KR102204046B1 - Correcting system restoring dead zone on the image - Google Patents

Abstract

The present invention relates to an image correction processing system having a blind spot supplementation function. According to the present invention, the image correction processing system having a blind spot supplementation function comprises: an image DB; a cadastral map DB for storing cadastral map information; a ground object information DB; a correction target detection module; an image analysis module; an object image extraction module; an editing module for generating a first edited image and a second edited image; and an auxiliary image reinforcement module. According to the present invention, a complete image can be generated.

Description

Image correction processing system with blind spot compensation function {CORRECTING SYSTEM RESTORING DEAD ZONE ON THE IMAGE}

The present invention searches for and edits a blind spot from a plurality of photographed images collected through photographing to create a video image for producing a video map or a digital map, and supplements the blind spot to check and supplement the range and location of the blind spot in the video image. It relates to a video image correction processing system having a function.

An image, which is a reference image for drawing for the production of an image map or digital map, is collected through aerial photography. The collected images are classified based on the reference point, overlapped, and edited to produce a video image. In the video image, blind spots (a2; see Fig. 1) and shadow zones (hereinafter,'blind spots') are generated by topographical structures and ground objects such as buildings or various vegetation, and even the same ground objects are blind spots according to the shooting angle. The scope of (a2) can be varied.

However, since the blind spot (a2) makes it impossible to accurately identify a specific area visually or visually in the video image, the video image having the blind spot (a2) could not be used as it is for the production of an image map or a digital map. Eventually, a field survey was conducted on the blind spot (a2) separately, and the location coordinates of the blind spot (a2) and the shape and occupied range of ground objects were identified and utilized in the production of image maps or digital maps.

However, this production method was burdensome in terms of cost and business, and the burden was not small in terms of time as a number of blind spots (a2) had to be inspected on-site.

In the end, there is an urgent need for a technology that can more quickly identify the blind spot (a2), supplement and correct it.

Prior Art Document 1. Patent Registration No. 10-1938402 (announced on January 15, 2019)

Accordingly, the present invention is to solve the above problem, and the image image correction processing system having a blind spot supplement function capable of identifying and supplementing the blind spot in an image image and generating a complete image image as basic data for map generation. Make it a task to solve the provision.

In order to achieve the above object, the present invention,

A video DB for storing video images synthesized and edited according to GPS coordinates;

A cadastral map DB that stores cadastral map information in which parcels are classified according to GPS coordinates;

Ground object information DB for storing GPS coordinate values and specification data of ground objects;

A correction target detection module for designating a correction target range of the image image in proportion to the collection height of the image image retrieved from the image DB;

In the image image, the RGB values of pixels within the range to be corrected are checked, and the RGB values of the pixels of the chromaticity belonging to the designated representative chromaticity group are unified with the corresponding representative chromaticity, and the position values of the pixels unified with the representative chromaticity are checked. The cluster shape of pixels having RGB values is standardized through deep learning, the standardized cluster shape is set as an independent shape image, a collection of three or more shape images in contact with each other is designated as an object image, and the shape of the object image An image analysis module that designates a shape image having the largest area among the images as a flat shape, and designates another shape image as a side shape;

If the outline of the object that is not in contact with the planar shape among the side shapes of the object image is located at a reference ratio or more in the range to be corrected, and the width of one side shape relative to the total width of the flat shape and one side shape is within the reference value, the object image is corrected. An object image extraction module designated as a target;

A first edited image is created in which the plane shape is matched to the object outline and the side shape is deleted, and the surface object and the photographing point by searching the ground object specification data corresponding to the GPS coordinate value of the object image in the ground object information DB. The distance value between the distance, the shooting altitude, the height of the ground object, the GPS coordinate value of the shooting point and the GPS coordinate value of the ground object, and the distance value, the shooting altitude and height value, the GPS coordinate value of the shooting point and the GPS coordinate value of the ground object A second edited image in which the first edited image is expanded in proportion to the vector amount is generated, and cadastral map information corresponding to the correction target range of the video image is retrieved from the cadastral map DB, and the cadastral map image is overlapped with the correction target range, An editing module for generating an edited video image by deleting the video image for each lot in line with the parcel boundary of the cadastral map image and synthesizing the second edited image to a corresponding deletion area; And

An auxiliary image reinforcement module for generating an image map image by synthesizing at least one selected from a tree image, a road image, and an entrance image in a section other than the second edit image in the deletion area of the edited image image;

It is an image image correction processing system having a blind spot supplement function including.

