JP4928993B2 - Farm district drawing data creation system - Google Patents

Description

  The present invention is a land parcel data creation system that analyzes observation images obtained by photographing the ground surface from an altitude (high sky) using a satellite, an aircraft, etc., and creates data relating to land parcels mainly composed of agricultural land on the surface. In particular, the present invention relates to a technique for creating agricultural district image data for facilitating extraction of agricultural land included in a geographic image.

  In recent years, the use of satellite images and aerial photograph images has become widespread, and techniques relating to the creation of maps using these images and the analysis of the ground surface have been developed. In this, it is indispensable to extract the land parcels in the image in order to analyze the photograph of the farmland part.

  Traditionally, land parcel extraction has been performed manually. Therefore, it was a problem that a great human cost was required. Therefore, a method for automating these processes by a computer has been proposed. As an example, in Patent Document 1 below, first, an outline of an agricultural district image, that is, an edge is extracted from an image obtained by photographing a ground surface, and an intersection of a straight line and an edge that is radially extended from an arbitrary point in the edge image is obtained. A process for extracting a polygonal segment area generated by connecting a plurality of intersections has been proposed. By this process, the land parcel can be automatically extracted. Non-Patent Documents 1 and 2 are academic papers on these image processing.

JP 2003-256807 A J. Canny, `` A Computational Approach to Edge Detection '' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.PAMI-8, No6, November 1986 Mamoru Onoe, “Image Processing Handbook”, Shosodo Publishing (1987)

  However, in many cases, the section area extracted from the geographic image by the method of Patent Document 1 cannot accurately extract the actual section shape. For example, in the method described in Patent Document 1, the extraction accuracy of the corner portion of the partition region may be deteriorated. In other words, the method described in Patent Document 1 recognizes the shape of a section based on an edge extracted from a geographic image, but the extraction accuracy of the edge of the section is low or noise is extracted as an edge. In addition, the shape of the extracted partition region may be different from the actual shape (see the regions (a) and (c) in FIG. 2D).

  Therefore, it is necessary to add a process for further shaping the extracted partition area. Since this operation is difficult to automate, there is a problem that a great human cost is required and an operator needs a great concentration and time. In addition, in order to work on a wide range of images in a limited time, a plurality of operators are required. In this case, the shaping result is based on the difference in subjective judgment criteria of each operator. There is a problem that there is a high possibility that variations will occur.

  An object of the present invention is to provide an agricultural district image data creation technique capable of easily creating agricultural district image data from a geographic image.

  As a result of diligent research in view of the above-mentioned problem, the present inventor failed to extract the segmented region extracted by the method of Patent Document 1 due to the process of estimating the corner of the segment and the mistake of edge extraction. It has been thought that the above problem can be solved by adding a process for estimating the shape of the partitioned area.

  That is, the present invention is a system for extracting and shaping a partitioned area included in a geographic image, extracting an edge of a farm area such as a field in the geographic image, and extracting a partitioned area based on the extracted edge. It includes a section extracting means and a section shaping means for shaping the shape of the extracted section area so as to match the shape of the actual land section. Further, the section shaping means calculates the angle of each vertex of each section area and examines the acute angle shaping means for shaping an acute angle that is an angle equal to or less than a certain angle, the surroundings of each side of each section area, and the section area of each side Deterministic edge determining means for determining the degree of definiteness as a side, a corner missing area shaping part for shaping a corner part of each divided area, and a protruding area shaping part for shaping an unnaturally protruding part of each divided area It is characterized by including these.

  More specifically, according to one aspect of the present invention, a geographical image data creation system that analyzes geographical image data obtained by photographing the ground surface and creates agricultural district image data, the geographic image data, A partition region extraction unit that extracts a partition region based on the edge extracted by the edge extraction processing, and if there is a partial region having an acute angle equal to or less than an angle in the extracted partition region, the partial region is removed and region shaping is performed. The degree of proximity between the sharp angle shaping unit to be performed and the edge of each side of the partition area in the image after the edge extraction processing is calculated, and a side having a high proximity is determined as a confirmed side determined as a side of the partition area A deterministic edge determination unit that determines an uncertain edge that has not been determined as a low-adjacent side, and a corner-missing region shaping unit that shapes vertices that have not been sufficiently extracted in the partition region. Characteristic Farmland partition data creation system is provided. Furthermore, it is preferable to have a projecting region shaping unit that removes an extra extracted portion in the partition region.

