JP7403124B2 - Corrosion analysis system - Google Patents

Description

The present invention relates to a corrosion analysis system, and particularly to a technique for analyzing corrosion occurring in metal public equipment (guardrails, etc.) installed in public places.

Proper management of public facilities allows them to maintain their roles and safety. However, the burden of managing this is enormous, and in Japan, where the working population is decreasing, there is an urgent need to reduce this burden.

In view of the above background, various techniques and methods regarding the management of public facilities have been proposed.
For example, Patent Document 1 discloses a system that drives a vehicle equipped with a camera, transfers the captured images to a server, and detects abnormalities in equipment installed around roads through image analysis on the server. .

JP 2019-79303 Publication

The content disclosed in Patent Document 1 lacks specificity and still leaves room for improvement. In particular, no concrete consideration has been given to how to organize a report on equipment in which an abnormality has been detected to the manager of that equipment.

The present invention has been made in view of the above-mentioned problems, and provides a corrosion analysis system that outputs a report analyzing corrosion occurring in metal public facilities such as guardrails.

According to the present invention, there is provided an acquisition means for acquiring video data of an area where a plurality of metal columns are arranged side by side from a vehicle traveling on a road , and an acquisition unit for extracting the metal columns photographed in the video data. , an identification means for allocating identification information to each of the extracted metal columns so that they can be distinguished from each other; and an identification means for extracting a corroded part of the metal column photographed in the video data, and indicating the degree of corrosion in the extracted corroded part. generating a report in which information that associates an analysis means for estimating an index value, the identification information assigned by the identification means, and the index value estimated by the analysis means in a format that is recognizable by the user; and output means for outputting a frame group included in the video data, at least two or more of the metal pillars are photographed for one frame, and the identification means is configured to output An ordinal number that increases from the front to the rear in the direction is assigned to each of the metal pillars photographed in the video data as the identification information, and the identification information is assigned to each of the metal pillars to which the identification information is assigned. A frame in which a metal pillar is photographed is extracted from a group of frames included in the video data and associated with each other, and the output means outputs each frame associated with a plurality of metal pillars by the ordinal number. Provided is a corrosion analysis system that generates and outputs the report arranged in the order shown .

According to the above invention, identification information assigned to a metal column captured in video data is associated with an index value indicating the degree of corrosion of a corroded part of the metal column. Since a report is output, the user (facility manager) can easily recognize metal pillars that require repair.

According to the present invention, a corrosion analysis system is provided that outputs a report analyzing corrosion occurring in metal public equipment such as guardrails.

FIG. 3 is a diagram showing a photographing method in implementing the present invention. This is a specific example of an image photographed by the photographing method shown in FIG. 1. FIG. 1 is a system configuration diagram related to this embodiment. 3 is a flowchart showing a processing procedure executed by the analysis device. FIG. 3 is a diagram showing a part of a frame group included in video data captured by a camera. FIG. 3 is a diagram showing a still image captured by the analysis device. This is a marking of the corroded part of the support column photographed in the still image of FIG. FIG. 3 is a diagram illustrating part of the content included in a report displayed on a display device. FIG. 3 is a diagram illustrating part of the content included in a report displayed on a display device.

Embodiments of the present invention will be described below with reference to the drawings. In addition, in all the drawings, the same reference numerals are given to the same components, and the explanation is omitted as appropriate.

<About the photographing method in carrying out the present invention>
FIG. 1 is a diagram showing a photographing method in the implementation of the present invention. FIG. 1 shows a camera C2 mounted on a vehicle C1 traveling in an overtaking lane of an expressway to photograph a guardrail CB installed in a median strip. Note that the broken line shown in FIG. 1 indicates the range (angle of view) photographed by the camera C2.

