KR20180020421A - Method and system for extracting coastline based on a large-scale high-resolution satellite images - Google Patents

Abstract

The present invention provides a method and a system for extracting a coastline using a large-scale high resolution satellite image, which can perform a coastline extraction work by using a satellite image obtained through a satellite. The method comprises the following steps of: identifying a coastline position within the satellite image based on a pre-registered standard coastline position database, performing an image separation considering the coastline position, and obtaining multiple separated images; obtaining moisture exponent weighted images of each of the separated images; obtaining binary images of each of the moisture exponent weighted images; removing a noise edge corresponding to inland water and an island area after detecting an edge of the binary image, and extracting coastlines of each of the separated images; and synthesizing coastline extracted results of each of the separated images, and obtaining the entire coastline of the satellite image.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a method and system for extracting a coastline using a large-

The present invention relates to a shoreline extraction method and system, and more particularly, to a shoreline extraction method and system using a large-capacity high-resolution satellite image that enables a more reliable and effective shoreline extraction operation using a satellite image of large capacity and high resolution.

A coastline is a boundary line between land and water in coastal zones. In general, coastal areas are characterized by continuous changes in the surface due to natural reasons such as typhoons and tsunamis and artificial reasons such as reclamation and breakwater construction. Therefore, coastline extraction is very important for coastal area variation calculation, coastal erosion detection and coastal resource management.

Conventional shoreline extraction is performed by a method of collecting and analyzing images in narrow areas such as high-precision GPS, aerial photographs, and aviation LiDAR. This is because the person or aircraft must directly visit the shoreline to collect the necessary data, which is advantageous in terms of accuracy, but it is economically costly and requires a lot of time for surveying, and the coastline that changes due to anthropogenic, There is a disadvantage that it is difficult to cope with.

However, there is no systematic coastal environment monitoring system yet. In addition, due to the data capacity of several gigabytes of satellite images, it is almost impossible to carry out shoreline extraction work using satellite images in a general computing environment.

Korean Patent No. 10-1602293 Korean Patent No. 10-1480173 Korean Patent No. 10-0571121

Accordingly, it is an object of the present invention to provide a shoreline extraction method and system using a large-capacity high-resolution satellite image that can perform shoreline extraction using satellite images acquired through a satellite.

The present invention also provides a method and system for extracting shorelines using large-capacity high-resolution satellite images that can be processed through a general computing environment even when satellite images are large-capacity high-resolution images.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

As a means for solving the above problems, according to an embodiment of the present invention, a shoreline position in a satellite image is determined based on a previously registered standard shoreline position database, and an image segmentation considering the shoreline position is performed, Acquiring an image; Obtaining a moisture exponent weighted image of each of the divided images; Obtaining a binary image of each of the moisture exponent weighted images; Extracting a coastline of each of the divided images by removing an inland number and a noise edge corresponding to the book area after detecting an edge of the binarized image; And a step of synthesizing the shoreline extraction results of each of the divided images to acquire the entire shoreline of the satellite image, the shoreline extraction method using the large-capacity high resolution satellite image.

The step of acquiring the plurality of divided images may include extracting location information of the satellite image using a GDAL (Gospatial Data Abstraction Library) library; Comparing the position information of the satellite image with coordinate information of a standard coastline registered in advance to determine a shoreline position in the satellite image; And acquiring the plurality of divided images by performing an image segmenting operation based on the shoreline position.

The step of acquiring the moisture exponent weighted image can be obtained using one of the Normalized Difference Water Index (NDWI) and Modified NDWI (MNDWI) algorithms.

The step of acquiring the binarized image is characterized by removing or canceling noise in the binarized image through an open operation.

The step of extracting the shoreline is characterized by extracting the edge having the longest length among the edges of the binarized image as a shoreline.

The step of extracting the shoreline may further include extracting the shoreline by considering at least one of the number of points of the edge, the area of the area, and the volume of the pixel cluster.

In addition, the method may further include adjusting an image segmentation condition based on the size of the satellite image and the system processing capacity before the step of acquiring the plurality of segmented images.

According to another aspect of the present invention, there is provided a method of detecting a shoreline position in a satellite image based on a previously registered standard shoreline position database, performing an image segmentation considering the shoreline position, A satellite image acquiring unit acquiring an image; A division image processing unit for obtaining a moisture exponent weighted image of each of the divided images and binarizing the extracted water exponent weighted images, and detecting and filtering an edge of the binarized image to extract coastlines of the divided images; And a coastline obtaining unit for obtaining the entire coastline of the satellite image by synthesizing the shoreline extraction results of the respective divided images, and to provide a shoreline extraction system using the large-capacity high resolution satellite image.