  The corner-missing region shaping unit may include the first definite side and the second definite side when there is a region including an uncertain side sandwiched between the first definite side and the second definite side. It is preferable to shape the region surrounded by the extension line including the intersection point among the extension lines of the determined sides and in which the region formed by the extension line at the intersection point is close to 90 degrees.

  The projecting region shaping unit may include the first deterministic side and the second deterministic side when there is a region including an uncertain side sandwiched between the first definite side and the second definite side. In the case where there is no region surrounded by the extension line including the intersection among the respective extension lines, and the angle formed by the extension line at the intersection is not close to 90 degrees, the first definite side and the first When one of the two definite sides has an intersection with the other side of the partition area, the protrusion includes the definite side that does not wait for the intersection by an extension line of the definite side having the intersection It may be shaped so as to cut the area.

  Further features of the present invention will become apparent from the best mode for carrying out the present invention and the accompanying drawings.

  According to the geographic image processing system of the present invention, the work of extracting and shaping land blocks from geographic images such as satellite images and aerial photograph images can be made efficient. In addition, since the work process that has traditionally relied on the skill of the operator is automated, even when a large number of operators are working, a uniform land is not affected by differences in the skill level of the operator. Partition data can be obtained.

  Hereinafter, a geographic image processing system according to an embodiment of the present invention will be described with reference to the drawings. 1 to 13 are diagrams showing an example of a farm district drawing system according to an embodiment of the present invention. In these drawings, parts denoted by the same reference numerals represent the same items, and the basic configuration and operation are the same. In addition, this invention is not limited to the form demonstrated by this Embodiment. A person skilled in the art can make various changes and improvements to the configuration and function of the invention according to the embodiments without departing from the gist of the present invention.

<System configuration>
FIG. 1 is a functional block diagram schematically showing a configuration example of a geographic image processing system of the present invention. Referring to FIG. 1, a geographic image processing system according to the present embodiment includes a processing device 10 composed of a personal computer, a workstation, and the like, and a RAM (random access memory) used as a main memory, a magnetic disk storage device, and the like. A storage device 20 including a storage device and an input / output device 30 are provided.

  The input / output device 30 includes an input device 31 including a pointing device such as a keyboard and a mouse, a display device 32 such as a liquid crystal display device, and a printer 33. The input device 31 is used for input of parameters by a user, activation of commands, and generation of land parcel data using geographic images subjected to image processing by the present system. The display device 32 and the printer 33 are used for presenting geographic image data and land parcel data handled by the system according to the present embodiment to the user. The display function may include only one of the display device 32 and the printer 33.

  The processing device 10 includes each processing unit based on the geographic image processing program 40. The geographic image processing program 40 implements, as program modules, a zone extraction unit 100 that extracts zones such as farmland included in the geographic image, and a zone shaping unit 200 that performs a shaping process on each of the extracted zone areas. The

  Further, the section shaping unit 200, as a sub-module, checks the angle of each vertex of the polygon of each section area and corrects an unnatural vertex, and the side of each side of the polygon of each section area Determining edge determination unit 202 for determining the degree of definiteness, corner missing region shaping unit 203 for shaping a portion lacking a corner unlike the original shape in each partitioned region, Unlike the shape, it includes a protruding region shaping unit 204 that shapes an unnaturally protruding portion.

  The storage device 20 stores geographic image data 21, partition area data 22, and edge data 23. Among these, the geographic image data 21 is data obtained from an artificial satellite image or an aerial photograph image, and is data stored in advance before execution of processing by the system according to the present embodiment. On the other hand, the partition area data 22 and the edge data 23 are data generated based on the geographic image data 21 in the system according to the present embodiment.