The present invention has an effect of recognizing a blind spot in an image image, supplementing it with a shape, and generating a complete image image as basic data for generating a map.

1 is a diagram schematically showing a state of collection of an image image corrected by a correction processing system according to the present invention,
2 is a block diagram showing an embodiment of a module configured in the correction processing system according to the present invention,
3 is a flowchart sequentially showing the operation process of the correction processing system according to the present invention,
4 is a diagram showing a reference for detecting whether an object image is to be corrected by the correction processing system according to the present invention;
5 is a diagram showing an cadastral view of an image image area searched by the correction processing system according to the present invention,
6 is a diagram schematically illustrating a case of synthesizing an cadastral map to a video image before editing,
7 is an image showing a state in which the correction processing system according to the present invention deletes the parcel where the object image to be corrected is located from the image image,
8 and 9 are diagrams schematically showing a change in the planar shape of the object image for each photographing angle,
10 is a diagram schematically showing a state in which the correction processing system according to the present invention corrects the planar shape according to a specified ratio,
11 is a diagram schematically showing a state in which the correction processing system according to the present invention synthesizes the planar shape of object images for each cadastral area,
12 is an image showing FIG. 11 as a video image.

The features and effects of the present invention described above will become apparent through the following detailed description in connection with the accompanying drawings, whereby those of ordinary skill in the technical field to which the present invention pertains can easily implement the technical idea of the present invention. There will be. Since the present invention can apply various changes and have various forms, specific embodiments will be illustrated in the drawings and described in detail in the text. However, this is not intended to limit the present invention to a specific disclosed form, and it should be understood to include all changes, equivalents, and substitutes included in the spirit and scope of the present invention. The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention.

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

FIG. 1 is a diagram schematically showing a collection of image images corrected by a correction processing system according to the present invention, and FIG. 2 is a block diagram showing an embodiment of a module configured in the correction processing system according to the present invention.

1 and 2, the correction processing system of the present invention comprises: an image DB 11 for storing an image image M1 (refer to FIG. 5) synthesized and edited according to a GPS coordinate; A cadastral map DB 12 for storing cadastral map information on which parcels (Z1, Z2; see Fig. 5) are divided and displayed according to GPS coordinates; A ground object information DB 13 for storing GPS coordinate values and specification data of the ground objects B1 to B5; A correction target detection module 14 that designates a range to be corrected in proportion to the collection height of the image image M1 retrieved from the image DB 11 in the image image M1; In the image image (M1), the RGB values of the pixels within the range to be corrected are checked, and the RGB values of the pixels of the chromaticity belonging to the designated representative chromaticity group are unified with the corresponding representative chromaticity, and the location values of the pixels unified with the representative chromaticity are checked. Thus, a cluster shape of pixels having the same RGB value is standardized through deep learning, the standardized cluster shape is set as an independent shape image, and a collection of three or more shape images in contact with each other is an object image (BM, BM'; 4), and the shape image with the largest area among the shape images of the object image (BM, BM') is designated as the flat shape (P1, P1'; see Fig. 4), and the other shape image is the side shape (P2). , An image analysis module 15 designated as P2', P3, P3'); Of the side shapes (P2, P2', P3, P3') of the object image (BM, BM'), the object outlines (UL1, UL2; see Fig. 4) that are not in contact with the planar shapes (P1, P1') are within the range to be corrected. An object image extraction module 16 for designating a corresponding object image (BM, BM') as a correction target if it is positioned above the reference ratio; Create a first edited image in which the flat shape (P1, P1') is aligned with the object outline (UL1, UL2) and the side shape (P2, P2', P3, P3') is deleted, and the object image (BM, BM') ) Of the ground object (B1 to B5) corresponding to the GPS coordinate value of the ground object (B1 to B5) is searched in the ground object information DB (13) to check the distance value between the corresponding ground object (B1 to B5) and the shooting point and the height value of the ground object And, in proportion to the distance value and the height value, a second edited image (MM') in which the first edited image (MM) is expanded at a ratio of the vector amount is generated, and a cadastral map corresponding to the correction target range of the video image (M1) The information is retrieved from the cadastral map DB 12, overlaps the cadastral map image (M2; see Fig. 5) with the range to be corrected, and matches the parcel boundary (BL; see Fig. 5) of the cadastral map image M2) to the image image M1. An editing module 17 that deletes the image for each parcel (Z1, Z2) and combines the second edited image (MM') into a corresponding deletion area; An auxiliary image reinforcement module that combines at least one selected from a tree image (not shown), a road image (not shown), and an entrance image (not shown) in the section excluding the second edited image (MM') in the deletion area (18); includes.

