KR101480173B1 - Apparatus for extracting coastline automatically using image pixel information and image pixel information change pattern by moving variance and the method thereof - Google Patents

Abstract

The present invention relates to an apparatus and method for automatically extracting coastline using image pixel information and pixel information change pattern by moving average. The apparatus includes: an average image creating unit creating an average image of coast images captured for a predetermined time by a plurality of cameras; a color profile analysis unit extracting a characteristic value for each pixel from the average image created by the average image creating unit; and a coastline extracting unit comparing a moving average for the characteristic value for each pixel and a total average of the pixel characteristic value to extract a coastline. Since the coastline can be extracted by using a rapid change of a pattern among pixels without applying a reference value for the coastline analysis like a coastline extraction by R and B intersection point analysis and a coastline analysis by a hue value of a reference value or greater in the conventional art, an accurate coastline can be extracted regardless of a image capturing time such as sunset and sunrise, or a weather environment such as a cloudy day, or a clear day.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an apparatus and method for automatically extracting a shoreline using pixel information and a pixel-

The present invention relates to an apparatus and a method for automatically extracting a shoreline, and more particularly, to an apparatus and a method for automatically extracting a shoreline from a shoreline of a coastal area by using pixel information and moving dispersion And an apparatus and method for automatically extracting shorelines using a pixel information change pattern.

Recently, coastal erosion area is increasing rapidly due to coastal development and changes in natural environment. As a result, not only economic losses but also environmental and social problems have led to a growing need for long-term monitoring of coastal erosion, thus increasing the need for accurate coastline identification.

As described above, when a long-term continuous observation and monitoring of an arbitrary object is required in the past, there is a method in which measurement is carried out individually by a surveying work in which manpower is input, or a method in which analysis is performed through satellite photographs, And a method of using data. However, these methods require a large number of manpower mobilization, expensive equipment is expensive, and there is a limitation in real time continuous observation because of constraints due to weather conditions.

In addition, in order to observe shoreline change, there is a risk of damages and loss of expensive equipments by observing survey using existing surveying and observing instruments, and it is impossible to observe in case of bad weather, and continuous observation in real time for a long time is very difficult.

In addition, considering the regional and seasonal characteristics of the coastal habitats, the extraction option is set to a fixed value, so that it can not cope with the change of the altitude of the sun which changes with time. Therefore, There is a problem that frequent errors occur.

Accordingly. Korean Patent Publication No. 2007-0044610 discloses a method of photographing a beach area using a plurality of cameras, storing pixel information related to sunset, sunrise, cloudy weather, backlight, and clear day in a database, Discloses a method for extracting a coastline in comparison with information in a database.

However, since a reference value must be set in the information extraction system of real-time blue and shoreline change using a video camera of Korean Patent Laid-Open Publication No. 2007-0044610, the reference value must be differently applied according to weather, In the case where the reference value is set incorrectly, the pixel information of the corresponding region does not reach the reference value even in the coastline, and the above-described conventional technique can not cope with the altitude change of the sun varying with time, Frequent errors arise due to backlight and shoreline color change.

Among the shoreline extraction methods of the prior art, there is a method of using H among the pixel characteristics of C (cyan), Y (yellow), H (hue), and S (saturation) when an image taken on a cloudy day is used. In this case, H generally represents a value of 100 or more on the sea side, and a value of 30 or less on the white side. Therefore, a predetermined value (eg, 50) is set as a reference, and the position of the first pixel having a value of H or less is determined as a shoreline. However, in this case, there is a problem that an error occurs in which a pixel that does not meet the set value is determined as a shoreline depending on the degree of fog.

SUMMARY OF THE INVENTION Accordingly, the present invention has been made keeping in mind the above problems occurring in the prior art, and it is an object of the present invention to provide an image processing apparatus and a method thereof, And an object of the present invention is to provide an apparatus and method for automatically extracting a shoreline using pixel information of an image and a pixel information change pattern by moving dispersion so that a shoreline can be easily extracted automatically.