The present invention minimizes the time and economic costs of collecting the baseline data by allowing the satellite to periodically extract the coastline using the satellite image captured and provided by the wide area.

Also, even if the satellite image is a high-capacity high-resolution image, it is possible to process the satellite image through the conventional general computing environment without constructing a separate system, thereby minimizing the cost of constructing the system.

1 and 2 are views for explaining a shoreline extraction method using a large-capacity high resolution satellite image according to an embodiment of the present invention.
3 is a view for explaining a satellite image segmentation step according to an embodiment of the present invention.
FIGS. 4 and 5 are views for explaining a step of acquiring a moisture index exponentiation image and a step of acquiring a binarized image according to an embodiment of the present invention.
FIG. 6 is a diagram for explaining a binary image edge detection and filtering step according to an embodiment of the present invention.
FIG. 7 is a view for explaining a shoreline information acquisition step of a satellite image according to an embodiment of the present invention.
FIG. 8 is a diagram for further illustrating a satellite image segmentation method according to an embodiment of the present invention. Referring to FIG.
9 is a view for explaining a coastline extraction system using a large-capacity high-resolution satellite image according to an embodiment of the present invention.

It is noted that the technical terms used in the present invention are used only to describe specific embodiments and are not intended to limit the present invention. In addition, the technical terms used in the present invention should be construed in a sense generally understood by a person having ordinary skill in the art to which the present invention belongs, unless otherwise defined in the present invention, Should not be construed to mean, or be interpreted in an excessively reduced sense. In addition, when a technical term used in the present invention is an erroneous technical term that does not accurately express the concept of the present invention, it should be understood that technical terms can be understood by those skilled in the art. In addition, the general terms used in the present invention should be interpreted according to a predefined or prior context, and should not be construed as being excessively reduced.

Furthermore, the singular expressions used in the present invention include plural expressions unless the context clearly dictates otherwise. In the present invention, terms such as "comprising" or "comprising" and the like should not be construed as encompassing various elements or various steps of the invention, Or may further include additional components or steps.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to the same or similar elements, and redundant description thereof will be omitted.

In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. It is to be noted that the accompanying drawings are only for the purpose of facilitating understanding of the present invention, and should not be construed as limiting the scope of the present invention with reference to the accompanying drawings.

1 and 2 are views for explaining a shoreline extraction method using a large-capacity high resolution satellite image according to an embodiment of the present invention.

As shown in FIGS. 1 and 2, the shoreline extraction method of the present invention includes an image segmentation condition determination step S10, a satellite image segmentation step S20, a moisture index exponential image acquisition step S30, An acquisition step S40, a binarized image edge detection and filtering step S50, a shoreline information acquisition step S60 of the satellite image, and the like.

Since the satellite image to be used in the present invention is a large-capacity high-resolution image like the KOMPSAT-3 image, which has a data capacity of several gigabytes, there is a problem in that a general computer can not load the entire original image into the memory at once . Accordingly, in the present invention, the data capacity is reduced through the satellite image segmentation process, and then the image processing operation is performed, so that the satellite image of large capacity and high resolution can be processed at one time and the time required for the image processing can be improved at the same time.

First, in step S10, the system initialization is performed, thereby adjusting the image segmentation condition (for example, the number, size, and shape of the divided images) of the satellite image in consideration of the size of the satellite image, .

In step S20, when a satellite image is inputted (S21), four vertex information (for example, GPS coordinates) of the input image is extracted using a library such as a GDAL (Gospatial Data Abstraction Library) (S22), and it is compared with the location database of the standard coastline to determine whether a coastline exists in the satellite image (S23). If a shoreline exists in the satellite image (S24), a plurality of segmented images including a shoreline area and a data size that can be processed by the general platform are acquired from the satellite image (S25).

As described above, according to the present invention, rather than simply dividing a large-capacity high-resolution satellite image according to a fixed pattern, it is possible to grasp an analysis required area based on shoreline information and to divide an analysis required area into a plurality of images, So that capacity can be more effectively and reliably reduced. In addition, the adjacent divided images include the same coastline so that the divided images can stably include all the coastlines of the satellite image.

The location database of the standard shoreline is pre-registered information before image processing, and it is acquired by accessing a data server which is a GPS coordinate data set stored in a local database of the image processing system or a private company or a government server May be a GPS coordinate data set.

In step S30, a moisture exponent weighted image of each of the divided images as shown in FIG. 4A is acquired using NDWI (Normalized Difference Water Index) or MNDWI (Modified NDWI) algorithm. That is, in the present invention, water and land are distinguished from each other based on the moisture index in consideration of the difference in water index between water and land.

