it as GIS data. Here, the digital terrain model or terrain model may be regarded as a model for analyzing satellite images, that is, a preset program. More precisely, it can be seen as a model for 3D data analysis. Generally, digital terrain models are largely used in three ways. These models include a contour model, a lattice-type DEM model, and a TIN model. In an embodiment of the present invention, a DEM model may be used.

Reservoir detection device 220 utilizes data obtained in a vast area as 3D spatial image data such as high-resolution satellite image or DEM, identifies the exact location of reservoirs scattered across the country, detects the exact boundary of reservoirs, and It is possible to measure the change in reservoir area by season using N high-resolution satellite images taken at the time. A reservoir is a type of man-made pond, a large pond created by damming a stream or valley for irrigation, water supply, hydroelectric power, flood control, and agricultural water supply.

As will be discussed later, the reservoir detection device 220 according to an embodiment of the present invention produces a normalized difference water index image using a multi-spectral satellite image obtained by an optical sensor of the satellite 200. Then, using the normal water index image and the DEM, a water body and a region other than the water body are distinguished to produce a binarized image. Here, NDWI can be calculated using a near infrared (NIR) wavelength and a green wavelength. In addition, the reservoir detection device 220 applies geomorphology operations to the binarized image to remove errors included in the water body of the binarized image and preserves (or measures or calculates) the size and boundary of the water body. The reservoir detection device 220 according to an embodiment of the present invention applies a structure element-based dilation algorithm, that is, a program, to remove errors included in the water body in the binarized image, and determines the size and boundary of the water body. In order to preserve the same structural element-based erosion algorithm can be applied.

Morphology is a broad set of image processing operations that process images according to their shape. It can be understood simply as an arithmetic program. Morphological operations apply structuring elements to an input image to generate an output image of the same size. In morphological operations, the value of each pixel in the output image is based on the result of comparing the corresponding pixel in the input image with neighboring pixels. The most basic morphological operations are dilation and erosion. Dilation adds pixels to the boundaries of objects in an image, while erosion removes pixels from the boundaries of objects. The number of pixels added to or removed from an object in an image depends on the size and shape of the structuring elements used to process the image. In morphological dilation and erosion operations, the state of each pixel of the output image is determined by applying a rule to the corresponding pixel of the input image and its neighboring pixels. The rules used when processing pixels define operations as either dilation or erosion. For example, erosion marks a 0 if there is even a single 1 in the kernel. Erosion is an operation in which, when a mask is placed on each pixel of an input binary image, the result value is 255 only when the input image also has a value of 255 for all pixel positions where the mask has a value of 255. If even one pixel at the target location has a value of 0, the resulting value becomes 0, resulting in a reduction in the area with a value of 255 as a whole. On the other hand, the dilation operation, in contrast to the erosion operation, serves to brighten all the pixels in the effective area of the mask.

The reservoir detection device 220 applies the above morphology operation to select an object of a certain size or more from the binarized image from which the error of the water body has been removed, selects it as a reservoir object, and converts the selected reservoir object into a GIS shapefile. . Here, the predetermined size may be a designated size or a standard size. In addition, a shape file refers to a vector-type file structure used to store location and attribute information of points, lines, and planes. In addition, the reservoir detection device 120 builds a single satellite image-based reservoir area database (DB) including ID, reservoir name, satellite image capture date, and reservoir area information for the area of each reservoir included in one satellite image, and time series In other words, by using N satellite images taken according to time changes (of course, time intervals can vary), the amount of change in area of individual reservoirs can be calculated, and a time-series satellite image-based reservoir area change database can be constructed through database combination. Details will be further discussed in FIG. 6 .

The third party device 230 may include various types of devices operated by the National Weather Service Center or may include various devices of program producers that develop programs according to embodiments of the present invention. For example, in the case of the National Center for Meteorology and Physics, satellite images captured through the artificial satellite 200 may be received and stored, and then provided in real time upon request from the reservoir detection device 220. In addition, in the case of a program manufacturer, a program for detecting a reservoir according to an embodiment of the present invention may be developed and installed in the reservoir detection device 220.

