JP2021051022A - Building structure diagnosis system - Google Patents

Abstract

To provide a building structure diagnosis system that can increase the efficiency of a diagnosis work about damaged parts such as cracking parts in a building or in a structure.SOLUTION: A server device 30 (edition means 32) extracts an outline shown in an image displayed by display means 23, and specifies a damaged part in the image on the basis of the extracted outline. The server device 30 (diagnosis means 33) marks the specified damaged part and diagnoses the degree of at least the marked damaged part.SELECTED DRAWING: Figure 1

Description

The present invention relates to a building structure diagnostic system.

Against the backdrop of large-scale disasters and the recent boom in renovation, there is an increasing need for diagnostic systems for diagnosing the exterior and interior of buildings and structures.

For example, in Patent Document 1, information indicating a state of cracking, peeling, corrosion, etc. (target equipment damage information) is provided based on a user's operation with respect to an image of equipment to be inspected displayed on a display device. The corresponding system is disclosed.

Japanese Unexamined Patent Publication No. 2018-5661

Patent Document 1 describes that when inputting the position of a crack photographed in an image displayed on an input screen, the position of the crack is traced with a user's finger.
However, if the position of the crack is specified by this method, there is a concern that the wrong position will be registered due to an erroneous operation by the user. In addition, since the exact position cannot be registered without tracing all the crack positions with a finger, there is still room for improvement from the viewpoint of work cost.

The present invention has been made in view of the above problems, and provides a building structure diagnostic system capable of improving the efficiency of diagnostic work for damaged parts (cracks, etc.) generated in buildings and structures. ..

According to the present invention, an acquisition means for acquiring an image of a building or a structure, a display means for displaying the image acquired by the acquisition means, and an editing means for editing the image displayed by the display means. The editing means includes a diagnostic means for diagnosing an edited image edited by the editing means, and the editing means includes a contour extracting means for extracting a contour captured in an image displayed by the display means. Based on the contour extracted by the contour extracting means, the damage identifying means for identifying the damaged portion captured in the image displayed by the display means and the damaged portion identified by the damage identifying means are marked. A building structure diagnostic system is provided which includes a marking means for performing an editing process, and the diagnostic means diagnoses at least the degree of damage to a damaged portion marked by the marking means.

According to the above invention, the editing means automatically identifies and marks the damaged part captured in the image displayed on the display means, and then the degree of damage to the damaged part marked by the diagnostic means. Therefore, it is possible to improve the efficiency of the work of identifying the position of the damaged part, the work of marking, and the work of diagnosing the damaged part.

According to the present invention, there is provided a building structure diagnostic system capable of improving the efficiency of diagnostic work for damaged parts (cracks, etc.) generated in a building or a structure.

It is a system block diagram in embodiment of this invention. It is a figure which shows the specific example of the display screen of a communication terminal. It is a figure which shows the specific example of the display screen of a communication terminal. It is explanatory drawing about the camera icon illustrated in FIG. It is a figure which shows the specific example of the display screen of a communication terminal. It is a figure which shows the specific example of the display screen of a communication terminal. It is a flowchart of a series of processes for identifying a damaged part. It is a schematic diagram which shows the change of the target image by the process of identifying a damaged part. It is a schematic diagram which shows the change of the target image by the process of identifying a damaged part. It is a schematic diagram which shows the change of the target image by the process of identifying a damaged part. It is a figure which shows the image before the editing process which concerns on this invention. It is a figure which shows the image after the editing process which concerns on this invention. It is a schematic diagram which shows the shooting environment of the image shown in FIG.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are designated by the same reference numerals, and the description thereof will be omitted as appropriate.

<About the system configuration of the present invention>
First, the system configuration of the present invention will be described.
FIG. 1 is a system configuration diagram according to an embodiment of the present invention.

The building structure diagnosis system 100 according to the present invention includes a communication terminal 20 and a server device 30.
The communication terminal 20 and the server device 30 are connected to each other so as to be able to communicate with each other via the network 10.

The network 10 is a computer network such as the Internet or a local network (LAN), and connects a plurality of computer devices (in this embodiment, a communication terminal 20 and a server device 30) by communication.