For reference, NDWI and MNDWI are technologies for extracting images that emphasize the moisture index by using the difference in reflectance value of each image band. NDWI is a technique for extracting the image of the water between the infrared and green bands in consideration of low reflectance in the infrared region. Differences are exploited, and MNDWI is characterized by the difference between the neutral and green bands.

In step S40, binarization is performed on the moisture exponent weighted image to generate a binarized image as shown in FIG. 4 (b). Then, by applying the open operation, which is one of the morphology techniques, to the binarized image, various noise (i.e., various noise objects generated by the inland water, the book area, etc.) existing in the binarized image as shown in FIG. Removed or canceled.

The noise of the binarized image can be removed by using both the open method and the closed method in the morphology method. However, when the open method is used, as shown in FIG. 5 (a) In the case of using the closing method, as shown in FIG. 5 (b), there is a difference that small pixels such as inland water are segmented and expressed. In this case, in the case of the closed calculation, it is effective to remove the object (for example, double) noise adjacent to the land, but since it is difficult to extract the shoreline due to the inter-pixel segment, in the present invention, Allow objects to be removed and canceled.

In step S50, an edge of the binarized image is detected using an edge detection algorithm such as a canny algorithm, as shown in FIG. 6, and an edge having the longest length among the detected edges is detected as an edge corresponding to the shoreline And output it.

Since the binarized image includes not only the coastline but also the inland water and the island area, in order to extract the shoreline, the inland water and the island area in the binarized image must be removed. Therefore, the present invention extracts the edge having the longest length among the edges of the binarized image as the coastline, considering that the inland water and the island area have a morphological shape and the edge length is relatively shorter than the coastline.

In addition, since the shoreline has a morphological feature with a number of points above the threshold, an area width, and a volume of pixel populations, if necessary, at least one of the number of points of the edge, the area width, and the volume of the pixel cluster, So that the accuracy can be improved by extracting the shoreline. For example, when edge length and area width are used, when there are a plurality of edges having a similar length, the edge having the largest area width among a plurality of edges can be extracted.

In step S60, the coastline extraction result for each divided image is collected to restore the entire coastline of the satellite image. The shoreline restoration method can be implemented in various forms. For example, as shown in FIG. 7, after shoreline edge is mapped to a segmented image, a segmented image mapped to the shoreline is re-synthesized into an original satellite image, The entire coastline information displayed overlay on the image can be obtained. Alternatively, it is possible to acquire the entire coastline information by only collecting and connecting the shoreline edge of the segmented image, and then directly map to the satellite image.

In addition, according to the present invention, the result of shoreline extraction for each divided image is corrected in consideration of coordinate adjustment, actual coordinate value of the satellite image self-starting pixel, and image resolution value per pixel width, So that it can be improved. At this time, since the correction value is a decimal point, it may be a float type or a double type.

FIG. 8 is a diagram for further illustrating a method of dividing a satellite image according to an embodiment of the present invention. In FIG. 8, a divided image is represented by a green square.

As described above, the present invention estimates a shoreline area existing in a satellite image by comparing and analyzing the position information of the satellite image itself and the standard shoreline position database, and acquires only the image including the corresponding area as a plurality of divided images, .

In addition, according to the present invention, the data processing capacity of a plurality of divided images can be further adjusted through an image segmentation condition, thereby maximizing image processing efficiency.

For example, as shown in FIG. 8 (a), the size and shape of each divided image may have a fixed value. However, as shown in FIG. 8 (b) So that it can be actively varied depending on the shape.

For example, when the shoreline has a straight line shape in the vertical or horizontal direction, a divided image having a rectangular shape having a relatively long or long length is obtained, and when the shoreline has an ellipse shape, So that a divided image having a similar rectangular shape can be obtained. In other words, the peripheral region of the shoreline coordinates is set as the shoreline region, and the shape of each divided image (i.e., the width and height of the divided region) can be actively adjusted based on the shape of the shoreline region. According to this method, the number of divided images including the shoreline information can be reduced as compared with the case where the divided images are generated in a fixed size and shape, thereby providing an advantage that the system processing capacity can be further reduced.

Nevertheless, when the data processing capacity exceeds the system processing capacity, the resolution of each of the divided images may be downsampled by the capacity excess value. That is, by forcibly decreasing the data processing capacity of each of the divided images, the system processing capacity can be maintained at a constant value or less.

9 is a view for explaining a coastline extraction system using a large-capacity high-resolution satellite image according to an embodiment of the present invention.