The camera C2 is mounted on the vehicle C1 so that the photographing direction is oblique to the traveling direction of the vehicle C1. Although FIG. 1 illustrates that the photographing direction of the camera C2 is diagonally forward with respect to the traveling direction of the vehicle C1, it may be diagonally backward with respect to the traveling direction of the vehicle C1.
As a result, the time during which each support of the guardrail CB is within the field of view of the vehicle C1 becomes longer than when photographing in the direction perpendicular to the direction of travel of the vehicle C1 (directly lateral to the vehicle C1), so high-speed cameras, etc. Each pillar of the guardrail CB can be photographed in high definition without using a special camera. In other words, when shooting in a direction perpendicular to the traveling direction of the vehicle C1, since the vehicle C1 moves at high speed on the expressway, each support of the guardrail CB moves at high speed in the shot video, and the analysis device 10 described later Processing (analysis of corroded parts) cannot be performed with sufficient accuracy.
Furthermore, since the physical range that can fit within the viewing angle of the vehicle C1 is expanded, the number of pillars of the guardrail CB that can fit in one frame of video data can be increased. Note that it is preferable that at least two or more pillars (in the example of FIG. 1, three pillars S1, S2, and S3) are photographed in each frame. This is to accurately perform processing (numbering of columns) by the analysis device 10, which will be described later.

When shooting a video by vehicle C1, it is sufficient that the area where the equipment to be analyzed is installed is included in the video, and in accordance with the example of FIG. 1, it is sufficient that the area from one end of the guardrail CB to the other end is included. .
Please note that in some cases, the equipment to be analyzed is installed in multiple separate locations, so the area between adjacent equipment may be included in the video shot (if the equipment to be analyzed is not captured). frame exists).

FIG. 2 is a specific example of an image photographed by the photographing method shown in FIG.
Experience has shown that guardrail supports are more likely to corrode on the side where the vehicle travels, and are more likely to corrode from below (from the ground side), as shown in the corroded area S21 on the support post S2 shown here. known as the rule.
Note that in this embodiment, corrosion includes not only rust but also deterioration and loss (holes).

<About the system configuration of the present invention>
Next, the system configuration of the present invention will be explained.
FIG. 3 is a system configuration diagram related to this embodiment.

A corrosion analysis system 100 according to the present invention includes an analysis device 10, a camera C2 and a display device 20, which are electrically connected to the analysis device 10.
The camera C2 shown in FIG. 3 is the same as the camera C2 mounted on the vehicle C1 shown in FIG. 1, and sends video data of the guardrail CB to the analysis device 10.
The analysis device 10 performs analysis processing on the received video data, and outputs a report to the display device 20 as a result of the analysis processing.
The display device 20 displays the report input from the analysis device 10.

The analysis device 10 includes a processor 11, a memory 12, a storage 13, a communication IF 14, and an input/output IF 15, and these components are electrically connected to each other by a communication bus.
The processor 11 loads various programs and various data stored in the storage 13 into the memory 12, and executes the loaded programs.
The memory 12 is used to store programs executed by the processor 11 and various data generated during execution of the programs.
The storage 13 stores various programs and various data.
The communication IF 14 is configured to be able to communicate with an external network (for example, the Internet) not shown.
In addition to being connected to the camera C2 and the display device 20, the input/output IF 15 is configured to be electrically connectable to an external device (for example, a printing device) not shown.

FIG. 4 is a flowchart showing the processing procedure executed by the analysis device 10. Note that the flowchart merely enumerates processes that require explanation regarding implementation of the present invention, and allows unillustrated processes to be executed by the analysis device 10.

The analysis device 10 acquires video data from the camera C2 (step S11).
The analysis device 10 extracts the pillars of the guardrail CB photographed in the video data acquired in step S11, and numbers each of the extracted pillars so that they can be identified from each other (step S13).
The analysis device 10 extracts the corroded portion of the pillar of the guardrail CB captured in the video data acquired in step S11, and estimates the degree of corrosion in the extracted corroded portion (step S15).
The analysis device 10 generates a report in which the numerical value numbered in step S13 and the degree of corrosion estimated in step S15 are associated with each other in a user-recognizable format, and displays the report. It is output to the device 20 (step S17).

In this embodiment, as an example of the video data acquired in step S11, a road is photographed from a vehicle running on the road, and a plurality of guardrail supports are arranged side by side in the photographed area.
However, when implementing the present invention, the object photographed in the video data is not limited to the support of a guardrail, but may be a plurality of columnar metal structures arranged in parallel. Specifically, the photographing target may be a lamp post, a traffic light post, a road sign post, or the like.
In addition, in this embodiment, the above-mentioned columnar metal structures are generally referred to as "metal columns."

