KR101480172B1 - Apparatus for measuring size of cost area using image pictured by camera and the method thereof - Google Patents

Abstract

The present invention relates to an apparatus and method for calculating an area of a coast region using a camera image. An intertidal zone topography change monitoring 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 high resolution correction image creating unit converting the average image into an image displayed on a plan view according to a perspective to create a high resolution image; 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 calculating a moving average for the characteristic value for each pixel extracted by the color profile analysis unit, calculating a difference between the moving average value and pixel characteristic value, classifying pixels having a threshold value or greater, and selecting a land side pixel from between two adjacent pixels whose total average value is between two values among the classified pixels to extract a coastline; and an area calculation unit setting a land side boundary of an area calculation target region to a high resolution corrected average image of a coast region including a coastline extracted by the coastline extraction unit, wherein the area of the area calculation target area can be easily calculated by capturing the area calculation target region including the coastline.

Description

[0001] APPARATUS FOR MEASURING SIZE OF COST AREA USED IMAGE PICTURED BY CAMERA AND THE METHOD THEREOF [0002]

More particularly, the present invention relates to a method for automatically calculating an area for a specific area including a shoreline of a beach using a camera without performing photographing operation using aviation, artificial satellites, or the like The present invention relates to an apparatus and method for calculating an area area using a camera image.

Recently, coastal erosion area is rapidly increasing due to coastal development and changes in natural environment. As a result, not only economic loss but also environmental and social problems are increasing. Therefore, there is an increasing need for long term coastal erosion monitoring. There is a need to measure the area of the adjacent area.

In addition, in order to efficiently preserve and manage marine resources such as tidal flats and sandy beaches, it is necessary to accurately and precisely observe the area of the tidal flats to accurately grasp the terrain change.

In this case, accurate extraction of the shoreline is necessary for accurate area calculation of the sea area including coastline. Accordingly, in order to calculate the change in the area of the coastal area in the past, it is necessary to continuously observe and monitor for a long period of time. As a result, there is a method in which a human force is applied to perform actual measurements or analysis through satellite photos, And a method using airborne laser surveying data of -0571121.

However, these methods require large manpower mobilization for coastline measurement and terrain conversion measurement for calculating the area of the sea area, and expensive equipment is used, which is costly and can not be continuously monitored in real time .

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, shooting time, When the reference value is set incorrectly, the pixel information of the corresponding area does not reach the reference value even in the coastline, and the above-described conventional technique can not cope with the change in altitude of the sun varying with time, And frequent errors occur due to the color change of the shoreline. Thus, when the area of the specific area of the sea area is calculated by using the extracted shoreline, there is a problem that the accuracy is remarkably deteriorated.

Among the shoreline extraction methods of the prior art, there is a method of using H among colors of C (cyan), Y (yellow), H (hue) and S (saturation) when using an image taken on a cloudy day. 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, the position of the first pixel with the H value less than the predetermined value (eg, 50) was determined as the 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. Therefore, when the area change of the sea area is detected using the shoreline extracted in this manner, the accuracy and reliability of the shoreline are significantly deteriorated.

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 a navigation system, a navigation system, Which can easily calculate an area of a specific area including a shoreline in a shanty area regardless of the shanty area of the shanty area, and a method for calculating the shanty area using the camera image.

According to an aspect of the present invention, there is provided an apparatus for monitoring a terrain terrain change using a camera image, the apparatus comprising: an average image generation unit for generating an average image of a background region image photographed by a plurality of cameras for a predetermined time; An ortho corrected image generation unit for generating an ortho corrected image by converting the average image into an image displayed on a plan view displayed according to a perspective view; A color profile analyzer for extracting a characteristic value for each pixel from the average image generated by the average image generator; Calculating a difference between the moving average value and the pixel characteristic value by calculating moving average of the characteristic value for each pixel extracted by the color profile analyzing unit and then calculating a difference between the moving average value and the pixel characteristic value, A shoreline extracting unit for extracting a shoreline by selecting a shoreline pixel as a first pixel on the land side among values whose values are less than or equal to the overall average; And an area calculating unit for calculating an area after forming a curved surface together with a coastline by setting a land boundary of an area calculation target area on an ortho corrected average image of a coastline extracted from the coastline extracting unit And the like.

Wherein the moving average value includes a first moving average representing a pixel characteristic value pattern and a second moving average for reducing amplification of an error pixel, and the first moving average section is set to be smaller than the second moving average section do.