9, the system of the present invention includes a satellite image obtaining unit 10, a satellite image dividing unit 20, a divided image processing unit 30, a coastline obtaining unit 40, and a data output unit 50. [ And the like.

The satellite image acquisition unit 10 connects to an external server that collectively stores, manages, and provides all the satellite images provided by the satellites to search and acquire satellite images of the analysis target area.

The satellite image segmentation unit 20 adjusts the image segmentation condition based on the satellite image size and the system processing capacity before performing the satellite image segmentation operation. Then, when the satellite image is input, the image segmentation operation based on the image segmentation condition is performed. More specifically, when a satellite image is input, four GPS coordinates of a vertex of a satellite image are extracted, and a location database of a previously registered standard coastline is searched to determine whether a coastline exists in the satellite image . Then, only when the coastline exists in the satellite image, the satellite image is divided according to the image segmentation condition to acquire a plurality of segmented images including each of the images corresponding to the standard coastline.

The divided image processing unit 30 acquires the moisture exponent weighted images of each of the divided images using the NDWI and MNDWI algorithms, binarizes them, and detects the edges of the binarized images. Then, by removing the noise edge corresponding to the inland water and the book area, the shoreline information corresponding to each of the divided images is acquired.

The shoreline acquisition unit 40 acquires and stores the entire coastline information of the satellite image based on the image processing result of the divided image processing unit 30, that is, the shoreline information of each divided image.

The data output unit 50 visualizes the entire shoreline information of the satellite image, and guides the user to a user interface (for example, a monitor or the like) connected to the system, or stores the file in a database or outputs the file to an external device .

The features, structures, effects and the like described in the foregoing embodiments are included in at least one embodiment of the present invention and are not necessarily limited to one embodiment. Further, the features, structures, effects, and the like illustrated in the embodiments may be combined or modified in other embodiments by those skilled in the art to which the embodiments belong.

Therefore, it should be understood that the present invention is not limited to these combinations and modifications. While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be construed as limiting the scope of the present invention. It can be seen that various modifications and applications are possible. For example, each component specifically shown in the embodiments may be modified and implemented. It is to be understood that the present invention may be embodied in many other specific forms without departing from the spirit or essential characteristics thereof.

Claims (8)

Determining a shoreline position in a satellite image based on a previously registered standard shoreline position database and performing image segmentation considering the shoreline position to obtain a plurality of segmented images;
Obtaining a moisture exponent weighted image of each of the divided images;
Obtaining a binary image of each of the moisture exponent weighted images;
Extracting a coastline of each of the divided images by removing an inland number and a noise edge corresponding to the book area after detecting an edge of the binarized image; And
And combining the shoreline extraction results of each of the divided images to acquire the entire coastline of the satellite image. The method of claim 1, wherein obtaining the plurality of divided images comprises:
Extracting position information of the satellite image using a GDAL (Geospatial Data Abstraction Library) library;
Comparing the position information of the satellite image with coordinate information of a standard coastline registered in advance to determine a shoreline position in the satellite image; And
And extracting the plurality of divided images by performing an image segmentation operation based on the shoreline position. The method of claim 1, wherein the step of acquiring the moisture index highlight image
(NDWI), and a modified NDWI (MNDWI) algorithm. A method of extracting a coastline using a large-capacity high-resolution satellite image is provided. 2. The method of claim 1, wherein obtaining the binarized image comprises:
And extracting or canceling noise in the binarized image through an open operation. The method of claim 1, wherein extracting the shoreline comprises:
Wherein the edge having the longest length among the edges of the binarized image is extracted as a shoreline. 6. The method of claim 5, wherein extracting the shoreline comprises:
Wherein the shoreline is extracted by considering at least one of the number of points of the edge, the area of the area, and the volume of the pixel cluster. 6. The method of claim 5,
Further comprising the step of adjusting an image segmentation condition based on the size of the satellite image and the system processing capacity before the step of acquiring the plurality of segmented images. A satellite image acquiring unit for acquiring a plurality of divided images by performing an image segmentation in consideration of a shoreline position in a satellite image based on a previously registered standard shoreline position database and considering the shoreline position;
A division image processing unit for obtaining a moisture exponent weighted image of each of the divided images and binarizing the extracted water exponent weighted images, and detecting and filtering an edge of the binarized image to extract coastlines of the divided images; And
A shoreline extraction system using a large-capacity high-resolution satellite image including a shoreline acquisition unit for synthesizing shoreline extraction results of each of the divided images to acquire the entire shoreline of the satellite image.

Images