The communication terminal 20 is a computer device having communication means (not shown), and also includes an image capturing means 21, an operation input means 22, and a display means 23.
The image capturing means 21 is a so-called camera function, and is a means for acquiring an image by photographing. However, in the practice of the present invention, the subject of the image captured by the image capturing means 21 needs to be a building or a structure.
The operation input means 22 is a means for accepting a user's operation in order to exert various functions described later.
The display means 23 is a means for displaying an image taken by the image capturing means 21 and displaying a guide, an icon, or the like for prompting the operation of the operation input means 22.

The communication terminal 20 according to the present embodiment is a so-called touch panel device, and assumes that a touch pad that realizes the operation input means 22 and a liquid crystal display device that realizes the display means 23 are integrally configured. As will be described below, the present invention has been implemented according to an embodiment in which these are realized as separate devices (for example, the operation input means 22 is realized as a pointing device, the display means 23 is realized as a liquid crystal display device, and the like). You may.

The server device 30 is a computer device having communication means (not shown), and also includes a storage means 31, an editing means 32, a diagnostic means 33, and an image drawing corresponding means 34.
The storage means 31 is a means for storing an image taken by the image capturing means 21 and a drawing (hereinafter, may be referred to as a building structure drawing) relating to a building or a structure as a subject.
The editing means 32 is a means for editing the image displayed on the display means 23. The editing process by the editing means 32 is based on the user's operation received by the operation input means 22, and will be described later, but other editing processes may be included.
The diagnostic means 33 is a means for diagnosing an image edited by the editing means 32 (hereinafter, may be referred to as an edited image).
The image drawing corresponding means 34 is a means for storing the image taken by the image taking means 21 and the building structure drawing in the storage means 31 in association with each other.

<About the display screen of the communication terminal 20>
Next, a specific example of the display screen displayed on the communication terminal 20 (display means 23) will be described.
2, FIG. 3, FIG. 5, and FIG. 6 are diagrams showing specific examples of display screens of the communication terminal 20.
FIG. 4 is an explanatory diagram relating to the camera icons A1 to A5 illustrated in FIG.

FIG. 2 displays a list of related information (external photograph, address, number of drawings per building or structure, last shooting date and time) related to building structure drawings stored in the server device 30 (storage means 31). This is a display screen of the communication terminal 20.
When the user selects information related to the building or structure to be investigated from the related information displayed on the display screen, the user can display the building structure drawing related to the building or structure on the communication terminal 20. ..

FIG. 3 is a display screen of the communication terminal 20 for displaying the building structure drawing stored in the server device 30 (storage means 31).
The server device 30 corresponds to a camera icon indicating the shooting position and shooting direction of the image uploaded from the communication terminal 20 at an arbitrary position (position specified based on the user's operation) in the displayed building structure drawing. Can be attached and memorized.
The timing of associating the camera icon with the building structure drawing may be any time after the image related to the camera icon is uploaded.

The camera icon consists of a combination of a figure that imitates the shape of the camera and a round figure that indicates the direction (shooting direction) of the figure.
For example, the camera icon A1 indicates that the upper left direction in the building structure drawing was photographed, the camera icon A2 indicates that the downward direction in the building structure drawing was photographed, and the camera icon A3 indicates that the building structure drawing was photographed. The camera icon A4 indicates that the normal direction in the building structure drawing (the ceiling direction in the actual building) was taken, and the camera icon A5 indicates that the building structure drawing was taken. It shows that the photograph was taken in the upper left direction.

After arranging the camera icon on the display screen of FIG. 3 (superimposed on the building structure drawing), the orientation of the camera icon can be changed based on the user's operation.
For example, if you click the round shape of the camera icon (see Fig. 4 (a)) facing the upper right and move the round shape clockwise, the camera icon will turn clockwise as a whole. The orientation is determined when the camera is rotated and the click is released (in FIG. 4B, the orientation is determined to be the lower right orientation).

By double-clicking the camera icon on the display screen of FIG. 3, an image related to the camera icon (an image taken at the shooting position and shooting direction indicated by the camera icon) can be displayed.

