JP6368207B2 - Inspection support device, inspection support method, and program for concrete structure - Google Patents

Description

  The present technology relates to an inspection support device, an inspection support method, and a program for a concrete structure.

  Conventionally, a technique for detecting a crack from an image of a concrete structure has been proposed (for example, Patent Document 1). In this technique, a plurality of two-dimensional edge filters having different directions and widths are respectively applied to an image, and a crack candidate image is generated using a Hopfield type neural network.

  In addition, a technique has been proposed in which an image of reinforced concrete is divided into meshes, and the magnitude of scientific degradation is displayed in different colors for each mesh (for example, Patent Document 2). In this technology, the deterioration factors such as chloride ion concentration and calcium carbonate concentration and the reinforced concrete cover are input for each mesh, and the service life of the reinforced concrete is input, and the deterioration degree of each mesh is obtained based on the input values. .

JP 2011-242365 A JP 2010-271062 A

  Conventionally, technologies that improve the accuracy of distinguishing cracks and dirt in image processing, and technologies that display the degree of deterioration based on specific factors such as chemical deterioration by inputting information on reinforced concrete have been proposed. It had been. Here, in order to perform a concrete structure inspection at a level that can withstand practical use without depending on the knowledge and ability of the inspector, it is possible to identify the cause of deterioration while reducing the work burden on the inspector. Is desirable.

  This invention is made in view of such a problem, and it aims at improving the precision at the time of estimating a deterioration state based on the image which imaged the concrete structure.

  An inspection support device for a concrete structure according to the present invention relates to an image reading unit that reads out image data in which a concrete structure to be inspected is imaged and to which position information indicating a position is added, and is associated with information on the concrete structure. A deterioration factor acquisition unit for acquiring a deterioration factor associated with the information of the concrete structure corresponding to the position information of the image data read by the image reading unit, and a deterioration factor acquisition from the storage device that stores the deterioration factor The image data read by the image reading unit is analyzed using the degradation information acquired by the unit and the reference information obtained by learning in advance the features that appear on the surface of the concrete structure for each degradation factor. And an image analysis unit that determines the state of deterioration of the structure.

  In this way, it is possible to analyze the image data in consideration of not only the captured concrete structure information but also the deterioration factor associated with the concrete structure. Therefore, it is possible to improve the accuracy when estimating the deterioration state based on the image obtained by capturing the concrete structure.

  In addition, the image analysis unit may preferentially select a deterioration state caused by the deterioration factor acquired by the deterioration factor acquisition unit in the analysis of the image data. By preferentially selecting the reference information indicating the characteristics of the deterioration state caused by the deterioration factor associated with the concrete structure, the accuracy in estimating the deterioration state can be improved.

  In addition, the image analysis unit preferentially uses the reference information obtained by learning the characteristics of the deterioration state caused by the deterioration factor acquired by the deterioration factor acquisition unit in the determination of the deterioration state to the concrete structure. Deterioration that occurs in concrete structures by judging the state of deterioration that occurred or weighting the deterioration state caused by the deterioration factor acquired by the deterioration factor acquisition unit more than other deterioration states The state may be determined. Specifically, the accuracy in estimating the deterioration state is improved by such processing.

  In addition, the storage device stores a cause of deterioration that may occur in the concrete structure in association with the area information indicating the area, and the deterioration factor acquisition unit is the position information of the image data read by the image reading unit The factor of deterioration associated with the area including In this way, degradation factors that may occur depending on the area where the concrete structure is located can be narrowed down and prioritized, and judgment when recognizing images by analyzing image data Become a material. That is, it is possible to improve the accuracy when estimating the deterioration state based on an image obtained by imaging a concrete structure.

  Further, the storage device may store information on salt damage, information on alkali-silica reactive aggregate, information on frost damage, or information on chemical corrosion as a cause of deterioration associated with regional information. . Specifically, for example, by using at least one of these pieces of information, it is possible to improve the accuracy when estimating the deterioration state.

  The information on the concrete structure includes information on the design of the concrete structure, information on the construction, or information indicating the maintenance history, and the storage device stores information on the design of the concrete structure in association with the cause of deterioration. The condition that should be satisfied by the information related to the construction or the information indicating the history of maintenance may be stored. Specifically, the accuracy in estimating the deterioration state can be improved also by using at least one of these pieces of information.

  The contents described in the means for solving the problems can be combined as much as possible without departing from the problems and technical ideas of the present invention. The contents of the means for solving the problems can be provided as a device such as a computer or a system including a plurality of devices, a method executed by the computer, or a program executed by the computer. A recording medium that holds the program may be provided.

