WO2017110279A1 - 損傷情報処理装置及び損傷情報処理方法 - Google Patents
損傷情報処理装置及び損傷情報処理方法 Download PDFInfo
- Publication number
- WO2017110279A1 WO2017110279A1 PCT/JP2016/083191 JP2016083191W WO2017110279A1 WO 2017110279 A1 WO2017110279 A1 WO 2017110279A1 JP 2016083191 W JP2016083191 W JP 2016083191W WO 2017110279 A1 WO2017110279 A1 WO 2017110279A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- damage
- vector
- information
- hierarchical structure
- vectors
- Prior art date
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 64
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 239000013598 vector Substances 0.000 claims abstract description 478
- 238000000034 method Methods 0.000 claims description 49
- 238000000605 extraction Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 8
- 239000004567 concrete Substances 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 4
- 235000008733 Citrus aurantifolia Nutrition 0.000 claims description 3
- 235000011941 Tilia x europaea Nutrition 0.000 claims description 3
- 239000004571 lime Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 22
- 238000007689 inspection Methods 0.000 description 8
- 230000008439 repair process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000004568 cement Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000011150 reinforced concrete Substances 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Definitions
- the present invention relates to an apparatus and method for processing damage to a structure, and more particularly to an apparatus and method for processing information obtained by vectorizing damage.
- Patent Document 1 describes that in measuring cracks in concrete and the like, vector data of cracks is created and information such as group numbers and continuation points, end points, and branch points is given.
- Japanese Patent Application Laid-Open No. H10-228561 describes that crack vector data is created in concrete defect inspection and information on the intersection of cracks is written in a file.
- the present invention has been made in view of such circumstances, and an object of the present invention is to provide a damage information processing apparatus and a damage information processing method capable of easily grasping the connection relationship between damage vectors.
- a damage information processing apparatus includes a damage information acquisition unit that acquires damage information about damage to a structure, and a damage vector obtained by vectorizing the acquired damage information. And a hierarchical structure information generating unit that generates hierarchical structure information that is information that hierarchically expresses the connection relationship between the damage vectors based on the generated damage vector.
- damage information is vectorized to generate a damage vector, and based on this, hierarchical structure information that is information that hierarchically represents the connection relationship between the damage vectors is generated.
- hierarchical structure information that is information that hierarchically represents the connection relationship between the damage vectors.
- the damage information may be acquired by inputting an image of the structure and processing the image, or may directly acquire the damage information extracted from the image.
- “hierarchically” means that damage vectors have an upper or lower relationship determined by a connection relationship.
- the hierarchy of damage vectors can be determined by various methods, and the method to be used may be determined according to the purpose of analysis and / or evaluation.
- examples of the “structure” include a bridge, a tunnel, a building, and a road, but are not limited thereto.
- the hierarchical structure information generation unit includes information on a vector group to which one damage vector belongs, information on other damage vectors linked to the one damage vector, and And hierarchical structure information including unique information of one damage vector.
- the second mode shows an example of the structure of the hierarchical structure information, and includes not only specific information of one damage vector of interest, but also information on a vector group and information on other damage vectors linked to one damage vector. I can grasp. In this way, in the second mode, the relationship between the damage vectors can be grasped more easily.
- the “vector group” is a set of vectors composed of one or a plurality of damage vectors, for example, a plurality of damage vectors connected to each other or separated but close to each other. Damage vectors present can be made into vector groups.
- the hierarchical structure information generation unit is configured such that when a plurality of other damage vectors are connected to one damage vector, the other plurality of damage vectors are one. Hierarchical structure information is generated assuming that it belongs to a lower hierarchy than the damage vector.
- the third aspect shows an example of a technique for determining a hierarchy of damage vectors. In this aspect, when a plurality of other damage vectors are connected to one damage vector (that is, branched), the connection is performed. Each time (branch) is passed, the hierarchy becomes lower.
- the hierarchical structure information generation unit is configured such that the angle between one damage vector and another damage vector connected to the one damage vector is equal to or less than a threshold value.
- the hierarchical structure information is generated assuming that the other damage vectors belong to the same hierarchy as the one damage vector.
- the fourth aspect shows another example of the technique for determining the hierarchy of damage vectors. In this aspect, the angle formed by the damage vectors is small (below the threshold) and is regarded as a substantially collinear vector. If possible, the damage vectors belong to the same hierarchy.
- the hierarchical structure information generation unit includes a damage vector in which another damage vector connected to the one damage vector is temporally generated after the one damage vector.
- the hierarchical structure information is generated assuming that other damage vectors belong to a lower hierarchy than one damage vector.
- the fifth aspect shows yet another example of a technique for determining the hierarchy of damage vectors.
- the damage caused to a structure generally changes in shape and size with time, and a new damage vector.
- a damage vector generated later in time belongs to a lower hierarchy.
- the context of the occurrence of the damage vector can be determined based on, for example, the date and time when the image of the structure was taken or the date and time when the structure was inspected.
- the damage information processing apparatus is the second aspect, wherein the hierarchical structure information generation unit, when there is only one other damage vector linked to one damage vector, Hierarchical structure information is generated assuming that the vector belongs to the same hierarchy as the one damage vector.
- the sixth aspect shows still another example of the technique for determining the hierarchy of damage vectors. When only one other damage vector is connected to one damage vector, the damage vectors are regarded as damage. It is assumed that they are continuous and belong to the same level.
- the damage information processing apparatus is any one of the second to sixth aspects, wherein the unique information includes identification information of one damage vector, and to which hierarchy of the hierarchical structure the one damage vector belongs Affiliation hierarchy information indicating that, and the positions of the start point and end point.
- the seventh aspect shows the structure of the unique information of the damage vector, and the unique information includes the identification information of one damage vector, affiliation hierarchy information, the position of the start point and the end point.
- the damage information processing apparatus is any one of the first to seventh aspects, wherein the hierarchical structure information generation unit generates hierarchical structure information by the same item and format regardless of the hierarchy to which the damage vector belongs. To do. According to the eighth aspect, since the hierarchical structure information is the same item and format regardless of the hierarchy to which the damage vector belongs, it is possible to quickly and easily grasp the connection relationship between the damage vectors.
- the damage information processing apparatus is any one of the first to eighth aspects, wherein the damage vector generation unit connects a plurality of spatially separated damage vectors to obtain one or a plurality of vectors. Generate. When damage is recognized as a separate damage vector because it is continuous inside the structure but separated at the surface, it is actually continuous but extracted as a separate vector by image processing etc. Therefore, in the ninth aspect, one or more vectors are generated by concatenating a plurality of damage vectors.
- the connection of damage vectors may be determined based on conditions such as the distance and angle between the damage vectors, or may be determined based on user input.
- the damage information processing apparatus includes a damage vector extraction unit that extracts a damage vector that satisfies a specified condition with reference to the hierarchical structure information.
- damage is extracted by referring to hierarchical structure information, which is information that hierarchically represents the connection relationship between damage vectors, so that damage can be easily searched, analyzed, and evaluated. be able to.
- the damage information processing apparatus is the tenth aspect, wherein the damage vector extraction unit is connected to the specified damage vector and belongs to a higher level than the specified vector, and the specified damage At least one of a damage vector belonging to the same hierarchy as the designated vector connected to the vector and a damage vector belonging to the lower hierarchy than the designated vector connected to the designated damage vector is extracted. According to the eleventh aspect, it is possible to quickly and easily extract damage vectors that are connected to a specified damage vector and whose hierarchy is higher, the same, or lower.
