Test support system, test support method, and program
The inspection support system improves reinforcement inspection efficiency by using machine learning for attribute estimation and group-based correction, addressing the inefficiencies in confirming and correcting reinforcing bar attributes in reinforced concrete structures.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- PRIME LIFE TECHNOLOGIES CORP
- Filing Date
- 2025-05-29
- Publication Date
- 2026-06-22
AI Technical Summary
Existing reinforcement inspection methods in reinforced concrete construction lack efficiency in confirming the attributes of reinforcing bars, such as diameter, orientation, and length, and do not facilitate quick and accurate correction of estimation errors.
An inspection support system and method utilizing a portable device with image acquisition, machine learning for attribute estimation, and a display interface for superimposed or listed attributes, allowing for group-based correction and batch modifications.
Enhances the efficiency of confirming and correcting reinforcing bar attributes by prioritizing low-confidence results and enabling simultaneous correction, improving work efficiency compared to existing systems.
Smart Images

Figure 2026101577000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an inspection support system for supporting the inspection of a reinforcing bar structure.
Background Art
[0002] In the construction of a reinforced concrete building, before placing concrete, reinforcement inspection (inspection of the arrangement of reinforcing bars) is carried out according to the design information. As a technique related to reinforcement inspection, Patent Document 1 discloses a reinforcement measurement system capable of improving the work efficiency of reinforcement inspection.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] The present invention provides an inspection support system and the like that can support the confirmation of the attributes (such as the diameter of the reinforcing bar) of the reinforcing bars.
Means for Solving the Problems
[0005] An inspection support system according to an aspect of the present invention is an inspection support system for supporting the inspection of a reinforcing bar structure, including an acquisition unit that acquires image information of an image in which the reinforcing bar structure is reflected, an estimation unit that estimates, together with a reliability, an attribute related to the structure of each of a plurality of reinforcing bars included in the reinforcing bar structure reflected in the image based on the acquired image information, a display unit, and a display control unit that displays the estimated attribute and reliability on the display unit.
[0006] An inspection support system according to one aspect of the present invention is an inspection support system for supporting the inspection of a reinforced concrete structure, comprising: an acquisition unit that acquires image information of an image showing the reinforced concrete structure; an estimation unit that estimates the structural attributes of each of a plurality of reinforced concrete bars included in the reinforced concrete structure shown in the image based on the acquired image information; a display unit; a display control unit that displays the image on the display unit in which the estimated results of the attributes of each of the plurality of reinforced concrete bars are superimposed or listed together; a grouping unit that groups the plurality of reinforced concrete bars based on structural features obtained from the image information that are different from the attributes; and an operation reception unit that receives operator operations for batch modifying the estimation results in groups based on the structural features.
[0007] An inspection support system according to one aspect of the present invention is an inspection support system for supporting the inspection of a reinforced concrete structure, comprising: an acquisition unit that acquires image information of an image showing the reinforced concrete structure; an estimation unit that inputs the acquired image information into a machine learning model to estimate the structural attributes of each of the multiple reinforced concrete bars included in the reinforced concrete structure shown in the image; a display unit; a display control unit that displays the estimated attributes on the display unit; and an operation reception unit that receives operations from an operator to correct the estimated attributes.
[0008] An inspection support method according to one aspect of the present invention is an inspection support method performed by a computer to support the inspection of a reinforced concrete structure, comprising: an acquisition step of acquiring image information of an image showing the reinforced concrete structure; an estimation step of estimating the structural attributes of each of the multiple reinforced concrete bars included in the reinforced concrete structure shown in the image, along with their reliability, based on the acquired image information; and a display step of displaying the estimated attributes and reliability on a display unit.
[0009] An inspection support method according to one aspect of the present invention is an inspection support method performed by a computer to support the inspection of a reinforced concrete structure, comprising: an acquisition step of acquiring image information of an image showing the reinforced concrete structure; an estimation step of estimating the structural attributes of each of a plurality of reinforced concrete bars included in the reinforced concrete structure shown in the image based on the acquired image information; a display step of displaying the image on a display unit in which the estimated results of the attributes of each of the plurality of reinforced concrete bars are superimposed or listed together; a grouping step of grouping the plurality of reinforced concrete bars based on structural features obtained from the image information that are different from the attributes; and an operation reception step of receiving an operation from an operator to collectively modify the estimation results in groups based on the structural features.
[0010] An inspection support method according to one aspect of the present invention is an inspection support method performed by a computer to support the inspection of a reinforced concrete structure, comprising: an acquisition step of acquiring image information of an image showing the reinforced concrete structure; an estimation step of inputting the acquired image information into a machine learning model to estimate the structural attributes of each of the multiple reinforced concrete bars included in the reinforced concrete structure shown in the image; a display step of displaying the estimated attributes on a display unit; and an operation reception step of receiving an operation from an operator to correct the estimated attributes.