  ADVANTAGE OF THE INVENTION According to this invention, the precision at the time of estimating a deterioration state based on the image which imaged the concrete structure can be improved.

It is a figure for demonstrating the outline | summary of an inspection. It is a functional block diagram which shows an example of an inspection assistance apparatus. It is a figure which shows an example of the data structure of the information hold | maintained in structure DB. It is a figure which shows an example of the data structure of the information hold | maintained in deterioration factor DB. It is an apparatus block diagram which shows an example of a computer. It is a processing flowchart which shows an example of an inspection assistance process. It is a figure for demonstrating an example of the evaluation division of the damage grade regarding a concrete floor slab crack. It is a figure for demonstrating an example of the determination division regarding a concrete floor slab crack.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In addition, the following embodiment is an illustration of this invention and this invention is not limited to the following structure.

<Outline of inspection support>
FIG. 1 is a diagram for explaining an outline of inspection of a concrete structure (also simply referred to as “structure”) including inspection support according to the present embodiment. FIG. 1 shows an inspection support device 1, a structure 2, and an imaging device 3. The inspection support device 1 analyzes image (photograph) data obtained by imaging the structure 2 and other information, and estimates the state of deterioration of the structure 2 or evaluates the degree of deterioration. The inspection support apparatus 1 has a database (Database) in which predetermined information such as position information of the structure 2 to be inspected is stored in advance. The structure 2 is a structure formed of concrete, such as a bridge, tunnel lining concrete, a dam embankment, a retaining wall for a revetment, a building, etc., and is subject to inspection for deterioration in this embodiment. It is. The imaging device 3 is a device that generates image data such as a digital still camera or a digital video camera. The imaging device 3 includes a receiver for using a satellite positioning system such as GPS (Global Positioning System), and adds position information of the imaging device 3 to image data as metadata. The metadata can be embedded in the image data based on a standard such as Exif (Exchangeable Image File Format). Further, the position information may include latitude and longitude based on a predetermined geodetic system, and may further include altitude. In the case of image data taken at a place not under the GPS reception environment, the latitude and longitude of the position information may be added later by manual input. In such a system, the image data generated by the imaging device 3 is taken into the inspection support device 1 via a storage medium such as a memory card or via a network (not shown). Then, the inspection support apparatus 1 analyzes the image by using the position information added to the image data and the predetermined information held in the DB, and determines the deterioration state and the degree of the captured structure 2. .

  The inspection performed in this embodiment includes at least one of so-called daily inspection, periodic inspection, detailed inspection, emergency inspection, and temporary inspection. The inspection is carried out for the purpose of obtaining information necessary for efficient maintenance and management of the structure. Specifically, grasp the damage status, evaluate the degree of damage, determine countermeasures, record the inspection results, etc. According to the present embodiment, it is possible to reduce costs such as labor costs as compared with the case where such an inspection is carried out visually, and to reduce variations in determination accuracy caused by the ability of the inspector. .

  Moreover, the deterioration phenomenon of reinforced concrete is classified as follows. First, deterioration of reinforced concrete can be roughly divided into deterioration of concrete and deterioration of rebar. Furthermore, concrete deterioration can be classified into deterioration phenomena such as strength deterioration, cracking, and surface deterioration. On the other hand, the deterioration of reinforcing bars is mainly corrosion of reinforcing bars. And if the cause of deterioration of each deterioration phenomenon is mentioned, the strength deterioration of concrete will be mainly due to insufficient strength due to the water-cement ratio. In addition, concrete cracks include drying shrinkage, repeated temperature changes, alkali-aggregate reaction, repeated freeze / thaw action (freezing damage), poor construction, heat of hydration (mass concrete), reinforcing steel corrosion, fire cracks, structural cracks (bending)・ Deterioration causes such as shear), overload (large deflection), earthquake / foundation (unsettled settlement), and the like. On the other hand, rebar corrosion is caused by deterioration such as cracks, neutralization due to water cement ratio or lack of cover thickness, or chloride ions due to initial internal chloride (internal salt damage) or foreign chloride (external salt damage). It is done.

The deterioration phenomenon as described above appears in the appearance of reinforced concrete as a crack pattern that varies depending on the cause of deterioration. Therefore, the crack pattern can be recognized by image processing, the cause of deterioration can be specified, and the degree of damage and the necessity for repair can be determined. In addition, the cause of deterioration described above is, for example, that the structure closer to the coast is more likely to be corroded by external salt damage, or there is a difference in the risk of frost damage depending on the region, depending on the position of the structure. Can predict the possibility. In addition, it is possible to predict the possibility of deterioration depending on the constituent material of the structure and the size such as length or thickness. Therefore, in this embodiment, in addition to image processing, a deterioration state that is highly likely to occur using construction information such as position information of structures, design information such as constituent materials and sizes, construction time, temperature records during construction, etc. To identify. By doing so, it is possible to improve the accuracy of specifying the degradation state and the degree of evaluation by the image processing.