The shoreline extraction unit calculates a first moving average pixel characteristic value difference distribution having the pixel characteristic value pattern by obtaining a first moving average pixel characteristic difference value obtained by subtracting a characteristic value of each pixel from the first moving average value corresponding to each pixel A second moving average pixel characteristic value difference obtained by subtracting a characteristic value of each pixel from the second moving average value is obtained to reduce a second moving average pixel characteristic difference of a pixel that can be erroneously selected from the sea side to the shoreline, Is prevented from being detected as a shoreline pixel.

The shoreline extraction unit is configured to perform a moving average pixel value difference amplification for multiplying a characteristic value difference of pixels by multiplying the absolute value of the first moving average pixel characteristic value difference and the absolute value of the second moving average pixel characteristic value difference .

In addition, the shoreline extraction unit may select, as shoreline candidate pixels, pixels having a value equal to or larger than a threshold value among the amplified moving average pixel value differences, and, when the pixel characteristic value is selected as a small value, The first pixel below the total average is selected as the shoreline pixel, and when the pixel characteristic value is selected as the land value, the first pixel above the entire average is selected as the 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.

The apparatus of claim 1, further comprising: a storage unit for storing GCP coordinate information of the background region, wherein the ortho correction unit comprises: The GCP measurement coordinates are used to calculate the pixels so as to reflect the actual distance, thereby generating an ortho corrected image in which the correspondence between the pixels of the image and the geographical coordinates of the object is quantitatively matched, and the area calculating unit calculates the area And calculate the actual area of the actual area corresponding to the closed curved surface using pixels in the closed curved surface to be calculated.

Wherein the roughness correction unit stores the digital topographic map of the depth region in the storage unit and the pixels are reflected on the actual distance using the GCP measurement coordinates when generating the ortho corrected image of the average image And the area calculating unit superimposes the digital topographical map on the generated ortho corrected image to calculate an area in the closed area of the area to be calculated, Is calculated.

According to another aspect of the present invention, there is provided a method for calculating a surface area using a camera image, the method comprising: averaging an average of coastal images taken by a plurality of cameras for a predetermined period of time; An ortho-corrected image generating step of generating an ortho corrected image by converting an image displayed on a plane view according to a perspective view of the average image; A color profile analyzing process of extracting a color profile for each pixel in the ortho corrected image of the average image generated in the ortho corrected image generation process; Calculating a moving average of characteristic values of each pixel extracted in the color profile analysis process to calculate a difference between the moving average value and the pixel characteristic value and then calculating a difference between the moving average value and the pixel characteristic value, A shoreline extraction process in which the shoreline is extracted by selecting the first pixel on the land side as a shoreline pixel among the values whose values are below or above the overall average; And an area calculating step of calculating an area after setting a land boundary of an area calculation target area in an ortho corrected average image of the beach area including the shoreline to form a closed curve together with a coast line, do.

Wherein the moving average value of the shoreline extraction process includes a first moving average representing a pixel characteristic value pattern and a second moving average for reducing amplification of error pixels, the first moving average interval being smaller than the second moving average interval .

The shoreline extraction process may include obtaining a first moving average pixel characteristic difference value obtained by subtracting a characteristic value of each pixel from the first moving average value corresponding to each pixel, and calculating a first moving average pixel characteristic difference distribution having the pixel characteristic value pattern Calculating a first moving average characteristic value distribution; And a second moving average pixel characteristic difference value obtained by subtracting the characteristic value of each pixel from the second moving average value to obtain a second moving average pixel characteristic difference value of a pixel that can be erroneously selected from the sea side to the shoreline, And a second moving average pixel characteristic value difference distribution calculating step of preventing the pixel from being detected as a shoreline pixel.

The shoreline extraction process further includes a moving average pixel difference difference amplifying step of amplifying a characteristic difference of pixels by multiplying the absolute value of the first moving average pixel characteristic value difference and the absolute value of the second moving average pixel characteristic difference, .

Also, the shoreline extraction process may include: a moving average shoreline candidate pixel selection process of selecting, as shoreline candidate pixels, pixels having a value equal to or greater than a threshold value among the amplified moving average pixel value differences; And when the pixel characteristic value of the selected pixels is selected as a small value on the land side, the first pixel below the overall average is selected as a shoreline pixel, and when the pixel characteristic value is selected as a large value on the land side, And a moving average shoreline pixel selection process of selecting a first pixel over the entire average as a shoreline pixel.