[0011] A program according to one aspect of the present invention is a program for causing the computer to execute the inspection support method. [Effects of the Invention]
[0012] The inspection support system of the present invention can assist in confirming the attributes of reinforcing bars. [Brief explanation of the drawing]
[0013] [Figure 1] Figure 1 is a block diagram showing the configuration of the inspection support system according to the embodiment. [Figure 2] Figure 2 shows a worker performing a rebar inspection using the inspection support system according to the embodiment. [Figure 3] Figure 3 is a flowchart showing an example of the operation of the inspection support device according to the embodiment. [Figure 4] Figure 4 shows an example of a confirmation screen. [Figure 5] Figure 5 shows an example of a confirmation screen when the horizontal selection button is selected. [Figure 6] Figure 6 shows a modified version of the confirmation screen. [Modes for carrying out the invention]
[0014] The embodiments will be described in detail below with reference to the drawings. Note that the embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, arrangement positions and connection configurations of components, steps, and the order of steps shown in the following embodiments are examples only and are not intended to limit the present invention. Furthermore, components in the following embodiments that are not described in an independent claim will be described as optional components.
[0015] Please note that each figure is a schematic diagram and not necessarily a strictly accurate representation. Furthermore, in each figure, substantially identical components are denoted by the same reference numerals, and redundant explanations may be omitted or simplified.
[0016] (Embodiment) [composition] First, the configuration of the inspection support system according to the embodiment will be described. Figure 1 is a block diagram showing the configuration of the inspection support system according to the embodiment.
[0017] The inspection support system 10 is a system that can support the reinforcement inspection by workers at the construction site. The reinforcement inspection is an inspection to confirm whether the arrangement of steel bars, the thickness (diameter of steel bars), the number of steel bars, etc. in a building under construction match the design information (design drawings). FIG. 2 is a diagram showing a worker who performs the reinforcement inspection using the inspection support system 10. The worker can perform the reinforcement inspection relatively easily by taking an image of the steel bar structure to be inspected using the portable inspection support device 20.
[0018] As shown in FIG. 1, the inspection support system 10 includes an inspection support device 20 and a server device 30.
[0019] The inspection support device 20 is a portable information terminal used by workers to perform the reinforcement inspection. The inspection support device 20 is realized, for example, by attaching a dedicated adapter to a general-purpose information terminal such as a smartphone or a tablet terminal, but it may also be a dedicated information terminal. Specifically, the inspection support device 20 includes an operation reception unit 21, a display unit 22, an information processing unit 23, a storage unit 24, a communication unit 25, an imaging unit 26, and an acceleration sensor 27.
[0020] The operation reception unit 21 receives the input (manual operation) of the worker. The operation reception unit 21 is realized, for example, by a touch panel.
[0021] [[ID=ID=16]]The display unit 22 displays an image. The display unit 22 is realized, for example, by a display panel such as a liquid crystal panel or an organic EL (Electro Luminescence) panel.
[0022] The information processing unit 23 performs information processing to support the reinforcement bar inspection by the worker. The information processing unit 23 is implemented by, for example, a microcomputer, but may also be implemented by a processor. The information processing unit 23 includes, as functional components, an acquisition unit 23a, an estimation unit 23b, a grouping unit 23c, a display control unit 23d, and an inspection unit 23e. The functions of the acquisition unit 23a, estimation unit 23b, grouping unit 23c, display control unit 23d, and inspection unit 23e are realized, for example, by the microcomputer or processor constituting the information processing unit 23 executing a computer program stored in the storage unit 24. The detailed functions of the acquisition unit 23a, estimation unit 23b, grouping unit 23c, display control unit 23d, and inspection unit 23e will be described later.
[0023] The memory unit 24 is a storage device that stores computer programs executed by the information processing unit 23, as well as various information necessary for the information processing unit 23 to perform the above processing. The memory unit 24 is implemented, for example, by semiconductor memory.
[0024] The communication unit 25 is a communication module (communication circuit) that enables the inspection support device 20 to communicate with the server device 30 via a wide-area communication network 90 such as the Internet. The communication performed by the communication unit 25 is, for example, wireless communication. The communication standard used for communication is not particularly limited.
[0025] The imaging unit 26 captures an image. The imaging unit 26 is a stereo camera capable of measuring, for example, the distance from the position of the inspection support device 20 when capturing an image to the subject appearing in the image.
[0026] The acceleration sensor 27 detects the acceleration applied to the inspection support device 20. The acceleration sensor 27 is used to detect the position (displacement), orientation, and vertical direction of the inspection support device 20 when an operator takes an image using the inspection support device 20.
[0027] The server device 30 communicates with the inspection support device 20 (communication unit 25) to receive login information entered by the worker into the inspection support device 20, and performs authentication of the received login information (in other words, user authentication). If user authentication is successful, the server device 30 sends a usage permission notification to the inspection support device 20. Upon receiving the usage permission notification, the inspection support device 20 becomes ready to perform rebar inspection. The following example of operation is assumed to occur after successful user authentication.
[0028] [Example of operation] Next, we will describe an example of the operation of the inspection support device 20, which assists workers in inspecting the reinforcement bar placement. Figure 3 is a flowchart of the operation example of the inspection support device 20.