According to an aspect of the present invention, there is provided an apparatus for automatically extracting shorelines using pixel information and a pixel information change pattern by motion distribution, the apparatus comprising: An image generation unit; A color profile analyzer for extracting a characteristic value for each pixel from the average image generated by the average image generator; And a shoreline extracting unit for extracting a shoreline by comparing the moving average of the characteristic values of each pixel with the overall average of the pixel characteristic values.

Wherein the shoreline extraction unit is configured to calculate the distribution of the moving variance values and to select the first pixel among the pixels having the pixel characteristic value less than or equal to the total average value as the shoreline pixel among the pixels having the moving dispersion value equal to or greater than the threshold value do.

Wherein the shoreline extraction unit selects, as shoreline candidate pixels, pixels having a dispersion greater than or equal to a threshold value among the moving dispersion values, and when the pixel characteristic value indicates a smaller value on the land side, Selecting a first pixel below the overall average as a shoreline pixel, and when the pixel characteristic value indicates a large value on the land side, the pixel characteristic value of the coastline candidate pixels is selected as a shoreline pixel .

The shoreline extraction unit is configured to extract the shoreline by comparing the color information of the pixels from the sea side of the average image, so that when the shoreline is compared from the land side, the shoreline is not easily recognized by an object having an achromatic color or a color similar to the sea So that it is prevented from being extracted.

According to an aspect of the present invention, there is provided a method for automatically extracting shorelines using pixel information and a pixel information change pattern based on motion distribution, the method comprising: averaging shoreline images captured by a plurality of cameras for a predetermined time, An average image generation process to generate; A color profile analyzing step of recording pixel-specific characteristic values from the first pixel to the last pixel of the generated average image; And a mobile dispersive shoreline extracting step of extracting a shoreline by comparing the moving average of the characteristic values of each pixel in the color profile analysis and the overall average of the pixel characteristic values.

And the first pixel in the color profile analysis process is a starting pixel of an averaged image, which is far from the land.

Wherein the mobile dispersive shoreline extraction process comprises: a mobile dispersion distribution calculation process of calculating a distribution of the mobile dispersion values; A mobile dispersive shoreline candidate pixel selection step of selecting pixels corresponding to the motion variance values having a variance value equal to or greater than the threshold value as the mobile dispersion shoreline candidate pixels; And a mobile distributed shoreline pixel selection step of selecting the first pixel among the values of the pixel values of the mobile dispersion shore candidate pixels that is less than or equal to the overall average as shoreline pixels.

Wherein the moving dispersion shoreline pixel selecting step selects pixels having a dispersion greater than or equal to a threshold value among the moving dispersion values as shoreline candidate pixels and, when the pixel characteristic value indicates a small value on the land side, Wherein if a pixel value of the shoreline candidate pixel is larger than a value of the shoreline candidate pixel, the pixel value of the shoreline candidate pixel is greater than the average pixel value of the first pixel, And select the shoreline pixels.

The present invention having the above-described configuration makes it possible to extract a shoreline after photographing a sea area using a general public digital camera without photographing by a satellite or an aircraft, thereby remarkably facilitating shoreline extraction, And provides a significant reduction in cost for shoreline extraction.

Further, the present invention described above can be applied to a coastline analysis without applying a reference value for shoreline analysis, such as shoreline extraction by R and B intersection point analysis, shoreline analysis by hue value above a reference value setting, The shoreline can be extracted using the pattern change between the pixels, so that it is possible to extract the accurate shoreline without being affected by the weather conditions such as sunset, sunrise, etc., cloudy day, or sunny day .

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram of a coastline automatic extraction apparatus using image pixel information and a pixel information change pattern according to an embodiment of the present invention; FIG.
FIG. 2 is a view showing an example in which the coastline automatic extraction apparatus 200 of FIG. 1 is constructed for coastline extraction. FIG.
3 is a flowchart showing a process of a shoreline automatic extraction method using image pixel information and a pixel information change pattern according to an embodiment of the present invention.
Figure 4 is a photograph of instantaneous images taken by the camera.
FIG. 5 shows an average image image generated by the average image generation unit 100; FIG.
FIG. 6 is a graph showing the pixel characteristic value distribution calculated by the color profile analysis process (S30) of FIG. 3;
FIG. 7 is a flowchart showing a detailed processing procedure of the mobile dispersed shoreline extraction process (S40) of FIG. 3;
8 is a graph showing the distribution of the mobile dispersion.
FIG. 9 is a graph showing the distribution of pixels extracted so as to have a motion dispersion greater than or equal to a threshold value. FIG.
10 is a graph showing a process of deriving shoreline pixels using adjacent pixels with an average value in between.

