JP2023007662A - Damage diagram creation method - Google Patents

Abstract

To provide a novel image synthesis method which improves damage shape measurement accuracy in overlapping areas.SOLUTION: An image synthesis method is provided, for generating a synthesized image using a plurality of images obtained by split-imaging an object such that some areas overlap. In an overlapping area, one having a smaller synthesis parameter is selected for synthesis.SELECTED DRAWING: Figure 30

Description

The present invention relates to a damage diagram creation method, a damage diagram creation apparatus, a damage diagram creation system, and a recording medium, and more particularly, to a technique for detecting damage based on a plurality of images obtained by separately photographing an object.

Conventionally, there has been known a system that analyzes the state of deterioration and damage of a huge structure such as a bridge based on images of the structure. For example, in Patent Document 1, a structure such as a bridge is divided into a plurality of areas and photographed, and then stitched together to generate a single composite image, identifying damaged locations such as cracks, and creating data thereof. (Creation of data such as crack length and width size) is described. In order to create a composite image, the divided images are photographed so that overlapping regions are generated, and projective transformation is performed on each of the images based on the features of the overlapping regions. A positional relationship is determined to generate a composite image. In order to prevent deterioration of the image in the overlapping area when creating the synthesized image, instead of synthesizing two images to generate an image of the overlapping area, only one of the images is used (adopted ) is getting the overlap region image. It is also described that the image selection method to be adopted is based on the brightness of the image, the sharpness of the subject, and the like.

WO/2019/003796

However, if the selection of the image of the overlap region is determined based on the brightness and sharpness of the image, the data accuracy of the damage (cracks, etc.) may be degraded.

Therefore, the present invention for solving the above problems provides a step of inputting a plurality of images acquired by dividing and photographing a subject such that a part of the area overlaps; a step of calculating a projective transformation parameter) based on the corresponding points of the images;
a step of detecting damage to the subject from images constituting the plurality of images; and a step of synthesizing the detection results of the plurality of images based on the synthesis parameter;
In the synthesizing step, in the overlapping region, one of the multiple overlapping images is selected and synthesized, and the selected one image has a higher value of the synthesizing parameter than the other image. is small.

According to the present invention, the measurement accuracy of the shape of the damage in the overlap region is improved.

1 is a block diagram showing the configuration of a damage drawing creation system according to a first embodiment; FIG. It is a figure which shows the structure of a process part. It is a figure which shows the information memorize|stored in a memory|storage part. It is a figure which shows the structure of a server. It is a figure which shows the flowchart of the damage diagram preparation method which concerns on 1st Embodiment. FIG. 5 is another diagram showing a flow chart of the damage diagram creation method according to the first embodiment. It is a figure which shows the example of the imaging|photography procedure of a floor slab. It is a figure which shows the example of the photography procedure of a coffer. It is a figure which shows the imaging|photography range of each image. It is a figure which shows each picked-up image. FIG. 4 is a diagram showing a hierarchical structure of folders; FIG. 10 is a diagram showing a state in which photographed images are stored in a folder; 10 is a flow chart showing image layout determination processing. FIG. 10 is a diagram showing how a reference image is set; FIG. 4 is a diagram showing an example of image arrangement for each image group; FIG. 11 is another diagram showing an example of image arrangement for each image group; It is a figure which shows a mode that the vectorized detection result was superimposed and displayed on the image. FIG. 10 is a diagram showing how the relative arrangement of each image group is changed; FIG. 10 is a diagram showing how corresponding points are set in an image group; It is a figure which shows the synthesis|combination of a detection result. FIG. 11 is another diagram showing synthesis of detection results; FIG. 10 is a diagram illustrating synthesis of detection results in areas where images overlap; It is a figure which shows the synthesized image. FIG. 11 is another diagram showing a synthesized image; It is a figure which shows a mode that the detection result etc. were stored in the same folder as an image. FIG. 11 is a block diagram showing the configuration of a damage diagram creation device according to a second embodiment; FIG. 10 is a diagram showing another example of combining detection results in an area where images overlap; FIG. 10 is a diagram showing another example of combining detection results in an area where images overlap; FIG. 10 is a diagram illustrating an example of calculation of synthesis parameters in an area where images overlap; FIG. 11 is a diagram showing a flowchart of a damage diagram creation method according to a third embodiment; FIG. 11 is a conceptual diagram of a damage diagram creation method according to a third embodiment;

EMBODIMENT OF THE INVENTION Hereafter, embodiment of the damage diagram creation method, damage diagram creation apparatus, damage diagram creation system, and recording medium which concerns on this invention is described in detail, referring an accompanying drawing.

<First Embodiment>
<Bridge structure>
A preferred structure to which the damage diagram creation method and damage diagram creation apparatus of the present invention can be applied is, for example, a bridge. See FIG. 1 of Patent Document 1 for this structure. In the present embodiment below, a bridge will be described as an object (subject), but the object building is not limited to a bridge, but may be a tunnel, a building, a road, or the like.

<Acquisition of image>
When detecting damage by photographing an image of a bridge, the inspector photographs the bridge from below using the digital camera 100 (see FIG. 1), and obtains a plurality of photographed images (different parts of the bridge are respectively photographed) for the inspection range. multiple images) are divided and acquired. Photographing is performed while moving appropriately in the extension direction of the bridge and in the orthogonal direction. If it is difficult for the inspector to move due to the surrounding conditions of the bridge, a digital camera 100 may be provided on a movable body that can move along the bridge to take pictures. An elevating mechanism and a rotating mechanism (a mechanism for panning and/or tilting) of the digital camera 100 may be provided in such a moving body. Examples of mobile objects include vehicles, robots, and flying objects (drones, etc.), but are not limited to these.

<Configuration of damage diagram creation system>
FIG. 1 is a block diagram showing a schematic configuration of a damage diagram creation system 10 (damage diagram creation system). The damage drawing creation system 10 is equipped with a digital camera 100, a client 200, and a server 300, and is a system for creating a damage drawing by detecting damage in a plurality of images obtained by separately photographing a subject, synthesizing the detection results, and the like. be. In the damage drawing creation system 10, a device (information terminal) such as a personal computer, a tablet terminal, or a smart phone that inputs an image and receives the result from the server 300 can be used as the client 200. A computer connected to the client 200 via a network can be used. It can be used as the server 300 .