<Outline of geographic image processing>
FIG. 2 is a diagram illustrating an overview of image processing performed by the system according to the present embodiment. FIG. 2A is a diagram illustrating an example of geographic image data 21 stored in the storage device 20 in advance. This Fig.2 (a) contains the paddy field and the tunnel which divides a paddy field. By performing edge detection processing on this geographic image data, for example, an edge image shown in FIG. 2B is obtained. The edge image shown in FIG. 2B is stored in the storage device 20 as edge data 23. Based on the edge data, a section extraction process is performed to extract polygon vector data representing land sections. First, an arbitrary point on the image is selected as a seed point. Next, a straight line is drawn radially from the seed point, and an intersection of the straight line and the edge is obtained (FIG. 2C). And the polygon as shown in Drawing 2 (d) can be created by combining the intersection in the order which adjoins. This polygon shows one division area. One partition area is data in which a plurality of vectors are connected. This data is stored in the storage device 20 as partitioned area data 22.

  However, the partition area obtained is often very different from the actual section shape. In part (a) of FIG. 2 (d), since the edge of the tunnel is partially broken in FIG. 2 (b), a sharp vertex is generated in the extracted partition area. In addition, in the portion (b), the corner portion of the actual section cannot be extracted properly. Further, in the portion (c), the extraction of the lane is incomplete as in the portion (a), so that the extracted section area protrudes outside the actual section.

  In order to shape such an incomplete partition region into a shape that matches the actual partition shape close to a rectangle as shown in FIG. 2 (h), first, with respect to the partition region in FIG. 2 (d). A sharp and sharp angle shaping process 201 is performed to shape sharply pointed vertices as shown in FIG. Next, a definite edge determination process 202 is performed on each side in the partition area, and an edge “determined edge” that is considered to be appropriately extracted as an edge in the partition area and an edge “indefinite edge that is considered to be erroneously extracted ". FIG. 2F is a diagram illustrating a processing result example of the definite side determination process, in which a solid line indicates a definite side and a dotted line indicates an uncertain side.

  Further, corner missing region shaping processing 203 is performed to shape an incomplete corner portion as shown in (b) of FIG. Finally, a protruding area shaping process 204 is performed to shape an unnaturally protruding portion as shown in FIG. This result is overwritten on the partition area data and stored in the storage device 20. Conventionally, the basic section extraction process and the sharp-pointed vertex shaping process as shown in FIG. 2D have been automated, but the parts such as (B) and (C) in FIG. Shaping was done manually. In the present embodiment, these shaping operations can also be performed automatically. A description will be given below.

<Details of geographic image processing>
Hereinafter, the segment extraction process, the sharp angle shaping process, the fixed edge determination process, the corner missing area shaping process, and the protruding area shaping process in the geographic image processing system according to the present embodiment will be described in detail. In the present embodiment, when the geographic image processing program 40 is activated, the segment extraction unit 100 and the segment shaping unit 200 are sequentially activated. In the section shaping unit 200, a sharp angle shaping unit 201, a defined edge determination unit 202, a corner missing area shaping unit 203, and a protruding area shaping unit 204 are activated. The order of 201 and 202, 203 and 204 may be reversed. The details of the processing by each will be described below.

(1) Section Extraction Processing FIG. 3 is a flowchart showing the flow of processing by the section extraction unit 100 of the geographic image processing program 40 according to this embodiment. In FIG. 3, the section extraction unit 100 reads the geographic image data 21 from the storage device 20 (S301), and extracts edges such as tabata roads existing in the image (S302). Various well-known techniques can be applied as the process of extracting the edge. For example, by applying various edge filters such as the Canny method (see the non-patent document 1) and the Sobel filter (see the non-patent document 2) to geographic image data, an edge such as a saddle can be extracted. By this processing, an edge image as shown in FIG. 4A is generated. That is, the seed point S is determined in a region surrounded by edges. Next, the section extraction unit 100 performs region extraction processing on the edge image in order to extract farmland sections (S303). A linear intersection method (see Patent Document 1) can be used for region extraction at this time. This process is a process of extracting a partitioned area including the seed point S from the given edge image and a single coordinate S called a seed point. The seed point S refers to the coordinates that serve as the starting point when extracting the partitioned area. The seed points can be determined by a method such as interspersed in a lattice pattern or randomly arranged.