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

In the following description of the present invention, detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

Embodiments in accordance with the concepts of the present invention can make various changes and have various forms, so that specific embodiments are illustrated in the drawings and described in detail in this specification or application. It should be understood, however, that the embodiments according to the concepts of the present invention are not intended to be limited to any particular mode of disclosure, but rather all variations, equivalents, and alternatives falling within the spirit and scope of the present invention.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between. Other expressions that describe the relationship between components, such as "between" and "between" or "neighboring to" and "directly adjacent to" should be interpreted as well.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, the terms "comprises ",or" having ", or the like, specify that there is a stated feature, number, step, operation, , Steps, operations, components, parts, or combinations thereof, as a matter of principle.

1 is a functional block diagram of an automatic shoreline extraction apparatus 200 using image pixel information and pixel information change patterns according to an embodiment of the present invention.

1, the shoreline automatic extraction apparatus 200 includes an average image generation unit 210, which receives an instantaneous image, which is an image captured during a predetermined period of time, A contrast enhancement unit 210 for enhancing the contrast of the average image generated by the average image generation unit 205, an ortho correction image generation unit 210 for generating an ortho corrected image of the enhanced image, A color profile analyzer 230 for extracting characteristic values for each pixel from the ortho corrected image and recording the characteristic values, and a chromaticity analyzer 230 for calculating a chromatic dispersion for each characteristic value of each pixel to generate a pixel variation pattern, And selects the shoreline candidate pixels from among the selected shoreline candidate pixels and sets the first pixel on the land side to the shoreline pixel Exodus is configured by including the coastline extraction unit 240 which extracts the shoreline. In the drawing, the shoreline display unit 300 refers to an external device such as a display device.

Among the above-mentioned constructions, the instant images are images captured at predetermined intervals for a predetermined time using a camera such as a digital camera, for a beach area to be a shoreline extraction target.

For example, images taken every 4 ~ 5 seconds for about 2 minutes in the sea area where the coastline is extracted can be used as a real-time image.

The average image generator 205 is an image generated by superimposing a pixel value of the instantaneous images described above. The average image generating unit 205 generates an average image that allows the user to clearly distinguish the shoreline continuously changing by the wave. When the superimposed average of the characteristic values of the pixels is performed in the process of generating the average image as described above, the moving object disappears from the image through filtering such as the color average. Since this process is applied throughout the entire shooting frame, only the fixed object appears in the average image, and the moving object disappears. Thus, the shoreline is clearly distinguished by a white line.

The contrast enhancement unit 210 enhances the contrast of the image to enhance the degree of recognition of the object by setting the bright portion of the average image to be brighter and the dark portion to be darker, and outputs the enhanced image to the ortho corrected image generation unit 220.

The ortho corrected image generation unit 220 converts an image displayed according to the perspective method into an image displayed on a plane view to generate an ortho corrected image, and provides the ortho corrected image to the color profile analysis unit 230. The ortho correction image generation unit 220 receives the enhanced contrast image and converts the shape of the image that changes according to the shooting angle into a projection image of a point on the projection surface such that the point is projected in a spatial coordinate system to generate an ortho corrected image do. At this time, GCP measurement coordinates are applied to the ortho corrected image.

The color profile analyzer 230 includes an RGB profile analyzing module 232 and a CMYK profile analyzing module 234. The color profile analyzing unit 230 analyzes the received average image or the average of the pixels of each of the pixels in the image obtained by enhancing the contrast of the received image and correcting the pixels of the image by using the red, green, blue, cyan, magenta, hue, saturation information, level information, and the like, which are information of the pixel values of the pixels, such as magenta, magenta, yellow, and black. The extraction of the pixel characteristic values is performed sequentially from the first pixel to the last pixel of the generated average image. And the first pixel is a sea area of the average image image pixel, which is a pixel at the sea edge far from the land.