  Note that the imaging device 3 may record a moving image. In this case, one frame of the moving image may be extracted as a still image, or a still image may be generated from the moving image based on a predetermined algorithm. The generation of image data by the imaging device 3 can be performed by various methods. For example, the image data may be generated by an inspection vehicle that can image the lining surface while traveling in a tunnel. Alternatively, an elevated road / bridge inspection vehicle having a plurality of booms and capable of inserting a basket carrying an inspector from above the bridge girder over the sound barriers and fences and under the bridge girder may be used. Furthermore, if the imaging device 3 is mounted on a multicopter having a plurality of rotor blades, it is possible to inspect places where it is difficult for an inspector to approach.

  The position information may be acquired using a satellite positioning system such as GLONASS (Global Navigation Satellite System), or may be acquired using a Wi-Fi access point or the like.

<Functional configuration>
FIG. 2 is a functional block diagram illustrating an example of the inspection support apparatus 1 according to the present embodiment. The inspection support apparatus 1 includes an image storage unit 101, an image reading unit 102, a structure information acquisition unit 103, a structure DB 104, a deterioration factor acquisition unit 105, a deterioration factor DB 106, an image analysis unit 107, and a feature. The database includes a DB, a damage degree evaluation unit 109, and a result output unit 110.

  The image storage unit 101 stores image data obtained by imaging the structure 2. In the present embodiment, it is assumed that the image data of the structure 2 generated by the imaging device 3 is stored in the image storage unit 101 in advance. The image data from the imaging device 3 to the image storage unit 101 may be taken in via a portable storage medium such as a flash memory or an optical disk, or via a network such as the Internet. May be.

  The image reading unit 102 reads image data to be processed from the image storage unit 101. The image reading unit 102 reads position information added as metadata in addition to information indicating the image itself. The position information indicates the position where the image is captured, and the approximate position where the captured structure 2 exists can be specified based on the position information embedded in the image data.

The structure information acquisition unit 103 reads information related to the structure 2 held in the structure DB 104 in association with the position information. It is assumed that the structure DB 104 holds information about a structure to be inspected in advance. FIG. 3 is a diagram illustrating an example of a data structure of information stored in the structure DB 104. The structure DB includes items such as “structure identification information”, “position information”, “design information”, “construction information”, and “maintenance management information”. Here, in the item “structure identification information”, a name, ID, and the like for managing the structure to be inspected are held. The structure 2 may be registered in the structure DB 104 with a bridge pier and a bridge girder protruding from the pier as one unit, or with a predetermined section of lining concrete as one unit. The “position information” includes “latitude”, “longitude”, and “elevation” (for example, above sea level based on the average sea level).

The design information includes medium classification items such as “structure”, “dimension”, and “material”. The item “structure” further includes items such as “use”, “type”, “type”, “part”, “rebar ratio”, and “reinforced concrete thickness”. For example, bridges, retaining walls, water and sewage systems are registered in the “use” field. In “Type”, for example, RC (Reinforced Concrete), PC (Precast Concrete), unstitched, and the like are registered. For example, piers, retaining walls, box culverts, and the like are registered in the “type”. For example, a floor slab, a wall, or a pillar is registered in the “part”. The item “dimension” further includes items such as “member thickness”, “member width”, “lift height”, “induced joint”, and the like. Further, the item “material” includes items such as “constituent material of concrete”, “mixing of concrete”, “reinforcing material (fiber reinforcing material, etc.)” and the like.

  The “construction information” includes items such as “construction time”, “placement interval (days)”, “construction temperature (placement temperature, maximum temperature)”, and “maximum crack width”. The “maintenance management information” includes items such as “inspection history”, “repair history”, and “reinforcement history”. The structure information acquisition unit 103 reads, from the structure DB 104, for example, information on the structure having the closest distance from the position information added to the image data.