  Assume that an edge image and a seed point S are given in advance as shown in FIG. First, straight lines (L1 to L3) are extended in all directions from the seed point S, for example, at equiangular intervals (FIG. 4B). And the intersection of each straight line (L1-L3) and the edge pixel in an edge image is calculated | required, and the obtained intersection P1-P8 is combined in order (FIG.4 (c)). A polygonal area extracted by this processing is defined as a partitioned area A1 (FIG. 4D). The number of vertices of the partition area A1 depends on the number of straight lines L extending from the seed point S. For example, in FIG. 4, the number of straight lines L is eight. By increasing the number of straight lines, it is possible to extract a more precise partition region. However, if the edge image contains a lot of noise, noise may be extracted as an intersection, so an appropriate number of straight lines is set. The above process is performed for all seed points (S1 to Sn, n is an integer of 1 or more).

  The partition extraction unit 100 stores the vector data of each partition region thus obtained in the storage device 20 as the partition region data 22 (S304). The partition area data is data having information as shown in FIG. An ID is assigned to each partition area, and the partition area can be uniquely specified by the ID. It also has information on the number of vertices n, the coordinates of each vertex, and the definition of each side. The degree of definiteness of each side will be described in the section of definite side determination processing described later. In the partition extraction unit 100, the partition area ID, the number of vertices, and the coordinates of each vertex are stored in the storage device 20.

(2) Sharp Angle Shaping Processing FIG. 6 is a flowchart showing the flow of processing in the sharp angle shaping unit 201 in the section shaping unit 200 of the geographic image processing program 40. The sharp angle shaping unit 201 checks the segment area data 22 obtained by the segment extraction unit 100 and corrects an unnaturally sharp apex portion. In FIG. 6, the sharp angle shaping unit 201 reads the partitioned area data 22 from the storage device 20 (S401), and selects one unprocessed partitioned area from the partitioned areas (S402). Next, the angle of each vertex of the read partitioned area is calculated (S403). At this time, if the calculated angle is equal to or less than a certain angle, the vertex is removed, and the vertices before and after the removed vertex are joined together (S404).

  FIG. 7 is a diagram illustrating an example in which the edge of a part of the section is not extracted and the contour of the part becomes unnatural. The sharp angle (θ) region 53 caused by the edge extraction failure region in the partition region 51a in the edge 55 is excluded from the target of the partition region (51b), and the correct partition region 51c is generated. By adding such a sharp angle shaping process, an unnatural part of the partitioned area can be shaped (51c). Then, the segment area data is updated after shaping (S407).

  When the processing of one vertex is completed, if no in S406, the angle of each vertex is recalculated (S405). Then, the process is repeated until there is no such vertex in the partitioned area (S406). Then, the processing from S402 to S407 is performed on all the partitioned areas (S408).

(3) Determined Edge Determination Processing FIG. 8 is a flowchart showing the flow of processing by the determined edge determination unit 202 in the section shaping unit 200 of the geographic image processing program 40. In FIG. 8, the determined edge determination unit 202 reads the partition area data 22 and the edge data 23 from the storage device 20 (S501). One unprocessed partition area is selected (S502), and one unprocessed side of the partition area is selected (S503). Then, the ratio R of edge pixels in the vicinity region of the side is obtained (S504). R is determined by the ratio of edge pixels in the area of several pixels outside each side, and is obtained by, for example, Expression 1.

  Here, S is the number of pixels in the vicinity region of each side, and Edge is an edge pixel existing in the region.

  FIG. 9 is a diagram showing a part of the partition area data, in which the image data and the edge data are overlapped. In the portion A11 of FIG. 9A and the portion A13 of FIG. 9B, the side L11 / L12 of the partition area and the edge data EG1 are close to each other, and the number of edge pixels existing in the vicinity area range is large. R in (1) is large. On the other hand, in the portion (b) of FIG. 9, R is small because the number of edge pixels in the neighborhood A12 is small.