5 and 6 are displays for displaying an image related to the camera icon and related information thereof. FIG. 5 is a display screen of the communication terminal 20 when the display screen is slid upward, and FIG. 6 is a display screen of the communication terminal 20 when the display screen is slid downward.

On the display screen shown in FIG. 5, icons related to editing processing and diagnostic processing that can be executed on the image displayed on the display screen are displayed.
The editing process and diagnostic process that can be performed here may include the following.
(B) Based on the user's operation on the operation input means 22, a specific part of the image displayed by the communication terminal 20 is specified by enclosing it in a square area (this square area is small in the following description). Called an area).
(B) Based on the user's operation on the operation input means 22, a free line is drawn with respect to the image displayed by the communication terminal 20.
(C) Based on the user's operation on the operation input means 22, characters are entered in the image displayed by the communication terminal 20.
(D) The image displayed by the communication terminal 20 is rotated or inverted according to the operation for the corresponding icon.
(E) In response to an operation on the corresponding icon, a damaged portion (for example, a cracked portion) of the image displayed by the communication terminal 20 is automatically identified and marked.
(F) According to the operation for the corresponding icon, the degree of damage related to the damaged part marked in (e) is diagnosed by artificial intelligence.
(G) Based on the user's operation on the operation input means 22, the free lines, characters, and markings drawn on the image displayed by the communication terminal 20 are erased.
The editing process of (e) above will be described in detail later.

On the display screen shown in FIG. 6, information on shooting the image displayed on the display screen and diagnostic items for the image are displayed.
The information and diagnostic items displayed here may include the following.
(A) Date and time when the image was taken (b) Name of the building or structure to be photographed (subject) (c) Identification information of the building structure drawing to which the image is associated (d) To the image Information about the damaged part being photographed (type and size of damage, etc.)
(E) Degree of damage related to the damaged part captured in the image (including the result of the above-mentioned diagnostic process (to), as well as the one manually determined by the user).

Since the above processing (e) and (f) are configured to be executable, the server device 30 (editing means 32) captures the contour captured in the image displayed by the display means 23. Based on the contour extraction means to be extracted and the contour extracted by the contour extraction means, the damage identification means for identifying the damaged portion captured in the image displayed by the display means 23 and the damage identification means have been specified. It can be said that it has a marking means for performing an editing process for marking a damaged portion. Then, it can be said that the server device 30 (diagnostic means 33) diagnoses at least the degree of damage related to the damaged portion marked by the marking means.

The above diagnostic process only mentions diagnosing the degree of damage related to the damaged part captured in one image, but the following process is used to diagnose the entire building or structure to be imaged. Can also be diagnosed.
That is, the server device 30 (diagnostic means 33) is based on the degree of damage related to the diagnosed damaged part and the number of damaged parts marked in one or more edited images associated with the building structure drawing. , The degree of damage to the entire building or the entire structure according to the building structure drawing may be diagnosed.

<About the process of identifying and marking damaged parts>
Next, a process of identifying and marking the damaged portion by the server device 30 (editing process of (e) above) will be described.
FIG. 7 is a flowchart of a series of processes for identifying the damaged portion. 8 to 10 are schematic views showing changes in the target image due to the process of identifying the damaged portion.

When the server device 30 receives an operation for the corresponding icon (YES in step S11), the server device 30 extracts the contour captured in the target image (step S13). However, when a small area is set in the target image, only the contour captured in the small area is extracted. If a small area is not set in the target image, the contour captured within the range of the target image is extracted.
Further, the server device 30 captures a part of the image displayed by the communication terminal 20 in the damaged portion based on the contour extracted in step S13 and a plurality of tuning parameters. It is specified as a candidate (hereinafter, this process is referred to as a damage identification process) (step S15).
The server device 30 repeats steps S13 and S15 until a predetermined number of damage identification processes are completed (while step S17 is NO). At this time, the server device 30 executes the damage identification process a plurality of times using different tuning parameters for each damage identification process, and captures the image based on the candidate of the damaged portion identified in each of the damage identification processes. Determine the damaged part that has been damaged.
Then, when the server device 30 completes the damage identification process a predetermined number of times (YES in step S17), the server device 30 marks the candidate for the damaged portion identified at that time as the damaged portion captured in the target image (step). S19).