<Configuration of digital camera>
The digital camera 100 acquires an image by an image pickup optical system 110 having a photographing lens and an image sensor (not shown). Examples of the imaging device include a CCD (Charge Coupled Device) type imaging device and a CMOS (Complementary Metal-Oxide Semiconductor) type imaging device. A color filter of R (red), G (green), or B (blue) is provided on the light receiving surface of the imaging device, and a color image of the subject can be obtained based on the signals of each color. The digital camera 100 wirelessly communicates with the client 200 via the wireless communication unit 130 and the antenna 132, and the photographed image is input to the processing unit 210 for processing described later. Note that the digital camera 100 and the client 200 may be incorporated in separate housings, or integrated with each other.

<Overall configuration of the client>
The client 200 includes a processing unit 210, a storage unit 220, a display unit 230, and an operation unit 240. These units are connected to each other to transmit and receive necessary information. Also, the client 200 performs wireless communication with the digital camera 100 via the antenna 212 and acquires an image captured by the digital camera 100 . Further, the client 200 is connected to the server 300 via the network NW, and exchanges with the server 300 the transmission of the acquired image, the processing result (composite detection result, composite image, etc.) for the transmitted image, the processing request, and the processing request. Send and receive the response, etc.

<Structure of Processing Unit>
FIG. 2 is a diagram showing the configuration of the processing unit 210. As shown in FIG. The processing unit 210 includes an image input unit 210A (image input unit), a file management unit 210B, a display control unit 210C, and a communication control unit 210D. It receives and controls the display of processing results on the monitor 232 . The image input unit 210A inputs photographed images of a bridge (a plurality of images obtained by dividing and photographing a bridge) from the digital camera 100 (or recording medium, network, etc.). The file management unit 210B creates folders according to user operations via the keyboard 242 and/or the mouse 244. FIG. The display control unit 210C performs display control on the monitor 232 of the obtained image, the received processing result, and the like. The communication control unit 210D transmits and receives images and information to and from the digital camera 100 via the antenna 212, and transmits and receives images and information to and from the server 300 via the network NW. The ROM 210E (ROM: Read Only Memory, non-temporary recording medium) contains programs necessary for processing such as image acquisition, transmission and reception (including a program for executing the damage diagram creation method according to the present invention or a part thereof) computer readable code is recorded.

Each function of the processing unit 210 described above can be realized by referring to software recorded in a recording medium by various processors or electric circuits, in the same way as the server 300 will be described in detail later.

<Structure of storage unit>
The storage unit 220 is composed of a non-temporary recording medium such as a CD (Compact Disk), a DVD (Digital Versatile Disk), a hard disk, various semiconductor memories, etc., and a control unit thereof, and the images and information shown in FIG. stored in association with each other. The photographed image 220A is a plurality of images obtained by dividing and photographing the bridge (floor slab portion), which is a subject, with the digital camera 100 and inputting the photographed image with the image input unit 210A. It should be noted that an image obtained via a network or a recording medium may be stored instead of the image input by the digital camera 100 and the image input unit 210A. The detection result 220B includes damage detection results for the individual images that make up the captured image 220A and detection results obtained by synthesizing the detection results for the individual images. The synthesized image 220C is an image obtained by synthesizing the captured images (including a partially synthesized image group). The damage mapping image 220D is an image in which information indicating damage (detection results, etc.) is mapped. These images and information can be stored in folders (see FIGS. 11 and 12).

<Configuration of display unit and operation unit>
The display unit 230 includes a monitor 232 (display device), and can display input images, images and information stored in the storage unit 220, results of processing by the server 300, and the like. The operation unit 240 includes a keyboard 242 and a mouse 244 as input devices and/or pointing devices, and the user can create folders, store images in folders, and create corresponding points via these devices and the screen of the monitor 232 . , and other operations necessary for executing the damage diagram creation method according to the present invention (described later).

<Server configuration>
FIG. 4 is a diagram showing the configuration of the server 300. As shown in FIG. The server 300 includes an image acquisition unit 300A (image acquisition unit), a synthesis parameter calculation unit 300B (synthesis parameter calculation unit), an image synthesis unit 300C, a damage detection unit 300D (damage detection unit), a detection result synthesis unit 300E (detection result synthesis unit ), and a corresponding point designating section 300F (corresponding point designating section). The server 300 further includes a damage mapping section 300G, a detection result output section 300H (detection result output section), a display control section 300I (display control section), a communication control section 300J, and a ROM 300K (non-temporary recording medium). The server 300 is connected to the client 200 via the network NW, acquires a photographed image (the photographed image 220A in FIG. 3) from the client 200, detects damage, synthesizes the detection results, and the like.

The image acquisition unit 300A receives a captured image (captured image 220A in FIG. 3) from the client 200 . The compositing parameter calculator 300B calculates compositing parameters for compositing captured images based on corresponding points between the images. The image synthesizing unit 300C synthesizes the captured images based on the synthesizing parameters. The damage detection unit 300D detects (extracts and measures) damage (cracks, delamination, corrosion, etc.) of the subject (bridge) from the captured image. The detection result synthesizing unit 300E synthesizes damage detection results (detection results) for the captured image based on the synthesis parameters calculated by the synthesis parameter calculating unit 300B. The corresponding point designation unit 300F designates corresponding points for one image group among the displayed image groups and another image group among the image groups based on the instruction input by the user. The damage mapping unit 300G maps information indicating damage to the composite image. The detection result output unit 300</b>H outputs damage detection results, synthesized detection results, identification information, synthesized images, damage mapping images, and the like to the client 200 . The display control unit 300I causes the monitor 232 (display device) to display the captured image, the detection result, and the like. The communication control unit 300J transmits and receives images and information to and from the client 200 via the network NW. The ROM 300K (non-temporary recording medium) records computer-readable codes of various programs for operating the damage diagram creation system 10, such as a damage diagram creation program for executing the damage diagram creation method according to the present invention. be done. The server 300 includes a recording device (for example, a magneto-optical recording medium such as a hard disk) (not shown) in addition to the above-described units. results, etc.). The recorded images and the like can be transmitted to the client 200 upon request.

The function of each unit of the server 300 described above can be realized using various processors. Various processors include, for example, a CPU (Central Processing Unit), which is a general-purpose processor that executes software (programs) to realize various functions. The various processors described above also include a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacturing, such as an FPGA (Field Programmable Gate Array). Furthermore, a dedicated electric circuit, which is a processor having a circuit configuration specially designed for executing specific processing such as ASIC (Application Specific Integrated Circuit), is also included in the various processors described above.