  By comparing R obtained from equation (1) with a predetermined threshold value, the degree (determinism) that each side L11, L12, L13 represents the actual shape is determined (S505). If R is larger than a certain threshold, the side is set as a “determined side” (S506), and if R is smaller than a certain threshold, it is set as an “indeterminate side” (S507). Then, the partition area data corresponding to the side where the processing is completed is updated (S508). In this way, it is determined whether all sides of all partitioned areas are determined sides or undefined sides (S509) and (S510). In the example of FIG. 5, the degree of definiteness is represented as “1” for the definite side and “0” for the uncertain side. The degree of definiteness is used in corner missing area shaping processing and protruding area shaping processing.

(4) Corner missing area shaping process FIG. 10 is a flowchart showing the flow of processing by the corner missing area shaping section 203 in the section shaping section 200 of the geographic image processing program 40. The corner-missing region shaping unit 203 shapes a portion where the corner is missing as shown in (b) of FIG. In FIG. 10, the corner missing area shaping unit 203 first reads the section area data 22 from the storage device 20 (S601). Thereafter, the processing from S602 to S611 is performed on each partition area. These processes will be described with reference to FIG. FIG. 11 (a) shows an example of the result of the section extraction process performed on a square section. In this example, the corner portion of the upper left region has not been properly extracted. The corner missing area shaping unit 203 estimates and interpolates the shape of the corner portion that cannot be extracted. First, one unprocessed partition area is selected (S602).

  Next, one unprocessed fixed edge is selected from the selected partition area (S603). The side selected here is set as side A in FIG. Next, the sides adjacent to side A are examined in order, and the next definitive side of side A is found (S604). In FIG. 11, the check is performed counterclockwise from the side A, and the definite side B is detected with one uncertain side C in between. Let this side be side B. In addition, although the example investigated counterclockwise is demonstrated here, you may investigate clockwise.

A side between side A and side B (referred to as side C) is an indeterminate side, that is, a side with a small number of edge pixels in the vicinity. Therefore, there is a high possibility that the shape of the actual section is not extracted around the uncertain side C, and the corner portion of the actual section may not be extracted. The following processing is performed to estimate the true angle of a region that may be missing. An intersection point (referred to as an intersection point P) between the first extension line extending the definite side A toward the uncertain side C and the second extension line extending the definite side B toward the uncertain side C is obtained (FIG. 11). (B)) (S605). This intersection P is a point where there is a possibility of a corner portion where extraction has failed. It is checked whether or not the intersection P is highly likely to be a corner (S606). If it is a section of farmland, that is, a section of a field, the corner is considered to be an angle close to a right angle. Therefore, by checking the angle, it can be determined whether or not it is a corner portion of the partitioned area. At that time, examining the sides A, the angle formed theta _P between extension and intersection point P which extended from the respective sides B. If θ _P is not an angle close to a right angle (the allowable range can be arbitrarily set: 70 degrees to 110 degrees, that is, 90 degrees ± 20 degrees), the process returns to S603. If theta _P is an angle close to a right angle, the intersection point P is determined that there is a high possibility that the angular part of the actual compartment.

  In that case, first, the vertex / side between side A and side B is deleted (S607). Then, the point P is set as a new vertex of the partition area, and the extension lines of the side A and the side A and the extension lines of the side B and the side B are set as new sides (FIG. 11C) (S608). Further, the new side set at this time is set as a definite side, thereby expanding the corner missing region. Then, the partition area data is updated with the changed data.

  The above processing is performed for all the definite sides of all the divided areas (S610) (S611). By adding such processing, it is possible to interpolate a portion lacking corners such as (B) in FIG. 2D as shown in FIG.