The image image data input to the color profile analyzer 230 may include an average image generated by the average image generator 205, an average image enhanced by the contrast enhancement unit 210, The ortho corrected image generated by the ortho corrected image generating unit 220 or the ortho corrected image generated by the ortho corrected image generating unit 220 directly without the enhancement of the contrast in the average image generating unit 205 And can be selectively input.

In this case, when the color profile is directly analyzed in the average image, the contrast enhancement unit 210 and the ortho correction image generation unit 220 of FIG. 1 may not be provided. In addition, if the color profile is directly analyzed in the average image in which the contrast is enhanced, the ortho correction image generation unit 220 of FIG. 1 may not be provided. If the color profile is analyzed after the average image is directly orally corrected, the contrast enhancement unit 210 of FIG. 1 may not be provided.

The shoreline extracting unit 240 calculates the average of the characteristic values of pixels of the average image analyzed by the color profile analyzer 230. Then, by selecting the interval of 0.5%, 1%, 2%, 5%, etc. of the entire pixels according to the specific moving dispersion period starting from the sea side, for example, by calculating the moving dispersion for each pixel, And the distribution is calculated. Then, pixels included in the top 0.5%, 1%, 2%, 5%, etc. of the total scattered values of all the pixels are selected as the mobile scattered shoreline candidate pixels according to the accuracy of the calculated mobile dispersion values. Thereafter, the characteristic values of the shoreline candidate pixels are compared with the line of the average value of the pixel characteristic values, and the shoreline is extracted by extracting the first pixel among the pixels above or below the entire average value as shoreline pixels. That is, when the pixel characteristic value appears as a small value on the land side, the first pixel whose pixel characteristic value is less than the overall average among the coastline candidate pixels is selected as a shoreline pixel, The shoreline candidate pixel is configured such that the pixel value of the shoreline candidate pixels is the shoreline pixel as the first pixel of the total average or more. For example, when the pixel property value is set to R (red), one of the adjacent pixels has an R value smaller than the average value and an R value larger than the average value because the R value is smaller on the sea side and the R value is larger on the land side. , The shoreline is extracted by extracting the land pixels having a large R value as shoreline pixels. In contrast, when the pixel characteristic value is set to B (blue), since the B value on the sea side is larger, if one of the adjacent pixels has a B value larger than the average value and a B value smaller than the average value of the other pixels, And extracts the shoreline by extracting shoreline pixels as land pixels.

FIG. 2 is a view showing an example of a coastline extraction system in which the coastline automatic extraction apparatus 200 of FIG. 1 is constructed for shoreline extraction.

2, the system includes a plurality of digital cameras 10, a video server 20, a network hub (not shown) A central data processing server 60, and a web server 70 for managing an internet home page, and the like.

The digital cameras 10 capture blue and coastline images in real time and transmit them to the video server 20 through a communication network.

The video server 20 transmits the received image to the shoreline automatic extraction device 200 through the network hub 30.

As described above, the shoreline automatic extraction apparatus 200 obtains an average image by overlapping averaging the received shoreline images on a pixel-by-pixel basis, and then calculates a moving dispersion value for each characteristic value of each pixel of the average image, The coastline is extracted using the average value.

The extracted shoreline information is transmitted to the central data processing server 60. The central data processing server 60 extracts all of the extracted coastal information from the information extraction system of the coastal blue (a) and coastal (b) It can be constructed so as to provide services such as receiving data and updating data in real time on the Internet homepage.

FIG. 3 is a flowchart illustrating a process of an automatic shoreline extraction method using image pixel information and a pixel information change pattern according to an exemplary embodiment of the present invention. FIG. 4 is a photograph of real-time images taken by a camera, FIG. 6 is a graph showing a pixel characteristic value distribution calculated by the color profile analysis process S30 of FIG. 3; FIG.

A method for automatically extracting shorelines using image pixel information and pixel information change patterns of the present invention will be described with reference to FIGS. 1, 2, and 3 to 6. FIG.

As shown in FIG. 3, the shoreline automatic extraction method using the image pixel information and the pixel information change pattern includes a coastal area image sensing step S10, an average image generation step S20, a color profile analysis step S30, And a mobile dispersed shoreline extraction process (S40).