- the damage information processing apparatus includes a display unit that displays the extracted damage vector and the generated hierarchical structure information. According to the twelfth aspect, by displaying the extracted damage vector and the generated hierarchical structure information, it is possible to easily grasp the connection relationship between the damage vectors and the information on the damage vector.
- the damage information processing apparatus includes a hierarchical structure information recording unit that records hierarchical structure information.
- the hierarchical structure information recorded in the hierarchical structure information recording unit can be used for purposes such as analysis and / or evaluation of damage vectors.
- the damage information processing apparatus acquires damage information by performing image processing on an image obtained by imaging the structure.
- the fourteenth aspect defines one aspect of a technique for acquiring damage information.
- the damage information processing apparatus is a concrete structure, and the damage includes at least one of cracks and free lime.
- the fifteenth aspect defines an example of a structure and damage.
- a damage information processing method includes a damage information acquisition step of acquiring damage information about damage to a structure, and a damage vector obtained by vectorizing the acquired damage information. And a hierarchical structure information generating step of generating hierarchical structure information, which is information that hierarchically represents the connection relationship between the damage vectors based on the generated damage vector.
- the present invention is defined as a damage information processing method.
- the connection relation between damage vectors can be easily grasped, and damage vector analysis and / or Search can be easily performed.
- the damage information processing apparatus and the damage information processing method of the present invention it is possible to easily grasp the connection relationship between the damage vectors.
- FIG. 1 is a diagram illustrating a bridge as an example of a structure.
- FIG. 2 is a block diagram showing a configuration of the damage information processing apparatus according to the embodiment of the present invention.
- FIG. 3 is a flowchart showing a procedure of the damage information processing method according to the embodiment of the present invention.
- FIG. 4 is a diagram illustrating a state in which a curved damage is divided to generate a plurality of damage vectors.
- FIG. 5 is a diagram for explaining how the start point of the damage vector is determined.
- FIG. 6 is another diagram for explaining how the start point of the damage vector is determined.
- FIG. 7 is a diagram illustrating the connection of the separated damage vectors.
- FIG. 8 is another diagram showing the connection of the separated damage vectors.
- FIG. 9 is a table showing image information included in the hierarchical structure information.
- FIG. 10 is a diagram illustrating an example of damage vector information included in the hierarchical structure information (corresponding to hierarchical determination method example 1).
- FIG. 11 is a diagram for explaining Example 1 of the damage vector hierarchy determination method.
- FIG. 12 is another diagram for explaining Example 2 of the damage vector hierarchy determination method.
- FIG. 13 is a table showing an example of hierarchical structure information (damage vector information) corresponding to Example 2 of the hierarchy determination method.
- FIG. 14 is a diagram for explaining Example 3 of the damage vector hierarchy determination method.
- FIG. 15 is another diagram for explaining an example 3 of the damage vector hierarchy determination method, and is a diagram showing an image taken later in time than FIG. FIG.
- FIG. 16 is still another diagram for explaining Example 3 of the damage vector hierarchy determination method, and is a diagram showing an image taken after the time of FIG.
- FIG. 17 is a table showing an example of hierarchical structure information (damage vector information) corresponding to Example 3 of the hierarchy determination method.
- FIG. 18 is a diagram for explaining an example 4 of the damage vector hierarchy determination method.
- FIG. 19 is a table showing an example of hierarchical structure information (damage vector information) corresponding to Example 4 of the hierarchy determination method.
- FIG. 1 is a perspective view showing a structure of a bridge 1 (structure, concrete structure) which is an example of a structure to which a damage information processing apparatus and a damage information processing method according to the present invention are applied.
- the bridge 1 shown in FIG. 1 has a main girder 3, and the main girder 3 is joined by a joint 3A.
- the main girder 3 is a member that is passed between the abutment and / or the pier and supports a load of a vehicle or the like on the floor slab 2.
- a floor slab 2 for driving a vehicle or the like is placed on the upper portion of the main girder 3.
- the floor slab 2 is made of reinforced concrete.
- the bridge 1 has members such as a horizontal girder, a tilted frame, and a horizontal frame (not shown) in addition to the floor slab 2 and the main girder 3.
- the inspector photographs the bridge 1 from below using the digital camera 104 (see FIG. 2) (C direction in FIG. 1), and acquires an image of the inspection range.
- the photographing is performed while appropriately moving in the extending direction of the bridge 1 (A direction in FIG. 1) and the orthogonal direction (B direction in FIG. 1).
- the digital camera 104 may be installed on a movable body that can move along the bridge 1 to perform imaging.
- a moving body may be provided with a lifting mechanism and / or a pan / tilt mechanism of the digital camera 104. Examples of the moving body include a vehicle, a robot, and a flying body, but are not limited to these.
- FIG. 2 is a block diagram illustrating a schematic configuration of the damage information processing apparatus 100 according to the present embodiment.
- the damage information processing apparatus 100 includes a damage information acquisition unit 102, a damage vector generation unit 110, a hierarchical structure information generation unit 112, a damage vector extraction unit 114, a hierarchical structure information recording unit 116, a display unit 118, and an operation unit 120. They are connected to each other so that necessary information can be transmitted and received between them.
- each unit can be realized by a control device such as a CPU (Central Processing Unit) executing a program stored in the memory.
- the damage information acquisition unit 102 includes a radio communication antenna and an input / output interface circuit, and the hierarchical structure information recording unit 116 includes a non-temporary recording medium such as an HDD (Hard Disk Drive).
- the display unit 118 includes a display device such as a liquid crystal display, and the operation unit 120 includes an input device such as a keyboard. Note that these are examples of the configuration of the damage information processing apparatus according to the present invention, and other configurations can be adopted as appropriate.
- an image photographed using the digital camera 104 is input to the image acquisition unit 106 by wireless communication, and damage information is acquired by the image processing unit 108.
- the digital camera 104, the image acquisition unit 106, and the image processing unit 108 constitute a damage information acquisition unit 102.
- the damage vector generation unit 110 generates a damage vector (crack vector) from the damage information acquired by the damage information acquisition unit 102, and connects the damage vectors separated spatially.
- the hierarchical structure information generation unit 112 generates hierarchical structure information based on the damage vector generated by the damage vector generation unit 110, and the generated hierarchical structure information is recorded in the hierarchical structure information recording unit 116.
- the damage vector extraction unit 114 refers to the hierarchical structure information and extracts a damage vector that satisfies a specified condition such as a damage vector belonging hierarchy.
- the display unit 118 displays an input image, a generated or extracted damage vector, hierarchical structure information, and the like.
- the display unit 118 also performs image processing necessary for display, such as generating a line segment image from damage vector information.
- the operation unit 120 receives a user's instruction input regarding the setting of extraction conditions and display conditions of damage vectors and hierarchical structure information, editing of hierarchical structure information, and the like.
- FIG. 3 is a flowchart showing the procedure of damage information processing according to this embodiment.
- the damage is a crack generated in the floor slab 2
- the damage is appropriately described as “crack”.
- the damage to which the present invention can be applied is not limited to the crack, and free lime, etc. May be damaged.
- step S100 image input process
- a plurality of images of the bridge 1 are input in accordance with the inspection range, and information on photographing date and time is added to the input image by the digital camera 104.
- the shooting date and time of the input image does not necessarily have to be the same for all images, and may be for a plurality of days.