The function of each unit may be realized by one processor, or may be realized by combining a plurality of processors. Also, a plurality of functions may be realized by one processor. As an example of configuring a plurality of functions in one processor, first, as represented by computers such as clients and servers, one processor is configured by combining one or more CPUs and software, and this processor is implemented as multiple functions. Secondly, as typified by System On Chip (SoC), there is a form of using a processor that implements the functions of the entire system with a single IC (Integrated Circuit) chip. In this way, various functions are configured using one or more of the various processors described above as a hardware structure. Further, the hardware structure of these various processors is, more specifically, an electric circuit combining circuit elements such as semiconductor elements.

When the processor or electric circuit described above executes software (program), the processor (computer) readable code of the software to be executed (including the program for executing the damage diagram creation method according to the present invention) is stored in the ROM 300K ( (see FIG. 4), etc.), and the processor refers to the software. Codes may be recorded in non-temporary recording media such as various magneto-optical recording devices and semiconductor memories instead of the ROM 300K. During processing using software, for example, a RAM (Random Access Memory) is used as a temporary storage area, and data stored in, for example, an EEPROM (Electronically Erasable and Programmable Read Only Memory) is referred to. In FIG. 4, illustration of devices such as RAM and EEPROM is omitted.

Each function of the client 200 described above can also be realized by various processors, electrical circuits, and software, like the server 300 .

<Image processing procedure>
Image processing by the damage diagram creation system 10 will be described. 5 and 6 are flow charts showing the procedure of image processing (including each process of the damage diagram creation method according to the present invention). In these figures, steps S100 to S112 show processing in client 200, and steps S200 to S236 show processing in server 300. FIG.

photograph
In the procedure shown in FIGS. 5 and 6, the digital camera 100 divides and photographs the bridge 1 (building) to obtain a plurality of photographed images (step S100).

In this embodiment, a case of photographing the floor slab 6 will be described. FIG. 7 is a diagram showing an example of the photographing procedure of the floor slab 6. As shown in FIG. In FIG. 7, an area A including a coffer GO defined by a main girder (a member extending in the x direction) and a horizontal girder (a member extending in the y direction) is photographed as a unit, and the photographing area is taken in the y direction and the x direction. It shows a state in which photographing is repeated while being sequentially moved (in the direction of the arrow). As long as an image of the entire imaging range can be acquired, the imaging may be performed by other procedures. In FIG. 7, the extending direction of the bridge (floor slab) is x, the direction perpendicular to x in the plane of the floor slab is y, the direction perpendicular to the floor slab (vertically downward direction) is z, and (x, y, z) constitute the coordinates.

FIG. 8 is a diagram showing an example of a photographing procedure in one crate GO. In the example of FIG. 8, the image is taken while moving from the area A1 on the +x side end of the partition GO to the area Ai on the -x direction end, then returning to the +x side end again and starting from the area Aj. A total of n images (n is an integer equal to or greater than 2) are taken up to the area An at the end in the -x direction. A pattern different from this (for example, the order of areas A1 to Ai to An to Aj) may be used. When shooting, the shooting position may be moved each time an image is shot and an image always facing the front may be shot, or a plurality of images may be shot while changing the shooting direction at one shooting position ( In this case, images taken from an oblique direction will be included). In addition, in photographing, by appropriately setting the photographing position and photographing direction, it is possible to generate a sufficient overlap (for example, about 30%) in adjacent images, and to easily detect and set corresponding points with high accuracy. preferable.

FIG. 9 is an example of captured images, and shows how 10 images i1 to i10 are captured while ensuring overlap. Also, FIG. 10 is a diagram showing the images i1 to i10 individually. 9 and 10 show the frame F of the coffer GO (a rectangle defined by the main girder and the horizontal girder), and omit the illustration of damage to other members and floorboards.

The client 200 captures the plurality of captured images via the digital camera 100 (imaging optical system 110, wireless communication unit 130, antenna 132) and processing unit 210 (communication control unit 210D, image input unit 210A, antenna 212). Input (step S102).

<Storing images and information>
In the damage drawing creation system 10, a folder is created in the storage unit 220 of the client 200 to store the photographed images. FIG. 11 is a diagram showing an example of the folder structure. In the example of FIG. 11, a main folder MF is created for the entire bridge, and subfolders SF1 and SF2 are created in this main folder for each imaging area (inspection area 1A, inspection area 1B). In the subfolder for each photographing area, subfolders SS1 to SS5 are further created for each girder GO defined by the main girder and the horizontal girder to store the photographed images. FIG. 12 shows a state in which 10 photographed images are stored for the case with the case number A001 (subfolder SS1).

The folder structures shown in FIGS. 11 and 12 can be created by the file management unit 210B according to the operation of the operation unit 240 (keyboard 242, mouse 244). The folder structure may be different from the examples shown in FIGS. 11 and 12. For example, subfolders may be created for each member number. As will be described in detail later, the damage diagram creation system 10 synthesizes the damage detection results (detection results) for each folder (subfolders are also included in "folders"), and stores the synthesized detection results in the same folder as the captured image. Store.

<Image acquisition>
The operation unit 240 of the client 200 receives an instruction operation for damage detection and synthesis via the keyboard 242 and/or the mouse 244 (step S104), and the server 300 (image acquisition unit 300A) acquires a captured image in response to this operation. (Step S200). The image acquisition unit 300A acquires images stored in the same folder in the client 200 (storage unit 220) as images belonging to the same group. For example, ten captured images stored in the subfolder SS1 shown in FIGS. 11 and 12 are acquired as images belonging to the same group.

<Calculation of synthetic parameters>
After the captured images are acquired in step S200, the server 300 (synthesis parameter calculation unit 300B) calculates synthesis parameters for synthesizing a plurality of images based on corresponding points between the images (step S202). For example, a projective transformation matrix of another image with respect to the reference image among the captured images can be calculated as a synthesis parameter. Although the flow chart of FIG. 5 describes an example in which the synthetic parameter calculation in step S202 is performed first, the damage detection in step S204 may be performed first, or steps S202 and S204 may be performed in parallel. good.

<Damage detection>
The server 300 (damage detection unit 300D) detects (extracts and measures) damage from the captured image (step S204). Damage can be classified into delamination, water leakage, cracks, rust, etc., but the specific types of damage to be detected are set according to conditions such as the type and characteristics of the building (object) and the purpose of the inspection. you can The items to be detected include position, size, direction, range, shape, etc. The items to be detected also depend on the type of damage, the type of building, the characteristics of the building, the purpose of the inspection, and other conditions. can be set. In the damage detection, the damage detection unit 300D vectorizes the detection result (detection result), a line segment having a start point and an end point or a set thereof (in the case of linear damage such as a crack), or such a line segment It is represented by a figure such as a polygon formed by (in the case of extensive damage such as peeling and corrosion).