[0029] The operator performs a shooting operation to photograph the reinforcing bar structure to be inspected, and the operation reception unit 21 receives the shooting operation (S11). Based on the received shooting operation, the acquisition unit 23a uses the imaging unit 26 to capture an image (still image) of the reinforcing bar structure and acquires the image information of the captured image (S12). As described above, the imaging unit 26 is a stereo camera, and in step S12, image information of two images taken from different shooting positions is acquired in a single shooting. In other words, the image information includes the actual image data of the two images (stereo images) and viewpoint information (information indicating the distance between the shooting positions), and it is possible to identify the three-dimensional shape of the reinforcing bar structure using such image information. In other words, the reinforcing bars can be detected in the next step S13. In step S12, as an example, the reinforcing bar structure of a column, as shown in Figure 2, is taken. Image capture is performed multiple times, for example, by changing the shooting position, but it is sufficient to perform it at least once.
[0030] Next, the estimation unit 23b estimates the attributes of each of the multiple reinforcing bars included in the reinforcing structure shown in the image, along with their confidence levels, based on the image information acquired in step S12 (S13). The estimation unit 23b, for example, uses a machine learning model (a trained model) to detect multiple reinforcing bars shown in the image and estimates the diameter of each of the detected reinforcing bars along with its confidence level (in other words, likelihood). Specifically, for a single reinforcing bar, the estimation unit 23b estimates the diameter of the reinforcing bar and its confidence level, such as reinforcing bar diameter D10 (confidence level 50%), reinforcing bar diameter D13 (confidence level 30%), and so on. In other words, the machine learning model is a trained model that takes image information as input and can output the diameter of each of the one or more reinforcing bars shown in the image indicated by the image information, along with its confidence level. The machine learning model is an example of AI (Artificial Intelligence), and the diameter of the reinforcing bar is an example of an attribute of a reinforcing bar. If multiple images are taken in step S12, the rebar diameter may be estimated using a method such as majority voting.
[0031] The attributes of the reinforcing bars may also include their orientation (position) and length. In step S13, it is sufficient for at least one of the structural attributes of the reinforcing bars—the orientation, diameter, and length—to be estimated along with a confidence level. Each of the detected reinforcing bars is assigned individual identification information.
[0032] Next, the grouping section 23c groups the multiple reinforcing bars detected in step S13 based on the confidence level estimated in step S13 (S14).
[0033] For example, the grouping unit 23c treats the most reliable diameter of each of the multiple reinforcing bars as the estimated diameter of that reinforcing bar. The grouping unit 23c groups the multiple reinforcing bars into a first group whose confidence level for the estimation result is above a threshold, and a second group whose confidence level for the estimation result is below the first threshold, and assigns common group identification information to the reinforcing bars belonging to the same group. The first threshold is, for example, 50%, but is not particularly limited. The grouping unit 23c may also group the multiple reinforcing bars into three or more groups.
[0034] Next, the display control unit 23d displays a confirmation screen on the display unit 22 for the operator to check and correct the estimated diameter of multiple reinforcing bars (S15). Figure 4 shows an example of the confirmation screen. The confirmation screen in Figure 4 includes a first area 22a where the image taken in step S12 is displayed, and a second area 22b located to the right of the first area 22a where multiple reinforcing bars are displayed in a list.
[0035] Object 22d is superimposed on each of the multiple reinforcing bars shown in the image displayed in the first region 22a. Object 22d is associated with individual identification information assigned in step S13 (detection numbers from 0 to 11 in Figure 4) and the estimated reinforcing bar diameter results estimated in step S13 (such as D10 and D13 in Figure 4). In other words, on the confirmation screen, the estimated reinforcing bar diameter results are superimposed on the image.
[0036] In area 22b, the individual identification information and estimated diameter of each of the multiple reinforcing bars are displayed in a list. In other words, on the confirmation screen, the estimated diameter of the reinforcing bars is shown alongside the image.
[0037] In the second area 22b, there is a first tab 22e for selecting a first group whose confidence level for the estimation results is above a threshold, and a second tab 22f for selecting a second group whose confidence level for the estimation results is below a threshold. When the first tab 22e is selected, the first area 22a displays the reinforcing bar objects 22d belonging to the first group, and the second area 22b displays a list of the individual identification information and estimated reinforcing bar diameters of the reinforcing bars belonging to the first group. When the first tab 22e is not selected, the first area 22a does not display the reinforcing bar objects 22d belonging to the first group, and the second area 22b does not display the individual identification information and estimated reinforcing bar diameters of the reinforcing bars belonging to the first group.
[0038] Furthermore, when the second tab 22f is selected, the first area 22a displays the reinforcing bar objects 22d belonging to the second group, and the second area 22b displays a list of the individual identification information and estimated reinforcing bar diameters of the reinforcing bars belonging to the second group. When the second tab 22f is not selected, the first area 22a does not display the reinforcing bar objects 22d belonging to the second group, and the second area 22b does not display the individual identification information and estimated reinforcing bar diameters of the reinforcing bars belonging to the second group. Figure 4 shows the confirmation screen when the first tab 22e is selected and the second tab 22f is not selected.