In this embodiment, numbering is given to the guardrail pillars extracted in step S13, but it is sufficient to assign identification information that enables each to be identified, and the identification information is not limited to numerical values. .

It is preferable that the degree of corrosion estimated in step S15 can be divided into a plurality of stages and shown to the user, and more preferably it can be shown quantitatively (expressed numerically).
In this embodiment, the parameters indicating the degree of corrosion estimated by the analysis device 10 are generally referred to as "index values."
As will be described in detail later, the analysis device 10 assumes that the height (in millimeters) of the corroded part and the area (in square millimeters) of the corroded part extracted in step S15 correspond to the above-mentioned index value. Estimated. However, in implementing the present invention, index values that correspond to the above examples are not limited to those that can be divided into multiple stages, such as indicators that indicate whether or not the degree of replacement is necessary (the degree of corrosion is determined in two stages). It may also be possible to indicate the degree of corrosion by ranking it in three or more stages. Further, the index value may be one (for example, one of the height of the corroded part and the area of the corroded part).

Details of the report output in step S17 will be described later, but the contents are just one specific example, and the format of the report can be changed as appropriate depending on the above-mentioned "identification information" and "index value".

<About analysis by analysis device 10>
Next, analysis by the analysis device 10 will be explained.
The video data analyzed by the analysis device 10 is preferably a frame in which the support of the guardrail CB is photographed, and only necessary frames need to be cut out.
This cutting may be performed automatically by a predetermined image analysis process, or may be performed manually by the user (for example, from the frame in which the first pillar is photographed in the video data taken by camera C2). (Processing such as cutting out the frame up to the frame in which the last pillar is photographed may also be performed.)

FIG. 5 is a diagram showing a part of the frame group (frames F1 to F14) included in the video data shot by the camera C2, and only the frames in which the pillars of the guardrail CB are shot are cut out. .
For example, in the frame F1, the first (initial) to third pillars are photographed, and the first pillar has a corroded portion.
The second to fourth pillars are photographed in frame F2, and the fourth pillar has a corroded part.
The fourth to sixth pillars are photographed in frame F3, and the fourth pillar has a corroded part.
In frame F4, the 6th to 8th pillars are photographed, and the pillars with corroded parts are not photographed.
In frame F5, the 7th to 9th pillars are photographed, and the pillars with corroded parts are not photographed.
In frame F6, the 8th to 10th pillars are photographed, and the pillars with corroded parts are not photographed.
In frame F7, the 10th to 12th pillars are photographed, and the 11th pillar has a corroded part.
In frame F8, the 11th to 13th pillars are photographed, and the 11th pillar has a corroded part.
In frame F9, the 12th to 14th pillars are photographed, and the pillars with corroded parts are not photographed.
In frame F10, the 14th to 16th pillars are photographed, and the 15th pillar has a corroded part.
As for the frames F11 to F14, the columns with corroded parts were not photographed, so detailed explanations will be omitted.
As described above, although a plurality of pillars are photographed in all frames, only some of the frames are photographed in which pillars with corroded parts are photographed.

Subsequently, the analysis device 10 reads video data including a frame group as shown in FIG. 5, and numbers each photographed support (performs the process of step S13 in FIG. 2).
At this time, the analysis device 10 captures a still image in which the numbered pillars are photographed from a frame included in the video data.

FIG. 6 is a diagram showing a still image captured by the analysis device 10.
A frame F1 in which the first pillar is photographed on the right side is captured as a still image corresponding to the first pillar.
A frame F1 in which the second pillar is photographed in the center is captured as a still image corresponding to the second pillar.
Frame F2, in which the third pillar is photographed in the center, is captured as a still image corresponding to the third pillar.
Frame F3, in which the fourth pillar is photographed on the right side, is captured as a still image corresponding to the fourth pillar.
As mentioned above, the numbers numbered on the struts and the ordinal numbers of the frames do not necessarily have to match, allowing one frame to be captured as a still image corresponding to multiple struts.
Furthermore, it is preferable that the frame captured as a still image corresponding to the pillar be taken at a position where the pillar is easily visible (near the center), but the frame is not necessarily limited to this.