<Specific example of processing to identify damaged parts>
For example, a case where the image shown in FIG. 8A is displayed on the communication terminal 20 and the server device 30 performs each process shown in FIG. 2 on the image to identify the damaged portion will be described.
Here, in the present embodiment, it is assumed that the server device 30 sets the small area P1 by an arbitrary operation by the user. At this time, the set small area P1 is superimposed on the image displayed on the communication terminal 20 and displayed as shown in FIG. 8 (b).

In the present embodiment, the set small area will be displayed on the communication terminal 20, but it is sufficient that the server device 30 is set to be processable for the small area, and the communication is not necessarily visible to the user. It does not have to be displayed on the terminal 20.
Further, in the present embodiment, when setting a small area, it is described that the small area is surrounded by a square area, but the embodiment of the present invention is not limited to this. In other words, the small area may be designated as a part of the image displayed on the communication terminal 20 (area narrower than the entire image), and the shape of the small area is not limited to a square shape.

Then, the server device 30 repeats the process of step S13 (contour extraction process) and the process of step S15 (damage identification process) until the damaged portion is finally identified.
In the present embodiment, the contour extraction process and the damage identification process will be repeated four times each, which will be described below, but the embodiment of the present invention is not limited to this.
For the implementation of the present invention, it is sufficient that the damage identification process is executed a plurality of times, and the contour extraction process may be executed once. Further, the damage identification process may be executed twice or more, and may be executed less than four times or more than four times.

First, the contour extraction process and the damage identification process that are performed first will be described.

The server device 30 extracts a contour from an image in which a small area is manually set, and identifies a region of a certain area or more from the extracted contour as a candidate for a damaged portion. The area used as the threshold value for this process may be referred to as the first area in the following description.
For example, the result of executing this process on the image illustrated in FIG. 8 (b) is shown in FIG. 9 (a). In FIG. 9A, the portions (photographed object S1, photographed object S2, photographed object S3) shown by thick lines as compared with FIG. 8B are candidates for the damaged portion identified by this process. is there.

Next, if the area related to the damaged portion candidate identified by the above process and the brightness of the adjacent pixel are similar, the server device 30 also sets the adjacent pixel as a damaged portion candidate. By executing this process, it is possible to extract a candidate for a new damaged portion from the pixels that could not be extracted as a contour by the contour extraction process or from the contours that are smaller than the first area by the contour extraction process. ..
In this embodiment, it is assumed that there is no change in the pixels that are candidates for the damaged portion as a result of executing this process on the image illustrated in FIG. 9 (a).

Subsequently, the server device 30 calculates a threshold value based on the brightness of the set small area, and leaves pixels smaller (darker in brightness) than the threshold value as candidates for the damaged portion. Here, the threshold value calculated by the server device 30 is not particularly limited, but for example, it is preferable to calculate using the difference between the average value of the brightness of the set small area and the standard deviation of the brightness as the threshold value. By executing this process, even if the area is extracted as a contour by the contour extraction process and has a first area or more, those having a bright brightness can be excluded from the candidates for the damaged portion.
In this embodiment, it is assumed that there is no change in the pixels that are candidates for the damaged portion as a result of executing this process on the image illustrated in FIG. 9 (a).

Further, the server device 30 stretches the candidates for the damaged portion in the length direction, and if there is another candidate for the damaged portion in the stretched portion, collects the candidates for the damaged portion as one candidate for the damaged portion.
For example, the result of executing this process on the image illustrated in FIG. 9 (a) is shown in FIG. 9 (b). Specifically, FIG. 9B shows the photographing areas of the photographed object S1, the photographed object S2, and the photographed object S3 specified as candidates for the damaged portion in the length direction (extending direction of each photographed object). It is an illustration of the state of being stretched to.
Then, since the stretched photographed object S1, the photographed object S2, and the photographed object S3 exist in the extending direction of each other, they are integrated into a single photographed object S4. FIG. 10A illustrates the photographed object S4 after integration.
By executing this process, pixels that cannot be picked up by the process using the area and brightness as tuning parameters (in the example of this embodiment, the minimum size existing between the photographed object S1, the photographed object S2, and the photographed object S3). The area) can also be identified as a candidate for the damaged part.
Further, since the cracks occur inside the structure, there are many cases where the cracks are actually single cracks even if they are divided into a plurality of cracks on the surface. Even in such a case, it is possible to identify the case according to the actual situation.