  The deterioration factor acquisition unit 105 reads information on the deterioration factor held in the deterioration factor DB 106. FIG. 4 is a diagram illustrating an example of a data structure of information stored in the deterioration factor DB 106. It is assumed that the deterioration factor DB 106 stores a “condition” indicating a deterioration factor in advance in association with “deterioration factor identification information”. Here, in the item of deterioration factor identification information, a name, ID, and the like indicating the deterioration factor are held. “Condition” includes “Regional information” indicating the area having the deterioration factor, “Structure”, “Dimension (size)”, “Material”, “Construction time”, “Laying interval”, “Construction temperature” of the structure ”Or“ maximum crack width ”and other information indicating deterioration factors are held in advance. “Regional information” is information indicating an area that includes a plurality of location information. “Salt damage environment area”, “Alkali silica reactive aggregate production area”, “Frost damage occurrence risk area”, Hot spring area For example, an area related to a “chemically corrosive environment area” such as an acidic river basin is registered together with information indicating the degree of its influence, for example. As the information indicating the area, for example, identification information of an area obtained by dividing the map into a grid mesh can be used. Specifically, a regional mesh code defined in Japanese Industrial Standard JIS X0410 may be used. In addition, in the item “material”, a constituent material of the structure 2 that can cause deterioration, such as sea sand, is held. In the “dimension” item, information indicating the dimension of the structure 2 that may cause deterioration, such as the length and thickness of the portion of the structure, the cover of the reinforcing bar, and the like is held. “Construction time” indicates the time when the structure was built. The construction time can affect the factors of deterioration due to the influence of regulations, such as materials and design standards. The deterioration factor acquisition unit 105 may affect the structure 2 from the deterioration factor DB 106 based on the position information read by the image reading unit 102, the structure design information acquired by the structure information acquisition unit 103, and the like. Read the information of the characteristic deterioration factor.

  The image analysis unit 107 analyzes the image data read by the image reading unit 102 using a model indicating deterioration characteristics for each deterioration factor stored in advance in the feature DB 108, and determines whether or not damage is caused by the deterioration factor. Determine. The feature DB 108 stores in advance a function in which a plurality of images showing typical damage states for each deterioration factor are input and each feature is machine-learned, and a model indicating the feature for each deterioration factor. Shall. It should be noted that a function or a model showing a feature obtained by machine learning of features can be generated by using an existing technique such as supervised learning using a neural network, and the generation method is not limited in this embodiment. . In the present embodiment, a function obtained by machine learning of a feature or a model indicating the feature is also referred to as reference information. In the present embodiment, the image analysis unit 107 improves the accuracy of image data recognition using information on the deterioration factor specified from the information of the structure 2 including the position information.

  Generally, deterioration (damage) appearing in the appearance of a concrete structure has a pattern corresponding to the cause of the deterioration. For example, cracks resulting from the heat of hydration of concrete occur on the surface of the member with a temperature difference between the inside and outside of the member. Also, if the member shrinks due to gradual air cooling after the temperature rise of the member due to heat of hydration, such as the side wall of the box culvert, the shrinkage is constrained by the bottom plate and cracks upward from the lower surface of the side wall. Occur. Cracks due to rusting of the reinforcing bars due to neutralization or chloride intrusion occur along the reinforcing bars. Furthermore, rust juice may flow out to the concrete surface due to water intrusion from cracks. Moreover, when the aggregate containing an alkali-silica reactive mineral is contained in concrete, it may expand | swell and a turtle shell-like crack may generate | occur | produce. In addition, a test method and a criterion are defined as measures against such alkali silica reaction, and damage due to the deterioration factor is reduced depending on the construction time of the structure. In addition, in the case of fire or surface heating, thick cracks are generated in the beams and columns as well as fine mesh cracks. Therefore, when the cause of deterioration that is likely to occur in the imaged structure 2 is known from the position information of the structure 2 (information on the area including the position), design information, construction information, maintenance information, etc. Considering these pieces of information, it is possible to improve the accuracy of determination of the state and degree of deterioration by image recognition. In the present embodiment, the deterioration factor associated with the concrete structure corresponding to the position information added to the image data is specified, and the reference information indicating the characteristics of the deterioration state caused by the deterioration factor is provided. Select and preferentially perform image analysis.

  As a result of image analysis, deterioration such as presence or absence of cracks, pattern of cracks, presence or absence of peeling of concrete, presence or absence of rebars, presence or absence of water leakage, presence or absence of free lime, presence or absence of concrete floating, presence or absence of discoloration of concrete Parameters indicating the degree of deterioration such as the state of cracks, crack width, spacing, and density are output. The deterioration state can be determined using a function or model generated in advance by inputting a plurality of typical images for each deterioration state and performing machine learning. Of the degree of deterioration, for example, the crack width can be calculated backward from the number of pixels in the portion corresponding to the crack. For crack width, gauges and markers of a predetermined size are imaged at the same time in the image, and the width is estimated as a dimensional reference, or the width is back calculated by keeping the distance between the structure and the camera constant when imaging. It is required by doing. As with the crack width, the crack interval is calculated from comparison with a reference gauge that has been imaged at the same time, or the interval is back-calculated while keeping the imaging distance constant. The crack density is calculated by, for example, calculating the total length of cracks in the captured image by adding up the recognized crack lengths, and dividing the total extension value by the area of the target member in the image. calculate. For example, as described above, parameters indicating the degree of deterioration such as the state of deterioration such as the occurrence of cracks, the width, spacing, and density of cracks are obtained. As for the degree of deterioration, for example, a DB for storing crack intervals and widths, and an evaluation category indicating the degree may be prepared, and the evaluation category indicating the degree may be output as a parameter.