Damage can be detected by various methods depending on the classification. For cracks, for example, the crack detection method described in Japanese Patent No. 4006007 can be used. The method is a crack detection method comprising the steps of creating a wavelet image and determining a crack region based on the wavelet image. In the step of creating a wavelet image, calculating wavelet coefficients corresponding to two densities to be compared, and calculating respective wavelet coefficients when the two densities are changed respectively to create a wavelet coefficient table, Wavelet transformation is performed on the input image of the concrete surface, which is the target of crack detection. In the step of determining a crack region, the wavelet coefficients corresponding to the average density of neighboring pixels in the local region and the density of the pixel of interest are used as thresholds in the wavelet coefficient table, and the wavelet coefficients of the pixel of interest are compared with the threshold. Cracked and non-cracked areas are determined.

Further, as a method for detecting rust and peeling, for example, a processing method for a coating film inspection system for steel bridges described in Japanese Patent Publication No. 2010-538258 can be used. In this processing method, rust and flaking are detected using color information, image processing, water sheds, and Parzen windows from image files of steel bridge coatings taken.

In the damage diagram creation system 10 according to the first embodiment, damage is detected from the photographed images before synthesis in this way. Therefore, damage detection performance is not degraded due to deterioration of image quality in the overlapped area of the images, so damage can be detected with high accuracy based on a plurality of images obtained by separately photographing the subject. As will be described later, the damage detection result is synthesized using the synthesis parameters of the images.

<Judgment on whether synthesis is possible>
The server 300 (synthesis parameter calculation unit 300B) determines whether or not all the captured images can be synthesized into one based on the synthesis parameter calculated in step S202 (step S206). Whether or not synthesis is possible depends on the number of corresponding points, whether or not the reliability of the corresponding points is sufficient (whether or not the corresponding points are characteristic points), and whether or not the projective transformation matrix can be calculated from the corresponding points. can be determined based on At this time, the combination of corresponding points may be changed by a RANSAC (RANdom SAmple Consensus) algorithm or the like, and the projective transformation matrix and its evaluation value may be repeatedly calculated and determined. If all the images can be combined into one image (YES in step S206), the process proceeds to step S222 to combine the detection results (detection results). If all the images cannot be combined into one image (NO in step S206), steps S208 to S220 are performed as described below, and then the process proceeds to step S222. Steps S208 to S220 are processing when all images cannot be synthesized (automatic synthesis) into one image. The detection results are combined for each image group. On the other hand, between image groups that cannot be combined, as described below, corresponding points are specified based on user operations, combining parameters are calculated, and detection results are combined based on the calculated combining parameters. For example, in the case of image groups G1 and G2 (see FIGS. 15 to 18), which will be described later, the detection results of the images constituting the image groups G1 and G2 are respectively combined, and between the image groups G1 and G2, based on the user's operation. Based on the synthesis parameters calculated in the above, the detection results synthesized for the image groups G1 and G2 are synthesized into one (see FIGS. 19 to 21).

<Image classification>
If it is determined in step S206 that "all the captured images cannot be combined into one image", the combining parameter calculation unit 300B divides the captured images into groups of images that can be combined (step S208), The image arrangement is determined (combining parameters are calculated) based on the corresponding points (step S210). Once the image layout is determined, detection results can be synthesized based on the layout.

<Determination of image layout>
FIG. 13 is a flow chart showing the details of the image layout determination process in step S210 of FIG. The synthesis parameter calculation unit 300B sets a reference image that serves as a reference for projective transformation from among the plurality of captured images (step S210A). The reference image can be set (selected) according to the characteristics of the image such as the degree of positivity and sharpness, but an image in a specific photographing order (for example, the first photographed image) may be used as the reference image. In the examples of FIGS. 9 and 10, as shown in part (a) of FIG. 14, the image i1 can be set as the reference image for the images i1 and i2.

After the reference image is set, the synthesizing parameter calculation unit 300B calculates a projective transformation matrix of an image other than the reference image with respect to the reference image based on corresponding points between the images (step S210B). In the examples of FIGS. 9 and 10, as shown in part (a) of FIG. 14, an image i2 (an image other than the reference image) is projected onto the same plane as the image i1 (reference image), and the corresponding points are matched. Calculate the projective transformation matrix. When the projective transformation matrix of image i2 with respect to image i1 (reference image) is calculated, as shown in part (b) of FIG. Compute the matrix. In this way, while changing the reference image, the projective transformation matrix is calculated for all the images in the image group (until YES in step S210C).

After calculating the projective transformation matrix for all images, the synthesis parameter calculating unit 300B moves, rotates, enlarges or reduces, transforms, etc. each image based on the calculated projective transformation matrix, and arranges each image in the image group. is determined (step S210D). In the following description, images i1 to i4 and i6 to i9 constitute a synthesizable image group G1, and images i5 and i10 constitute a synthesizable image group G2. In the determination of the image layout described above, each image is moved, rotated, deformed, etc., using a projective transformation matrix. etc. is not an accurate representation.

The image layout determined in step S210D may be an image layout in which the overlapping areas of the images overlap (see FIG. 15) or an image layout in which the images do not overlap (see FIG. 16). In the case of image arrangement in which the images do not overlap each other, the images are spaced apart in the x and y directions as shown in FIG. can be arranged.

<Image display>
When the image layout is determined in step S210 (steps S210A to S210D), server 300 (display control unit 300I, communication control unit 300J) instructs client 200 to display a group of images that can be combined (step S212). The instruction to the client 200 includes the image to be displayed, information on the arrangement of the image, and information obtained by vectorizing the damage detection results in step S204. The client 200 (display control unit 210C) superimposes the information obtained by vectorizing the damage detection result on the image in accordance with the display instruction, and displays it on the monitor 232 for each synthesizable image group (step S106). In the above example, the display control unit 210C displays the image groups G1 and G2 in an image arrangement as shown in FIG. 15 or FIG. FIG. 17 shows how the cracks in the images i4, i5, i9, and i10 in the image arrangement of FIG. 15 are vectorized and superimposed. During display, the display control unit 300I and/or the display control unit 210C may surround the image groups G1 and G2 with a frame, display each image group in a different color, or display the number of the image group. Processing may be applied to facilitate identification of groups of images.