Also, in the method for calculating the area of the background using the camera image of the present invention, the ortho-corrected image generation process may include a step of calculating the area of the image by using the GCP (ground control point) measurement coordinate information stored in the storage unit And an area calculating step of calculating an area using the pixels in the area to be calculated is characterized in that the area calculating step calculates an area by using pixels in the area to be calculated, do.

Alternatively, in the method for calculating the area area using the camera image according to the present invention, the ortho-corrected image generation process may include the steps of: calculating the actual distance by using the GCP (ground control point) measurement coordinate information stored in the storage unit; And the area calculating unit superimposes the digital topographic map stored in the storage unit on the generated ortho corrected image to calculate the area to be calculated, Area is set, and then the area in the closed curved surface is calculated.

The present invention having the above-described configuration can be applied to a method for realizing an area calculation in a sea area including a coastline by photographing a sea area by photographing a camera without performing photographing by a satellite or an airplane or performing a specific actual measurement procedure The area of the target area can be remarkably easily, accurately, and reliably calculated.

FIG. 1 is a block diagram of an apparatus 200 for calculating a screen area area using a camera image according to an embodiment of the present invention.
Fig. 2 is a diagram showing an example in which the apparatus for calculating the area area 200 of Fig. 1 is constructed for calculating the area area. Fig.
3 is a flowchart showing a process of a method of calculating a screen area area using a camera image 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.
6 is a conceptual diagram of photographic image coordinates;
7 is a photograph of an ortho corrected image formed by ortho correction of an average image.
8 is a conceptual diagram of a coordinate system of an ortho corrected image.
FIG. 9 is a graph showing a pixel characteristic value distribution calculated by the color profile analysis process (S40) of FIG. 3;
FIG. 10 is a flowchart showing a detailed processing procedure of the coastline extraction process (S50) of FIG. 3;
11 is a graph showing a first moving average line and a pixel characteristic value distribution.
Fig. 12 is an enlarged graph of the abrupt change area of the pixel characteristic value of Fig. 8;
13 is a distribution diagram of the absolute value of the difference between the first moving average value and the pixel characteristic values;
14 is a graph showing a second moving average line and a pixel characteristic value distribution.
15 is a graph showing a first moving average line and a second moving average line and a pixel characteristic value distribution.
16 is a distribution diagram of the absolute value of the difference between the second moving average value and the pixel characteristic values;
FIG. 17 is a diagram showing a moving average value and a pixel characteristic value difference distribution amplified by multiplying the first and second moving average values and the pixel characteristic value difference; FIG.
18 is a graph showing a distribution of pixels extracted so as to have a difference value equal to or greater than a threshold value by using the difference between the amplified moving average value and the pixel characteristic value.
19 is a graph showing a process of deriving shoreline pixels through comparison with an average value of all pixels among pixels having a value equal to or greater than a threshold value.
20 is a photograph showing the setting of the closed curved surface of the area to be calculated.
21 is a diagram showing an area calculation using a digital topographic map.

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 block diagram of a terrestrial terrestrial monitoring apparatus 200 using camera images according to an embodiment of the present invention.

1, the inter-terrestrial terrestrial monitoring apparatus 200 includes an average image generating unit 210 for receiving an instantaneous image, which is a captured image of a tidal flat for a predetermined period of time, A color profile analyzer 230 for extracting and recording a color profile for each pixel in the average image, a color profile analyzer 230 for calculating a color profile of each pixel, A shoreline extracting unit 240 for extracting a shoreline by using a profile, an area for calculating the area after the subject for area calculation is created as a closed curve in the ortho corrected image including the shoreline extracted from the shoreline extracting unit 240 (260) for storing at least one of a calculation unit (250) and a ground control point (GCP) measurement coordinate information of a depth region or a digital topographic map of a depth region It is configured. In the drawing, the area display unit 300 refers to an external device such as a display device for outputting an ortho corrected image, a closed curved area, and an area value.

 In order to improve the accuracy and reliability of the calculation of the area of a predetermined region of the background region, the above-described area area calculation apparatus 200 enhances the contrast of the average image generated by the average image generation unit 205 And a contrast enhancement unit 210, and FIG. 1, which illustrates an embodiment of the present invention, includes a contrast enhancement unit 210. FIG.

Among the above-mentioned constructions, the instantaneous images are generated by using a camera such as a digital camera for a predetermined time interval, at predetermined time intervals, and at a time interval of 4 to 5 times .

For example, images taken every 4 ~ 5 seconds at intervals of about 2 minutes for 1 hour in the sea area to be area calculation can be used as instant images.

After receiving the instantaneous images, the average image generating unit 205 superimposes averages of pixel values of the photographed images for each time period to generate average images for each imaging period.