The coastal ocean image acquisition step S10 acquires the ocean images as instant images through a plurality of digital cameras 10 installed to photograph a sea area as shown in FIG. At this time, the images captured at various time intervals such as 2 to 3 seconds or 4 to 5 seconds for a predetermined time such as 2 minutes, 3 minutes, or 5 minutes form instant images as shown in FIG. 4 . As described above, the instant images photographed by the digital cameras 10 are transmitted to the shoreline automatic extraction device 200 through a communication network for shoreline extraction.

The average image generation process S20 is a process in which the average image generation unit 205 of the shoreline automatic extraction apparatus 200 receiving the instantaneous images by the above-described coastal oceanographic image capturing step S10 superimposes the instantaneous images on a pixel by pixel basis And averaging is performed to generate one average image as shown in FIG. As described above, the information of the moving object disappears in the average image, and a blue, white foam that is broken at the breaking wave appears as a line. Thus, the coastline can be clearly distinguished. In the average image generation process S20, the image generated by the average image generation unit 205 is transmitted to the color profile analysis unit 230. [ In this process, the average image may be enhanced by the contrast enhancement unit 210 or may be converted into the ortho corrected image by the ortho correction image generation unit 220.

In the color profile analysis process S30, the color profile analyzing unit 230 including the RGB profile analyzing module 232 and the CMYK profile analyzing module 234 analyzes the average image or the contrast of the received image, For each pixel in the image, color information of red, green, blue or cyan, magenta, yellow, black, hue, The pixel characteristic values such as saturation information and level information are extracted as shown in FIG. The extraction of the pixel characteristic values is performed sequentially from the first pixel to the last pixel of the generated average image. And the first pixel is a sea area of the average image image pixel, which is a pixel at the sea edge far from the land. The characteristic values of the extracted average image are output to the shoreline extraction unit 240.

In the mobile dispersive shoreline extraction process (S40), a total average of the pixel characteristic values of each average image of FIG. 6 is obtained, a specific motion dispersion interval is set, and a motion dispersion value for each pixel is calculated. At this time, the mobile dispersion interval can be arbitrarily set to 0.5%, 1%, 2%, 5%, etc. of the total number of pixels depending on the accuracy and processing speed. Then, pixels having a variance value greater than or equal to a specific threshold value are selected as the mobile dispersion shoreline candidate pixels from the calculated moving dispersion value. The threshold value may also be arbitrarily set to an upper 0.5%, 1%, 2%, 5%, or the like among the moving dispersion values depending on the accuracy and the processing speed. Thereafter, the characteristic values of the shoreline candidate pixels are compared with the line of the total average value of the pixel characteristic values, and the pixel characteristic value is set to a value larger or smaller than the total average value, The extraction of the first pixel among the pixels as a shoreline pixel is as described above. This process is repeated for each pixel line to extract the shoreline.

FIG. 7 shows a detailed processing procedure of the above-described mobile dispersed shoreline extraction process (S40) of FIG. As shown in FIG. 7, the mobile dispersed shoreline extraction process S40 includes a moving dispersion distribution calculation process S41, a mobile dispersive shoreline candidate pixel selection process S42, and a mobile dispersion shoreline pixel selection process S43, Automatically extracts the shoreline from the image.

Specifically, in the moving dispersion variance calculating process S41, a moving variance value is calculated for each pixel by applying the set moving variance interval. FIG. 8 is a graph showing the movement variance for each pixel calculated as described above.

Thereafter, in the mobile dispersive shoreline candidate pixel selection process (S42), upper pixels above the threshold value set for the motion variance values of the pixels are selected as the mobile dispersive shoreline candidate pixels. FIG. 9 is a graph showing the distribution of pixels selected as pixels that correspond to the upper 1% range of the motion variance values as the mobile dispersive shoreline candidate pixels by setting the threshold value to the upper 1%.

In the mobile dispersive shoreline pixel selection process S43, the characteristic values of the selected mobile dispersive shoreline candidate pixels are compared with the overall average value of the characteristic values of the pixels, and the first The pixels are extracted as shoreline pixels, and this process is repeated to extract the shoreline.