- a plurality of images may be input at a time, or one image may be input at a time.
- the image of the bridge 1 may be input via a non-temporary recording medium such as various memory cards instead of wireless communication, or image data that has already been captured and recorded is input via a network. Also good.
- the image of the bridge 1 input in step S100 may be a captured image as it is or may be a preprocessed image of the captured image.
- step S110 extracts damage (crack) from the input image (step S110; damage extraction process).
- the image input process in step S100 and the damage extraction process in step S110 constitute a damage information acquisition process in the damage information processing method of the present invention.
- step S110 if damage is extracted from the image input in step S100, that is, if the damaged area in the image is identified, it may be considered that the damage information has been acquired, and the detailed characteristics of the damage are described. It doesn't need to be grasped.
- the damage extraction in step S110 can be performed by various methods.
- a crack detection method described in Japanese Patent No. 4006007 can be used. This method calculates wavelet coefficients corresponding to the two concentrations to be compared, calculates each wavelet coefficient when each of the two concentrations is changed, creates a wavelet coefficient table, and detects the crack detection target.
- a wavelet image is generated by wavelet transforming an input image obtained by photographing a concrete surface, and a wavelet coefficient corresponding to an average density of neighboring pixels in a local area and a density of a target pixel is set as a threshold in the wavelet coefficient table.
- a step of determining a cracked area and a non-cracked area by comparing the wavelet coefficient of the pixel of interest with the threshold value.
- step S110 may be performed after the necessary preprocessing is performed on the image input in step S100.
- step S110 When damage is extracted in step S110 (when damage information is acquired), the damage vector generation unit 110 generates a damage vector (a crack vector) by vectorizing the acquired damage information (step S120; damage vector generation). Process).
- the extracted damage (crack) is binarized and / or thinned as necessary. “Vectorization” is to obtain a line segment determined by the start point and the end point for damage.
- the damage (crack) is a curve, multiple damages are made so that the distance between the curve and the line segment is less than the threshold. And a damage vector is generated for each of the plurality of sections. In the example of FIG.
- the curved damage Cr is divided into four sections Cr1 to Cr4, and the damage vectors Cv1 to Cv4 are generated for each section, so that the damage and the damage vectors Cv1 to Cv4 in the sections Cr1 to Cr4
- the distances d1 to d4 are equal to or less than the threshold value.
- the feature point of the floor slab 2 is set as the origin of the coordinate system, and for the damage vector group (vector group), the end point that minimizes the distance from the origin is set as the first start point.
- the end point and start point can be determined sequentially along the running direction.
- the point P13 having the shortest distance d from the point P0 is set as the start point of the damage vector C7-1, and hereinafter the point P14 is set as the end point of the damage vector C7-1 (and the damage vectors C7-2, C7). ⁇ 3), and points P15 and P16 can be the end points of the damage vectors C7-2 and C7-3, respectively.
- the point P17 becomes the start point of the damage vector C8-1
- the point P18 becomes the start point of the damage vectors C8-2 and C8-3
- the traveling direction of the damage vector C8-3 (The direction from the point P18 to the point P20) is opposite to the traveling direction of the damage vector C8-1. Therefore, in such a case, as shown in FIG. 6, the point P19 is the start point of the damage vector C8A-1, and the point P18 is the end point of the damage vector C8A-1 (and the start points of the damage vectors C8A-2 and C8A-3).
- Points P17 and P20 may be the end points of the damage vectors C8A-2 and C8A-3, respectively. Note that the collection of damage vectors in this case is referred to as a vector group C8A.
- Such processing may be performed by the damage vector generation unit 110 without the user's instruction input, or may be performed by the damage vector generation unit 110 based on the user's instruction input through the operation unit 120. Also good.
- FIG. 7 is a diagram showing an example of connection of damage vectors.
- a vector group C3 including damage vectors C3-1 (points P21 and P22 are start points and end points, respectively), and damage vectors C4-1 (points P23 and P24). Indicates a state in which a vector group C4 including a start point and an end point is extracted. Also, the angle formed by the damage vector C3-1 and the line connecting the points P22 and P23 is ⁇ 1, and the angle formed by the line connecting the points P22 and P23 and the damage vector C4-1 is ⁇ 2.
- the damage vectors C3-1 and C4-1 are connected, and the vector groups C3 and C4 are fused.
- a new damage vector C5-2 is generated and other damage vectors C5-1 (same as damage vector C3-1) and C5-3 (same as damage vector C4-1).
- a new vector group including these damage vectors C5-1, C5-2, and C5-3 is defined as a vector group C5.
- the above-described method is an example of a damage vector concatenation method, and other methods may be used. Further, whether or not the damage vectors are to be linked as described above may be determined by the damage vector generation unit 110 regardless of the user's instruction input, or may be input by the user via the operation unit 120. The damage vector generation unit 110 may determine based on the above.
- the damage information processing apparatus 100 it is possible to accurately grasp the connection relationship between the damage vectors by appropriately connecting the damage vectors separated spatially (on the surface of the floor slab 2). it can.
- Hierarchical structure information is information that hierarchically represents the connection relationship between damage vectors, and is composed of image information (see FIG. 9) and damage vector information (see FIGS. 10, 13, 17, and 19). These image information and damage vector information are related through a vector group which is an aggregate of damage vectors (crack vectors). Therefore, the damage vector can be extracted from the damage image by referring to the ID (Identification) of the vector group, and conversely, the image can be extracted based on the damage vector. Since the hierarchical structure information is generated in the same item and format regardless of the hierarchy (level) to which the damage vector belongs (see FIGS. 10, 13, 17, and 19), the user can easily access the hierarchical structure information. Can be recognized and grasped.
- the above-described image information is information about a captured image in which damage is imaged, and defines identification information (ID) of the captured image, image data, image acquisition date and time, etc., for a group of damage vectors.
- FIG. 9 is a table showing an example of image information.
- the image ID, image data, acquisition date and time, image width and height, number of channels, bit / pixel, and resolution are defined.
- the number of channels is 3 channels for RGB (R: red, G: green, B: blue) color images, and 1 channel for monochrome images.
- FIG. 10 is an example of damage vector information.
- the damage vector information includes information on a vector group to which the damage vector belongs, specific information on each damage vector, information on other damage vectors linked to each damage vector in the vector group, and additional information. .
- the information of the vector group includes the group ID.
- the damage vector specific information includes damage vector ID (identification information), hierarchy (level; affiliation hierarchy information), start point and end point (point number and position coordinates), and length.
- level 1 is the highest level, and the higher the number, the lower the level. Details of a specific hierarchy determination method will be described later.
- Other damage vector information includes the ID (identification information) of the parent vector, sibling vector, and child vector, as will be described below.
- the additional information includes a damage width, a deletion operation flag, an additional operation flag, an inspection date, and repair information.
- ⁇ Parent vector, sibling vector, and child vector> when the end point of one damage vector is the start point of another damage vector, such one damage vector is referred to as a “parent vector”, and the other damage vector is referred to as a “child vector”.
- the parent vector is determined to be zero or one for one damage vector, but there may be any number of child vectors equal to or greater than zero for one parent vector.
- the end point of the parent vector is the start point of a plurality of child vectors
- the plurality of child vectors are referred to as “sibling vectors”. There may also be any number of sibling vectors greater than zero.