The averaged images described above can clearly distinguish the coastline that is constantly changing by the wave. Each shoreline has a time interval. When a pixel overlapping average is generated in the process of generating the average images as described above, the moving object disappears from the image through filtering such as color averaging. Since this process is applied throughout the entire shooting frame, only the fixed object appears in the average image, and the moving object disappears. Therefore, the average images formed at each photographing time interval are clearly distinguished by displaying the shoreline of the photographing time period as 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 contrast enhancement unit 210 is an optional configuration for increasing the accuracy and reliability of monitoring the terrestrial terrain change.

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.

That is, the ortho-corrected image generation unit 220 calculates the orthogonal correction image using the GCP measurement coordinates when generating the ortho corrected image for the average image so that the corresponding relationship between the pixels of the image and the geographical coordinates of the object is It is possible to generate an ortho corrected image quantitatively.

If the land boundaries are unclear in the ortho corrected image, the area is calculated by superimposing the digital topographic map on the ortho corrected image in which the GCP survey coordinates are reflected.

In other words, the actual area can be calculated by mapping the ortho corrected image in which the correspondence between the pixels of the image and the geographical coordinates of the object are quantitatively matched to the digital topographical map. Even if the mapping process with the digital topographical map is not performed, Since the actual area per pixel is fixed, the area of the target area can be obtained only by the number of pixels included in the closed surface.

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 contrast of the pixels of each of the pixels in the rectified and corrected average image, pixel values such as color information of magenta, yellow, and black, hue, saturation information, and level information are extracted. 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 are ortho corrected average images generated by the ortho corrected image generator 220. [

In this case, when the color profile is directly analyzed in the average images, or when 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, two moving average sets are generated using two different moving average intervals starting from the sea side. In this case, the moving average set of the small moving average section is used for extracting shoreline pixels, and the moving average set of the larger moving average section is the moving average value of pixels having pixel information that can be extracted from the sea area to the shoreline, Is used to prevent the pixel from being selected as a shoreline pixel.

The differences between the pixel-by-pixel characteristic values are obtained from the moving average values of the two sets of moving average, and then the difference between the two moving averages and the pixel characteristic value is amplified by multiplying the absolute values of the respective differences. Thereafter, pixels corresponding to a value having a value equal to or larger than a threshold value among the amplified values of the moving average and the pixel characteristic value difference are selected. Here, the threshold may be arbitrarily set to 0.5%, 1%, 5%, etc. depending on the accuracy. Among the pixels whose difference value between the moving average value and the pixel characteristic value is greater than or equal to the threshold value, the first pixel on the land side is selected as the shoreline pixel and the shoreline is extracted . For example, when the pixel characteristic value is set to R (red), the first pixel above the entire average is selected as the shoreline pixel because the R value is small on the sea side and the R value is large on the land side. On the contrary, when the pixel characteristic value is set to B (blue), since the B value on the sea side is larger and the B value on the land side is smaller, the first pixel below the overall average is selected as a shoreline pixel, do.

In addition, the shoreline extraction unit 240 may be configured to select a pixel whose R value and B value intersect with each other as in the prior art, to select a pixel whose threshold value is greater than or equal to a threshold value, A method of selecting a pixel as a shoreline pixel or a method of extracting a shoreline by performing correction according to environmental information such as sunrise, sunset, and weather may be applied.

After the shoreline is extracted by the shoreline extraction unit 240 as described above, the area calculation unit 250 displays the area set as the area calculation target as a closed curve, and then calculates the actual area of the closed curve do.

Specifically, the area calculating unit 250 calculates the pixels using the GCP measurement coordinates by the ortho correction unit 230 so that the corresponding relationship between the pixels of the image and the geographical coordinates of the object is quantitative The area is calculated by grasping the number of pixels included in the closed curved surface in the generated ortho corrected image or the area is calculated by mapping the ortho corrected image to the digital topographic map.

FIG. 2 is a diagram showing an example of a topographic area calculation system constructed for area calculation in a topographic area including an area calculation area in the topographic area calculation device 200 of FIG.

2, the system includes a plurality of digital cameras 10, a video server 20 (hereinafter, referred to as " video camera "), ), A network hub 30, a space area calculation apparatus 200, a modem 50, a central data processing server 60, and a web server 70 for managing an internet homepage. have.

The digital cameras 10 capture the blue and coastline images of the intertidal zone 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 area area calculation device 200 through the network hub 30.

