KR101877173B1 - Coastline Detection System using Satellite Image and method thereof - Google Patents

Abstract

A coastline detection method using a satellite image according to an embodiment of the present invention includes a step of receiving a satellite image, performing a preset coordinate extraction algorithm on the received image and extracting two-dimensional coordinates; a step of comparing the GPS coordinate value of the satellite image with the GPS coordinate value of a region to be divided and determining whether the region is present in the satellite image; a step of dividing the satellite image based on the extracted coordinates; and a step of detecting a coastline by matching the divided images. It is possible to obtain high detection performance.

Description

[0001] Coastline Detection System Using Satellite Image and Method [0002]

More particularly, the present invention relates to a system and method for detecting a shoreline using a satellite image. More particularly, the present invention relates to a system and method for detecting a shoreline using a satellite image, The present invention relates to a coastline detection system and method using a satellite image having a high detection performance in various environments by detecting a coastline by applying an algorithm.

GPS measurement, aerial photography, and aviation LiDAR can achieve high accuracy for areas of extreme human and economic costs, but it is unsuitable for large areas.

Currently, it is most efficient to use optical and multispectral images when considering economical aspects and image supply and demand. Therefore, it is required to construct a monitoring system using optical and multispectral satellite images.

Although coastline change monitoring technology is required to obtain base information for coastal policy establishment, shoreline changes with time. Therefore, coastline survey using high precision GPS and aerial photogrammetry can not be used as monitoring technology for temporal and economic reasons This is inadequate.

Korean Patent Publication No. 10-2006-0065218

According to an embodiment of the present invention, a system and method for detecting a shoreline using a satellite image are provided. In order to solve the above problems, a satellite image is segmented and processed based on existing GPS coordinates, The present invention provides a coastline detection system and method using a satellite image having a high detection performance and a real time property by detecting a coastline by setting a threshold value.

According to an embodiment of the present invention, a coastline detection system using satellite images includes a satellite for collecting satellite images; And an image division device for dividing the satellite image, wherein the image segmentation device comprises: a communication unit for receiving the satellite image from the satellite; A coordinate value extracting unit for extracting a GPS coordinate value of the satellite image; A video segmenting unit dividing at least a part of the satellite image into a predetermined size; And a shoreline detection unit for detecting the shoreline by matching the divided images in the image segmentation unit.

According to another aspect of the present invention, there is provided a coastline detection method using a satellite image, comprising: receiving a satellite image and extracting two-dimensional coordinates by performing a preset coordinate extraction algorithm on the received image; Comparing a GPS coordinate value of the satellite image with a GPS coordinate value of an area to be divided and determining whether a region to be divided is present in the satellite image; Dividing the satellite image based on the extracted coordinates; And detecting a shoreline by matching the divided images.

The system and method for detecting a coastline using a satellite image according to an embodiment of the present invention can improve the detection rate and processing speed of the system because it is possible to set and process only the region of interest instead of processing the entire satellite image when detecting a desired region .

In addition, according to the embodiment of the present invention, a coastline detection system and method using a satellite image can detect a shoreline by setting an adaptive threshold value for each image, thereby achieving high detection performance and real-time performance.

1 is a view illustrating a coastline detection system using a satellite image according to an embodiment of the present invention.
2 is a diagram illustrating a process of dividing an image using a satellite image according to an embodiment of the present invention.
3 is a flowchart illustrating a method of dividing a coastline detection image using a satellite image according to an embodiment of the present invention.
4 is a diagram illustrating a method for detecting inland and coastal areas according to an embodiment of the present invention.
5 is a flowchart illustrating a method of mapping a shoreline detected in a divided image to an original 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. It is also to be understood that the technical terms used in the present invention are used only to describe specific embodiments unless the technical terms used in the present invention are defined in different meanings in the present invention. It should be noted that this is not intended. 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.

Also, in the present invention, the terms such as "comprises ", or" comprising ", etc. should not be construed as necessarily including the various elements described in the invention or various steps, May not be included, or may be interpreted to include additional components or steps.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to like or similar elements throughout the several views, 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 is a diagram illustrating an image segmentation system using GPS coordinates according to an embodiment of the present invention.

As shown in the figure, an image segmentation system using GPS coordinates according to an embodiment of the present invention includes a satellite 100 for collecting image information and an image segmentation device 200. The image segmentation device 200 includes a communication unit 210, A coordinate value extracting unit 220, an image dividing unit 230, a storage unit 240 for storing coordinate information of a satellite image, and a shoreline detecting unit 250.

An artificial satellite (100) collects images and transmits them to an image dividing device (200). The images to be collected may be near the coastline, but are not limited thereto.

The image dividing device 200 receives an image from the satellite 100 and divides a part of the received image. Since satellite images are of high quality and large capacity, it takes long processing time to process the general development platform, and it is difficult to upload the entire satellite image to general computer memory.