In more detail, the components of the correction processing system according to the present invention will be described in more detail, and the image DB 11 stores a general image image M1 forming a background of an image map. The video image M1 is a composite and edited image of a plurality of photographed images collected by aerial photographing by an aircraft D such as a drone according to the GPS coordinates according to a known image editing process. Since the image image (MI) generation technology based on the photographed image is a known technology, a detailed description thereof will be omitted here.

The cadastral map DB 12 stores cadastral map information in which parcels (Z1, Z2; see Fig. 5) are classified and displayed according to GPS coordinates. Since the cadastral map information includes the GPS coordinate value and the cadastral map image (M2), the parcels (Z1, Z2) of the corresponding section can be searched using the GPS coordinate value and displayed through the monitor.

The ground object information DB 13 stores GPS coordinate values and specification data of the ground objects B1 to B5. Since the ground object image posted on the video image (M1) is ground objects (B1 to B5) such as buildings and structures that exist on the ground, the actual position value of the GPS coordinate value and the height, number of floors, width, name, etc. Compose specification data. Accordingly, the GPS coordinate value and the specification data are linked for each corresponding ground object image posted on the image image M1, and the GPS coordinate value and the specification data are stored in the ground object information DB 13.

The correction object detection module 14 designates a correction object range of the image image ML in proportion to the collection altitude of the image image M1 retrieved from the image DB 11. As shown in FIG. 1, the camera is limited in the shooting range according to the angle of view, and the shooting range is limited according to the altitude of the shooting aircraft D. In other words, the larger the angle of view or the higher the photographing altitude, the greater the photographing range. However, since the deformation and distortion of the image increases toward the edge of the shooting range, the effective range of the image image M1 is limited to the center, and the ground object image that can be corrected among the ground object images located at the center is extremely limited. Accordingly, the correction target detection module 14 sets the correction target range according to a specified ratio according to the collection altitude of the photographed image, which is the basis for the generation of the image image M1. When the range to be corrected is set, the target to be processed in the subsequent process is limited to the range to be corrected, and the target to be processed is limited to an image of a ground object located within the range to be corrected.

The image analysis module 15 checks the RGB values of pixels within the range to be corrected in the image image M1 and unifies the RGB values of the pixels of the chromaticity belonging to the designated representative chromaticity group with the corresponding representative chromaticity. By checking the position values of unified pixels, the cluster form of pixels having the same RGB value is formalized through deep learning, the standardized cluster form is set as an independent shape image, and a collection of three or more shape images in contact with each other is an object. It is designated as an image (BM, BM'; see Fig. 4), and the shape image with the largest area among the shape images of the object image (BM, BM') is designated as a flat shape (P1, P1'; see Fig. 4), Other shape images are designated as side shapes (P2, P2', P3, P3'). The image analysis module 15 analyzes the pixels located in the range to be corrected according to the position and RGB value, and an object image (P1, P1') and side shape (P2, P2', P3, P3') BM, BM') are classified and confirmed. A detailed description of this will be described in detail by describing the pro chart.