When displaying in step S106, there are cases where the arrangement between the image groups is inappropriate. For example, as shown in FIG. 18, an image group G2 to be arranged below the image group G1 (-x direction) may be arranged in the horizontal direction of the image group G1. Therefore, the server 300 (synthesis parameter calculation unit 300B) determines whether or not to change the arrangement of the image group (step S214). The image groups G1 and G2 are displayed again in the arrangement of . The determination in step S214 can be made based on the user's instruction input (for example, movement of the image group G2 via the keyboard 242 and/or the mouse 244, that is, operation to change the relative arrangement). In the example of FIG. 18, the synthesis parameter calculation unit 300B and the display control unit 300I move the image group G2 below the image group G1 (move in the direction of the arrow) based on the user's operation (for example, dragging with the mouse 244). and can be displayed as shown in FIG.

If the image groups are displayed in an inappropriate relative arrangement, it may take time to specify the corresponding points. and can be done easily.

<Specification of corresponding points>
When the arrangement of the image groups is determined by the processing up to step S214, the server 300 (corresponding point designation unit 300F) designates corresponding points for one image group and the other image group among the displayed image groups ( step S216). For example, when the image groups G1 and G2 are arranged and displayed as shown in FIG. 15, a point P1a is displayed in response to a click of the mouse 244 in the image group G1 or the like (corresponding point designation operation in step S108), as shown in FIG. is specified, and a point P1b corresponding to the point P1a in the image group G2 is specified. As corresponding points, it is possible to designate, for example, characteristic points such as start points, end points, branch points of cracks, and/or end portions, side portions, joint portions, etc. of members that are determined to be "same". At this time, the corresponding point specifying unit 300F and the display control unit 300I connect the specified points P1a and P1b with a straight line to identify and display the correspondence (see FIG. 19), thereby indicating that the specified points correspond to each other. can be easily grasped. Similarly, points P2a and P2b, points P3a and P3b, points P4a and P4b, points P5a and P5b, and points P6a and P6b are also designated.

Note that FIG. 19 shows an example in which six corresponding points are specified for each of the image groups G1 and G2, but the number of corresponding points to be specified is not particularly limited. Similarly, when the image groups G1 and G2 are arranged and displayed as shown in FIG. 16, corresponding points can be similarly specified between the images i4 and i5 and the images i9 and i10.

As described above, in the damage diagram creation system 10 according to the first embodiment, since image groups (image groups G1 and G2) that can be synthesized are displayed for each image group, which image group is (automatically) synthesized It is possible to easily grasp whether it was possible or not. In addition, since it is sufficient to specify corresponding points for the group of images (image group G1 and image group G2) that could not be synthesized, there is no need to specify corresponding points for all images. Calculation of point-based synthesis parameters can be done quickly and easily.

If the synthesis parameters cannot be calculated with high accuracy for the corresponding points specified as described above, the server 300 (the synthesis parameter calculation unit 300B, the corresponding point designation unit 300F, the display control unit 300I, etc.) and the client 200 (the display control unit 210C, etc.) , a warning message may be displayed on the monitor 232 to prompt the user to perform the corresponding point designation operation again.

<Determination of Image Arrangement Based on Designated Corresponding Points>
After the corresponding points are specified in step S216, the server 300 (synthesis parameter calculation unit 300B) calculates synthesis parameters for each image group that can be synthesized based on the specified corresponding points (step S218). In the example of FIG. 19, the synthesis parameter calculation unit 300B calculates the projective transformation matrix of the image group G2 with the image group G1 as the reference (or the image group G2 with the image group G2 as the reference) based on the corresponding points P1a to P6b Projective transformation matrix of G1) is calculated. The image synthesis unit 300C and synthesis parameter calculation unit 300B move, rotate, transform, etc. the images (images i5 and i10) that make up the image group G2 using the projective transformation matrix thus calculated, and determine the image layout. (Step S220). The determination of the image layout in step S220 can be performed in the same procedure as in step S210.

<Synthesis of detection results>
The server 300 (detection result synthesizing unit 300E) synthesizes the detection result (detection result) based on the synthetic parameters (projective transformation matrix) calculated in steps S202 and S220 (step S222). For example, assuming that different parts (partial overlap) of damage vectors V1 and V2 are detected in images i1 and i2 as shown in parts (a) and (b) of FIG. Assume that the end points are points P7 to P12. Parts (a) and (b) of FIG. 21 are tables showing start points and end points of damage vectors V1 and V2 corresponding to parts (a) and (b) of FIG. 20, respectively. In this case, as shown in part (c) of FIG. 20 (image i2 is synthesized by moving and rotating image i2 using a projective transformation matrix), the damage vector V1 has the starting point and the ending point at points P7 and P8, respectively. Thus, the damage vector V2 has a starting point and an ending point at points P8 and P12, respectively. Part (c) of FIG. 21 corresponds to part (c) of FIG. 20 and shows the start and end points of damage vectors V1 and V2 after synthesis.

<Synthesis of Detection Results in Overlapping Areas of Images>
When acquiring images such that the photographing ranges partially overlap as described above, in areas where multiple images overlap, the detection results that should normally be combined into one become multiple due to misalignment of the images. , the synthesis accuracy may deteriorate. Therefore, in the damage diagram creation system 10, in a region where a plurality of images overlap, one of the plurality of overlapping images is selected and the detection results can be synthesized, so that the detection results can be synthesized with high accuracy. FIG. 22 shows how such synthesis is performed. In the example of FIG. 22, since the images i1 and i2 overlap in the area OL, the image i2 with the smaller value of the synthesis parameter is selected in this area OL, and synthesized using the detection result for the image i2 ( (see FIG. 22(b)).

As a result, the deformation of the damage and the displacement of the damage can be suppressed, and the accuracy of the damage detection result and its data calculation is improved.

In the case of the above-mentioned projective transformation, the value of the synthesis parameter is a value representing the degree of projective transformation (deformation attitude due to projective transformation). parameter value is increased.

A specific description will be given with reference to FIG. Consider a case where two original images i1 and i2 in FIG. 29(a) are synthesized. For i1, a projective transformation matrix is calculated using i0 (not shown) as a reference image by the above-described method, and projective transformation is performed as i1 in FIG. 29(b). At this time, specific coordinates P1a, P2a, P3a, and P4a in i1 are moved to P1a', P2a', P3a', and P4a' by projective transformation. Next, corresponding points P1a to P4a and P1b to P4b of each image are specified (Pxa and Pxb are corresponding points) in order to calculate the projective transformation matrix of i2 using i1 after projective transformation as a reference image. A projective transformation matrix of i2 is calculated based on these corresponding points, and projective transformation is performed as i2 in FIG. 29(b). At this time, P1b, P2b, P3b, and P4b in i2 move to P1b', P2b', P3b', and P4b' by projective transformation. Then, the image layout is determined so that the corresponding points P1a' to P4a' of i1 and P1b' to P4b' of i2 match each other.