As described above, the gamut area calculation apparatus 200 superimposes the images of the background region including the received wave and shoreline images on a pixel-by-pixel basis to obtain an average image.

After the average image is generated as the ortho corrected image, the shoreline is extracted by using the average value and the moving average value of each pixel of the ortho corrected average image.

Then, the area calculating unit 250 calculates the area of the closed curved surface formed by the land side boundary from the extracted shoreline. In this case, since the GCP information is applied to the generation of the ortho corrected image, the area is calculated by calculating the number of pixels in the closed curved surface representing the area to be calculated. Also, if the boundary of the land side is unclear in the ortho corrected image, the area of the predetermined area including the shoreline is calculated by superimposing the digital topographic map on the ortho corrected image.

FIG. 3 is a flow chart illustrating a process of calculating a screen area area using a camera image according to an embodiment of the present invention. FIG. 4 is a photograph of instantaneous images photographed by a camera, FIG. 7 is a photograph of an ortho corrected image formed by ortho correction of an average image, FIG. 8 is a conceptual diagram of a coordinate system of an ortho corrected image, FIG. And FIG. 9 is a graph showing the pixel characteristic value distribution calculated by the color profile analysis process (S40) of FIG.

As shown in FIG. 3, the method for calculating the area of the background region includes the steps of capturing a background region image S10, an average image generation process S20, an ortho corrected image generation process S30, a color profile analysis process S40, A shoreline extraction process (S50), and an area calculation process (S50).

First, a normal corrected image generation process (S30) among the method of calculating the area of the background area using the camera image of the present invention will be described with reference to FIGS. 1, 2, and 3 to 9. FIG.

The image capturing process S10 of FIG. 2 acquires an image of the image area through the plurality of digital cameras 10 installed to capture the image area as shown in FIG. 2, as shown in FIG. At this time, the instant images are images of the background region photographed a plurality of times at a specific time interval for a predetermined time. For example, at a time interval of 2 minutes, 3 minutes, or 5 minutes for one hour, the beach area is photographed at various time intervals such as 2 to 3 seconds or 4 to 5 seconds. As described above, the instant images photographed by the digital cameras 10 are transmitted to the background area calculation apparatus 200 through the communication network for calculating the background area.

The average image generation process S20 is a process in which the average image generation unit 205 of the background region area calculation apparatus 200 receiving the instantaneous images by the image capturing process S10 described above superimposes real- 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 ortho corrected image generation unit 220 and converted into an ortho corrected image. At this time, the contrast of the average image may be enhanced by the contrast enhancement unit 210 before the ortho corrected image is generated.

In the ortho-corrected image generating step S30, the image displayed according to the perspective method is applied to the GCP measurement coordinates and converted into an image displayed on the floor plan to generate an ortho corrected image as shown in FIG. 7, 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. In this case, the photographed image is divided into regions as shown in FIG. 6, and the ortho corrected image is converted to reflect the actual size as shown in FIG.

The ortho corrected image is then transmitted to the color profile analyzer 230 as described above.

FIG. 9 is a graph showing the distribution of pixel characteristic values calculated by the color profile analysis process (S40) of FIG. 3, FIG. 10 is a flowchart showing a detailed process of the shoreline extraction process (S50) FIG. 12 is an enlarged graph of the abrupt change area of the pixel characteristic value in FIG. 8, and FIG. 13 is a graph showing the distribution of the absolute value of the difference between the first moving average value and the pixel characteristic values 15 is a graph showing a first moving average line, a second moving average line, and a pixel characteristic value distribution, FIG. 16 is a graph showing a second moving average value and a pixel characteristic value distribution, 17 is a diagram showing a moving average value and a pixel characteristic value difference distribution amplified by multiplying the first and second moving average values and the pixel characteristic value difference. FIG. 18 is a graph showing the difference between the amplified moving average value and the moving average value pixel FIG. 19 is a graph showing the distribution of pixels extracted to have a difference value equal to or greater than a threshold value by using the characteristic value difference. FIG. 19 illustrates a process of deriving shoreline pixels through comparison with an average value of all pixels among pixels having a value equal to or greater than a threshold value FIG.

The coastline extraction process (S50) during the process of the present invention will be described with reference to FIGS. 12 to 19. FIG.