The object image extraction module 16 includes object outlines (UL1, UL2) that are not in contact with the planar shapes (P1, P1') of the side shapes (P2, P2', P3, P3') of the object images (BM, BM'); 4) if the reference ratio or more is located in the range to be corrected, a corresponding object image (BM, BM') is designated as a correction target. The entire object images BM and BM' may be located in the range of the target to be corrected detected by the target detection module 14, but only a part of the image may be located. Accordingly, the object image extraction module 16 reads whether or not to be corrected based on the degree of position of the object outlines UL1 and UL2 with respect to the range to be corrected. A detailed description of this will be described in detail by describing the pro chart.

The editing module 17 generates a first edited image in which planar shapes (P1, P1') are aligned with object outlines (UL1, UL2) and side shapes (P2, P2', P3, P3') are deleted, The distance value between the ground object (B1 to B5) and the shooting point by searching the ground object information DB 13 for the specification data of the ground object (B1 to B5) corresponding to the GPS coordinate value of the object image (BM, BM') And the height value of the ground object are checked, and in proportion to the distance value and the height value, a second edited image (MM') in which the first edited image (MM) is expanded by the ratio of the vector amount is generated, and the image image (M1) is The cadastral map information corresponding to the range to be corrected is retrieved from the cadastral map DB 12, and the cadastral map image (M2; see Fig. 5) is overlapped with the correction target range, and the parcel border BL of the cadastral map image M2 (see Fig. 5)) In accordance with this, the image image M1 is deleted for each parcel (Z1, Z2), and the second edited image MM' is combined with the corresponding deletion area. The editing module 17 is a technology that removes the blind spot (a2) generated by the shooting angle from the ground object image without additional work such as collecting on-site information and collecting re-shooting information, and enables editing of a video image. To this end, the editing module 17 deletes the surrounding image of the ground object image, that is, a parked vehicle image, a tree image, a bench image, a park image, etc. from the video image M1, and edits the obliquely photographed ground object image. A detailed description of this will be described in detail by describing the pro chart.

The auxiliary image reinforcement module 18 includes a tree image (not shown), a road image (not shown) and an entrance image (not shown) in the section excluding the second edited image (MM') in the deleted area of the edited video image (M3). (Not shown) by synthesizing at least one selected to generate an image map image (M4). As described above, since the video image M1 is deleted and edited according to the parcels Z1 and Z2 of the cadastral map image M2, an empty space exists even when the second edited image MM' is combined with the deletion area. Accordingly, the auxiliary image reinforcement module 18 reinforces the auxiliary image in the empty space to plaster the edited image image M3.

For reference, if you delete all the video information for each lot (Z1, Z2) from the video image (M1), the entrance route, the exit route and other visible necessary information of the ground objects located on the lot (Z1, Z2) are edited. It may be omitted from (M3). In order to supplement this, the auxiliary image reinforcement module 18 reinforces and edits the auxiliary image as described above to produce an image map image M4.

3 is a flowchart sequentially showing the operation process of the correction processing system according to the present invention, and FIG. 4 is a diagram showing the criteria for detecting whether an object image is to be corrected by the correction processing system according to the present invention, and FIG. It is a diagram showing the state of the cadastral map of the image image area searched by the correction processing system according to the present invention, FIG. 6 is a diagram schematically illustrating a case of synthesizing the cadastral map to the image image before editing, and FIG. 7 It is an image showing the state that the parcel where the object image to be corrected is located has been deleted from the image image, and FIGS. 8 and 9 are diagrams schematically showing a change in the planar shape of the object image for each shooting angle, and FIG. 10 Is a diagram schematically showing a state in which the correction processing system according to the present invention corrects the planar shape according to a specified ratio, and FIG. 11 is a view in which the correction processing system according to the present invention synthesizes the planar shape of object images for each cadastral area. FIG. 12 is an image schematically showing FIG. 11 as an image image.

1 to 12, the correction processing system of the present invention operates in the following process to generate an image map image M4.

S10; Steps to specify the range to be corrected

When the operator searches the image image M1 in the image DB 11, the correction target detection module 14 checks the collection altitude of the photographed images constituting the image image M1, and at a specified ratio in proportion to the collection altitude. According to this, the range to be corrected is designated in the video image M1.