Here, how much P1a to P4a of i1 have moved due to the projective transformation is calculated. Specifically, the distance (|P1a-P1a'|) between P1a and P1a' is calculated, this is repeated for P2a to P4a, and finally the sum is obtained. Let this be the synthesis parameter of i1. Similarly for i2, the distance between P1b and P1b' (|P1b-P1b'|) is calculated, this is repeated for P2b to P4b, and finally the sum is taken. Let this be the synthesis parameter of i2. Using the compositing parameters calculated in this way, an image with a small compositing parameter (i2 in the example of FIG. 29(c)) is selected and composited in the overlapping region of i1 and i2.

As described above, the synthesis parameter represents the amount of coordinate movement due to projective transformation, so the larger the degree of transformation (the degree of deformation), the larger the value of the synthesis parameter. In this embodiment, the synthesis parameter is defined as the sum of the movement distances of the coordinates, but other calculation methods may be used as long as the parameter represents the degree of deformation. For example, there is a method of calculating the degree of similarity between a figure formed by connecting P1a to P4a and a figure formed by connecting P1a' to P4a'. In this case, by normalizing the sizes of the figures to be compared in advance, it is possible to ignore the difference in the size of the figures and focus only on the degree of deformation to calculate the synthesis parameter. In this case, the overlap region is selected assuming that the image with the higher shape similarity has a smaller degree of deformation (smaller synthesis parameter).

Synthesis of the detection results described above is performed for images (a plurality of images divided into groups) stored in the same folder. In the example shown in FIG. 12, detection results are combined for ten images stored in the subfolder SS1 (detection results are combined for each group).

<Synthesis of images>
The server 300 (image synthesizing unit 300C) synthesizes images based on the synthesizing parameters (projective transformation matrix) calculated in steps S202 and S218 (step S224). FIG. 23 shows the synthesized image G3. FIG. 24 shows an image G3a obtained by selecting and synthesizing one image in an area where images overlap, as in FIG. Since a damage diagram can be created by synthesizing the detection results, the synthesizing of images may be omitted.

<Orientation Correction after Synthesis>
In the damage diagram creation system 10, as described above, the projective transformation matrix of the other images with respect to the reference image is calculated to determine the image arrangement. A region that should be rectangular may not be rectangular. For example, the frame F between the cells may be trapezoidal in the synthesized image. In this case, the server 300 (synthesis parameter calculator 300B, image synthesizer 300C, etc.) generates a rectangle based on the user's operation via the keyboard 242 and/or the mouse 244 (for example, points at the four corners of the frame F). ) and let these four points form a rectangle by projective transformation. As a result, it is possible to obtain an image in which the subject faces directly (directly facing image) even after the image synthesis.

<Mapping of measurement results>
The server 300 (damage mapping unit 300G) may map the damage detection result to the composite image. Mapping can be performed, for example, by displaying characters, graphics, symbols, etc. associated with the detection result in the composite image. Characters, graphics, symbols, etc. to be displayed can be selected by operation via the operation unit 240 (keyboard 242 and/or mouse 244), and the server 300 (damage mapping unit 300G, display control unit 300I, etc.) according to the selection. And the client 200 (display control unit 210C) causes the monitor 232 to display the mapped image. Characters, figures, symbols, etc. may be simplified or emphasized actual damage, and may be displayed in different modes according to the type, size, etc. of the damage. An image in which the measurement result is mapped is stored in the storage unit 220 (damage mapping image 220D in FIG. 3) and displayed on the monitor 232 under the control of the display control unit 210C. Damage information may be input to the damage mapping image.

Such mapping of measurement results may be performed on drawing data (for example, CAD data, CAD: Computer-Aided Design) including diagrammatic information indicating the shape of the bridge 1 . At this time, if the coordinate system defining the CAD data differs from the coordinate system shown in FIGS. 23, 24, etc., coordinate conversion (movement, rotation, mirroring, etc.) is performed according to the relationship between the coordinate systems. Such conversion can be performed by server 300 (damage mapper 300G).

<Result display>
Server 300 (detection result output unit 300H, display control unit 300I, communication control unit 300J, etc.) instructs client 200 to display the detection result (step S226). ) displays the detection result on the monitor 232 (step S110). The detection results can be displayed using characters, numbers, symbols, etc. The detection results for each captured image may be displayed, or a combined detection result may be displayed (see FIGS. 20 and 21). In addition, together with the detection result or instead of the detection result, a photographed image, a synthesized image, a damage mapping image, or the like may be displayed. Information (see FIGS. 20 and 21) obtained by vectorizing the detection result may be superimposed on the image and displayed. The display control section 210</b>C can select the content and mode to be displayed on the monitor 232 according to the operation of the operation section 240 . The display control unit 210C measures the time after the result is displayed, and determines whether or not there is an output instruction after the result is displayed. If the display time is long without an output instruction, or if the screen transitions to another screen without an output instruction, there is a possibility that fraudulent copying such as visual copying has been performed. Judgment can detect such fraud. When fraud is detected, countermeasures such as stopping the display can be taken.

<Result output>
The server 300 (detection result output unit 300H, etc.) determines whether or not there is an output instruction operation (for example, an output instruction operation via the operation unit 240) for the detection result displayed in step S110 (step S228). Only when there is an output instruction operation (YES in step S228), the process advances to step S230 to instruct the client 200 to output the detection result (detection result for each image and synthesized detection result), and the client 200 (file The management unit 210B) outputs the detection result according to the output instruction (step S112). In the example of FIG. 12, the detection results for the images stored in the subfolder SS1 are stored in the same subfolder SS1 in which the images are stored (detection results are output in association with groups; see FIG. 25). The detection result may be output in the same format as drawing data (for example, CAD data) including diagrammatic information indicating the shape of the bridge 1 (subject). Also, the detection result may be printed by a printer (not shown).

As described above, in the first embodiment, the detection result is stored in the same folder as the folder in which the image is stored. Easy to manage and use. The output of the detection result is performed only when there is an output operation instruction (when YES in step S228), and when there is no output operation instruction, identification information is added to the image (step S232) The assigned identification information is notified to the client 200 and stored in the same folder as the folder in which the image is stored (subfolder SS1 in the examples of FIGS. 12 and 25).

After the detection result or identification information is output, server 300 determines whether or not the processing for all folders has been completed (step S234). If the determination is affirmative, the server 300 notifies the end to the client 200 in step S236 (step S236) and ends the process. If the processing for all folders has not been completed, the process returns to step S202 and steps S202 to S234 are repeated for other folders.