Next, the analysis device 10 extracts a corroded part from each numbered support by image analysis, and estimates an index value indicating the degree of corrosion in the extracted corroded part (performs step S15 in FIG. 2).
At this time, the analysis device 10 preferably marks the extracted corroded portion. Marking here is processing to make it easier for the user to see compared to a still image before marking, for example, processing to change a corroded part to a color that is easier to see.
By marking the captured still image, the analysis device 10 can highlight the corroded portion of the support in the report displayed on the display device 20.

FIG. 7 shows a marking of the corroded portion of the support column photographed in the still image of FIG. 6.
Frame F2, which is illustrated as a still image corresponding to the third pillar in FIG. 7, illustrates that the corroded part of the non-corresponding pillar (fourth pillar) is marked, but it does not correspond. It is not necessary to mark the corroded parts of the struts.

The analysis device 10 estimates an index value indicating the degree of corrosion for the corroded portion of the support column extracted as described above, as follows.
The analysis device 10 estimates the ratio of the height of the corroded part of the support column photographed in the still image to be analyzed to the dimension from the ground surface to the beam material, and calculates the ratio of the estimated height of the corroded part and the analysis. The height of the corroded part is estimated by multiplying by the dimension from the ground surface to the beam material, which the device 10 has in advance.
The analysis device 10 also estimates the area of the corroded portion by multiplying the height of the corroded portion estimated as described above by the width dimension of the corroded portion analyzed from the still image to be analyzed. The analysis device 10 determines whether the corroded part photographed in the still image to be analyzed goes around the entire circumference of the pillar (covers 360 degrees) or goes around half the pillar (covers 180 degrees). The width dimension of the corroded portion is estimated by multiplying the estimated ratio of the circumference of the corroded portion by the diameter of the support that is stored in advance in the analyzer 10.

For example, if the analysis device 10 estimates that the height of the corroded part on the first pillar is 1/4 of the dimension (200 mm) from the ground surface to the beam material, then the height of the corroded part The height is estimated to be 50mm.
In addition, regarding the area of the corroded part that has occurred on the first pillar, if the analysis device 10 estimates that it will go around half the pillar, it will multiply the diameter of the pillar (100 mm) by 1/2, and then calculate the area of the corroded part. Multiplying the height by 50 mm, the area of the corroded part is estimated to be 250 square mm.

Furthermore, the analysis device 10 determines which pillars require repair or replacement based on the height and area of the corroded portion estimated as described above. For example, the analysis device 10 determines whether the column having the corroded portion needs to be repaired or replaced by determining whether the estimated height and area of the corroded portion exceed predetermined threshold values.

Furthermore, the analysis device 10 estimates the cost required for replacement of the pillars that are determined to require repair or replacement based on the above determination. For example, the analysis device 10 stores information regarding the cost required for repair or replacement in the storage 13, and calculates the cost required for repair or replacement based on the information.

<About the report displayed on the display device 20>
Next, the report displayed on the display device 20 (the process of step S17 in FIG. 4) will be described.

FIG. 8 is a diagram illustrating part of the content included in the report displayed on the display device 20.
The circled numbers shown in FIG. 8 indicate the numerical values numbered on each support. For example, the circled number "1" indicates the first pillar.
The bar-shaped display below each circle number is a simple representation of the support column corresponding to the circle number, and the filled-in areas are simple representations of the corroded parts of the support support. The height and area of the filled-in area change in proportion to the height and area of the corroded part estimated by the analysis device 10.
The numerical values written below the bar-shaped display are the height and area of the corroded part estimated by the analysis device 10, and zero is displayed for columns for which the corroded part has not been extracted.

The content of the report shown in FIG. 8 is information that associates the circled numbers corresponding to the above-mentioned "identification information" with the height and area of the corroded part corresponding to the above-mentioned "index value", and the display device The process of displaying the report by 20 can be said to correspond to the process of step S17 in FIG.

Although not shown in FIG. 8, the display device 20 may be capable of displaying and outputting a report including the above-described determination result regarding whether or not repair or replacement is necessary.
In this modification, the display device 20 is capable of distinguishing information related to columns determined to require repair or replacement based on the threshold value from information related to other columns (pillars determined not to require repair or replacement). It is preferable to display and output the report in this format or in a format in which information related to other pillars is omitted.