- the hierarchical structure information includes the ID (identification information) of the parent vector, the sibling vector, and the child vector
- the parent vector with reference to the vector ID based on an arbitrary damage vector Sibling vectors and child vectors can be identified sequentially.
- a parent vector of a certain damage vector can be specified, and a parent vector of the parent vector can be further specified.
- the connection relationship between the damage vectors can be easily grasped, and the damage vectors can be easily analyzed and searched.
- the “width” included in the additional information indicates the width of a crack corresponding to each damage vector.
- the delete operation flag indicates whether or not the vector has been deleted, and is “1” when the delete operation is performed and “0” when the delete operation is not performed. With reference to this deletion operation flag, display and non-display of the damage vector can be switched.
- the additional operation flag relates to a detection mode of a damage vector, and is “0” when the vector is automatically detected, and “1” when the vector is manually added (by user instruction input). In the case of a vector that is manually added and generated by connecting different ID vectors, it is “2”.
- the “inspection date” is set to the date when the image of the damage was captured, but can be edited by the user's instruction input via the operation unit 120. Further, “repair” information can be generated based on a user instruction input (repair type and repair date) via the operation unit 120. Types of repairs include, for example, filling with cement, filling with resin, and leaving (follow-up observation) (represented as R1, R2, and R3 in the table of FIG. 10).
- FIG. 11 is a diagram showing the vector group C1.
- the vector group C1 is composed of damage vectors C1-1 to C1-6, and these damage vectors have points P1 to P7 as start points or end points.
- the hierarchy of the damage vector C1-1 is set to the highest “level 1”, and the damage vectors C1-2 and C1-3 starting from the point P2, which is the end point of the damage vector C1-1, It is assumed that “level 2” is lower than the vector C1-1.
- the hierarchy of the damage vectors C1-5 and C1-6 starting from the point P4 that is the end point of the damage vector C1-3 is assumed to be “level 3”, which is lower than the damage vector C1-3.
- the point P3 which is the end point of the damage vector C1-2 is the start point of the damage vector C1-4.
- the damage vector starting from the point P3 is only the damage vector C1-4 and has no branch.
- the level of ⁇ 4 is “level 2”, which is the same as C1-2.
- the hierarchy of each damage vector determined in this way is included in the hierarchical structure information as shown in the table of FIG.
- FIG. 12 is a diagram showing the vector group C1 (the connection relationship between the damage vectors is the same as that shown in FIG. 11).
- the angle formed with another damage vector is equal to or less than the threshold value (damage vector corresponding to “stem” in the tree structure) belongs to the same hierarchy.
- the damage vectors C1-1, C1-2, and C1-4 existing within the dotted line are set to “level 1” (the highest level) that is the same hierarchy. .
- the hierarchy becomes lower each time the damage vector branches as in Example 1, and the damage vector C1-3 (tree structure) (Corresponding to “branches” in FIG. 4) is “level 2”, and damage vectors C1-5 and C1-6 (corresponding to “leaves” in the tree structure) are “level 3”.
- the hierarchy and type (stem, branch, or leaf) of each damage vector determined in this way are included in the hierarchical structure information as shown in the table of FIG.
- Example 2 A modification of the above-described hierarchy determination method (example 2) will be described.
- the damage vector may be determined as “trunk” (level 1) and other damage vectors as “branches” or “leaves”.
- the damage vector C1-1 having a length of 100 mm is “stem” (level 1).
- Damage vectors C1-2 and C1-3 are “branches” (level 2)
- damage vectors C1-4 are “branches” (level 2) or “leaves” (level 3)
- damage vectors C1-5 and 6 are It can be “leaf” (level 3).
- the damage vector constituting the “longest crack” instead of the “longest damage vector” is “stem” (level 1), and the damage vector corresponding to the crack branched from the “stem” is “branch” or “ It may be “leaf”.
- the “longest crack” means “the longest crack as long as both a thick crack and a thin crack are connected”.
- the width (the width of damage corresponding to the damage vector) may also be considered to determine the type (stem, branch, and leaf) and the hierarchy.
- the hierarchy may be determined with the damage vector having the maximum “length ⁇ width” as “stem” and the other damage vectors as “branches” or “leaves”.
- the scratch vector C1-1 having the maximum “length ⁇ width” (100 mm 2 ) is “stem”.
- Damage vectors C1-2 and C1-3 are “branches” (level 2)
- damage vectors C1-4 are “branches” (level 2) or “leaves” (level 3)
- damage vectors C1-5 and 6 are It can be “leaf” (level 3).
- the damage vector hierarchy is determined in consideration of the length of the damage vector or “length ⁇ width”, so that the hierarchization accuracy can be improved.
- Example 3 14 to 16 are diagrams showing the vector group C1 (the connection relationship between the damage vectors is the same as that shown in FIGS. 11 and 12).
- the time before and after the occurrence of the damage vector is determined based on the photographing date and time of the image of the bridge 1, and the damage vector that is generated later in time belongs to the lower hierarchy.
- a vector group C1A including the damage vector C1-1 is generated in the first photographed image (FIG. 14), and in the next photographed image, the damage vectors C1-2 and C1-3 are newly added.
- the vector group C1B is generated (FIG. 15), and in the last photographed image, damage vectors C1-4, C1-5, and C1-6 are further generated to form the vector group C1 (FIG. 16). .
- Example 3 the damage vector C1-1 (the range indicated by the reference symbol Lv1 in FIG. 14) occurring in the first image is set to the highest “level 1”, and the damage occurring in the next image Vectors C1-2 and C1-3 (range indicated by reference symbol Lv2 in FIG. 15) are set to “level 2”, and damage vectors C1-4, C1-5, and C1-6 (FIG. 16) occurring in the last image are set.
- the hierarchy of each damage vector determined in this way is included in the hierarchical structure information as shown in the table of FIG.
- FIG. 18 is a diagram showing a crack C2A and a vector group C2 corresponding to the crack C2A.
- the other one damage vector belongs to the same hierarchy as the one damage vector.
- one curved crack C2A is divided into a plurality of cracks C2A-1 to C2A-4, and these cracks start at points P8 to P12.
- the damage vectors C2-1 to C2-4 only one damage vector (damage vectors C2-2 to C2-4) is provided at each end point of the damage vectors C2-1 to C2-3. Not connected.
- the damage vectors C2-1 to C2-4 are substantially one, and “level 1” (all having the same hierarchy) ( Belongs to the top).
- the hierarchy of each damage vector determined in this way is included in the hierarchical structure information as shown in the table of FIG.
- the damage vector affiliation hierarchy determination examples 1 to 4 have been described above. These techniques can be appropriately used according to specific damage modes, and a plurality of techniques can be used in combination as necessary. May be. For example, for a group of damage vectors having a complicated connection pattern, the hierarchy may be determined using Example 1 for some parts and the hierarchy may be determined using Example 4 for other parts. Such a combination of hierarchical methods may be determined by the hierarchical structure information generation unit 112 or may be performed based on a user instruction input via the operation unit 120.
- the hierarchical structure information includes a vector group to which the damage vector belongs, an ID (identification number) of the damage vector, an belonging hierarchy, IDs of other damage vectors to be connected (parent vector, sibling vector, and child vector), etc. (See FIGS. 10, 13, 17 and 19), it is possible to extract a damage vector by designating desired conditions for these items. Examples of conditions that can be specified include “hierarchies to which damage vectors belong” and “vectors with a specific vector as a parent vector, sibling vector, or child vector”. Examples of conditions that can be specified are in these examples. It is not limited.