As a result of the above configuration, the constructed data can be used for efficient flood control in the area adjacent to the reservoir by estimating the unmeasured inflow through the area change information of reservoirs scattered over a vast area, and in case of drought, individual reservoirs scattered over a vast area By checking the area of the reservoir without visiting the site, it is possible to check the supply status of agricultural and industrial water in the area adjacent to the reservoir, which can be used for efficient drought response work through systematic management of agricultural and industrial water.

3 to 6 are diagrams for explaining an automated operation of reservoir detection performed by the reservoir detection device of FIG. 2 .

Referring to FIGS. 3 to 6 together with FIG. 2 for convenience of explanation, the reservoir detection device 220 of FIG. 2 produces a normal moisture index image using a satellite image acquired through an artificial satellite 200, that is, a multi-spectral satellite image. Then, using the regular water index image and DEM, a binarized image that distinguishes the water body in the satellite image and the area other than the water body is produced. At this time, in order to produce a regular moisture index image, a visible light green band, that is, a single image taken by a green sensor and a near infrared (NIR) band are used. The production of NDWI images can be expressed by <Equation 1> and <Equation 2>.

Figure 3 (a) shows the location of the reservoir on the map, Figure 3 (b) shows the NDWI image. In addition, (c) of FIG. 3 shows a DEM, and (d) of FIG. 3 shows binarized images for distinguishing a water body from other areas, respectively.

In addition, the reservoir detection apparatus 220 is a step of removing errors included in the water body of the binarized image and preserving the boundary of the water body by applying the morphology operation to the binarized image divided into the water body and other regions. A dilatation algorithm is applied to remove errors included in the water body in the binarized image, and an erosion algorithm based on the same structural element is applied immediately to preserve the size and boundary of the water body. This can be expressed as <Equation 3> and <Equation 4>.

4, (a) represents a reservoir, and (b) of FIG. 4 is a binarized image divided into a water body containing errors (red circles) and other regions. Figure 4(c) shows an image in which errors included in the water body have been removed by applying the expansion algorithm of morphological operation, and Figure 4(d) shows an image in which the size and boundary of the water body are preserved by applying the erosion algorithm of morphology operation. show each video.

Subsequently, the reservoir erosion apparatus 120 applies morphology operation to select an object of a certain size or more (or a reference size or more) from the binarized image from which the error of the water body has been removed, selects it as a reservoir object, and selects the selected reservoir object as a GIS shape convert to file Here, the shape file can be seen to mean data having a vector-type structure. Figure 5 (a) shows a binarized image, and Figure 5 (b) shows an object of a certain size or more. Figure 5 (c) shows the selected reservoir object (GIS Shapefile).

On the other hand, the reservoir detection device 220 constructs a single satellite image-based reservoir area database including ID, reservoir name, satellite image capture date, and reservoir area information for the area of each reservoir included in one satellite image, and captures it in time series. Using N satellite images, the area change of each reservoir is calculated, and a time-series satellite image-based reservoir area change database is constructed through database combination. As shown in FIG. 6 , the reservoir detecting device 220 may calculate an area change amount of how the area of the reservoir changes in satellite images according to time-series changes.

7 is a block diagram illustrating a detailed structure of the reservoir detection device of FIG. 2 .

As shown in FIG. 7 , the reservoir detection device 220 of FIG. 2 includes some or all of a communication interface unit 700 , a control unit 710 , a reservoir detection unit 720 and a storage unit 730 .

Here, "including part or all" means that some components such as the storage unit 730 are omitted to configure the reservoir detection device 220, or some components such as the reservoir detection unit 720 are the control unit 710 ), which can be integrated with other components such as, etc., and will be described as including all to help a sufficient understanding of the invention.