Next, the contour extraction process and the damage identification process performed for the second time will be described.
The server device 30 performs the contour extraction process again on the image (the image shown in FIG. 10A) that has undergone the first damage identification process, and the extracted contour has a certain area or more (however, the above). An area larger than the first area of) is extracted and used as a candidate for a damaged part. The area used for this treatment may be referred to as a second area in the following description.
In the present embodiment, since the photographed object S4 in the image illustrated in FIG. 10A has a second area or more, the pixels that are candidates for the damaged portion as a result of executing the above processing are shown in FIG. 10 (a). It is assumed that the photographed object S4 is the same as the image illustrated in a).

Next, the contour extraction process and the damage identification process performed for the third time will be described.
The server device 30 performs the contour extraction process again on the image (the image shown in FIG. 10A) that has undergone the second damage identification process, and the extracted contour has a certain area or more (however, the above). An area larger than the second area) and an aspect ratio of less than a predetermined value is extracted and used as a candidate for a damaged portion. Here, the predetermined value is preferably a value exceeding 0 and less than 1, for example, a predetermined value = 0.5. Further, the area used for this treatment may be referred to as a third area in the following description.
In the present embodiment, since the photographed object S4 in the image illustrated in FIG. 10A has a third area or more and an aspect ratio of a predetermined value (0.5) or less, the above processing is executed. As a result, it is assumed that the pixel that is a candidate for the damaged portion is the photographed object S4 as in the image illustrated in FIG. 10 (a).

Next, the contour extraction process and the damage identification process performed for the fourth time will be described.
The server device 30 again performs contour extraction processing on the image that has undergone the third damage identification process (the image shown in FIG. 10A), and out of the extracted contour, a certain area or more (however, the above). An area larger than the third area of) is extracted and used as a candidate for a damaged part. The area used for this treatment may be referred to as a fourth area in the following description.
Then, the server device 30 finally determines the candidate of the damaged portion identified in the fourth damage identification process as a crack.
In the present embodiment, since the photographed object S4 in the image illustrated in FIG. 10A has a fourth area or more, the pixels that are candidates for the damaged portion as a result of executing the above processing are shown in FIG. 10 (a). It is assumed that the photographed object S4 is the same as the image illustrated in a).

The contour extraction process and damage identification process described above will be summarized.
In the damage identification process performed in the first time, whether or not a region equal to or larger than the first area is included in the contour extracted by the first contour extraction process is set as a tuning parameter, and the region is set as a candidate for the damaged portion. Therefore, it can be said that it includes a process corresponding to the "first damage identification process" in the present invention.
By this process, the server device 30 excludes the extracted contours having a smaller area than the first area, so that fine cracks can be excluded from the candidates for the damaged portion.

In the second contour extraction process, the contour photographed in the area selected as a candidate for the damaged portion by the first damage identification process is extracted. Then, does the second damage identification process include a region equal to or larger than the second area among the contours extracted from the areas that are candidates for the damaged portion by the first identification process (first damage identification process)? Whether or not it is a tuning parameter, the region is a candidate for a damaged portion, and the second area is larger than the first area. Therefore, it can be said that the processing corresponding to the "second damage identification processing" in the present invention is included.
By this process, the server device 30 removes the extracted contours having a smaller area than the first area and then removing the ones having a smaller area than the second area. In other words, the server device 30 can gradually increase the area used for the determination, gradually narrow the candidates for the damaged portion, and improve the determination accuracy (validity for determining the crack).

The process of extending the candidate of the damaged part in the first damage identification process is a process in which the first area in the first damage identification process is used as a tuning parameter (first damage identification process) and a second process in the second damage identification process. This is a process performed between the process of using two areas as tuning parameters (second damage identification process). Then, in the process of stretching the candidate of the damaged part in the first damage identification process, the candidate of the damaged part identified by the other damage identification process is stretched, and the stretched candidate of the damaged part and the candidate of another damaged part overlap. , It can be said that it is a process corresponding to the "third damage identification process" in the present invention because it is integrated and used as a candidate for a single damaged portion.
By this process, the candidates for the damaged portion are integrated and connected to the subsequent damage identification process, so that the server device 30 can identify the candidate for the damaged portion by a more comprehensive determination.