FIG. 9 is a diagram illustrating part of the content included in the report displayed on the display device 20. As shown in FIG.
The still image shown in FIG. 9 corresponds to a pillar that is determined to require repair or replacement based on the threshold value. In this embodiment, it is assumed that it is determined that the first pillar and the fifteenth pillar need to be repaired or replaced. Note that in these still images, it is preferable that the corroded portions be highlighted so that they can be easily visually recognized by the user.
The estimated amount shown in FIG. 9 represents the cost calculated by the above-mentioned analysis device 10.
The numerical values shown in FIG. 9 are the height and area of the corroded portion estimated by the analysis device 10.

As illustrated in FIG. 9, it is preferable that the still images displayed together with the estimated price exclude still images related to pillars that have been determined to require no repair or replacement. This is to prevent a user from being misled into thinking that a support that normally does not require repair or replacement is a support that requires repair or replacement.

The content of the report shown in Figure 9 is as described above, so it includes the cost calculated for the pillars that require repair or replacement (the 1st and 15th pillars) and the height of the corroded parts of each pillar. It can be said that the size and area are associated with the numerical value numbered on the pillar.

Since reports such as those shown in FIGS. 8 and 9 are output, the user can easily obtain detailed information (particularly information necessary for repair or replacement) regarding the corrosion that has occurred in the pillars of the guardrail CB.
<Modified example>
The embodiments of the present invention described above can be modified in various ways within the scope of achieving the objectives of the present invention.
For example, the implementation of the present invention is not limited to what is realized by the system configuration illustrated in FIG. 3, and other configurations may be adopted.

Although FIG. 3 illustrates that the camera C2 is included in the corrosion analysis system 100, the system configuration according to the present invention does not necessarily need to include the camera C2, and the video data captured by an external device is It may be analyzed by the system of the invention.

Although FIG. 3 illustrates that the analysis device 10 is a single device, in the system configuration according to the present invention, the various processes described as being performed by the analysis device 10 can be executed separately by a plurality of devices. You can.
In addition, in this modification, if some of the devices constituting the system according to the present invention have a shooting function, video data acquired by the shooting function may be analyzed by any device in the system. good.

Although FIG. 3 illustrates that the camera C2, the analysis device 10, and the display device 20 are directly connected, the configuration of the present invention is not limited to this.
For example, when implementing the present invention between a web server and a client terminal that are communicably connected via the Internet, after the client terminal acquires and saves video data of the analysis target, the client terminal transmits video data via the Internet. The present invention is implemented by a configuration in which the web server identifies and analyzes the analysis target captured in the video data, responds the result (report) to the client terminal, and the client terminal outputs the report. may be done.
According to this modification, the client terminal can constitute the acquisition means and output means according to the present invention, and the web server can constitute the identification means and analysis means according to the present invention.

In the configuration of FIG. 3 and the process of step S17 shown in FIG. 4, the report according to the present invention is displayed and outputted by the display device 20, but instead of this, the report is printed out by a printing device (not shown). Good too.

In Figure 8, the column to be analyzed is simply shown using a bar-shaped display, but instead of this, the analyzed still image may be included in the report, and the corroded portion of the column photographed in this still image may be included. It may be highlighted so that it is not easily visible to the user by marking it.

If the analysis device 10 has stored in the memory 12 or the storage 13 the results of past analysis of the same guardrail CB support, the display device 20 displays the above-mentioned information in addition to the report contents shown in FIGS. 8 and 9. It may also be possible to output a report showing changes in the "index value" over time.