- damage vector C1-2 is referred to by referring to the “hierarchy (level)” column of the hierarchical structure information.
- C1-3, and C1-4 are extracted and specified as a condition “damage vector connected to damage vector C1-2 and belonging to a layer higher than damage vector C1-2” as a condition, damage vector C1-1 ( Parent vector) is extracted.
- damage vector C1-2 and belonging to the same hierarchy as damage vector C1-2 is specified as a condition
- damage vector C1-3 (sibling vector) and damage vector C1-4 (child vector) Is extracted
- damage vectors C1-5 and C1-6 child vectors
- Such damage vector extraction can be performed by the damage vector extraction unit 114 referring to the hierarchical structure information recording unit 116 based on a user instruction input via the operation unit 120.
- the damage information processing apparatus 100 can easily search, analyze, and evaluate damage vectors.
- the extracted damage vector can be displayed in the form of individual information and / or line drawing (described later).
- step S140 the hierarchical structure information generated in step S130 is displayed on the display unit 118 (display process).
- the hierarchical structure information can be displayed, for example, in the form of tables shown in FIGS. 9, 10, 13, 17, and 19 or by using some information extracted from those tables. Examples of such “partial information” include “information on damage vectors extracted under specified conditions” and “information on specific items such as inspection date and / or repair date”.
- a line drawing indicating a damage vector may be drawn based on the hierarchical structure information and displayed on the display unit 118.
- the hierarchical structure information includes information on the start and end points of damage vectors and other damage vectors to be connected.
- a line drawing showing a vector (see, for example, FIGS. 11, 12, and 14 to 16) can be drawn and displayed.
- An arrow may be attached to the line drawing showing the damage vector so that the direction of the damage vector (direction from the start point to the end point) can be identified (see FIGS. 11, 12, and 14 to 16).
- all damage vectors included in the hierarchical structure information may be drawn and displayed, or some damage vectors (for example, extracted under specified conditions as described above) Only) may be displayed.
- One of the damage vector line drawing and the hierarchical structure information described above may be displayed, or both may be displayed simultaneously.
- an image obtained by imaging damage (cracking) in the above display (for example, the image “img_2015-001” shown in the table of FIG. 9) is displayed so as to be superposed or displayed side by side with the line drawing of the damage vector so that they can be compared. (See, for example, FIG. 18).
- damage vectors and / or hierarchical structure information are displayed in this manner, damage vector information and the connection relationship between damage vectors can be easily grasped.
- step S150 the hierarchical structure information is recorded in the hierarchical structure information recording unit 116 (recording process).
- the hierarchical structure information recorded in the hierarchical structure information recording unit 116 can be used for purposes such as damage analysis and evaluation.
- some information for example, a damage vector that satisfies a specified condition
- all the extracted information is included in the original hierarchical structure information, so the extraction result is not necessarily recorded.
- the hierarchical structure information generation unit 112 generates hierarchical structure information. However, based on a user instruction input via the operation unit 120, the hierarchical structure information generation unit 112 corrects the hierarchical structure information. You may be able to do that.
- the damage information processing apparatus 100 and the damage information processing method according to the present embodiment it is possible to easily grasp the connection relationship between the damage vectors, and analyze and / or search the damage vectors based on the hierarchical structure information. Can be easily performed.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