In the color profile analysis process S40, the color profile analyzer 230 including the RGB profile analysis module 232 and the CMYK profile analysis module 234 calculates red Color information of hue, saturation, level information of green, blue, or cyan, magenta, yellow, and black, 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 shoreline extraction process (S50), the average of the pixel characteristics of each of the ortho corrected average images of FIG. 9 is obtained, and the difference between the moving average and the pixel characteristic values of the two moving average sections is used to calculate the shoreline Select a candidate pixel. Then, the shoreline is extracted by extracting the first pixel on the land side where the characteristic value of the selected candidate pixels is less than or equal to the overall average as shoreline pixels and repeating the extraction.

FIG. 10 shows a detailed processing procedure of the coastline extraction process (S50) of FIG. 10, the shoreline extraction process S50 includes a first moving average pixel characteristic value difference distribution calculation step S51, a second moving average pixel characteristic difference value distribution calculation step S52, a moving average pixel difference difference amplification step S53, A moving average shoreline candidate pixel selection process S54, and a moving average shoreline pixel selection process S55 to automatically extract the shoreline from the ortho corrected average image.

Specifically, in the calculation of the first moving average pixel characteristic value difference distribution step S51, moving averages for moving average sections, such as setting a small moving average section, that is, a section to 2% of all pixels, And is displayed in a line with the characteristic values of the pixels of the ortho corrected average image. 11 is a graph showing the distribution of the first moving average line and the pixel characteristic value, that is, the pattern of pixel characteristic value change as described above. Fig. 12 is a graph showing the magnitude of the pixel characteristic value to be. In the graph of FIG. 9, there are pixels with characteristic values deviating from the first moving average value in pixels between 590 and 595 pixels, and these characteristic values are selected as shoreline candidate pixels by the second moving average as an error .

Next, a first moving average pixel characteristic value difference obtained by subtracting the pixel characteristic value from a first moving average value of each pixel is obtained, and then an absolute value is taken to calculate a first moving average pixel characteristic difference value distribution. FIG. 13 is a graph showing the distribution of the characteristic value differences of the first moving average pixel calculated by the first moving average pixel characteristic value difference distribution calculating step S51 as described above.

Next, in the second moving average pixel characteristic value difference value calculating step S52, a moving average section larger than the first moving average section is set to calculate the second moving average. By way of example, the second moving average interval may be set to 10% of the total number of pixels. The moving averages for the moving average intervals, such as setting the interval to 10% of the whole pixels, are calculated and displayed as lines along with the characteristic values of the pixels of the ortho corrected average image.

FIG. 14 is a graph showing the distribution of the second moving average line and the pixel characteristic value as described above, and FIG. 15 is a graph showing the first moving average line, the second moving average line and the pixel characteristic value distribution from 550 pixels to 650 pixels. In FIG. 15, since the slope of the second moving average value gradually decreases from the first moving average value, pixels between 590 pixels and 595 pixels are adjacent to the second moving average value. Accordingly, when the difference between the second moving average value and the pixel characteristic value is found, error pixels having characteristic values having a large difference from the first moving average value have a smaller difference, It is prevented from being selected as a candidate pixel.

Next, the second moving average pixel characteristic value difference obtained by subtracting the pixel characteristic value from the second moving average value of each pixel is obtained, and the absolute value is obtained to calculate the second moving average pixel characteristic value difference distribution. FIG. 16 is a graph showing the distribution of the characteristic value difference of the second moving average pixel calculated by the second moving average pixel characteristic value difference distribution calculating step S52 as described above.

After the difference between the first moving average pixel characteristic value difference and the second moving average pixel characteristic value is calculated as described above, in order to facilitate comparison with the average value of all the pixels, The moving average pixel characteristic value difference amplifying step S53 of increasing the difference in the characteristic values with respect to the moving average value by multiplying the absolute values of the two moving average pixel characteristic value differences with each other. 17 is a graph showing the distribution of the moving average pixel characteristic value difference amplified by the moving average pixel characteristic differential value amplification step (S53).

Then, in the moving average shoreline pixel selection step S54 of FIG. 10, pixels having a difference greater than a specific threshold value in the distribution of the amplified moving average pixel characteristic value difference are extracted as shoreline candidate pixels. At this time, the specific threshold value can be arbitrarily set to 0.5%, 1%, 5%, etc. according to the accuracy of shoreline extraction. In the embodiment of the present invention, the pixels having the upper 1% value are extracted as shoreline candidate pixels. 18 shows the distribution of the shoreline candidate pixels extracted as described above.