[0039] When the confirmation screen described above is displayed, the worker visually checks the diameter of the actual reinforcing bar and compares the result of the visual check with the estimated result of the reinforcing bar diameter displayed on the confirmation screen. If the result of the visual check and the estimated result differ, the worker performs a correction operation to correct the estimated result, and the operation reception unit 21 accepts the correction operation (S16). The correction operation here includes the selection operation of the pull-down 22g in the second area 22b and the operation of specifying the correction candidate displayed by the selection operation (i.e., the operation to correct the estimated result to the result of the visual check).
[0040] By deselecting the first tab 22e and selecting the second tab 22f, the worker can prioritize checking and correcting items with low confidence in the estimation results. In other words, the worker can quickly check and correct the rebar diameter.
[0041] Once the operator has confirmed and corrected the estimation results, they perform a save operation to save the confirmation results, and the operation reception unit 21 accepts the save operation (S17). The save operation is, for example, the selection of the save button 22h.
[0042] In response to the received save operation, the inspection unit 23e performs a process to store the image information acquired in step S12 and the confirmation result determined by the correction operation in step S16 in the storage unit 24 (S18). In other words, the inspection unit 23e saves the inspection result.
[0043] As described above, the inspection support device 20 can assist workers in inspecting reinforcement bar placement. The inspection support device 20 groups multiple reinforcing bars included in the reinforced bar structure based on the reliability of the estimated diameter of the reinforcing bar, and has a function to switch the display on and off of the estimated results of each of the multiple reinforcing bars on the display unit 22 for each group. With such an inspection support device 20, workers can prioritize checking and correcting those with low reliability in the estimated results. In other words, workers can quickly check and correct the diameter of the reinforcing bars.
[0044] [Bulk correction of rebar diameter] In the above example, the rebar diameter was corrected one by one by the worker. However, the worker can also correct the rebar diameter of multiple rebars at once.
[0045] In Figure 4, the first tab 22e contains a batch modification button 22i and a batch modification pull-down menu 22j. The batch modification button 22i includes four buttons: a deselect button, a select all button, a vertical selection button, and a horizontal selection button. By selecting the select all button and then selecting the batch modification pull-down menu 22j to specify modification candidates, the operator can batch modify the reinforcing bar diameters of the reinforcing bars belonging to the first group.
[0046] Furthermore, by selecting the vertical selection button and selecting the batch modification dropdown 22j to specify the modification candidates, the operator can batch modify the diameter of the vertically long reinforcing bars (main reinforcement bars in the case of a column structure) belonging to the first group. By selecting the horizontal selection button and selecting the batch modification dropdown 22j to specify the modification candidates, the operator can batch modify the diameter of the horizontally long reinforcing bars (stirrups in the case of a column structure) belonging to the first group.
[0047] Although not shown in the diagram, the second tab 22f also contains a batch modification button and a batch modification dropdown menu, allowing the operator to perform batch modifications on reinforcing bars belonging to the second group in the same way as reinforcing bars belonging to the first group.
[0048] When the Select All button, Vertical Selection button, or Horizontal Selection button is selected, the target reinforcing bars are displayed in a different manner from the excluding reinforcing bars in the second area 22b. Figure 5 shows an example of the confirmation screen when the Horizontal Selection button is selected. In this way, if the reinforcing bars belonging to the horizontal group are displayed in a different manner from the reinforcing bars belonging to the vertical group, the worker can easily identify reinforcing bars within the horizontal group whose estimated diameter differs from other reinforcing bars. In other words, the worker can easily check and correct the estimated reinforcing bar diameter.
[0049] Furthermore, reinforcing bars that are long in the vertical direction and reinforcing bars that are long in the horizontal direction are grouped in advance. The grouping unit 23c can detect the vertical direction in the image acquired in step S12 using the acceleration sensor 27. The grouping unit 23c assigns the reinforcing bars that are long in the vertical direction to the vertical group and the other reinforcing bars to the horizontal group. As a result, the inspection support device 20 can perform a batch correction of the reinforcing bar diameters of the reinforcing bars that are long in the vertical direction and a batch correction of the reinforcing bar diameters of the reinforcing bars that are long in the horizontal direction.
[0050] As explained above, the inspection support device 20 allows the operator to correct the diameter of multiple reinforcing bars simultaneously. Therefore, the operator can quickly check and correct the diameter of the reinforcing bars.
[0051] In addition, while the grouping section 23c groups multiple reinforcing bars included in the reinforced concrete structure into longitudinal and transverse groups, the grouping method is not limited to this method. Generally, reinforced concrete structures have the following characteristics.
[0052] Reinforcing bars aligned in the same direction often have the same diameter.
[0053] Reinforcing bars are often arranged at equal intervals.
[0054] Multiple reinforcing bars are often positioned either parallel to each other or perpendicular to each other.
[0055] Reinforcing bars of the same length often have the same diameter.
[0056] Reinforcing bars of the same length are often arranged in parallel.