The communication interface unit 700 may communicate with the satellite 200 or the third party device 230 of FIG. 2 to receive 3D space image data and transmit it to the controller 710 . Here, the 3D space image data may include a satellite image captured by the satellite 200 of FIG. 2 and a digital terrain model (DEM). The communication interface unit 700 may perform operations such as modulation/demodulation, encoding/decoding, muxing/demuxing, resolution conversion scaling, etc. in the course of communication, and since these operations are obvious to those skilled in the art, further descriptions are omitted. do. Digital terrain models are expressed in three ways. These are the contour model, the grid-type DEM model, and the TIN model. In the embodiment of the present invention, it is preferable to use the DEM model, but it will not be particularly limited to any one model.

Of course, the communication interface unit 700 can also provide a service related to reservoir detection through communication with the third party device 230 . For example, by building a service in the form of a platform in a server, even a person concerned with reservoir management or a general user can use the related service if necessary. Since this can be serviced in the same form as in FIG. 1, further description will be omitted.

The control unit 710 is in charge of overall control operations of the communication interface unit 700, the reservoir detection unit 720, and the storage unit 730. The control unit 710 receives high-resolution satellite images through the communication interface unit 700 and operates in conjunction with the reservoir detection unit 720 to perform an automated operation for detecting a reservoir using a digital terrain model, such as a DEM. there is. To this end, the control unit 710 may temporarily store the image data of the satellite image in the storage unit 730, call it out, and provide it to the reservoir detection unit 720. In addition, the control unit 710 receives data related to the location of the reservoir, the boundary of the reservoir, the area of the reservoir by season, etc. detected by the reservoir detection unit 720, and systematically classifies and stores them in the DB 220a of FIG. 2. The communication interface unit 700 may be controlled.

The reservoir detection unit 720 uses 3D spatial image data such as satellite imagery and DEM to determine the location of the reservoir and detects the boundary of the reservoir, and calculates the area of the reservoir by season using time-series satellite images to convert it into GIS data. Convert output. To this end, the reservoir detection unit 720 utilizes the visible light green band and the near-infrared (NIR) band of the multispectral satellite image acquired using the optical sensor mounted on the satellite 200 to produce a normal moisture index image, , a binarized image that distinguishes a water body, i.e., a place with water and other areas, is created using the production image and the DEM. The binarized image may be a black and white image.

In addition, the reservoir detection unit 720 preserves the size and boundary of the water body by applying a morphology operation, that is, an erosion algorithm based on the same structural elements as the expansion algorithm based on structural elements, to the binarized image. Through the dilatation algorithm, errors included in the water body are removed from the binarized image. Next, the reservoir detection unit 720 selects an object of a certain size, that is, a specified size or a standard size or larger, from the binarized image from which the error of the water body has been removed, selects the object as a reservoir object, and converts the selected reservoir object into a GIS shape file. It is to convert to a file structure in vector form. Since a vector has a direction, it can be regarded as including its information. The GIS shape file of the reservoir object is shown in (c) of FIG.

Furthermore, the reservoir detection unit 720 may generate data for building a database including ID, reservoir name, shooting date, and reservoir area information for the area of an individual reservoir included in a unit video frame of a satellite image, that is, one satellite image. In addition, according to the change in time, that is, N satellite images taken in time series can be used to calculate the amount of change in the area of the reservoir and create a database. Of course, the time series here may mean a series of video frames used at almost the same or similar times, but may mean using satellite images taken at different times or on different dates. For example, FIG. 6 shows the amount of change in the area of the reservoir in a time series when the dates are different, such as April 2, 2022 and May 17, 2022.

Of course, substantially, the reservoir detection unit 720 may generate data related to the reservoir every hour or every day, store the data in the DB 120a of FIG. 2, and manage the data. Of course, in this process, if there is no significant change from the state in the previous step, data can be created and stored in time series by selectively constructing data only when a change is detected. Therefore, the reservoir detection unit 720 retrieves the reservoir data belonging to the corresponding date in relation to which date the administrator of the third party device 230 designates and requests the amount of change in the reservoir, and through this, immediately measures the amount of change in area. . Therefore, if the reservoir detection unit 720 according to an embodiment of the present invention is filmed with 30 to 60 video frames per second from the satellite 200, the manager can check the amount of change based on the desired time or date Therefore, in the embodiments of the present invention, it will not be particularly limited to any one form.