The communication unit 210 performs data communication with an external device including the satellite 100 and receives the image captured by the satellite 100 and transmits the divided image from the image splitting device 200 to the outside Function.

The coordinate value extraction unit 220 extracts two-dimensional coordinates by performing a predetermined coordinate extraction algorithm on the received image.

The image divider 230 compares the GPS coordinate value of the area to be processed with the coordinate value of the input image (satellite image) to determine whether there is an area to be processed in the input image.

If there is no pre-stored region to be processed in the input image, it is determined that the terrain has been changed and the region is not included.

In addition, when there is an area to be processed in the input image, the image divider 230 divides the received image into predetermined areas based on the coordinates extracted by the coordinate value extractor 220. The size of the divided image may be set so as not to exceed a predetermined value. This can be set differently as needed and is changeable.

The shoreline detection unit 250 detects the shoreline by matching the divided images in the image segmentation unit 230. The shoreline detection unit 250 assigns a value of SAIL (Soil Adjusted Vegetation Index) to each of the divided images, and determines whether the applied SAVI value is 0 or less.

The functions and functions of the shoreline detection unit 250 will be described later with reference to FIG. 4 and FIG.

2 is a diagram illustrating a process of segmenting an image using GPS coordinates according to an embodiment of the present invention. The map screen shown in Fig. 2 has plane coordinates (X, Y) for a point where a specific area is located. At this time, the plane coordinates (X, Y) indicate the coordinate information on the map screen of the display unit, and correspond to the reference point.

The land 410 and the sea 420 are distinguished from the coastline 405 on the map screen shown in FIG. The plurality of regions 300 may include, but is not limited to, a portion of the shoreline 405.

Coastline 405 may change over time. The shoreline 405 may be divided into a plurality of regions 300. Each of the plurality of areas 300 is divided into a predetermined file size (size) or less.

3 is a flowchart illustrating an image segmentation method using GPS coordinates according to an embodiment of the present invention. First, a satellite image is received (S100), and two-dimensional coordinates are extracted by performing a predetermined coordinate extraction algorithm on the received image (S200).

Next, the GPS coordinate value of the area to be divided is compared with the GPS coordinate value of the satellite image to determine whether there is an area to be divided in the satellite image (S300).

The GPS coordinate value extracted in step S200 is a GPS coordinate value at the time of photographing the image, and the GPS coordinate value of the area to be divided in step S300 is a previously stored GPS coordinate value.

Next, in step S300, if the GPS coordinate value of the area to be divided is compared with the GPS coordinate value of the satellite image, if it is determined that the area to be divided is present in the satellite image, (S400). The image may include a shoreline.

The file size of the image to be divided in S400 is equal to or less than a preset value, and this can be set as needed.

4 is a diagram illustrating a method for detecting inland and coastal areas according to an embodiment of the present invention. First, a value of Soil Adjusted Vegetation Index (SAVI) is assigned to each of the divided images in the process of FIG. 3 (S510), and it is determined whether the given SAVI value is 0 or less (S520). SAVI represents the soil regulated vegetation index, and the soil regulated vegetation index is a transformation technique that minimizes the soil brightness effect of the spectral vegetation index including the infrared and near infrared (NIR) wavelengths. SAVI can be expressed by the following equation.

Where L is the number of canopy background adjustments. An L value of 0.5 in reflectance space minimizes the change in the brightness of the soil and eliminates the need for further correction for other soils. This conversion can remove most of the vegetation index induced by the soil.

If it is determined in step S520 that the SAVI value of the pixels constituting the divided image exceeds 0 (S521), if the SAVI value of the divided image is equal to or smaller than 0 in step S520, And stores it as pixel values of gray scale (S522). i and j denote the coordinates of the pixel.

Next, it is determined whether the corrected pixel value of the gray scale exceeds a predetermined threshold value (S523), and the pixel whose value is lower than the threshold value is removed (S524-1). If the pixel value exceeds the threshold value, (S524).

Next, the maximum value, the minimum value and the average value of the sea region detected in S524 are derived (S525), and the detected sea region is converted into a gray scale level (S530). Generally, a gray scale level in a display device means a colorless color table series in which color charts ranging from white to black are arranged in a manner corresponding to the object. For example, in the case of a black-and-white television, using grayscale can confirm how a color is displayed on a black-and-white screen.

Next, a threshold value for detecting the coastal road is derived using a multi-layer constant false alarm rate (CFAR) (S540). Among them, CA-CFAR (cell average constant false alarm rate) algorithm sets a window for a test cell and a reference cell around the test cell to perform processing on the received signal. By using this window, the noise of the neighboring reference cells is obtained and applied to the threshold, thereby increasing the detection rate. That is, when the ambient noise is large, the threshold value is increased, and when the ambient noise is small, the threshold value is low.