Description
図1は、本発明に係る損傷情報処理装置及び損傷情報処理方法が適用される構造物の例である橋梁1(構造物、コンクリート構造物)の構造を示す斜視図である。図1に示す橋梁1は主桁3を有し、主桁3は接合部3Aで接合されている。主桁3は橋台及び/または橋脚の間に渡され、床版2上の車輌等の荷重を支える部材である。また主桁3の上部には、車輌等が走行するための床版2が打設されている。床版2は鉄筋コンクリート製のものとする。なお橋梁1は、床版2及び主桁3の他に図示せぬ横桁、対傾構、及び横構等の部材を有する。
橋梁1の損傷を検査する場合、検査員はデジタルカメラ104(図2参照)を用いて橋梁1を下方から撮影し(図1のC方向)、検査範囲について画像を取得する。撮影は、橋梁1の延伸方向(図1のA方向)及びその直交方向(図1のB方向)に適宜移動しながら行う。なお橋梁1の周辺状況により検査員の移動が困難な場合は、橋梁1に沿って移動可能な移動体にデジタルカメラ104を設置して撮影を行ってもよい。このような移動体には、デジタルカメラ104の昇降機構及び/またはパン・チルト機構を設けてもよい。なお移動体の例としては車輌、ロボット、及び飛翔体を挙げることができるが、これらに限定されるものではない。
図2は、本実施形態に係る損傷情報処理装置100の概略構成を示すブロック図である。損傷情報処理装置100は、損傷情報取得部102、損傷ベクトル生成部110、階層構造情報生成部112、損傷ベクトル抽出部114、階層構造情報記録部116、表示部118、及び操作部120を備え、互いに接続されていて、必要な情報を互いに送受信できるようになっている。
次に、上述した構成の損傷情報処理装置100を用いた損傷情報処理について説明する。図3は本実施形態に係る損傷情報処理の手順を示すフローチャートである。なお、本実施形態では損傷が床版2に生じたひび割れである場合について説明し、損傷を適宜「ひび割れ」と記載するが、本発明が適用可能な損傷はひび割れに限らず、遊離石灰等他の損傷でもよい。
まず、上述のようにデジタルカメラ104で撮影した橋梁1の画像を、無線通信により画像取得部106に入力する(ステップS100;画像入力工程)。橋梁1の画像は検査範囲に応じて複数入力され、また入力する画像には、デジタルカメラ104により撮影日時の情報が付加されている。なお入力画像の撮影日時は必ずしも全ての画像において同一である必要はなく、複数日に亘っていてもよい。画像は複数の画像を一括して入力してもよいし、一度に1つの画像を入力するようにしてもよい。なお、橋梁1の画像は無線通信でなく各種メモリカード等の非一時的記録媒体を介して入力するようにしてもよいし、既に撮影され記録されている画像のデータをネットワーク経由で入力してもよい。なおステップS100で入力する橋梁1の画像は、撮影画像そのままでもよいし、撮影画像に前処理を施したものでもよい。
次に、画像処理部108は、入力した画像から損傷(ひび割れ)を抽出する(ステップS110;損傷抽出工程)。ステップS100の画像入力工程及びステップS110の損傷抽出工程は、本発明の損傷情報処理方法における損傷情報取得工程を構成する。なおステップS110では、ステップS100で入力した画像から損傷が抽出されていれば、即ち画像における損傷の領域が識別されていれば損傷情報が取得できたものと考えてよく、損傷の詳細な特徴が把握されることまでは要しない。
ステップS110で損傷が抽出されると(損傷情報が取得されると)、損傷ベクトル生成部110が、取得した損傷情報をベクトル化して損傷ベクトル(ひび割れベクトル)を生成する(ステップS120;損傷ベクトル生成工程)。ベクトル化に際しては、抽出した損傷(ひび割れ)を必要に応じ2値化及び/または細線化する。なお「ベクトル化」とは、損傷に対し始点及び終点で定まる線分を求めることであり、損傷(ひび割れ)が曲線状の場合、曲線と線分の距離が閾値以下になるように損傷を複数の区間に分割し、複数の区間のそれぞれについて損傷ベクトルを生成する。図4の例では、曲線状の損傷Crを4つの区間Cr1~Cr4に分割し、それぞれの区間について損傷ベクトルCv1~Cv4を生成することで、区間Cr1~Cr4における損傷と損傷ベクトルCv1~Cv4との距離d1~d4が閾値以下になるようにしている。
上述のようにして損傷ベクトルを生成する場合、損傷が床版2の内部では連続しているが表面では分離していると、分離した損傷ベクトルとして認識されてしまう可能性がある。そこで本実施形態に係る損傷情報処理装置100では、そのような複数の損傷ベクトルを連結して1または複数のベクトルを生成する。
ステップS120で損傷ベクトルが生成されると、生成した損傷ベクトルに基づいて、階層構造情報生成部112が階層構造情報を生成する(ステップS130;階層構造情報生成工程)。階層構造情報は損傷ベクトル同士の連結関係を階層的に表現した情報であり、画像情報(図9を参照)及び損傷ベクトル情報(図10,13,17,及び19を参照)により構成される。これら画像情報及び損傷ベクトル情報は、損傷ベクトル(ひび割れベクトル)の集合体であるベクトルグループを介して関連づけられている。したがって損傷の画像からベクトルグループのID(Identification)を参照して損傷ベクトルを抽出することもできるし、逆に損傷ベクトルに基づいて画像を抽出することもできる。なお、階層構造情報は損傷ベクトルが所属する階層(レベル)によらず同一の項目及び形式で生成されるので(図10,13,17,及び19を参照)、ユーザは階層構造情報を容易に認識及び把握することができる。
上述した画像情報とは、損傷が撮像された撮影画像についての情報であり、損傷ベクトルのグループについて、撮影画像の識別情報(ID)及び画像データ、画像取得日時等を規定したものである。図9は画像情報の例を示す表であり、ベクトルグループC1(図11参照)について、画像のID、画像データ、取得日時、画像の幅及び高さ、チャンネル数、ビット/ピクセル、解像度が規定されている。チャンネル数はRGB(R:赤、G:緑、B:青)カラー画像なら3チャンネルであり、モノクロ画像なら1チャンネルである。なお図9ではベクトルグループC1についてのみ記載しているが、ベクトルグループが複数存在する場合は、各グループについて同様の情報が生成される。
図10は、損傷ベクトル情報の例である。損傷ベクトル情報は、損傷ベクトルが所属するベクトルグループの情報と、各損傷ベクトルの固有情報と、ベクトルグループ内において各損傷ベクトルに連結する他の損傷ベクトルの情報と、付加情報と、から構成される。
本実施形態において、一の損傷ベクトルの終点が他の損傷ベクトルの始点となっている場合、そのような一の損傷ベクトルを「親ベクトル」といい、他の損傷ベクトルを「子ベクトル」という。親ベクトルは1つの損傷ベクトルについてゼロまたは1つとなるように決めるものとするが、子ベクトルは1つの親ベクトルに対しゼロ以上の任意の数だけ存在していてよい。また、親ベクトルの終点が複数の子ベクトルの始点となっている場合、それら複数の子ベクトルは互いに「兄弟ベクトル」という。兄弟ベクトルも、ゼロ以上の任意の数だけ存在していてよい。
付加情報に含まれる「幅」は、各損傷ベクトルに対応するひび割れの幅を示す。削除操作フラグは削除操作が行われたベクトルであるかどうかを示し、削除操作が行われた場合は“1”、行われていない場合は“0”である。この削除操作フラグを参照して、損傷ベクトルの表示と非表示とを切り替えることができる。追加操作フラグは、損傷ベクトルの検出態様に関連しており、自動で検出されたベクトルである場合は“0”、手動で(ユーザの指示入力により)追加されたベクトルである場合は“1”、手動で追加され異なるIDのベクトルを接続して生成されたベクトルである場合は“2”である。
次に、損傷ベクトルが所属する階層(レベル)について説明する。損傷ベクトルの階層は、例えば以下の例1~4で説明するように、種々の手法で決定することができる。
図11は、ベクトルグループC1を示す図である。ベクトルグループC1は、損傷ベクトルC1-1~C1-6により構成されており、これら損傷ベクトルは点P1~P7を始点または終点としている。このような状況において例1では、損傷ベクトルが分岐する(ある損傷ベクトルの終点が他の複数の損傷ベクトルの始点となっている)ごとに階層が下位になるとしている。具体的には損傷ベクトルC1-1の階層を最も上位の“レベル1”として、損傷ベクトルC1-1の終点である点P2を始点とする損傷ベクトルC1-2及びC1-3の階層は、損傷ベクトルC1-1よりも下位である“レベル2”とする。同様に、損傷ベクトルC1-3の終点である点P4を始点とする損傷ベクトルC1-5及びC1-6の階層は、損傷ベクトルC1-3よりも下位である“レベル3”とする。一方、損傷ベクトルC1-2の終点である点P3は損傷ベクトルC1-4の始点であるが、点P3を始点とする損傷ベクトルは損傷ベクトルC1-4だけであり分岐はないので、損傷ベクトルC1-4の階層はC1-2と同じ“レベル2”とする。このようにして決定した各損傷ベクトルの階層は、図10の表に示すように階層構造情報に含まれる。