[0057] Therefore, when checking and correcting attributes related to the structure of reinforcing bars, the grouping unit 23c can group multiple reinforcing bars based on structural features obtained from image information that are different from the above-mentioned attributes. For example, when checking and correcting one of the orientation, diameter, and length of reinforcing bars, multiple reinforcing bars can be grouped based on the other one of the orientation, diameter, and length of reinforcing bars.
[0058] Furthermore, in Figures 4 and 5, grouping based on structural characteristics is performed within each group based on confidence level, but grouping based on structural characteristics may be performed without performing grouping based on confidence level.
[0059] [Variations in displaying estimation results] In the second area 22b of the confirmation screen, only the attribute with the highest reliability (rebar diameter) was displayed as the estimated result for each of the multiple reinforcing bars. However, two or more attributes may be displayed in the second area 22b in order of highest reliability.
[0060] For example, for reinforcing bars among multiple reinforcing bars whose confidence level for the estimation result (highest confidence level) is less than the second threshold, the attribute with the second highest confidence level may be displayed in addition to the estimation result. Figure 6 shows a modified example of the display of estimation results in the second region 22b (a modified example of the confirmation screen). In the example in Figure 6, the reinforcing bar diameter corresponding to detection number: 1 is displayed with the reinforcing bar diameter D13, which has the second highest confidence level, in addition to the reinforcing bar diameter D10, which has the highest confidence level.
[0061] In this way, the inspection support device 20 displays two or more attributes in order of highest reliability, making it easier for operators to check and correct attributes.
[0062] Furthermore, in the first area 22a of the confirmation screen, two or more attributes may be displayed in order of highest confidence level. Specifically, in the object 22d assigned to a reinforcing bar among multiple reinforcing bars whose confidence level for the estimation result (highest confidence level) is less than the second threshold, the second most confident attribute may be displayed in addition to the estimation result.
[0063] Furthermore, the second threshold may be the same value as the first threshold used for confidence-based grouping, or it may be a different value. If the second threshold is the same value as the first threshold, then for all reinforcing bars displayed when the second tab 22f is selected, the second most confident attribute will be displayed in addition to the estimated result.
[0064] [Other variations] In the above embodiment, the confirmation screen displayed both the overlay display of attributes (object 22d) on the image and a list display of attributes (indication of attributes alongside the image). However, the confirmation screen only needs to display at least one of the overlay display of attributes on the image and a list display of attributes; it is not necessary to display both.
[0065] In the above embodiment, image information from images captured by a stereo camera was used to detect the reinforcing bars included in the reinforced concrete structure. However, the inspection support device 20 may also be equipped with a ToF (Time of Flight) camera as the imaging unit 26, and the estimation unit 23b may detect the reinforcing bars included in the reinforced concrete structure based on image information from images (distance images) captured by the ToF camera.
[0066] Furthermore, the inspection support device 20 may be equipped with a 3D scanner such as LiDAR (Light Detection And Ranging), and the reinforcing bars contained in the reinforcing structure may be detected based on point cloud data showing the unevenness of the reinforcing structure acquired by the 3D scanner.
[0067] In the above embodiment, the specifications of the GUI (Graphical User Interface) on the confirmation screen are just an example. For example, the display and hiding of the estimated results for each of the multiple reinforcing bars on the display unit 22 may be done by a toggle switch or the like instead of tabs.
[0068] In the above embodiment, some of the processes described as being performed by the inspection support device 20 may be performed by the server device 30. For example, the attribute and confidence level estimation processes may be performed by the server device 30.
[0069] [Effects, etc.] The following describes examples of inventions that can be obtained from the disclosures in this specification, and explains the effects and other benefits that can be obtained from these examples.
[0070] Invention 1 is an inspection support system 10 that assists in the inspection of reinforced concrete structures, comprising: an acquisition unit 23a that acquires image information of an image showing the reinforced concrete structure; an estimation unit 23b that estimates the structural attributes of each of the multiple reinforcing bars included in the reinforced concrete structure shown in the image, along with their reliability, based on the acquired image information; a display unit 22; and a display control unit 23d that displays the estimated attributes and reliability on the display unit 22.
[0071] Such an inspection support system 10 can assist in confirming the attributes of reinforcing bars. According to the inspection support system 10, workers can prioritize checking those with low confidence in the estimated results. In other words, workers can quickly confirm the attributes of reinforcing bars. The inspection support system 10 of Invention 1 can be said to be a system that improves the work efficiency of confirming the attributes of reinforcing bars compared to the reinforcing bar measurement system described in Patent Document 1.
[0072] Invention 2 is the inspection support system 10 of Invention 1, wherein the display control unit 23d displays an image on the display unit 22 in which the attribute with the highest reliability for each of the multiple reinforcing bars is superimposed or listed as the estimated result, and the inspection support system 10 further includes an operation reception unit 21 that receives operations from the worker to correct the estimated result, and a grouping unit 23c that groups the multiple reinforcing bars based on the reliability of the estimated result, and the display control unit 23d switches the display and hiding of the estimated result for each of the multiple reinforcing bars on the display unit 22 on a group basis.