  At this time, in this embodiment, the determination system is improved using the deterioration factor acquired by the deterioration factor acquisition unit. For example, the state of deterioration that may occur may be narrowed down or prioritized based on deterioration factors. Further, after the image recognition, it may be determined whether the recognition result is valid based on the deterioration factor. Furthermore, when determining the deterioration state by image recognition, for example, a weighting process may be performed so that the score of the deterioration factor related to the structure 2 becomes high. Thus, in this embodiment, the state of deterioration caused by the deterioration factor associated with the concrete structure corresponding to the position information added to the image data is preferentially selected.

The damage degree evaluation unit 109 evaluates the degree of damage and determines the necessity of countermeasures based on the deterioration factor output from the image analysis unit 107 and the deterioration parameter. Here, the necessity of countermeasures varies depending on the deterioration factor. For example, cracks due to rapid driving or rapid drying, temperature cracks, etc. occur immediately after the concrete is driven and the growth stops in a short period of time. Therefore, if the repair is performed at an early stage, the durability of the structure is not greatly affected. On the other hand, corrosion of reinforcing bars due to neutralization, salt damage, etc. leads to peeling of cover concrete in a short period of time after cracks along the reinforcing bars occur. In this way, it is possible to determine whether or not repair is necessary or promptly according to the deterioration factor. Specifically, it is assumed that a determination category that matches a predetermined condition is obtained using the state and degree of deterioration analyzed by the image analysis unit 107 and information stored in the deterioration factor DB.

  In addition, the result output unit 110 outputs the determination result of the deterioration state and the degree, and the evaluation of the countermeasure category as the output of the inspection support apparatus 1. The output destination may be on a display connected to the inspection support apparatus 1 or may be another computer via a network not shown. In addition, the result output unit 110 stores history information indicating the execution of the inspection and the evaluation result in association with the identification information of the structure 2 to be inspected in the structure DB 104.

  As described above, according to the inspection support apparatus 1, the possibility of occurrence of damage due to each of a plurality of deterioration factors is taken into account by using information on the imaged structure 2 and information on a region where the structure 2 exists. In addition, the accuracy of image analysis can be improved.

  1 and 2 show one inspection support device 1, the functions may be distributed to a plurality of devices. Further, the inspection support device 1 may be connected to the imaging device 3 via a network (not shown).

In the example of FIG. 2, the structure DB 104, the deterioration factor DB 106, and the feature DB 108 are called databases, but these may be a plurality of tables managed by one DBMS (Database Management System). Further, the data structure may be divided into an arbitrary number of tables by appropriately normalizing the data structure. Furthermore, although the example of FIG.3 and FIG.4 illustrated the item (attribute) contained in one record, the format which memorize | stores information is not specifically limited. For example, an RDBMS (Relational Database Management System) may be adopted, or a management system such as a document store type, a key-value type, an object database, or a multi-value database as so-called NoSQL may be adopted. Further, it may be a table created by spreadsheet software or a format in which data is held by delimiter separation such as CSV (Comma-Separated Values).