The storage unit 730 temporarily stores various types of data under the control of the control unit 710 of FIG. 7 . For example, the storage unit 730 may receive and temporarily store image data of a satellite image provided from an external device such as the satellite 200 or the third party device 230 and provide it to the reservoir detection unit 720. can be printed out. In addition, the storage unit 730 temporarily stores data such as the position of the reservoir analyzed by the reservoir detection unit 720, the result of detecting the boundary line, and the seasonal change in reservoir area, and then outputs the data to be stored in the DB 220a of FIG. 2. can

In addition to the above, the communication interface unit 700, the control unit 710, the reservoir detection unit 720, and the storage unit 730 of FIG. 7 can perform various operations, and other details have been sufficiently described above. want to replace them with

7 according to an embodiment of the present invention, the communication interface unit 700, the control unit 710, the reservoir detection unit 720, and the storage unit 730 are composed of hardware modules physically separated from each other, but each module is internally Software for performing the above operation may be stored and executed. However, since the corresponding software is a set of software modules, and each module can be formed of hardware, it will not be particularly limited to the configuration of software and hardware. For example, the storage unit 730 may be hardware storage or memory. However, since it is possible to store information in a software manner (repository), the above content will not be particularly limited.

Meanwhile, as another embodiment of the present invention, the control unit 710 may include a CPU and a memory, and may be formed as a single chip. The CPU includes a control circuit, an arithmetic unit (ALU), a command interpreter, and a registry, and the memory may include RAM. The control circuit performs control operations, the operation unit performs operation of binary bit information, and the instruction interpretation unit performs an operation of converting high-level language into machine language and machine language into high-level language, including an interpreter or compiler. , the registry may be involved in software data storage. According to the above configuration, for example, at the beginning of the operation of the reservoir detection device 220, the program stored in the reservoir detection unit 720 is copied, loaded into a memory, that is, RAM, and then executed, thereby speeding up data operation processing speed can increase In the case of a deep learning model, it can be loaded into GPU memory rather than RAM, and can be executed by accelerating the execution speed using the GPU.

8 is a flowchart illustrating an automated method for detecting a reservoir using 3D spatial image data according to an embodiment of the present invention.

Referring to FIG. 8 together with FIG. 2 for convenience of description, an external device such as a satellite 200 or a third party device 230 according to an embodiment of the present invention generates 3D spatial image data including satellite images of an arbitrary region. Provided (S800). Here, the 3D spatial image data may further include a digital terrain model (DEM). Here, the digital terrain model may be a program used to determine the location of a reservoir by forming a grid on a satellite image, or may be a three-dimensional analysis model, that is, a program that analyzes image data of a satellite image. In the case of this model, since it can be manufactured in advance and built into the reservoir detection device 220, therefore, in the embodiment of the present invention, the external device will not be particularly limited to providing the DEM.

In addition, the reservoir detection device 220 locates reservoirs in an arbitrary area using 3D spatial image data and a terrain model that analyzes the data, detects reservoir boundaries, and uses time-series satellite images to determine seasonal reservoirs. The area is calculated, and the data of the calculated area is converted into a GIS shape file and output (S810).

The specific process has been sufficiently described above. For example, the reservoir detection device 220 generates a binarized image of a satellite image. To this end, a regular moisture index image is generated using the visible light green band and the near infrared band of the satellite image. Then, by using the normal moisture index image and the DEM, a binarized image is generated by dividing the water body and other areas. In addition, morphological operations are applied to the binarized image to remove errors within the water body, and the size and boundary of the water body are preserved (or measured or calculated). In addition, among the water bodies, a water body object with a size outside the standard range or larger than the standard size is selected and determined as a reservoir object to be created as a GIS shape file. In addition, the reservoir detection device 220 may calculate the amount of change in the area of the reservoir for each season using time-series satellite images.

In addition to the above, the reservoir detection device 220 of FIG. 2 can perform various operations, and since other details have been sufficiently described above, they will be replaced with those contents.