(5) Protruding Area Shaping Process FIG. 12 is a flowchart showing the flow of processing by the protruding area shaping section 204 in the section shaping section 200 of the geographic image processing program 40. In the protruding area shaping process 204, a part that protrudes unnaturally from the actual shape of the section is shaped as shown in FIG. In FIG. 12, the protruding area shaping unit 204 reads the partitioned area data 22 from the storage device 20 (S701). Thereafter, the processing from S702 to S711 is performed on each partition area. These processes will be described with reference to FIG.

First, one unprocessed partition area is selected (FIG. 13A) (S702). Next, one unprocessed fixed edge is selected from the selected partition area (S703). Here, the selected side is set as side D. Next, it is checked whether or not the side D is an indefinite side (S704). If both sides of the side D are determined sides, the process returns to S703. When at least one side before and after the side D is an indefinite side, the side D is extended in the direction of the indefinite side until it intersects with another side (L22: S705). Also, let Q be the intersection at this time. If the intersection point Q is a point on an indefinite side, the process returns to S703 (S706). If the intersection Q is a point on the determined side, the process proceeds to S707. By making the closed region AR31 formed by the extension line L22 of the fixed side and the fixed side on the extended line as a new block region, an unnatural jump-out portion of the block caused by edge extraction failure or the like is corrected. In S707, it is determined whether the intersection point Q can be a new partition area. Specifically, it is checked whether the angle Q _theta formed by the base and the straight line L22 at the point Q is perpendicular angle close to (tolerances arbitrarily set). If _Qθ is an angle close to a right angle, it is determined that there is a high possibility that the intersection Q is a corner portion of an actual section, and the process proceeds to S708. _Q θ returns to S703 if it is not an angle close to a right angle. In S708, the intersection Q is a new vertex, the extension line L22 of the definite side D is a new side, and the closed region that is composed of the side L22 and the original partition area AR32 and does not include the uncertain piece L21 is closed. A region formed by the region AR33 is set as a new partitioned region (FIG. 13C). At that time, the extension line L22 of the side D is registered as a fixed side. Then, the partition area data is updated with the changed data (S709). The above processing is performed on all the definite sides of all the partitioned areas (S710, S711). Note Q is _θ whether right angles close, for example, be a reference at a right angle near about 110 degrees from 70 degrees. In an angle range close to a right angle, whether or not the division is well organized is considered to be the same in the same region. Therefore, for example, it may be determined according to a statistical value in a division of a nearby farmland.

  By performing the above-described processing, the unnaturally protruding section area corresponding to a part such as a tunnel where the edge has not been sufficiently extracted, such as the part (c) in FIG. 2 can be shaped as shown in FIG.

<Summary>
As described above, the agricultural district image data creation system according to the embodiment of the present invention relates to an agricultural district image data creation system that analyzes geographic image data obtained by photographing the ground surface and creates agricultural district image data. is there.

  The system includes a partition extraction unit (module) that extracts a partition area from geographic image data, a sharp angle shaping unit (module) that removes vertices at a very small angle in the partition area, and each side of the partition area. A definite edge determination unit (module) that determines whether or not the object is close to the edge, and a corner-missing region shaping unit (module) that interpolates the corner of the partition area when the corner that should be extracted is not extracted ) And a protruding area shaping unit (module) for shaping an unnaturally projected area that should not be extracted. As a result, the extraction of the agricultural district image can be automated, and the extraction based on subjective judgment and the variation in the extraction accuracy can be prevented.

  The functions described in this embodiment can also be realized by a software program. In this case, a storage medium in which the program code is recorded is provided to the system or apparatus, and the computer (or CPU or MPU) of the system or apparatus can read the program code stored in the storage medium. good. In this case, the program code itself read from the storage medium realizes the function according to the above-described embodiment, and the program code itself and the storage medium storing the program code constitute the system according to the present invention. . As a storage medium for supplying such program code, for example, floppy (registered trademark) disk, CD-ROM, DVD-ROM, hard disk, optical disk, magneto-optical disk, CD-R, magnetic tape, non-volatile A memory card, ROM, or the like is used.