<Device configuration>
FIG. 5 is an apparatus configuration diagram illustrating an example of a computer. The inspection support apparatus 1 is a computer as shown in FIG. 5, for example. A computer 1000 shown in FIG. 5 includes a CPU (Central Processing Unit) 1001, a main storage device 1002, and an auxiliary storage device (external storage device) 1.
003, a communication IF (Interface) 1004, an input / output IF (Interface) 1005, a drive device 1006, and a communication bus 1007. The CPU 1001 performs processing and the like according to this embodiment by executing a program. The main storage device 1002 caches programs and data read by the CPU 1001 and develops a work area of the CPU. Specifically, the main storage device is a RAM (Random Access Memory), a ROM (Read Only Memory), or the like. The auxiliary storage device 1003 stores programs executed by the CPU 1001, setting information used in the present embodiment, and the like. Specifically, the auxiliary storage device 1003 includes an HDD (Hard-disk Drive), an SSD (Solid State Drive), and an eMMC (embedded).
Multi-Media Card), flash memory, etc. The main storage device 1002 and the auxiliary storage device 1003 function as the image storage unit 101, the structure DB 104, the deterioration factor DB 106, and the feature DB 108 of the inspection support device 1. The communication IF 1004 transmits / receives data to / from other computers. The communication IF 1004 is specifically a wired or wireless network card or the like. The inspection support device 1 may be configured to receive image data from the imaging device 3 via a network. The input / output IF 1005 is connected to the input / output device and accepts input from the user or outputs information to the user. Specifically, the input / output device is a keyboard, a mouse, a display, a touch panel, or the like. The drive device 1006 reads data recorded on a storage medium such as a magnetic disk, a magneto-optical disk, and an optical disk, and writes data to the storage medium. The above components are connected by a communication bus 1007. A plurality of these components may be provided, or some of the components (for example, the drive device 1006) may not be provided. Further, the input / output device may be integrated with the computer. In addition, the program executed in this embodiment is provided via a portable storage medium readable by the drive device 1006, a portable auxiliary storage device 1003 such as a flash memory, a communication IF 1004, and the like. It may be. Then, when the CPU 1001 executes the program, the above-described computer is operated as the inspection support apparatus 1 shown in FIG. 2, for example.

<Inspection support processing>
FIG. 6 is a process flowchart illustrating an example of the inspection support process. First, the image reading unit 102 of the inspection support apparatus 1 reads image data from the image storage unit 101 (FIG. 6: S1). As described above, position information is embedded in the image data, and the image reading unit 102 reads information representing the image itself and position information indicating the position where the image is captured.

  Next, the structure information acquisition unit 103 of the inspection support apparatus 1 reads information on the structure 2 captured in the image data from the structure DB 104 (S2). The structure drawing method acquisition unit 103 stores the position of the structure having the position closest to the position information read by the image reading unit 101 as the value of the item “position information” in the data structure of the structure DB 104 shown in FIG. Get information. In this step, design information, construction information, maintenance management information and the like of the structure imaged in the image data are acquired.

  In addition, the deterioration factor acquisition unit 105 of the inspection support device 1 reads out deterioration factors that may affect the structure 2 captured in the image data from the deterioration factor DB 106 (S3). The deterioration factor acquisition unit 105 extracts a deterioration factor corresponding to the condition from the deterioration factor DB 106 based on the position information read by the image reading unit 102, the structure design information acquired by the structure information acquisition unit 103, and the like. To do.

  Thereafter, the image analysis unit 107 of the inspection support apparatus 1 analyzes the image data and determines the state and degree of deterioration (S4). In this step, for example, when damage appears in the image to be processed using a model indicating deterioration characteristics for each deterioration factor stored in advance in the feature DB 108, the damage is caused by any deterioration factor. Image recognition processing is performed to determine whether or not. In the present embodiment, processing is performed using the deterioration factor extracted in S3. For example, based on the degradation factor associated with the area to which the position information of the structure 2 belongs, first, the degradation factor that may occur is narrowed down or prioritized, and then the degradation factor is based on the priority. The image data may be recognized using a model indicating the characteristics of each. In addition, image data is first recognized using a model indicating characteristics of various deterioration factors, and then it is determined whether the recognition result is appropriate based on the deterioration factors associated with the area to which the position information of the structure 2 belongs. You may do it. Furthermore, when recognizing image data using a model indicating characteristics for each deterioration factor, for example, weighting may be performed so as to increase the score of the deterioration factor associated with the area to which the position information of the structure 2 belongs. As a result of image analysis, deterioration such as presence or absence of cracks, crack pattern, concrete peeling, rebar exposure, water leakage, free lime, concrete floating, concrete discoloration, etc. The degree of deterioration such as the state, crack width, and density is known.