On the other hand, even if all the components constituting the embodiment of the present invention are described as being combined or operated as one, the present invention is not necessarily limited to these embodiments. That is, within the scope of the object of the present invention, all of the components may be selectively combined with one or more to operate. In addition, although all of the components may be implemented as a single independent piece of hardware, some or all of the components are selectively combined to perform some or all of the combined functions in one or a plurality of pieces of hardware. It may be implemented as a computer program having. Codes and code segments constituting the computer program may be easily inferred by a person skilled in the art. Such a computer program may implement an embodiment of the present invention by being stored in a computer-readable non-transitory computer readable media, read and executed by a computer.

Here, the non-transitory readable recording medium means a medium that stores data semi-permanently and can be read by a device, not a medium that stores data for a short moment, such as a register, cache, or memory. . Specifically, the above-described programs may be provided by being stored in a non-transitory readable recording medium such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, or ROM.

Although the preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and is common in the art to which the present invention pertains without departing from the gist of the present invention claimed in the claims. Of course, various modifications and implementations are possible by those with knowledge of, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

200: artificial satellite 210: communication network
220: reservoir detection device 230: third party device
700: communication interface unit 710: control unit
720: reservoir detection unit 730: storage unit

Claims (10)

An external device that provides 3D space image data including satellite images of an arbitrary area; and
Using the provided 3D spatial image data and a terrain model that analyzes the data, the position of the reservoirs in the arbitrary area is determined, the boundary of the reservoir is detected, and the reservoirs according to time changes are measured using time-series satellite images. A reservoir detection device that calculates an area and converts the data of the calculated area into a Geographic Information System (GIS) shape file having a vector file structure and outputs it,
The reservoir detection device generates a binary image using the satellite image, analyzes the size and boundary of a water body using the generated binary image, and as a result of the analysis, sets a water body of a predetermined size in the reservoir. Based on the judgment, a GIS shape file of the reservoir according to the judgment is generated and output,
The reservoir detection device generates a normalized difference water index (NIR) image by using a visible light green band and a near infrared (NIR) band of a multispectral satellite image, and the normalized water index is generated. Generating the binarized image for dividing the water body and a region excluding the water body using an index image and the terrain model;
The reservoir detection device analyzes the satellite images taken at different times or dates to calculate the area of each reservoir, and calculates the area change of each reservoir by comparing the calculated areas of the reservoir. An automated system for reservoir detection using video data. delete delete According to claim 1,
The reservoir detection device detects a reservoir using dimensional space image data, which removes errors included in the water body in the binarized image by applying a dilatation algorithm of morphology operations when analyzing the size and boundary of the water body. automation system for delete providing, by an external device, 3D space image data including satellite images of an arbitrary region; and
The reservoir detection device determines the location of reservoirs in the arbitrary area using the provided 3D spatial image data and a terrain model that analyzes the data, detects the boundary of the reservoir, and uses time-series satellite images to determine the location of the reservoirs. Calculating the area of the reservoir according to the change, and converting and outputting the data of the calculated area into a GIS shape file having a vector file structure;
The outputting step is
generating a binary image using the satellite image;
analyzing the size and boundary of the water body using the generated binarized image; and
As a result of the analysis, determining a water body of a predetermined size as a reservoir and generating and outputting data of a GIS shape file of the reservoir according to the determination; including,
Generating the binarized image,
generating a normalized moisture index image by using a visible green band and a near infrared (NIR) band of the multispectral satellite image; and
Generating the binarized image for dividing the water body and a region excluding the water body using the generated normal water index image and the terrain model;
The outputting step is
calculating the area of each reservoir by analyzing the satellite images taken at different times or dates; and
An automated method for detecting reservoirs using 3-dimensional spatial image data, further comprising: calculating a change in the area of each reservoir by comparing the calculated areas of each reservoir. delete delete According to claim 6,
The outputting step is
When analyzing the size and boundary of the water body, removing errors included in the water body in the binarized image by applying a dilatation algorithm of morphological operation; automated method for detecting a reservoir using 3D spatial image data further comprising: . delete

Images