This embodiment includes the following technical ideas.
(1) An acquisition means for acquiring video data of an area where a plurality of metal columns are arranged side by side, extracting the metal columns captured in the video data, and identifying each of the extracted metal columns from each other. an identification means for allocating identification information to the metal column, an analysis means for extracting a corroded part of the metal column photographed in the video data and estimating an index value indicating the degree of corrosion in the extracted corroded part; and output means for generating and outputting a report in which the identification information allocated by the means and the index value estimated by the analysis means are made into a user-recognizable format. Analysis system.
(2) The analysis means has a threshold value related to the index value, and discriminates the metal column having the extracted corroded part based on the threshold value, and the output means discriminates the metal column having the extracted corroded part based on the threshold value. The index value relating to the corroded portion of each of the metal pillars that has been used is associated with the identification information assigned to each of the metal pillars. The corrosion analysis system according to (1), which generates and outputs the report in a format that is distinguishable from information or that excludes information related to other metal columns.
(3) The analysis means has information on the cost of replacing or repairing the metal pillar, calculates the cost of replacing or repairing the metal pillar determined based on the threshold value, and calculates the cost of replacing or repairing the metal pillar, and the output means is the cost calculated for the metal pillar determined based on the threshold value, the index value related to the corroded part that each of the metal pillars has, and the cost allocated to each of the metal pillars. The corrosion analysis system according to (2), which generates and outputs the report including information that associates the identification information with the identification information.
(4) The identification means captures a still image in which the metal pillar to which the identification information shown in the report is assigned is photographed from a frame included in the video data, and the output means captures the captured still image. The corrosion analysis system according to any one of (1) to (3), which generates and outputs the report including the following.
(5) The corrosion analysis system according to (4), wherein the corroded portion of the metal column photographed in the still image included in the report is highlighted.
(6) The video data is a photograph of the side of the road from a vehicle running on the road, and the metal pillars are among the pillars of guardrails, lighting lights, traffic lights, and road signs. The corrosion analysis system according to any one of (1) to (5).
(7) The video data is photographed by a photographing means mounted on the vehicle such that the photographing direction is oblique to the traveling direction of the vehicle, and the frames included in the video data include: The corrosion analysis system according to (6), wherein at least two or more of the metal columns are photographed.
(8) The corrosion analysis system according to any one of (1) to (7), wherein the index value is a numerical value representing at least one of the height or area of the corroded portion.

100 Corrosion analysis system 10 Analysis device 11 Processor 12 Memory 13 Storage 14 Communication IF
15 Input/output IF
20 Display device C1 Vehicle C2 Camera CB Guardrail

Claims (6)

an acquisition means for acquiring video data of an area where a plurality of metal pillars are arranged side by side from a vehicle traveling on a road ;
Identification means for extracting the metal pillars captured in the video data and assigning identification information to each of the extracted metal pillars so that they can be identified from each other;
analysis means for extracting a corroded part of the metal column captured in the video data and estimating an index value indicating the degree of corrosion in the extracted corroded part;
output means for generating and outputting a report in which the identification information allocated by the identification means and the index value estimated by the analysis means are associated with each other in a format recognizable by a user;
Equipped with
In the frame group included in the video data, at least two or more of the metal pillars are photographed for one frame,
The identification means is
Assigning an ordinal number that increases from the front to the back in the traveling direction of the vehicle to each of the metal pillars photographed in the video data as the identification information,
For each of the metal pillars to which the identification information has been assigned, one frame in which the metal pillar is photographed is extracted from a group of frames included in the video data and associated;
The output means generates and outputs the report in which each of the frames associated with the plurality of metal columns is arranged in the order indicated by the ordinal number.
A corrosion analysis system characterized by: The analysis means has a threshold value related to the index value, and discriminates the metal column having the extracted corroded part based on the threshold value,
The output means corresponds the index value related to the corroded part that each of the metal columns has, determined based on the threshold value, and the identification information assigned to each of the metal columns. generating and outputting the report in a format in which the attached information is distinguishable from information related to other metal columns or information related to other metal columns is omitted;
The corrosion analysis system according to claim 1. The analysis means has information on the cost of replacing or repairing the metal pillar, and calculates the cost of replacing or repairing the metal pillar determined based on the threshold value,
The output means includes the cost calculated for the metal pillar determined based on the threshold value, the index value related to the corroded part of each of the metal pillars, and the cost that is allocated to each of the metal pillars. generating and outputting the report including information associating the identification information with the
The corrosion analysis system according to claim 2. The metal column is any one of a guardrail column, a lighting column, a traffic light column, and a road sign column.
The corrosion analysis system according to any one of claims 1 to 3 . The video data is photographed by a photographing means mounted on the vehicle such that the photographing direction is oblique to the traveling direction of the vehicle;
At least two or more of the metal pillars are photographed in frames included in the video data;
The corrosion analysis system according to claim 4 . The index value is a numerical value representing at least one of the height or area of the corroded part,
The corrosion analysis system according to any one of claims 1 to 5 .

Images