[0073] Such an inspection support system 10 can assist in confirming the attributes of reinforcing bars. According to the inspection support system 10, the worker can prioritize confirming and correcting those with low reliability in the estimated results. In other words, the worker can quickly perform attribute confirmation and correction work. The inspection support system 10 of Invention 2 can be said to be a system that improves the work efficiency of confirming and correcting the attributes of reinforcing bars compared to the reinforcing bar measurement system described in Patent Document 1.
[0074] Invention 3 is an inspection support system 10 of Invention 2, wherein for reinforcing bars among multiple reinforcing bars whose confidence level for the estimated result is below a threshold, the second most reliable attribute is superimposed or listed alongside the estimated result.
[0075] This inspection support system 10 displays two attributes in order of reliability, making it easy for workers to confirm and correct attributes. Compared to the reinforcement measurement system described in Patent Document 1, the inspection support system 10 of Invention 3 is a system that improves the work efficiency of confirming and correcting the attributes of reinforcement bars.
[0076] Invention 4 is an inspection support system 10 of Invention 2 or 3, wherein the grouping unit 23c further groups multiple reinforcing bars based on structural features obtained from image information that are different from attributes, and the operation reception unit 21 receives operations from an operator to collectively modify the estimation results in groups based on structural features.
[0077] Such an inspection support system 10 allows the worker to modify the attributes of reinforcing bars all at once. The worker can quickly select the reinforcing bars to be inspected. Compared to the reinforcing bar measurement system described in Patent Document 1, the inspection support system 10 of Invention 4 is a system that improves the work efficiency of reinforcing bar selection work and revising the attributes of selected reinforcing bars.
[0078] Invention 5 is an inspection support system 10 of any of Inventions 1 to 4, wherein the attributes include at least one of the orientation of the reinforcing bar, the diameter of the reinforcing bar, and the length of the reinforcing bar.
[0079] Such an inspection support system 10 can assist in confirming at least one of the reinforcing bar orientation, diameter, and length. Compared to the reinforcing bar measurement system described in Patent Document 1, the inspection support system 10 of Invention 5 is a system that improves the work efficiency of confirming the attributes of reinforcing bars, such as the orientation, diameter, and length of the reinforcing bars.
[0080] Invention 6 is an inspection support system 10 for assisting in the inspection of reinforced concrete structures, comprising: an acquisition unit 23a that acquires image information of an image showing the reinforced concrete structure; an estimation unit 23b that estimates the structural attributes of each of the multiple reinforced concrete bars included in the reinforced concrete structure shown in the image based on the acquired image information; a display unit 22; a display control unit 23d that displays an image on the display unit 22 in which the estimated results of the attributes of each of the multiple reinforced concrete bars are superimposed or listed together; a grouping unit 23c that groups the multiple reinforced concrete bars based on structural features obtained from the image information that are different from the attributes; and an operation reception unit 21 that receives operator operations for batch correcting the estimation results in groups based on structural features.
[0081] Such an inspection support system 10 can assist in confirming the attributes of reinforcing bars. Specifically, the inspection support system 10 allows the inspector to modify the attributes of reinforcing bars all at once, thereby enabling the inspector to quickly confirm and modify the attributes. Compared to the reinforcing bar measurement system described in Patent Document 1, the inspection support system 10 of Invention 6 is a system that improves the work efficiency of reinforcing bar selection work and revising the attributes of selected reinforcing bars.
[0082] Invention 7 is an inspection support system 10 that assists in the inspection of reinforced concrete structures, comprising: an acquisition unit 23a that acquires image information of an image showing the reinforced concrete structure; an estimation unit 23b that inputs the acquired image information into a machine learning model to estimate the structural attributes of each of the multiple reinforcing bars included in the reinforced concrete structure shown in the image; a display unit 22; a display control unit 23d that displays the estimated attributes on the display unit 22; and an operation reception unit 21 that receives operator input to correct the estimated attributes.
[0083] Such an inspection support system 10 can assist in confirming the attributes of reinforcing bars. The inspection support system 10 of Invention 7 can be said to be a system that improves workability compared to the reinforcing bar measurement system described in Patent Document 1 by introducing a machine learning model.
[0084] Invention 8 is an inspection support method for assisting in the inspection of a reinforced concrete structure, which is performed by a computer and includes an acquisition step of acquiring image information of an image showing a reinforced concrete structure, an estimation step of estimating the structural attributes of each of the multiple reinforced concrete bars included in the reinforced concrete structure shown in the image, along with their reliability, based on the acquired image information, and a display step of displaying the estimated attributes and reliability on a display unit.
[0085] Such inspection support methods can assist in confirming the attributes of reinforcing bars. According to the inspection support method, workers can prioritize checking items with low reliability in the estimated results. In other words, workers can quickly confirm the attributes of reinforcing bars. The inspection support method of Invention 1 can be said to be a method that improves the work efficiency of confirming the attributes of reinforcing bars compared to the reinforcing bar measurement method described in Patent Document 1.
[0086] Invention 9 is an inspection support method in which, in the display step, an image is displayed on the display unit 22 in which the attribute with the highest reliability for each of the multiple reinforcing bars is superimposed or listed as the estimated result, and the inspection support method further includes an operation reception step that accepts operations from an operator to correct the estimated result, and a grouping step that groups the multiple reinforcing bars based on the reliability of the estimated result, and in the display step, the display and hiding of the estimated result for each of the multiple reinforcing bars on the display unit 22 is switched for each group.