図12は、ベクトルグループC1(損傷ベクトル同士の連結関係は図11に示すものと同一)を示す図である。例2では、連結する損傷ベクトルのうち他の損傷ベクトルとなす角度が閾値以下であるもの(木構造における「幹」に相当する損傷ベクトル)は同一の階層に属するものとしている。具体的には図12の点線内(参照符号Lv1で示す範囲)に存在する損傷ベクトルC1-1,C1-2,及びC1-4は同一の階層である“レベル1”(最上位)とする。また、それ以外の損傷ベクトルC1-3,C1-5,及びC1-6については、例1と同様に損傷ベクトルが分岐するごとに階層が下位になるとしており、損傷ベクトルC1-3(木構造における「枝」に相当)を“レベル2”、損傷ベクトルC1-5及びC1-6(木構造における「葉」に相当)を“レベル3”としている。このようにして決定した各損傷ベクトルの階層及び種別(幹、枝、あるいは葉)は、図13の表に示すように、階層構造情報に含まれる。
上述した階層決定手法(例2)の変形例について説明する。階層決定手法(例2)のように損傷ベクトルを木構造における幹、枝、及び葉に相当するものとして階層を決定するに際して、一般に「枝」は「幹」よりも短いと考えられるため、最長の損傷ベクトルを「幹」(レベル1)とし、その他の損傷ベクトルを「枝」または「葉」として階層を決定するようにしてもよい。この場合、例えば図13の表に示す損傷ベクトル情報では、長さ100mmの損傷ベクトルC1-1が「幹」(レベル1)となる。損傷ベクトルC1-2及びC1-3は「枝」(レベル2)とし、損傷ベクトルC1-4は「枝」(レベル2)または「葉」(レベル3)、損傷ベクトルC1-5,及び6は「葉」(レベル3)とすることができる。
図14~16は、ベクトルグループC1(損傷ベクトル同士の連結関係は図11,12に示すものと同一)を示す図である。例3では、損傷ベクトルが生じた時間の先後を橋梁1の画像の撮影日時に基づいて判断し、損傷ベクトルが時間的に後に生じたものであるほど下位の階層に属するものとしている。図14~16の場合、最初に撮影した画像では損傷ベクトルC1-1を含むベクトルグループC1Aが生じており(図14)、次に撮影した画像では損傷ベクトルC1-2及びC1-3が新たに発生してベクトルグループC1Bとなり(図15)、最後に撮影した画像ではさらに損傷ベクトルC1-4,C1-5,及びC1-6が発生してベクトルグループC1となった(図16)ものとする。
図18は、ひび割れC2A及びこれに対応するベクトルグループC2を示す図である。例4では、一の損傷ベクトルに連結している他の損傷ベクトルが1つのみである場合、そのような他の1つの損傷ベクトルは一の損傷ベクトルと同じ階層に属するものとしている。具体的には、図18に示すように一本の曲線状のひび割れC2Aが複数のひび割れC2A-1~C2A-4に分割されており、これらひび割れが点P8~点P12を始点または終点とする損傷ベクトルC2-1~C2-4にそれぞれ対応している場合を考えると、損傷ベクトルC2-1~C2-3の終点にはそれぞれ1つの損傷ベクトル(損傷ベクトルC2-2~C2-4)しか連結していない。このような場合、例4では損傷ベクトルC2-1~C2-4(図18において参照符号Lv1で示す範囲)は実質的に1つであると考え、全て同一の階層である“レベル1”(最上位)に属するものとする。
本実施形態では、図10,13,17,及び19の表に示すように階層構造情報が損傷ベクトルの属する階層によらず同一の項目及び形式なので、損傷ベクトル同士の連結関係を迅速かつ容易に把握することができる。
次に、損傷ベクトルの抽出について説明する。本実施形態において、階層構造情報には損傷ベクトルが所属するベクトルグループ、損傷ベクトルのID(識別番号)、所属階層、連結する他の損傷ベクトル(親ベクトル、兄弟ベクトル、及び子ベクトル)のID等が含まれているので(図10,13,17,及び19参照)、これらの項目について所望の条件を指定して損傷ベクトルを抽出することができる。指定する条件としては、例えば「損傷ベクトルが所属する階層」及び「特定のベクトルを親ベクトル、兄弟ベクトル、あるいは子ベクトルとするベクトル」を挙げることができるが、指定しうる条件はこれらの例に限定されるものではない。
ステップS140では、ステップS130で生成された階層構造情報を表示部118に表示する(表示工程)。階層構造情報の表示は、例えば図9,10,13,17,及び19に示す表の形式で行ったり、それらの表から抽出した一部の情報により行ったりすることができる。そのような「一部の情報」の一例としては、「指定した条件で抽出した損傷ベクトルの情報」及び「点検日及び/または補修日等、特定の項目についての情報」を挙げることができる。
ステップS150では、階層構造情報を階層構造情報記録部116に記録する(記録工程)。階層構造情報記録部116に記録された階層構造情報は、損傷の分析及び評価などの目的に使用することができる。なお階層構造情報から一部の情報(例えば指定した条件を満たす損傷ベクトル)を抽出した場合、そのようにして抽出した情報は全て元の階層構造情報に含まれるため、抽出結果は必ずしも記録しておかなくてもよいが、抽出結果についても階層構造情報記録部116に記録しておくことで、必要に応じ迅速に参照することができる。
上述のように、本実施形態では階層構造情報生成部112が階層構造情報を生成するが、操作部120を介したユーザの指示入力に基づいて、階層構造情報生成部112が階層構造情報を修正することができるようにしてもよい。
2 床版
3 主桁
3A 接合部
100 損傷情報処理装置
102 損傷情報取得部
104 デジタルカメラ
106 画像取得部
108 画像処理部
110 損傷ベクトル生成部
112 階層構造情報生成部
114 損傷ベクトル抽出部
116 階層構造情報記録部
118 表示部
120 操作部
Claims (16)
- 構造物の損傷についての損傷情報を取得する損傷情報取得部と、
前記取得した損傷情報をベクトル化して損傷ベクトルを生成する損傷ベクトル生成部と、
前記生成した損傷ベクトルに基づいて前記損傷ベクトル同士の連結関係を階層的に表現した情報である階層構造情報を生成する階層構造情報生成部と、
を備える損傷情報処理装置。 - 前記階層構造情報生成部は、一の損傷ベクトルが属するベクトルグループの情報と、前記一の損傷ベクトルと連結する他の損傷ベクトルの情報と、前記一の損傷ベクトルの固有情報と、を含む前記階層構造情報を生成する請求項1に記載の損傷情報処理装置。
- 前記階層構造情報生成部は、前記一の損傷ベクトルに他の複数の損傷ベクトルが連結している場合、前記他の複数の損傷ベクトルは前記一の損傷ベクトルよりも下位の階層に属するものとして前記階層構造情報を生成する請求項2に記載の損傷情報処理装置。
- 前記階層構造情報生成部は、前記一の損傷ベクトルと前記一の損傷ベクトルに連結している他の損傷ベクトルとのなす角度が閾値以下であるときは、前記他の損傷ベクトルは前記一の損傷ベクトルと同じ階層に属するものとして前記階層構造情報を生成する請求項2に記載の損傷情報処理装置。
- 前記階層構造情報生成部は、前記一の損傷ベクトルに連結する前記他の損傷ベクトルが前記一の損傷ベクトルよりも時間的に後に生じた損傷ベクトルである場合は、前記他の損傷ベクトルは前記一の損傷ベクトルよりも下位の階層に属するものとして前記階層構造情報を生成する請求項2に記載の損傷情報処理装置。
- 前記階層構造情報生成部は、前記一の損傷ベクトルに連結している他の損傷ベクトルが1つのみである場合、前記他の1つの損傷ベクトルは前記一の損傷ベクトルと同じ階層に属するものとして前記階層構造情報を生成する請求項2に記載の損傷情報処理装置。
- 前記固有情報は、前記一の損傷ベクトルの識別情報と、前記一の損傷ベクトルが階層構造のどの階層に属するかを示す所属階層情報と、始点及び終点の位置と、を含む請求項2から6のいずれか1項に記載の損傷情報処理装置。
- 前記階層構造情報生成部は損傷ベクトルの属する階層によらず同一の項目及び形式により前記階層構造情報を生成する請求項1から7のいずれか1項に記載の損傷情報処理装置。
- 前記損傷ベクトル生成部は、空間的に分離した複数の損傷ベクトルを連結させて1または複数のベクトルを生成する請求項1から8のいずれか1項に記載の損傷情報処理装置。
- 前記階層構造情報を参照して、指定された条件を満たす損傷ベクトルを抽出する損傷ベクトル抽出部を備える請求項1から9のいずれか1項に記載の損傷情報処理装置。
- 前記損傷ベクトル抽出部は、指定された損傷ベクトルと連結し前記指定されたベクトルよりも上位の階層に属する損傷ベクトルと、前記指定された損傷ベクトルと連結し前記指定されたベクトルと同じ階層に属する損傷ベクトルと、前記指定された損傷ベクトルと連結し前記指定されたベクトルよりも下位の階層に属する損傷ベクトルと、のうち少なくとも1つを抽出する請求項10に記載の損傷情報処理装置。
- 前記抽出した損傷ベクトル及び前記生成した階層構造情報を表示する表示部を備える請求項10または11に記載の損傷情報処理装置。
- 前記階層構造情報を記録する階層構造情報記録部を備える請求項1から12のいずれか1項に記載の損傷情報処理装置。
- 前記損傷情報取得部は前記構造物を撮像した画像を画像処理して前記損傷情報を取得する請求項1から13のいずれか1項に記載の損傷情報処理装置。
- 前記構造物はコンクリート構造物であり、前記損傷はひび割れと遊離石灰とのうち少なくとも一方を含む請求項1から14のいずれか1項に記載の損傷情報処理装置。
- 構造物の損傷についての損傷情報を取得する損傷情報取得工程と、
前記取得した損傷情報をベクトル化して損傷ベクトルを生成する損傷ベクトル生成工程と、
前記生成した損傷ベクトルに基づいて前記損傷ベクトル同士の連結関係を階層的に表現した情報である階層構造情報を生成する階層構造情報生成工程と、
を含む損傷情報処理方法。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201680075328.7A CN108431584B (zh) | 2015-12-25 | 2016-11-09 | 损伤信息处理装置及损伤信息处理方法 |