In the first identification process, the pixel corresponding to the area that is a candidate for the damaged part by the process using the first area as the tuning parameter in the first damage identification process (other damage identification process) and the pixel adjacent to the pixel are adjacent to the pixel. The tuning parameter is whether or not the brightness is similar to that of the pixel, and the pixel whose brightness is similar is used as a candidate for the damaged portion. Therefore, it corresponds to the "fourth damage identification process" in the present invention. It can be said that it includes processing.
By this process, it is possible to realize a multifaceted determination as compared with the process in which only the area is used as the tuning parameter, and the server device 30 can improve the accuracy of the specific process.

The first damage identification process was calculated based on the brightness of the pixels included in the area that was a candidate for the damaged part by the process using the brightness comparison in the first damage identification process as a tuning parameter (other damage identification process). Since the threshold value is used as the tuning parameter and the pixel having a brightness lower than the calculated threshold value is used as the candidate for the damaged portion, it can be said to be a process corresponding to the "fifth damage specifying process" in the present invention.
By this process, it is possible to realize a multifaceted determination as compared with the process in which only the area is used as the tuning parameter, and the server device 30 can improve the accuracy of the damage identification process.

The third damage identification process (at least one of the damage identification processes performed by the damage identification means) includes whether or not the aspect ratio is a region less than a predetermined value in the tuning parameter, and the region is included as a candidate for the damaged portion. It can be said that this is the process.
By this process, it is possible to leave an elongated region as a candidate for a crack, so that four more appropriate crack shapes can be left as candidates for a damaged part as compared with a process in which only the area is used as a tuning parameter. , The server device 30 can improve the accuracy of the damage identification process.

As described above, the server device 30 can identify and mark the damaged portion captured in the image by executing various processes in combination, so that the user can identify the position of the damaged portion by himself / herself. The work of marking can be omitted.
In particular, as is clear by comparing FIG. 8 (b) and FIG. 10 (a), if a small area is roughly set so as to surround a part of the image displayed on the communication terminal 20, the damaged portion Since the entire image can be specified, the user can accurately identify the damaged part without paying attention to the setting of the small area.

In addition, in order to realize the above-mentioned various processes (particularly, contour extraction process and damage identification process), a known artificial intelligence process (machine learning process) may be applied, and within a range not contrary to the object of the present invention. The type is not particularly limited.
Further, as the edited image generated as a result of the above-mentioned various processes, the trained model generated by machine learning as teacher data may be applied to the diagnostic process by the server device 30.

<About Examples of the Present Invention>
Hereinafter, an example in which an editing process (a series of processes shown in FIG. 7) according to the present invention is performed on an actual image will be described.
FIG. 11 is a diagram showing an image before the editing process according to the present invention. FIG. 12 is a diagram showing an image after the editing process according to the present invention. FIG. 13 is a schematic view showing a shooting environment of the image shown in FIG.
The arrow B1 shown in FIG. 13 indicates the shooting direction of the image shown in FIG.

The image shown in FIG. 11 is an image of a concrete curb C1 provided on a step between an asphalt-paved ground G1 and a ground G2 existing at a position lower than the ground G1.
The curb C1 has cracks on a part of the lateral surface C2 and protrudes in the depth direction when viewed from the shooting direction (direction indicated by the arrow B1), and the appearance is estimated from the cracks on the upper surface C3. To.

In the image shown in FIG. 11, in addition to the cracks generated on the side surface C2 and the upper surface C3, the upper edge portion C4 and the lower edge portion C5 of the curb C1 are photographed as the contours that can be extracted. The fine line segment of is photographed.
In the image shown in FIG. 12, a portion having a darker color than that in FIG. 11 is a portion specified as a damaged portion.
As is clear from the image shown in FIG. 12, if the editing process according to the present invention is performed, only the damaged portion is accurately identified, and other portions that can be photographed as contours are not specified as the damaged portion.
Therefore, it can be said that the present invention has achieved the above-mentioned object.