As described above, according to the damage diagram creation system 10 according to the first embodiment, damage can be detected with high accuracy based on a plurality of images obtained by separately photographing the subject.

<Second embodiment>
In the above-described first embodiment, the damage diagram creation system 10 including the server 300 and the client 200 has been described, but in the second embodiment, the damage diagram creation apparatus 20 will be described. FIG. 26 is a diagram showing the configuration of the damage diagram creation device 20. As shown in FIG. The damage diagram creation device 20 is composed of a digital camera 100 and a device body 500 . Since the configuration of the digital camera 100 is the same as that of the digital camera 100 in the first embodiment, the same reference numerals are given and detailed description thereof will be omitted. Note that the digital camera 100 may be configured integrally with the device body 500 .

<Configuration of damage diagram creation device>
The damage diagram creation system 10 according to the first embodiment includes a server 300 and a client 200, and main processing such as damage detection and synthesis is performed by the server 300. However, the damage diagram creation apparatus 20 according to the second embodiment Then, the processing unit 510 of the apparatus main body 500 performs the processing. Specifically, the processing unit 510 has the functions of the client 200 shown in FIG. 2 and the functions of the server 300 shown in FIG. The storage unit 520 stores the same information (see FIG. 3) as the storage unit 220 according to the first embodiment. The configuration and function of the operation unit 540 (keyboard 542, mouse 544) are the same as those of the operation unit 240 (keyboard 242, mouse 244) according to the first embodiment. Also, the configuration and function of the display unit 530 (monitor 532) are the same as those of the display unit 230 (monitor 232) according to the first embodiment. In the damage diagram creating apparatus 20, a device (information terminal) such as a personal computer, a tablet terminal, and a smart phone that inputs an image and performs processing such as damage detection and synthesis can be used as the device main body 500.

<Processing of damage diagram creation method>
The processing in the damage diagram creating apparatus 20 (processing of the damage diagram creating method according to the present invention) is the same as the flow charts of FIGS. For example, multiple images captured by splitting the subject are input, and the synthesis parameters (projective transformation matrix) for synthesizing the multiple images are calculated based on the corresponding points between the images to form multiple images. Damage to a subject is detected from images, and detection results for a plurality of images are synthesized based on synthesis parameters. Such processing is performed by the processing unit 510 of the device main body 500 . In the first embodiment, communication is performed between the client 200 and the server 300 , but in the damage diagram creation device 20 , communication is performed inside the device body 500 .

In the damage diagram creation apparatus 20 according to the second embodiment, as in the damage diagram creation system 10 according to the first embodiment, damage is detected from the photographed images before synthesis. As for the image of the overlapping area, an image with a small synthesis parameter value is used as in the first embodiment. As a result, the deformation and displacement of the damage can be suppressed, and the accuracy of the damage detection result and its data calculation is improved.

Therefore, damage detection performance is not degraded due to deterioration of image quality in the overlapped area of the images, so damage can be detected with high accuracy based on a plurality of images obtained by separately photographing the subject.

In both the first embodiment and the second embodiment described above, images to be used may be selected according to the positional relationship between the overlapping area and damage (cracks, etc.). For example, as shown in (a) of FIG. 27 , there is a case where damage exists in the overlapping region, the damage is located in the image i2 from the inside of the overlapping region to the outside of the region, and the damage is not located in the image i1. be. In such a case, as shown in FIG. 27(b), one image i2 may be used as the image of the overlapping area (irrespective of the value of the synthesis parameter). In other words, in one image i2, the damage protrudes outside the overlapping region, and in the other image i1, if the damage is contained (does not protrude) within the overlapping region, (combining parameter One image i2 may be used as the image of the overlap region (regardless of the value). This ensures the continuity of damage and improves the accuracy of damage detection results and data calculation thereof. In addition, as shown in (a) of FIG. 28, when the damage is positioned across the inside and outside of the overlap region in both the image i2 and the image i1 of the other, as shown in (b) of FIG. It is preferable to use the image i2 with a larger number of damages that span the inside and outside of the region in the overlapping region. This reduces the number of lesions for which continuity is lost and improves the accuracy of the lesion detection results and their data calculations.

Also, for an overlapping area in which there is no damage among the overlapping areas, an image with good image quality may be used as the image of the overlapping area regardless of the value of the synthesis parameter. At this time, whether the image quality is good or bad can be judged from image quality judgment information such as the appropriateness of brightness, the appropriateness of saturation, and the degree of focusing. This not only improves the accuracy of damage detection results and data calculation, but also improves the image quality of the composite image, making it possible to provide better damage diagrams to the user. It should be noted that the quality of the image quality is not determined by only one image quality judgment information (one of judgment information such as the appropriateness of brightness, the regular accuracy of saturation, and the degree of focus), but two It is preferable to obtain a judgment result by comprehensively judging based on the above judgment information. This makes it possible to provide the user with a better damage diagram. In this way, for overlapping areas that do not correspond to the above case, images with small synthesis parameter values are selected and synthesized, and for overlapping areas that apply to the above case, images are selected and synthesized under the above conditions. By doing so, it is possible to improve the accuracy of damage detection results and data calculation thereof, and to obtain the various effects described above.

<Third Embodiment>
A third embodiment will be described with respect to the processing in the damage diagram creation apparatuses 10 and 20 described above.

Although the configuration of the damage diagram creation system 10 in the first embodiment will be described here, it can also be applied to the configuration of the damage diagram creation device 20 in the second embodiment. Also, the processing in the damage diagram creation apparatus is the same as that in the flow charts of FIGS. 5 and 6, but the image arrangement determination processing in steps S210 and S220 is different.

Specifically, image layout determination processing in the third embodiment will be described with reference to FIGS. Here, as an example, a method of creating a damage diagram from a group of images of an arch-shaped bridge photographed from below as shown in FIG. 31(a) will be described.

<Determination of image layout>
FIG. 30 is a flow chart showing the details of the image layout determination process in steps S210 and S220 of FIG. The synthesis parameter calculation unit 300B sets a reference image that serves as a reference for projective transformation from among the plurality of captured images (step S210E). The reference image can be set (selected) according to the characteristics of the image such as the degree of positivity and sharpness, but an image in a specific photographing order (for example, the first photographed image) may be used as the reference image. In the example of FIG. 31, the image i1 can be set as the reference image for the images i1, i2, i3, .