The range to be corrected is a circular section centered on the point where the aircraft D is located at the time of photographing the photographed image forming the corresponding image M1.

Consequently, the higher the altitude of the aircraft D, the wider the range to be corrected. However, since the effective photographed image for the production of the image image M1 is limited to the photographed image collected while the aircraft D is located at a limited altitude, the correction target detection module 14 is the target of correction specified in the image image M1. The range does not show much difference for each image image (M1).

S11; Video image analysis stage

The image analysis module 15 analyzes the position value and RGB value of the pixels on the ground object image posted within the range of the object to be corrected detected by the detection module 14 to be corrected to form a planar shape (P1, P1') ;See Fig. 4) and side shapes (P2, P2', P3, P3') are extracted.

The photographed image collected by the digital camera in the aircraft D is corrected and edited into the image image M1, and then output to the monitor through the pixel set with the RGB value. Therefore, the image analysis module 15 checks the position value and corresponding RGB value for each pixel for outputting the image image M1 to the monitor. Ground objects are painted with a unique color on their surface, so they have a different chromaticity than other adjacent ground objects. However, even if the surface is painted in the same color, the image of the ground object may show a difference in chromaticity due to the surface curvature of the ground object and the difference in contrast by location. That is, even with the same surface of the same ground object image, there may be a slight difference in the RGB value set for the corresponding pixel.

Accordingly, the image analysis module 15 unifies the RGB values of pixels set as chromaticities belonging to the designated representative chromaticity group with the corresponding representative chromaticity. For example, if red, pale red, and bright red form a group in an arbitrary representative chromaticity group, and the representative chromaticity is red, if the RGB value set in a random pixel is confirmed as bright red, the set RGB value of the pixel is determined. The RGB value is changed to red, which is the representative chromaticity of the corresponding chromaticity.

When the RGB values are unified by the representative chromaticity as described above, the image analysis module 15 checks the position values of the pixels and formalizes the cluster form of pixels having the same RGB value through deep learning. However, even if a subject has been stereotyped in a specific shape, the boundary line may become unclear or distorted in the image of the ground object collected by photographing. In other words, even if the subject is a square, the sides that form the boundary of the subject may form a curved shape rather than a straight line. Therefore, even if the ground object image is a somewhat curved square, the image analysis module 15 generates an independent shape image by forming the ground object image into a square shape through deep learning technology.

Subsequently, the image analysis module 15 analyzes the image image M1, extracts an aggregate of three or more shape images (P1, P2, P3) in contact with each other among the standardized shape images, and converts the aggregate into an object image (BM, P3). BM'). As can be seen from the video image M1, the structure is photographed slightly inclined during aerial photographing, so the plane and at least two or more sides are collected in contact with each other. Therefore, an aggregate of three or more shape images (P1, P2, P3) in contact with each other is regarded as a ground object image and is designated as an object image (BM, BM').

S12; Step of extracting object image to be corrected

The image analysis module 15 designates the shape image with the largest area from three or more shape images (P1, P2, P3) designated as object images (BM, BM') as flat shapes (P1, P1'), and The shape image is designated as the side shape (P2, P2', P3, P3').

Subsequently, the object image extraction module 16, compared to the total width of the planar shape (P1, P1') and one side shape (P2, P2', P3, P3'), one side shape (P2, P2', P3, P3). The width of') is within the standard value, and the outline of the object (UL1, UL2) not in contact with the planar shape (P1, P1') of the side shapes (P2, P2', P3, P3') of the object image (BM, BM') If it is located above the reference ratio in the range to be corrected, the object image (BM, BM') is designated as the target to be corrected.

In more detail, when the ground object image is collected in an excessively inclined state, the overall width d1, P1' and one side shape P2, P2', P3, P3' Compared to d1'), the widths d2, d2' of one side shape (P2, P2', P3, P3') increase. In other words, it is unreasonable as a correction target because the target ground object is photographed too sideways during the shooting process. Therefore, object images (BM, BM') collected in this way are excluded from correction. For reference, in the drawing (a) of FIG. 4, since the width (d2) of one side shape (P2) compared to the total width (d1) of the planar shape (P1) and one side shape (P2) is more than the reference value, the object image extraction module (16) is excluded from correction.