[0087] Such inspection support methods can assist in confirming the attributes of reinforcing bars. According to the inspection support method, workers can prioritize confirming and correcting those with low reliability in the estimated results. In other words, workers can quickly perform attribute confirmation and correction work. The inspection support method of Invention 9 can be said to be a method that improves the work efficiency of confirming and correcting the attributes of reinforcing bars compared to the reinforcing bar measurement method described in Patent Document 1.
[0088] Invention 10 is an inspection support method for assisting in the inspection of a reinforced concrete structure, which is performed by a computer and includes an acquisition step of acquiring image information of an image showing the reinforced concrete structure; an estimation step of estimating the structural attributes of each of the multiple reinforced concrete bars included in the reinforced concrete structure shown in the image based on the acquired image information; a display step of displaying an image on a display unit 22 in which the estimated results of the attributes of each of the multiple reinforced concrete bars are superimposed or listed together; a grouping step of grouping the multiple reinforced concrete bars based on structural features obtained from the image information that are different from the attributes; and an operation reception step of receiving an operation from an operator to collectively modify the estimation results in groups based on structural features.
[0089] Such inspection support methods can assist in confirming the attributes of reinforcing bars. Compared to the reinforcing bar measurement method described in Patent Document 1, the inspection support method of Invention 10 is a system that improves the work efficiency of reinforcing bar selection and the modification of the attributes of selected reinforcing bars.
[0090] Invention 11 is an inspection support method for assisting in the inspection of a reinforced concrete structure, which is performed by a computer and includes an acquisition step of acquiring image information of an image showing the reinforced concrete structure, an estimation step of inputting the acquired image information into a machine learning model to estimate the structural attributes of each of the multiple reinforced concrete bars included in the reinforced concrete structure shown in the image, a display step of displaying the estimated attributes on a display unit 22, and an operation reception step of receiving operations from an operator to correct the estimated attributes.
[0091] Such inspection support methods can assist in confirming the attributes of reinforcing bars. The inspection support method of Invention 7 can be said to be a system that improves work efficiency compared to the reinforcing bar measurement method described in Patent Document 1 by introducing a machine learning model.
[0092] Invention 12 is a program for causing a computer to execute one of the inspection support methods of Inventions 8 to 11.
[0093] Such a program allows a computer to assist in verifying the attributes of reinforcing bars.
[0094] (Other embodiments) Although embodiments have been described above, the present invention is not limited to the embodiments described above.
[0095] For example, in the above embodiment, the inspection support system was implemented by multiple devices, but it may also be implemented as a single device. For example, the inspection support system may be implemented as a single device corresponding to an inspection support device. When the inspection support system is implemented by multiple devices, the components of the inspection support system may be distributed among the multiple devices in any way.
[0096] Furthermore, the communication method between devices in the above embodiment is not particularly limited. In addition, a relay device (not shown) may be interposed in the communication between devices.
[0097] Furthermore, in the above embodiment, a process performed by a specific processing unit may be performed by another processing unit. For example, in the above embodiment, some or all of the processes described as being performed by the information processing server may be performed by an information terminal. Also, the order of multiple processes may be changed, or multiple processes may be executed in parallel.
[0098] Furthermore, in the above embodiment, each component may be realized by executing a software program suitable for each component. Each component may also be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.
[0099] Furthermore, each component may be implemented by hardware. For example, each component may be a circuit (or integrated circuit). These circuits may form a single circuit as a whole, or they may be separate circuits. Also, each of these circuits may be a general-purpose circuit or a dedicated circuit.
[0100] Furthermore, general or specific embodiments of the present invention may be implemented as a system, apparatus, method, integrated circuit, computer program, or recording medium such as a computer-readable CD-ROM. Alternatively, they may be implemented as any combination of a system, apparatus, method, integrated circuit, computer program, and recording medium.
[0101] For example, the present invention may be implemented as an inspection support system or inspection support device as described above. The present invention may be implemented as a method executed by a computer such as an inspection support system or inspection support device, or as a program (computer program product) for causing a computer to execute such a method. The present invention may be implemented as a computer-readable non-temporary recording medium on which these programs are recorded.
[0102] Furthermore, the present invention also includes forms obtained by applying various modifications to each embodiment that a person skilled in the art could conceive, or forms realized by arbitrarily combining the components and functions of each embodiment without departing from the spirit of the present invention. [Explanation of Symbols]
[0103] 10. Inspection support system 20 Inspection support device 21 Operation Reception Section 22 Display section 22a 1st area 22b Second area 22d object 22e Tab 1 22f Second Tab 22g pull down 22h Save button 22i Batch Correction Button 22j Batch Editing Dropdown 23 Information Processing Department 23a Acquisition Department 23b Estimation part 23c Grouping section 23d Display Control Unit 23e Inspection Department 24 Memory section 25 Communications Department 26 Imaging Department 27. Accelerometer 30 Server Devices 90 Wide-area telecommunications network
Claims
1. An inspection support system that assists in the inspection of reinforced concrete structures, An acquisition unit that acquires image information of the image showing the aforementioned reinforced concrete structure, An estimation unit that estimates the structural attributes of each of the multiple reinforcing bars included in the reinforcing bar structure shown in the image, along with their reliability, based on the acquired image information. Display unit and The system includes a display control unit that displays the estimated attribute and the confidence level on the display unit. Inspection support system.