FIG. 19 is a graph illustrating a process of selecting shoreline pixels in the moving average shoreline pixel selection process (S55) of FIG. After the pixels after the shoreline are extracted as described above, the entire average line of the characteristic values of the pixels is superimposed on the shoreline candidate pixels as shown in FIG. And selects the first pixel among the pixels that is less than or equal to the total average line as the shoreline pixel according to the selection method of the pixel characteristic value. In the case of the embodiment of the present invention, a pixel characteristic value having a large sea side characteristic value such as B is applied. In Fig. 19, the sea side has a characteristic value above the overall average, and the land side has a characteristic value below the overall average. Thus, the first of the pixels below the overall average is selected as the shoreline pixel.

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

In addition, the shoreline extraction process (S50) described above may be performed by selecting pixels whose R and B values intersect with each other as in the prior art, selecting a pixel having a threshold value greater than or equal to a threshold value A method of selecting a pixel as a shoreline pixel or a method of extracting a shoreline by performing correction according to environmental information such as sunrise, sunset, and weather may be applied.

The shoreline information extracted by the process as described above is then transmitted to the area calculation unit 250.

20 is a photograph showing the setting of the closed curved surface of the area to be calculated, and Fig. 21 is a diagram showing an area calculation using the digital topographic map.

Hereinafter, an area calculating process (S60) in the process of FIG. 3 will be described with reference to FIGS. 20 to 21. FIG.

In the area calculating process S60, the area calculating unit 250 calculates the area of the land surface including the predetermined area calculation target area and the closed curve consisting of the coastline, as shown in FIG. 20, in the received ortho corrected average image .

Then, the area calculating program is applied to calculate the area of the closed curved surface.

Since the GCP information is applied to the ortho corrected image, the pixels in the curved surface are counted and then the actual area corresponding to each pixel is multiplied to calculate the actual area of the curved surface.

In addition, the area calculation process S60 may be configured to calculate the area by superimposing the digital topographic map on the ortho corrected image as shown in FIG.

If the GCP surveying information is performed only once, then the area of a specific area including the coastline can be easily calculated only by photographing the beach area without performing the surveying procedure.

200: area area area calculating device 205: average image generating part
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
250: area calculating unit 260:
300:
10: camera 20: video server
30: network server 50: modem
60: central data processing server 70: web server

Claims (15)