The evaluation of the degree of damage due to deterioration and the determination of countermeasures corresponding to it shall comply with the standards to be applied according to the structure to be inspected. For example, the “Regular Bridge Inspection Procedure (Draft)” (Ministry of Land, Infrastructure, Transport and Tourism, March 2004) shall be followed for directly controlled national road bridges. According to the said procedure, the evaluation classification of the damage degree regarding the crack of the concrete floor slab of the bridge is defined as shown in FIG. That is, when the minimum crack interval is approximately 1.0 m or more, the crack is mainly in only one direction, and the maximum crack width is 0.05 mm or less (about hair crack), it is set to a relatively light category a. Moreover, it is set as the division | segmentation b when the crack interval is 1.0m-0.5m, and a crack is one direction main, a perpendicular direction is subordinate, and it is not a lattice form. In addition, the crack interval is about 0.5 m immediately before the lattice shape, and the crack width is mainly 0.2 mm or less. In addition, if the crack interval is 0.5 m to 0.2 m, the cracks are generated in a lattice shape, and the crack width is conspicuous 0.2 mm or more, and a partial corner drop is observed, it is classified as category d. If the crack interval is 0.2 m or less and occurs in a lattice pattern, and the crack width is 0.2 mm or more, and the conspicuous and continuous angle drop occurs, it is determined as a heavy section e. For example, in order to recognize the size such as the interval and width of cracks from the image, the size of the cracks in the image can be calculated by determining the distance between the structure and the imaging device at the time of imaging. May be. In addition, a marker whose size is known in advance may be imaged together with the structure to be inspected, and the size of the crack may be calculated based on this, or the distance between two points of the imaged structure may be input. The crack size may be calculated on the basis of this. It is assumed that such a determination criterion is also defined in advance for structures other than bridges.

  Then, the damage degree evaluation unit 109 of the inspection support apparatus 1 determines whether or not the captured structure 2 has deteriorated (S5). For example, if the above-described evaluation category is equal to or greater than a predetermined threshold (such as a or greater or b or greater), it is determined that deterioration has occurred. When it is determined that there is deterioration (S5: YES), the damage degree evaluation unit 109 evaluates the degree of deterioration (S6). Here, the necessity of countermeasures is determined using the above-described deterioration state and degree of deterioration. In addition to the result of image analysis, the necessity of countermeasures may be determined using design information, construction information, and maintenance information of the structure 2. For example, the degree of damage and the determination category are determined based on the information stored in the evaluation category, the structure DB, or the deterioration factor DB in FIG.

  FIG. 8 is a diagram for explaining an example of the judgment section of the concrete floor slab. FIG. 8 shows the determination category, the contents of the category, and the conditions for determining the category in association with each other. The conditions according to the present embodiment are determined in advance using the evaluation category obtained in S4 and the deterioration factor extracted in S3. For example, if the evaluation category for cracks is a or b, it is determined that no damage is observed or damage is minor and repair is not required, and the determination category is A. Moreover, when the evaluation classification regarding a crack is c, it determines with it being necessary to repair according to a condition, and sets the determination classification to B. If the evaluation category for cracks is d, it is determined that repair or the like needs to be performed promptly, and the determination category is C. If the evaluation category for cracks is e, for example, if the structure 2 is a bridge, it is determined that an emergency response is necessary from the viewpoint of the safety of the bridge structure, and the determination category is E1. . In addition, when the evaluation category for cracks is e, for example, when the image is taken of a bridge slab and it can be determined that the floor slab is cracked, the emergency It is determined that there is a need for handling, and the determination category is E2. In addition, for example, when the evaluation classification regarding cracks is b, and it is determined that the degree of damage is large compared to other structures constructed at the same age, the position information of the structure 2 is included. When it is judged that there is a possibility of a specific event such as alkali aggregate reaction or salt damage in the region, it is judged that detailed investigation is necessary, and the judgment category is S. In addition, when the structure to be treated is, for example, an application other than a bridge or a part other than a concrete floorboard, and a predetermined condition is met, a judgment category indicating that it is necessary to deal with maintenance work is It may be selected.

After S6 or when it is determined that there is no deterioration in S5 (S5: NO), the result output unit 110 outputs the processing result (S7). Note that the processing of FIG. 6 is performed for each of a plurality of image data obtained by imaging the structure 2. The processing result may be output after integrating the results after processing a plurality of image data obtained by imaging the same structure 2. In addition, history information indicating the execution and result of inspection is stored in the maintenance management information of the structure DB 104. For example, information such as the determination category described above is output. In addition, the result output unit 110 stores the evaluation category and the determination category in, for example, the structure DB, and the damage level evaluation unit 109 averages other structures constructed in the same age for a certain structure. It may be possible to determine whether the degree of damage is large or not.

  According to the inspection support process of FIG. 6, by using the information of the imaged structure 2 and the information of the area where the structure 2 exists, the possibility of occurrence of damage due to each of a plurality of deterioration factors is taken into consideration. Analysis accuracy is improved. That is, in the present invention, the accuracy of image analysis is improved by preferentially selecting the state of deterioration caused by the deterioration factor associated with the concrete structure corresponding to the position information added to the image data. improves. The deterioration factors associated with concrete structures include the deterioration factors according to the design information, construction information, maintenance management information, etc. of the concrete structure, as well as the area where the concrete structure was constructed. There is a factor of deterioration.