  Also, based on the instruction of the program code, an OS (operating system) running on the computer performs part or all of the actual processing, and the functions of the above-described embodiments are realized by the processing. May be. Further, after the program code read from the storage medium is written in the memory on the computer, the computer CPU or the like performs part or all of the actual processing based on the instruction of the program code. Thus, the functions of the above-described embodiments may be realized.

  In addition, the program code of the software that realizes the functions of the embodiment is distributed via a network, so that it is stored in a storage means such as a hard disk or memory of a system or apparatus or a storage medium such as a CD-RW or CD-R. It may also be achieved by the computer (or CPU or MPU) of the system or apparatus reading and executing the program code stored in the storage means or the storage medium.

  The present invention can be used as an agricultural district image data creation system.

It is a block diagram which shows the example of 1 structure of the geographic image processing system by one embodiment of this invention. FIG. 2A to FIG. 2H are diagrams sequentially showing an outline of image processing performed by the geographic image processing system according to the present embodiment. It is a flowchart figure which shows the flow of a process of the division extraction part by this Embodiment. FIGS. 4A to 4D are diagrams sequentially showing an outline of the process of the section extraction unit according to the present embodiment. It is a figure which shows the example of 1 structure of division area data. It is a flowchart figure which shows the flow of a process of the acute angle shaping part by this Embodiment. It is a figure which shows the outline | summary of the process of the acute angle shaping part by this Embodiment. It is a flowchart figure which shows the flow of a process of the fixed edge determination part by this Embodiment. It is a figure which shows the principle of the fixed edge determination process by this Embodiment. It is a flowchart which shows the flow of a process of the corner missing area shaping part by this Embodiment. It is a figure which shows the outline | summary of a process of a corner missing area shaping part. It is a flowchart figure which shows the flow of a process of the protrusion area | region shaping part by this Embodiment. It is a figure which shows the outline | summary of a process of a protrusion area | region shaping part.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Processing apparatus 20 Memory | storage device 21 Geographic image data 22 Compartment area | region data 23 Edge data 30 Input / output device 31 Input device 32 Display apparatus 33 Printer 40 Geographic image processing program 100 Compartment extraction part 200 Compartment shaping part 201 Sharp angle shaping part 202 Definite edge Determination unit 203 Corner missing region shaping unit 204 Protruding region shaping unit

Claims (4)

An agricultural district image data creation system that analyzes geographical image data obtained by photographing the ground surface and creates agricultural district image data,
For the geographic image data, a partition area extraction unit that extracts a partition area based on the edge extracted by the edge extraction process;
If there is a partial area having an acute angle equal to or smaller than an angle in the extracted partitioned area, a sharp angle shaping unit that removes the partial area and performs area shaping; and
Calculate the proximity of each side of the partition area with the edge in the image after the edge extraction process, determine a side having a high proximity as a confirmed side determined as a side of the partition area, and select a side having a low proximity A deterministic edge determination unit that determines an uncertain uncertain edge;
An agricultural district image data creation system comprising: a corner missing area shaping unit for shaping a vertex of the partition area that has been insufficiently extracted.   The farm area drawing data creation system according to claim 1, further comprising a protruding area shaping unit that removes an extra extracted portion in the partition area. The corner missing region shaping unit is
When there is a region including an uncertain side sandwiched between the first and second deterministic sides, an intersection of the extended lines of the first deterministic side and the second definite side is determined. The farm district image according to claim 1 or 2, wherein the area is surrounded by an extension line including the area, and the area formed by the extension line at the intersection is shaped so as to expand near 90 degrees. Data creation system. The protruding region shaping part is
When there is a region including an uncertain side sandwiched between the first and second deterministic sides, an intersection of the extended lines of the first deterministic side and the second definite side is determined. One of the first deterministic side and the second deterministic side when there is no region surrounded by the containing extension line and the angle formed by the extension line at the intersection is close to 90 degrees When one side has an intersection with the other side of the partition area, the extended area of the determined side having the intersection is shaped so as to cut the protruding area including the determined side that does not wait for the intersection. The farm district image data creation system according to any one of claims 1 to 3.

Images