2. The display control unit displays the image on the display unit in which the attribute with the highest reliability for each of the plurality of reinforcing bars is superimposed or listed as an estimated result. The aforementioned inspection support system further, An operation reception unit that receives operator input to correct the aforementioned estimation result, The system includes a grouping section that groups the plurality of reinforcing bars based on the confidence level of the estimation result, The display control unit switches the display and hiding of the estimation results for each of the plurality of reinforcing bars on the display unit on a group-by-group basis. The inspection support system according to claim 1.
3. For any of the aforementioned multiple reinforcing bars whose confidence level for the estimation result is below a threshold, the attribute with the second highest confidence level is superimposed or listed alongside the estimation result. The inspection support system according to claim 2.
4. The grouping section further groups the plurality of reinforcing bars based on structural features obtained from the image information that are different from the attributes, The operation reception unit receives operations from the operator to collectively modify the estimation results in groups based on the structural characteristics. The inspection support system according to claim 2 or 3.
5. The aforementioned attributes include at least one of the orientation of the reinforcing bar, the diameter of the reinforcing bar, and the length of the reinforcing bar. The inspection support system according to any one of claims 1 to 3.
6. An inspection support system that assists in the inspection of reinforced concrete structures, An acquisition unit that acquires image information of the image showing the aforementioned reinforced concrete structure, An estimation unit that estimates the structural attributes of each of the multiple reinforcing bars included in the reinforcing bar structure shown in the image based on the acquired image information, Display unit and A display control unit that displays the image on the display unit in which the estimated results of the attributes of each of the plurality of reinforcing bars are superimposed or listed together, A grouping unit that groups the plurality of reinforcing bars based on structural features obtained from the image information that are different from the attributes, The system includes an operation reception unit that accepts operator input for batch modification of the estimation results in group units based on the structural characteristics. Inspection support system.
7. An inspection support system that assists in the inspection of reinforced concrete structures, An acquisition unit that acquires image information of the image showing the aforementioned reinforced concrete structure, An estimation unit that inputs the acquired image information into a machine learning model to estimate the structural attributes of each of the multiple reinforcing bars included in the reinforcing bar structure shown in the image, Display unit and A display control unit that displays the estimated attribute on the display unit, It includes an operation reception unit that receives operator input for correcting the estimated attribute. Inspection support system.
8. A computer-based inspection support method for assisting in the inspection of reinforced concrete structures, The acquisition step involves acquiring image information of an image showing the aforementioned reinforced concrete structure, An estimation step in which, based on the acquired image information, the structural attributes of each of the multiple reinforcing bars included in the reinforcing bar structure shown in the image are estimated along with their reliability, The step includes displaying the estimated attribute and the confidence level on the display unit. Testing support methods.
9. In the display step, the image in which the attribute with the highest reliability for each of the plurality of reinforcing bars is superimposed or listed as an estimated result is displayed on the display unit. The aforementioned inspection support method further, An operation reception step that accepts operator operations to correct the aforementioned estimation result, The group of reinforcing bars is formed based on the confidence level of the estimation result. Includes a step, In the display step, the display and hiding of the estimation results for each of the plurality of reinforcing bars on the display unit is switched on a group-by-group basis. The inspection support method according to claim 8.
10. A computer-based inspection support method for assisting in the inspection of reinforced concrete structures, The acquisition step involves acquiring image information of an image showing the aforementioned reinforced concrete structure, An estimation step in which, based on the acquired image information, the structural attributes of each of the multiple reinforcing bars included in the reinforcing bar structure shown in the image are estimated, A display step in which the estimated results of the attributes of each of the plurality of reinforcing bars are superimposed or listed together in the image displayed on the display unit, A grouping step of grouping the plurality of reinforcing bars based on structural features obtained from the image information that are different from the attributes, The estimation results include an operation acceptance step that accepts an operator's operation to collectively modify them in groups based on the structural characteristics. Testing support methods.
11. A computer-based inspection support method for assisting in the inspection of reinforced concrete structures, The acquisition step involves acquiring image information of an image showing the aforementioned reinforced concrete structure, An estimation step in which the acquired image information is input into a machine learning model to estimate the structural attributes of each of the multiple reinforcing bars included in the reinforcing bar structure shown in the image, A display step in which the estimated attribute is displayed on the display unit, Includes an operation acceptance step that accepts an operator's operation to correct the estimated attribute. Testing support methods.
12. A program for causing the computer to execute the inspection support method described in any one of claims 8 to 11.
Citation Information
Patent Citations
Bar arrangement measurement system, bar arrangement measurement method, and program
JP2020166660A