Also, among the side shapes (P2, P2', P3, P3') of the object image (BM, BM'), the object outlines (UL1, UL2) that are not in contact with the planar shape (P1, P1') are This is where it is actually located. Consequently, even if the planar shapes P1 and P1' are out of the range to be corrected, the object outlines UL1 and UL2 must be located within the range to be corrected. Therefore, if the object outline (UL1, UL2) is located within the range to be corrected above the reference ratio, that is, more than 90%, the ground object of the object image (BM, BM') is considered to be located within the range to be corrected and designated as the target for correction. . Since the reference ratio is changed as necessary, it is not limited to the illustrated 90%.

S13; Cadastral Map Search Step

The editing module 17 checks the GPS coordinates of the range to be corrected, searches for corresponding cadastral map information from the cadastral map DB 12, and extracts a cadastral map image M2 from the cadastral map information.

S14; Deletion and editing steps for each cadastral section of video images

The editing module 17 overlaps the previously extracted cadastral map image M2 with the range to be corrected, and deletes the video image M1 for each parcel (Z1, Z2) according to the parcel boundary BL of the cadastral map image M2. . That is, the editing module 17 overlaps the boundary line BL of the cadastral map image M2 with the video image M1 as shown in (b) of FIG. 5 to create a composite image M12 as shown in FIG. The edited video image M3 as shown in FIG. 7 is created by deleting the (Z1, Z2) section.

S15; Plane shape correction step

The editing module 17 moves the flat shape (P1, P1') from the object image (BM, BM') to fit the object outline (UL1, UL2), and adjusts the side shape (P2, P2', P3, P3'). After deletion, the first edited image (MM) is created.

However, even if the planar shapes P1 and P1' constituting the first edited image MM are the same ground object, the shooting distances L1, L2, h1, h2, the shooting angle, and the distance value 37, 37', 38, 38') and photographing altitudes h1, h2, etc., the photographing areas 31 to 36 of the corresponding object images BM3 to BM8 vary.

Therefore, the editing module 17 takes the first edited image (MM) from the shooting distance (L1, L2), the shooting altitude (h1, h2), the shooting angle, and the distance (37, 37', 38, 38') to the aircraft (D). Regardless of variable factors such as ), etc., it is corrected as if the aircraft D accurately photographed the plane in the vertical direction from the ground object. To this end, the editing module 17 checks the GPS coordinate value of the object image (BM, BM'), searches for the specification data of the corresponding ground object (B1 to B5) in the ground object information DB 13, and By checking the distance values (37, 37', 38, 38') between the water (B1 to B5) and the photographing point and the height value of the ground object, the amount of change in the photographing area (31 to 36) is confirmed. That is, as shown in FIG. 8, the plane D is taken as a standard image of the object image (BM4) collected by photographing the ground object at a corresponding shooting altitude h1 and a shooting distance of'L1'. ), and the shooting area (31, 33 to 36) changed by the shooting angle and shooting distance (L2), the height of the corresponding ground object identified in the specification data, and the distance values between shooting points (37, 37', 38, 38'), etc. ) To the size of the reference area 32.

As a result, the editing module 17 is in proportion to the distance value (37, 37', 38, 38'), the height value, the shooting altitude (h1, h2), the GPS coordinate value of the shooting point, and the GPS coordinate value of the ground object. The second edited image MM' is generated by expanding the edited image MM at the ratio of the vector amount as shown in Fig. 10C. For reference, the distance values 37, 37', 38, 38' are the difference between the GPS coordinate values of the aircraft D and the GPS coordinate values of the corresponding ground objects B1 to B5.

S16; Planar shape synthesis step

As shown in FIGS. 11 and 12, the editing module 17 synthesizes the second edited images MM1 and MM2 corresponding to the deletion areas of the parcels Z1 and Z2 configured in the edited video image M3, thereby synthesizing the image map image M4. ). Since the edited video image M3 is composed of a GPS coordinate system (not shown), the second edited images MM1 and MM2 linked to the corresponding coordinate values of the ground object are combined into the edited video image M3 according to the coordinate values. .