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;
An ortho corrected image generation unit for generating an ortho corrected image by converting the average image into an image displayed on a plan view displayed according to a perspective view;
A color profile analyzer for extracting a characteristic value for each pixel from the average image generated by the average image generator;
Calculating a difference between the moving average value and the pixel characteristic value by calculating moving average of the characteristic value for each pixel extracted by the color profile analyzing unit and then calculating a difference between the moving average value and the pixel characteristic value, A shoreline extraction unit for extracting a shoreline by selecting a first pixel among the values whose values are less than or equal to the overall average as shoreline pixels; And
And an area calculating unit for calculating an area after forming a closed curve along with the coastline by setting a land boundary of the area to be calculated on the average corrected image of the sea area including the coastline extracted by the coastline extracting unit And calculating the area of the image area using the camera image.
The apparatus of claim 1,
A first moving average value indicating a pixel characteristic value pattern and a second moving average value for reducing amplification of error pixels, and the first moving average value interval is set smaller than the second moving average value interval. Area area calculating device.
The system according to claim 2,
Calculating a first moving average pixel characteristic value difference distribution having the pixel characteristic value pattern by calculating a first moving average pixel characteristic value difference obtained by subtracting a characteristic value of each pixel from the first moving average value corresponding to each pixel,
By subtracting the characteristic value of each pixel from the second moving average value to obtain a second moving average pixel characteristic value difference to reduce the second moving average pixel characteristic difference of the pixel that can be erroneously selected from the sea side to the shoreline, Wherein the pixel is configured to prevent the pixel from being detected as a shoreline pixel.
[4] The method according to claim 3,
And performing a moving average pixel value difference amplification for multiplying a characteristic value difference of pixels by multiplying the absolute value of the first moving average pixel characteristic value difference and the absolute value of the second moving average pixel characteristic difference value. Area area calculating device.
[5] The apparatus of claim 4,
Pixels having values equal to or greater than a threshold value among the amplified moving average pixel value differences are selected as shoreline candidate pixels,
When the pixel characteristic value is selected as a shoreline pixel, the first pixel below the overall average is selected as a shoreline pixel when the pixel characteristic value is selected as a small value on the land side, And selecting a first pixel above the average as a shoreline pixel.
[6] The method according to claim 5,
And comparing the color information of the pixels from the sea side of the average image to extract the shoreline, the shoreline is prevented from being extracted by the achromatic object when compared from the land side. An apparatus for calculating the surface area of an image using an image.
The method according to claim 1,
And a storage unit for storing GCP (ground control point) measurement coordinate information of the background region,
Wherein the ortho corrected image generation unit calculates the ortho corrected image using the GCP measurement coordinates when generating the ortho corrected image with respect to the average image so that the pixels correspond to the actual distance so that the corresponding relationship between the pixels of the image and the geographical coordinates of the object quantitatively coincides Generates a corrected image,
Wherein the area calculating unit is configured to calculate an actual area of an actual area corresponding to the closed curved surface using pixels in the area to be calculated calculated in the ortho corrected image, .
The method according to claim 1,
And a storage unit for storing ground control point (GCP) measurement coordinate information and a digital topographic map of the navigation area,
Wherein the ortho corrected image generation unit calculates the ortho corrected image using the GCP measurement coordinates when generating the ortho corrected image with respect to the average image so that the pixels correspond to the actual distance so that the corresponding relationship between the pixels of the image and the geographical coordinates of the object quantitatively coincides Generates a corrected image,
Wherein the area calculating unit is configured to calculate the area in the closed curved surface to be calculated by superimposing the digital topographic map on the generated ortho corrected image.
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;
An ortho-corrected image generating step of generating an ortho corrected image by converting an image displayed on a plane view according to a perspective view of the average image;
A color profile analyzing process of extracting a color profile for each pixel in the ortho corrected image of the average image generated in the ortho corrected image generation process;
Calculating a moving average of characteristic values of each pixel extracted in the color profile analysis process to calculate a difference between the moving average value and the pixel characteristic value and then calculating a difference between the moving average value and the pixel characteristic value, A shoreline extraction process in which a shoreline is extracted by selecting the first pixel among the values whose values are less than or equal to the overall average as shoreline pixels; And
And an area calculating step of calculating an area after forming a closed curve along with a coastline by setting a land boundary of an area calculation target area in an orthonally corrected average image of the beach area including the coastline A method for calculating area area using camera images.
The method of claim 9,
The moving average value of the shoreline extraction process includes a first moving average value representing a pixel characteristic value pattern and a second moving average value for reducing amplification of error pixels, and the first moving average value interval is set to be smaller than the second moving average value interval And calculating the area area area using the camera image.
The method according to claim 10,
Calculating a first moving average pixel characteristic value difference obtained by subtracting a characteristic value of each pixel from the first moving average value corresponding to each pixel, calculating a first moving average pixel characteristic value difference distribution having the pixel characteristic value pattern, A process of calculating the distribution of characteristic values; And
By subtracting the characteristic value of each pixel from the second moving average value to obtain a second moving average pixel characteristic value difference, by reducing the second moving average pixel characteristic difference of the pixel that can be erroneously selected from the sea side to the shoreline, And calculating a second moving average pixel characteristic value difference distribution calculating step of calculating a second moving average pixel characteristic value difference distribution calculating step of calculating a second moving average pixel characteristic value difference distribution calculating step.
The method according to claim 11,
And a moving average pixel value difference amplifying step of amplifying a characteristic difference of pixels by multiplying the absolute value of the first moving average pixel characteristic value difference and the absolute value of the second moving average pixel characteristic difference, A method for calculating the area of a used beach area.
The method according to claim 12,
A moving average shoreline candidate pixel selecting step of selecting, as shoreline candidate pixels, pixels having a value equal to or greater than a threshold value among the amplified moving average pixel value differences; And
When the pixel characteristic value of the selected pixels is selected as a shoreline pixel, the first pixel below the overall average is selected as a shoreline pixel when the shoreline is selected as a large value, And a moving average shoreline pixel selection process for selecting the first pixel as a shoreline pixel based on the moving average shoreline pixel selection process.
The method of claim 9,
The ortho-corrected image generation process may be performed such that the correspondence between the pixel of the image and the geographical coordinates of the object is quantitatively calculated by using the GCP (ground control point) measurement coordinate information stored in the storage unit, Generates a matching ortho corrected image,
Wherein the area calculation process is performed to calculate an actual area using pixels in the closed curve to be calculated.
The method of claim 9,
The ortho-corrected image generation process may be performed such that the correspondence between the pixel of the image and the geographical coordinates of the object is quantitatively calculated by using the GCP (ground control point) measurement coordinate information stored in the storage unit, Generates a matching ortho corrected image,
Wherein the area calculating unit is configured to calculate an area in the closed curved surface after superimposing the digital topographic map stored in the storage unit on the generated ortho corrected image to set the calculation target curved surface area, Way.

Images