Next, it is checked whether the threshold value derived in S540 is included in the minimum, maximum, and average value ranges derived from the sea area (S550), and it is determined whether the gray scale exceeds the threshold value (S560). If the gray scale exceeds the threshold value, the inland area and the coast road are detected (S570). A pixel whose gray scale pixel value is lower than the threshold value is removed (S570-1).

By the processes of S510 to S570, inland areas and coast roads for each of the divided images are detected. However, it is not fixed at the present stage, but may be corrected in the process of mapping the coastline detected in the subsequent divided image to the original image.

5 is a flowchart illustrating a method of mapping a shoreline detected in a divided image to an original image according to an embodiment of the present invention. First, the divided images are combined (S610). The inland area and the coast road detected in the step of FIG. 4 are obtained for each of the divided images, and these divided images are recombined.

Next, hole filling is performed (S620). In FIG. 3, in the inland area and the coast road are detected for each of the divided images, a hole may be generated due to interference due to a structural pattern in the process of combining the inland and coast roads, and the hole is filled in step S620.

Next, the hole-filled image is labeled (S630). Labeling refers to assigning the same number (label) to all pixels connected adjacent to each other, and assigning another number (label) to another connected component. That is, the labeling refers to a process of considering regions, which are connected to the current pixel and are connected or have the same color range, as one object. If only the region having an arbitrary number is extracted from the labeled image, the region is separated, and it becomes possible to extract the size, the center coordinate, and the circumference length only for the special region.

Next, the edge is detected for the labeled image (S640). This can be done by generating an edge value for each pixel.

Next, the broken edge is checked and connected (S650). If the edge value of an adjacent pixel differs by exceeding a predetermined value, it is judged that the edge of the difference pixel is broken, and the edge is connected so as to have the edge value of the adjacent pixel.

Next, in step S660, the lengths of the edges connected in the step S650 are compared with each other, and the edge having the longest edge length is determined as a coast line and detected (S660).

Next, the shoreline detected in the divided image, that is, the shoreline detected in S560, is mapped to the original image, that is, the satellite image (S670). The coastline that changes with the lapse of time can be updated by the process of S670.

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.

100: satellite
200: image dividing device
210:
220: coordinate value extracting unit
230:
240:
250: Coastline detection unit

Claims (10)

Satellites that collect satellite images; And
And an image dividing device for dividing the satellite image,
Wherein the image dividing device comprises:
A communication unit for receiving the satellite image from the satellite;
A coordinate value extracting unit for extracting a GPS coordinate value of the satellite image;
A video segmenting unit dividing at least a part of the satellite image into a predetermined size; And
And a shade line detecting unit for detecting a shade line by matching the divided images in the image dividing unit,
The shoreline detection unit
The pixels having a value smaller than the threshold value are removed and the pixels having a threshold value exceeding the threshold value are determined as a sea region, Wherein the inland area and the coast road are detected based on the minimum, maximum and average values at the gray scale level of the sea area, and the images are combined.
The method according to claim 1,
Wherein the coordinate value extractor compares the GPS coordinate value of the area to be divided with the GPS coordinate value of the satellite image to determine whether the area to be divided exists in the satellite image.
The method according to claim 1,
The shoreline detection unit
Wherein a value of a Soil Adjusted Vegetation Index (SAVI) is assigned to each of the divided images before correcting the divided image by grayscale, and it is determined whether a given SAVI value is 0 or less. Coastline Detection System.
Receiving a satellite image and extracting two-dimensional coordinates by performing a preset coordinate extraction algorithm on the received image;
Comparing a GPS coordinate value of the satellite image with a GPS coordinate value of an area to be divided and determining whether a region to be divided is present in the satellite image;
Dividing the satellite image based on the extracted coordinates; And
And detecting a shoreline by matching the divided images,
The step of detecting the shoreline
Determining whether the pixel value of the corrected gray scale of the divided image exceeds a predetermined threshold value, removing pixels having a value lower than the threshold value, and determining pixels having a threshold value exceeding the threshold value as a sea region ; And
Detecting an inland area and a coast road based on a minimum, a maximum, and an average value at a gray scale level of the sea area, and combining images.
5. The method of claim 4,
Wherein the step of dividing the satellite image comprises dividing the satellite image so that the size of the satellite image is less than a predetermined file size.
5. The method of claim 4,
Wherein the step of detecting the coastline comprises:
Wherein the step of dividing the satellite image based on the extracted coordinates is performed before the dividing the image into grayscale,
Applying a value of SAIL (Soil Adjusted Vegetation Index) to each of the divided images, and determining whether the given SAVI value is 0 or less.

delete delete 5. The method of claim 4,
After combining the images,
Hole filling the image;
Labeling the hole-filled image; And
And detecting an edge of the labeled image.
10. The method of claim 9,
After the step of detecting the edge,
Inspecting and connecting broken edges of the image; And
And detecting the edge having the longest edge as a shoreline and detecting the shoreline using the satellite image

Images