After the reference image is set, the synthesizing parameter calculator 300B calculates the projective transformation matrix of the image adjacent to the reference image with respect to the reference image based on the corresponding points between the images (step S210F). In the example of FIG. 31, as shown in FIG. 31(b), the image i2 (image adjacent to the reference image) is projected onto the same plane as the image i1 (reference image), and the projective transformation matrix for matching the corresponding points is Calculate

After calculating the projective transformation matrix for the image i2, the synthesis parameter calculation unit 300B calculates the synthesis parameter for i2 based on the calculated projective transformation matrix. Here, the synthesis parameter is a value that represents the degree of projective transformation (the degree of deformation due to projective transformation). becomes larger. Specifically, as described in the first embodiment, it can be calculated from the amount of movement of the coordinates of each corresponding point by projective transformation. In the first embodiment, the synthesis parameter is calculated by focusing on the overlapping region of i1 and i2. A synthesis parameter may be calculated from the amount of movement of the coordinates of the four vertices of the image i2.

After calculating the synthesis parameters for the image i2, the synthesis parameter calculator 300B determines whether or not to permit the projective transformation of the image i2 based on the calculated synthesis parameters (step S210H). Here, if the calculated synthesis parameter is equal to or less than a predetermined value, the projective transformation is permitted, and if it is greater than the predetermined value, the projective transformation is not permitted.

When projective transformation is permitted, the synthesis parameter calculation unit 300B performs projective transformation on image i2 based on the calculated projective transformation matrix (step S210I), and arranges it side by side with image i1 (step S210J). At this time, the image arrangement may be such that the overlapping areas of the images overlap, or the image arrangement may be such that the images do not overlap each other.

When the projective transformation is not permitted, the synthesis parameter calculation unit 300B arranges the image i2 side by side with the image i1 without performing the projective transformation on the image i2 (step S210J). In this case, the image layout is such that areas where the images overlap each other do not overlap.

After that, the image i2 is set as the reference image, and the above-described processing (steps S210E to S210J) is similarly performed on the image i3 adjacent to the image i2. In this way, while changing the reference image, the process is repeated for all the images in the image group (until YES in step S210K).

In the example of FIG. 31, since the bridge is arch-shaped, as the projective transformation is repeated with the image i1 as the first reference image, the degree of deformation due to the projective transformation gradually increases (the same plane as the image i1). ). Therefore, as shown in FIG. 31(b), images i2 and i3 can be projectively transformed and combined without any problem, but images i4 and subsequent images are not suitable as damage diagrams because the degree of deformation increases. Therefore, by setting an appropriate value in step S210H of the third embodiment, projective transformation of image i4 can be prohibited (FIG. 31(c)). In this case, the image i4 cannot be synthesized with the image i3, but each image can maintain the image quality (shape) suitable for the damage diagram.

As shown in FIG. 31(c), if the projective transformation is not permitted in step S210H, the display is displayed in such a manner that the user can recognize that effect, such as by inserting a dotted line between the images i3 and i4. good too.

Further, when determining whether or not to permit the projective transformation in step S210H, the determination may be made based on the positivity of the captured image. For example, if the photographed image faces the object and is deformed in the opposite direction due to the projective transformation, the projective transformation is not permitted. In this case, it may be determined to allow the projective transformation.

As described above, according to the third embodiment, it is possible to create an appropriate damage diagram even for a structure such as an arch-shaped bridge that is not on the same plane.

Although the embodiments of the present invention have been described above, the present invention is not limited to the above aspects, and various modifications are possible without departing from the spirit of the present invention.

200 Client 210 Processing Unit 210A Image Input Unit 220 Storage Unit 220A Captured Image 300 Server 300A Image Acquisition Unit 300B Synthesis Parameter Calculation Unit 300C Image Synthesis Unit 300D Damage Detection Unit 300E Detection Result Synthesis Unit

Claims (9)

a step of inputting a plurality of images acquired by dividing and photographing a subject so that some areas overlap;
calculating synthesis parameters for synthesizing the plurality of images based on corresponding points between the images;
a step of detecting damage to the subject from images constituting the plurality of images;
combining results of the detection for the plurality of images based on the combining parameters;
has
In the synthesizing step, in the overlapping region, one image is selected from among the plurality of overlapping images and synthesized, and the selected one image has a higher value of the synthesizing parameter than the other images. is small. 2. The method according to claim 1, wherein in said synthesizing step, said selected one image has a better judgment result of image quality judgment information than said other image when said overlapped area is free of damage. damage diagram creation method. 3. The damage diagram creation method according to claim 2, wherein the image quality determination information is any one of brightness adequacy, chroma adequacy, and focusing adequacy. 4. The damage diagram creation method according to claim 3, wherein said determination result is determined based on at least two pieces of said determination information. In the synthesizing step, when synthesizing an image in which the damage is contained in the overlapping region and an image in which the damage extends inside and outside the overlapping region, the selected one image is the overlapping region 2. The method of creating a diagram of damage according to claim 1, wherein the image is an image in which the damage straddles the inside and outside. In the synthesizing step, if the images in which the damage extends inside and outside the overlapping region are synthesized, the selected one image is more likely to have damage that extends inside and outside the overlapping region than the other images. 2. The method of creating a damage diagram according to claim 1, wherein the images are a large number of images. an image input unit for inputting a plurality of images acquired by dividing the subject so that some areas overlap;
a synthesis parameter calculation unit that calculates a synthesis parameter for synthesizing the plurality of images based on corresponding points between the images;
a damage detection unit that detects damage to the subject from images constituting the plurality of images;
a detection result synthesizing unit that synthesizes the detection results of the plurality of images based on the synthesis parameter;
has
The detection result synthesizing unit selects and synthesizes one image from among the plurality of overlapping images in the overlapping region, and the selected one image has the synthesis parameter higher than the other images. A damage diagram creation device characterized by having a small value. A damage diagramming system comprising a server and a client,
Said client
An image input unit for inputting a plurality of images acquired by dividing the subject so that some areas overlap,
The server is
an image acquisition unit that acquires the plurality of images from the client;
a synthesis parameter calculation unit that calculates a synthesis parameter for synthesizing the plurality of acquired images based on corresponding points between the images;
a damage detection unit that detects damage to the subject from images constituting the plurality of images;
a detection result synthesizing unit that synthesizes the detection results of the plurality of images based on the synthesis parameter;
a detection result output unit that outputs the detection result to the client;
with
The detection result synthesizing unit selects and synthesizes one image from among the plurality of overlapping images in the overlapping region, and the selected one image has the synthesis parameter higher than the other images. A damage diagram creation system characterized by a small value. 9. A recording medium in which computer-readable code of a program for causing a computer to execute the damage diagram creation method according to any one of claims 1 to 8 is recorded.

Images