<Others>
The present invention includes a computer program that executes the above-described processing. Furthermore, a computer-readable recording medium on which the program is recorded also belongs to the category of the present invention. With respect to the recording medium on which the program is recorded, the above-described processing can be performed by causing the computer to read and execute the program on the recording medium.

  Here, the computer-readable recording medium refers to a recording medium in which information such as data and programs is accumulated by electrical, magnetic, optical, mechanical, or chemical action and can be read from a computer. Examples of such a recording medium that can be removed from the computer include a flexible disk, a magneto-optical disk, an optical disk, a magnetic tape, and a memory card. Further, examples of the recording medium fixed to the computer include a hard disk drive and a ROM.

DESCRIPTION OF SYMBOLS 1 Inspection support apparatus 101 Image storage part 102 Image reading part 103 Structure information acquisition part 104 Structure DB
105 Degradation factor acquisition unit 106 Degradation factor DB
107 Image Analysis Unit 108 Feature DB
109 Damage degree evaluation unit 110 Result output unit 2 Structure (concrete structure)
3 Imaging device

Claims (8)

An image reading unit that reads out image data in which a concrete structure to be inspected is imaged and position information indicating the position is added;
The deterioration factor associated with the information on the concrete structure corresponding to the position information of the image data read by the image reading unit is acquired from a storage device that stores the deterioration factor in association with the information on the concrete structure. A deterioration factor acquisition unit;
Using the deterioration factor acquired by the deterioration factor acquisition unit and the reference information obtained by learning in advance the features appearing on the surface of the concrete structure for each deterioration factor, the image data read by the image reading unit is An image analysis unit that analyzes and determines the state of deterioration of the captured concrete structure;
An inspection support device for a concrete structure comprising: 2. The concrete structure according to claim 1, wherein the image analysis unit preferentially selects a deterioration state caused by the deterioration factor acquired by the deterioration factor acquisition unit in the determination of the deterioration state. Inspection support device. In the determination of the deterioration state, the image analysis unit preferentially uses the reference information obtained by learning the characteristics of the deterioration state caused by the deterioration factor acquired by the deterioration factor acquisition unit. Determining the state of deterioration that has occurred in the concrete structure, or more weighting the deterioration state caused by the deterioration factor acquired by the deterioration factor acquisition unit than other deterioration states The inspection support device for a concrete structure according to claim 1 or 2, wherein a state of deterioration occurring in the concrete structure is determined. The storage device stores a factor of deterioration that may occur in a concrete structure in association with regional information indicating a region,
The concrete structure according to any one of claims 1 to 3, wherein the deterioration factor acquisition unit acquires the deterioration factor associated with an area including position information of image data read by the image reading unit. Inspection support device. The storage device stores information on salt damage, information on alkali-silica reactive aggregate, information on frost damage, or information on chemical corrosion as a cause of deterioration associated with the regional information. Inspection support device for concrete structures. The information on the concrete structure includes information on design of the concrete structure, information on construction, or information indicating a history of maintenance and management,
The said storage device memorize | stores the conditions which the information regarding the design of a concrete structure, the information regarding construction, or the information which shows the history of a maintenance management should satisfy | fill corresponding to the factor of the said deterioration. The inspection support device for concrete structures described in 1. An image reading step of reading out image data in which a concrete structure to be inspected is imaged and position information indicating the position is added;
Stores the information of the concrete structure constructed on the position in association with the position information, from the storage device for storing the cause of deterioration in association with the information of the concrete structure, which is read out in the image reading step Deterioration factor acquisition step of acquiring the information of the concrete structure associated with the position information of the image data, and the deterioration factor associated with the information of the concrete structure;
Wherein a cause of degradation obtained in the degradation factor acquisition step, by using the pre-reference information obtained by learning the features appearing on the surface of the concrete structure for each factor of deterioration, the is read out in the image reading step the An image analysis step of analyzing image data and determining a deterioration state of the imaged concrete structure;
An inspection support method for concrete structures that is executed by a computer. An image reading step of reading out image data in which a concrete structure to be inspected is imaged and position information indicating the position is added;
Stores the information of the concrete structure constructed on the position in association with the position information, from the storage device for storing the cause of deterioration in association with the information of the concrete structure, which is read out in the image reading step Deterioration factor acquisition step of acquiring the information of the concrete structure associated with the position information of the image data, and the deterioration factor associated with the information of the concrete structure;
Wherein a cause of degradation obtained in the degradation factor acquisition step, by using the pre-reference information obtained by learning the features appearing on the surface of the concrete structure for each factor of deterioration, the is read out in the image reading step the An image analysis step of analyzing image data and determining a deterioration state of the imaged concrete structure;
An inspection support program for concrete structures that allows a computer to execute the above.

Images