<Modification example>
The embodiments of the present invention described above can be variously modified within the scope of the object of the present invention and the achievement.

The implementation of the present invention is not limited to that realized by the system configuration shown in FIG. 1, and other configurations may be adopted.
For example, the server device 30 may include the means provided by the communication terminal 20, or the communication terminal 20 may include the means provided by the server device 30.
Further, in FIG. 1, the communication terminal 20 and the server device 30 are shown as if they were one each, but one or both of them may be realized by a plurality of devices.
Further, in the system configuration shown in FIG. 1, the image to be diagnosed is acquired by the image capturing means 21 included in the communication terminal 20, but the image captured by the camera (not shown) is acquired and the server device 30 is acquired. It may be replaced with the configuration to be stored in.

The processing procedure described with reference to FIG. 7 is a specific example relating to the implementation of the present invention, and within the range of achieving the object of the present invention, the order of processing is changed, some processing is omitted, or the above-mentioned You may make changes such as adding a process not described in the embodiment of.

This embodiment includes the following technical ideas.
(1) An acquisition means for acquiring an image of a building or a structure, a display means for displaying an image acquired by the acquisition means, an editing means for editing an image displayed by the display means, and the editing. The editing means includes a diagnostic means for diagnosing an edited image edited by the means, and the editing means includes a contour extraction means for extracting a contour captured in an image displayed by the display means, and the contour extraction means. Based on the contour extracted by the means, the damage identifying means for identifying the damaged part captured in the image displayed by the display means and the editing process for marking the damaged part identified by the damage identifying means are performed. A building structure diagnostic system comprising marking means to perform, the diagnostic means diagnosing at least the degree of damage to a damaged portion marked by the marking means.
(2) The storage means for storing the building structure drawing relating to the building or structure to which the image acquired by the acquisition means is to be captured and the edited image are associated with the building structure drawing stored in the storage means. The diagnostic means includes an image drawing corresponding means, and the diagnostic means includes the degree of damage related to the diagnosed damaged part and the number of damaged parts marked in one or more of the edited images associated with the building structure drawing. , The building structure diagnosis system according to (1), which diagnoses the degree of damage to the entire building or the entire structure according to the building structure drawing.
(3) The damage identifying means captures a part of the image displayed by the display means on the image based on the contour extracted by the contour extracting means and a plurality of tuning parameters. The damage identification process specified as a candidate for the damaged part is executed a plurality of times, and the tuning parameter different for each damage identification process is used, and the damage identification process is used based on the damage identification process specified in each of the damage identification processes. The building structure diagnostic system according to (1) or (2), which identifies a damaged part photographed in an image.
(4) In the first damage identification process executed by the damage identification means, whether or not a region equal to or larger than the first area is included in the contour extracted by the contour extraction means is set as the tuning parameter. The building structure diagnostic system according to (3), wherein the area is a candidate for a damaged part.
(5) The contour extracting means extracts a contour photographed in a region designated as a candidate for a damaged portion by the damage identifying process, and the second damage identifying process executed by the damage identifying means is the first. Whether or not a region equal to or larger than the second area is included in the contour extracted from the region selected as a candidate for the damaged portion by one damage identification process is set as the tuning parameter, and the region is set as the candidate for the damaged portion. The building structure diagnosis system according to (4), wherein the second area is larger than the first area.
(6) The third damage identification process performed by the damage identification means between the first damage identification process and the second damage identification process is a candidate for a damaged portion identified by the other damage identification process. The building structure diagnostic system according to (5), wherein when a candidate for a stretched damaged part and a candidate for another damaged part overlap, they are integrated into a single candidate for a damaged part.
(7) The fourth damage identification process executed by the damage identification means compares a pixel corresponding to an area that is a candidate for a damaged portion by another damage identification process with a pixel adjacent to the pixel. The building structure according to any one of (3) to (6), wherein whether or not the brightness is similar is used as the tuning parameter, and the pixels having similar brightness are used as candidates for the damaged portion. Diagnostic system.
(8) In the fifth damage identification process executed by the damage identification means, the tuning parameter is a threshold value calculated based on the brightness of the pixels included in the area that is a candidate for the damage portion by the other damage identification processing. The building structure diagnosis system according to any one of (3) to (7), wherein pixels having a brightness lower than the calculated threshold value are candidates for the damaged portion.
(9) At least one of the damage identification processes executed by the damage identification means sets whether or not the aspect ratio is a region less than a predetermined value as the tuning parameter, and uses the region as a candidate for the damaged portion. The building structure diagnosis system according to any one of (3) to (8).