10 is a graph showing that a shoreline pixel is selected by applying a pixel characteristic value having a larger sea-side characteristic value as shown in Fig. In the case of FIG. 10, since the characteristic value of the pixel is selected as the characteristic value B, if the characteristic value of the adjacent pixels is changed from below the average to below the average value, Is selected.

By repeating the above process repeatedly along the pixel line of the entire average image and connecting the selected shoreline pixels, the shoreline can be automatically extracted in the average image.

 The extracted coastline may be displayed on the coastline display unit 300 together with a background including coordinate information, and may be provided as coastline information on the web as in the description of FIG.

200: shoreline extraction unit 205: average image generation unit
210: contrast enhancement unit 220: ortho correction image generation unit
230: color profile analyzer 232: RGB profile analyzer module
233: CMYK profile analysis module 240: Shoreline extraction section
300: shoreline display unit 10: camera
20: video server 30: network server
50: modem 60: central data processing server
70: Web server

Claims (8)

An average image generation unit for generating an average image of the shots by superimposing a plurality of color information of each pixel of the instantaneous images of the coastal shore taken at regular intervals for a predetermined time by a plurality of cameras;
A color profile analyzer for extracting a characteristic value for each pixel from the average image generated by the average image generator; And
And a shoreline extracting unit for extracting a shoreline by comparing the moving average of the characteristic values of each pixel with the overall average of the pixel characteristic values. Automatic coastline extraction system.
[2] The method according to claim 1,
Wherein the controller is configured to calculate the distribution of the moving variance values and to select the first pixel among the pixels having the pixel characteristic value less than or equal to the overall average as the shoreline pixel among the pixels having the moving variance value equal to or greater than the threshold value. Automatic Shoreline Extraction Using Pattern of Pixel Information Change by Dispersion.
[3] The method according to claim 2,
If the pixel characteristic value is smaller on the land side, the shoreline pixel is selected as the first pixel having the pixel characteristic value less than the average of the shoreline candidate pixels, and if the pixel characteristic value is larger on the land side Wherein the shoreline candidate pixels are configured such that a pixel characteristic value of the shoreline candidate pixels is selected as a shoreline pixel over the entire average of the shoreline candidate pixels.
[2] The method according to claim 1,
And comparing the color information of the pixels from the sea side of the average image to extract a shoreline, the shoreline is prevented from being erroneously extracted by an achromatic object when compared from the land side. Automatic shoreline extraction using pixel information and pixel information change patterns by moving dispersion.
An average image generation process of generating an average image of a beach by superimposing and averaging the color information of each pixel of the instantaneous images of coastal beaches taken at regular intervals by a plurality of cameras;
A color profile analyzing step of recording pixel-specific characteristic values from the first pixel to the last pixel of the generated average image; And
And a mobile dispersed shoreline extracting step of extracting a shoreline by comparing the moving average of the characteristic values of each pixel and the average of the pixel characteristic values in the color profile analyzing step. A Method for Automatic Shoreline Extraction Using Pixel Information Change Pattern by.
The method of claim 5,
Wherein the first pixel in the color profile analysis process is a starting pixel of a sea farther from the land than the average image, and the pixel information of the image and the pixel information change pattern by the motion dispersion.
The method of claim 5,
A moving dispersion distribution calculating process for calculating a distribution of moving dispersion values;
A mobile dispersive shoreline candidate pixel selection process of selecting pixels corresponding to the motion variance values having a variance value equal to or greater than the threshold value among the motion variance values as the mobile dispersion shoreline candidate pixels; And
And a mobile distributed shoreline pixel selection step of selecting, as a shoreline pixel, the first pixel among the values of the pixel values of the mobile scattered shoreline candidate pixels that is less than or equal to the overall average value, Automatic Shoreline Extraction Method Using Pixel Information Change Pattern.
9. The method of claim 7,
When the pixel characteristic value indicates a small value on the land side, the first pixel whose pixel characteristic value is less than the overall average among the mobile dispersive shoreline candidate pixels is selected as a coastline pixel, and when the pixel characteristic value is larger And the pixel characteristic value of the mobile dispersive shoreline candidate pixels is selected as the shoreline pixel as the first pixel of the entire average or more. Automatic shoreline extraction method.

Images