In the image map image M4 shown in FIG. 12, only the section Z21 in which the second edited images MM1 and MM2 are combined in the parcel Z2 is deleted, and the other section retains the existing image.

S17; Secondary image enhancement step

Since the editing module 17 deletes the video image in units of parcels (Z1, Z2), even if the second edited image MM' is combined into the deletion area, an unfilled empty space remains as shown in FIG. 11. Therefore, the auxiliary image reinforcement module 18 is selected from a tree image (not shown), a road image (not shown), and an entrance image (not shown) in the empty space of the deleted area excluding the second edited image (MM'). By combining one or more, the image map image (M4) is beautifully reinforced.

In the end, the image map image M4 can be used to form a realistic image without the crude appearance seen due to the deletion of images in the parcels (Z1, Z2).

In the detailed description of the present invention described above, it has been described with reference to preferred embodiments of the present invention, but those skilled in the art or those of ordinary skill in the relevant technical field, the spirit of the present invention described in the claims to be described later. And it will be understood that various modifications and changes can be made to the present invention within a range not departing from the technical field.

a2; Blind spots B1 to B5; Ground water BL; boundary
BM, BM', BM1 to BM8; Object image D; aircraft
d1, d2; Width M1; Video image M12; Composite image
M2; Cadastral map image M3; Edited video image M4; Video map image
MM; The first edited image MM'; Second edited images P1, P1'; Plane shape
P2, P2', P3, P3'; Side name shape UL1, UL2; Object outline

Claims (1)

In the image image correction processing system that complements the blind spots created for each object image due to an inclined shooting angle,
An image DB for storing the image image synthesized and edited according to the GPS coordinates;
A cadastral map DB that stores cadastral map information in which parcels are classified according to GPS coordinates;
Ground object information DB for storing GPS coordinate values and specification data of ground objects;
A correction target detection module for designating a correction target range of the image image in proportion to the collection height of the image image retrieved from the image DB;
In the image image, the RGB values of pixels within the range to be corrected are checked, and the RGB values of the pixels of the chromaticity belonging to the designated representative chromaticity group are unified with the corresponding representative chromaticity, and the position values of the pixels unified with the representative chromaticity are checked. The cluster shape of pixels having RGB values is standardized through deep learning, the standardized cluster shape is set as an independent shape image, a collection of three or more shape images in contact with each other is designated as an object image, and the shape of the object image An image analysis module that designates a shape image having the largest area among the images as a flat shape, and designates another shape image as a side shape;
If the outline of the object that is not in contact with the planar shape among the side shapes of the object image is located at a reference ratio or more in the range to be corrected, and the width of one side shape relative to the total width of the flat shape and one side shape is within the reference value, the object image is corrected. An object image extraction module designated as a target;
The first edited image from which the side shape is deleted is generated by moving the object outline to match the plane shape, and the ground object data corresponding to the GPS coordinate value of the object image is retrieved from the ground object information DB, Check the distance value between the shooting points, the shooting altitude, the height of the ground object, the GPS coordinate value of the shooting point, and the GPS coordinate value of the ground object, and the distance value, the shooting altitude and height value, the GPS coordinate value of the shooting point and the GPS of the ground object. In proportion to the coordinate value, the first edited image is expanded by the ratio of the vector amount to create a second edited image, and the cadastral map information corresponding to the correction target range of the video image is retrieved from the cadastral map DB, and the cadastral map image is overlapped with the correction target range. And an editing module for generating an edited video image by deleting the image image for each lot in accordance with the parcel boundary of the cadastral map image, and synthesizing the second edited image with a part of the deletion area so that empty space remains in the deletion area; And
An auxiliary image reinforcement module for generating an image map image by synthesizing at least one selected from among a tree image, a road image, and an entrance image in the empty space of the deletion area in the edited image image;
Image image correction processing system having a blind spot compensation function comprising a.

Images