100 Building structure diagnostic system 10 Network 20 Communication terminal 21 Imaging means 22 Operation input means 23 Display means 30 Server device 31 Storage means 32 Editing means 33 Diagnostic means 34 Image drawing Corresponding means

Claims (9)

Acquisition means for acquiring images of buildings or structures, and
A display means for displaying an image acquired by the acquisition means and a display means for displaying the image.
An editing means for editing an image displayed by the display means, and
A diagnostic means for diagnosing an edited image edited by the editing means, and
With
The editing means
A contour extraction means for extracting the contour captured in the image displayed by the display means, and a contour extraction means.
Based on the contour extracted by the contour extracting means, the damage identifying means for identifying the damaged portion captured in the image displayed by the display means, and the damage identifying means.
A marking means that performs an editing process for marking a damaged portion identified by the damage identifying means,
Have and
The diagnostic means diagnoses at least the degree of damage to the damaged portion marked by the marking means.
Building structure diagnostic system. A storage means for storing a building structure drawing relating to a building or a structure for which an image acquired by the acquisition means is to be taken, and a storage means.
An image drawing-corresponding means for associating the edited image with the building structure drawing stored in the storage means,
With
The diagnostic means is based on the degree of damage to the diagnosed damaged part and the number of damaged parts marked in the edited image associated with the building structure drawing. Diagnose the degree of damage to the entire building or structure
The building structure diagnostic system according to claim 1. The damage identifying means
Damage that identifies a part of the image displayed by the display means as a candidate for a damaged portion captured in the image based on the contour extracted by the contour extraction means and a plurality of tuning parameters. Execute specific processing multiple times
Using the tuning parameters that are different for each of the damage identification processes, the damaged portion captured in the image is specified based on the candidate of the damaged portion identified in each of the damage identification processes.
The building structure diagnostic system according to claim 1 or 2. In the first damage identification process executed by the damage identification means, whether or not a region equal to or larger than the first area is included in the contour extracted by the contour extraction means is set as a tuning parameter, and the region is damaged. Candidate for the club,
The building structure diagnostic system according to claim 3. The contour extraction means extracts a contour imaged in a region that is a candidate for a damaged portion by the damage identification process, and extracts the contour.
Does the second damage identification process executed by the damage identification means include a region equal to or larger than the second area among the contours extracted from the regions selected as candidates for the damaged portion by the first damage identification treatment? Whether or not is used as the tuning parameter, and the area is used as a candidate for the damaged part.
The second area is larger than the first area.
The building structure diagnostic system according to claim 4. The third damage identification process performed by the damage identification means between the first damage identification process and the second damage identification process stretches the candidates for the damaged portion identified by the other damage identification process. When a stretched damaged part candidate and another damaged part candidate overlap, they are integrated into a single damaged part candidate.
The building structure diagnostic system according to claim 5. The fourth damage identification process executed by the damage identification means compares the pixels corresponding to the area designated as the candidate of the damage portion by the other damage identification processes with the pixels adjacent to the pixels and has a brightness. Is the tuning parameter, and the pixels with similar brightness are candidates for the damaged portion.
The building structure diagnostic system according to any one of claims 3 to 6. The fifth damage identification process executed by the damage identification means is calculated by using a threshold value calculated based on the brightness of pixels included in a region designated as a candidate for a damaged portion by another damage identification process as a tuning parameter. Pixels with a brightness lower than the threshold value are used as candidates for the damaged portion.
The building structure diagnostic system according to any one of claims 3 to 7. At least one of the damage identification processes executed by the damage identification means sets whether or not the aspect ratio is a region less than a predetermined value as the tuning parameter, and uses the region as a candidate for the damaged portion.
The building structure diagnostic system according to any one of claims 3 to 8.

Images