JP2017557778A JP6573986B2 (ja) | 2015-12-25 | 2016-11-09 | 損傷情報処理装置及び損傷情報処理方法 |
EP16878177.1A EP3396359B1 (en) | 2015-12-25 | 2016-11-09 | Damage information processing device and damage information processing method |
US16/009,673 US10942130B2 (en) | 2015-12-25 | 2018-06-15 | Damage information processing device and damage information processing method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015-254976 | 2015-12-25 | ||
JP2015254976 | 2015-12-25 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/009,673 Continuation US10942130B2 (en) | 2015-12-25 | 2018-06-15 | Damage information processing device and damage information processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017110279A1 true WO2017110279A1 (ja) | 2017-06-29 |
Family
ID=59090093
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2016/083191 WO2017110279A1 (ja) | 2015-12-25 | 2016-11-09 | 損傷情報処理装置及び損傷情報処理方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US10942130B2 (ja) |
EP (1) | EP3396359B1 (ja) |
JP (4) | JP6573986B2 (ja) |
CN (1) | CN108431584B (ja) |
WO (1) | WO2017110279A1 (ja) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019009214A1 (ja) * | 2017-07-07 | 2019-01-10 | キヤノン株式会社 | 画像から変状を検知する画像処理装置、画像処理方法及びプログラム |
JP2020113052A (ja) * | 2019-01-11 | 2020-07-27 | 富士通株式会社 | ひび線抽出装置、ひび線抽出方法、及び、ひび線抽出プログラム |
JP2021036213A (ja) * | 2019-08-30 | 2021-03-04 | 富士通株式会社 | 撮影漏れ検出装置、及び、撮影漏れ検出方法 |
WO2021171839A1 (ja) * | 2020-02-28 | 2021-09-02 | 富士フイルム株式会社 | 画像表示装置、画像表示方法、及びプログラム |
WO2021187157A1 (ja) | 2020-03-16 | 2021-09-23 | 富士フイルム株式会社 | 画像処理装置、画像処理方法、及び画像処理プログラム |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019021729A1 (ja) * | 2017-07-25 | 2019-01-31 | 富士フイルム株式会社 | 損傷図作成方法、損傷図作成装置、損傷図作成システム、及び記録媒体 |
WO2019163556A1 (ja) * | 2018-02-22 | 2019-08-29 | パナソニックIpマネジメント株式会社 | 検査装置及び検査方法 |
JP7429648B2 (ja) * | 2018-12-13 | 2024-02-08 | 富士フイルム株式会社 | 損傷図作成支援装置、損傷図作成支援方法、損傷図作成支援プログラム及び損傷図作成支援システム |
JP7564865B2 (ja) * | 2020-04-01 | 2024-10-09 | 富士フイルム株式会社 | 3次元表示装置、3次元表示方法、及びプログラム |
WO2022114006A1 (ja) | 2020-11-27 | 2022-06-02 | 富士フイルム株式会社 | 情報処理装置、情報処理方法及び情報処理プログラム |
JPWO2023053705A1 (ja) * | 2021-09-30 | 2023-04-06 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH03138775A (ja) * | 1989-10-25 | 1991-06-13 | Tokyo Electric Power Co Inc:The | ひび割れ測定システム |
JPH06148089A (ja) * | 1992-05-29 | 1994-05-27 | Shimizu Corp | ひび割れ計測処理装置 |
JP2000046691A (ja) * | 1998-07-27 | 2000-02-18 | Asahi Optical Co Ltd | 光学部材検査装置,画像処理装置,及び、コンピュータ可読媒体 |
JP2002257744A (ja) * | 2001-03-02 | 2002-09-11 | Takenaka Komuten Co Ltd | コンクリートの欠陥検査方法およびコンクリートの欠陥検査装置 |
JP2013250058A (ja) * | 2012-05-30 | 2013-12-12 | Railway Technical Research Institute | コンクリート表面の線状変状検出方法 |
JP2016050887A (ja) * | 2014-09-01 | 2016-04-11 | 関西工事測量株式会社 | クラック計測システム |
Family Cites Families (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0718696B2 (ja) * | 1986-06-23 | 1995-03-06 | 清水建設株式会社 | ひび割れ自動計測装置 |
JP2554516B2 (ja) | 1988-01-14 | 1996-11-13 | 東京電力株式会社 | ひび割れ自動計測装置 |
JP4189061B2 (ja) | 1998-07-10 | 2008-12-03 | 株式会社Ihi | コンクリート表面のクラック検出方法 |
JP2006132973A (ja) * | 2004-11-02 | 2006-05-25 | Fujimitsu Komuten:Kk | コンクリート構造物のクラック検査装置及びクラック検査方法 |
JP4006007B2 (ja) | 2004-11-10 | 2007-11-14 | 大成建設株式会社 | ひび割れ検出方法 |
JP4848532B2 (ja) * | 2006-08-21 | 2011-12-28 | 名古屋市 | 路面画像作成方法および路面画像作成装置 |
JP2008291440A (ja) * | 2007-05-22 | 2008-12-04 | Hokkaido Electric Power Co Inc:The | 構造物劣化曲線算出システムおよびライフサイクルコスト評価方法 |
DE102009033614B4 (de) * | 2009-07-17 | 2020-01-23 | Wolfgang Klippel | Anordnung und Verfahren zur Erkennung, Ortung und Klassifikation von Defekten |
JP2011169055A (ja) * | 2010-02-19 | 2011-09-01 | Nagoya Electrical Educational Foundation | 道路補修自走作業車 |
JP5505818B2 (ja) * | 2010-06-14 | 2014-05-28 | 新日鐵住金株式会社 | 欠陥判別装置 |
JP2012098045A (ja) | 2010-10-29 | 2012-05-24 | Mitsubishi Electric Corp | クラック検出装置及びクラック検出プログラム |
US9235902B2 (en) * | 2011-08-04 | 2016-01-12 | University Of Southern California | Image-based crack quantification |
CN102507587B (zh) * | 2011-09-20 | 2013-11-27 | 株洲时代电子技术有限公司 | 巡视检测系统及方法 |
JP6009956B2 (ja) * | 2013-01-31 | 2016-10-19 | 株式会社日立ハイテクノロジーズ | 欠陥検査装置および欠陥検査方法 |
CN103400139A (zh) * | 2013-07-04 | 2013-11-20 | 中南大学 | 一种混凝土裂缝特征信息的识别方法 |
JP5688533B1 (ja) * | 2014-01-23 | 2015-03-25 | デ・ファクト・スタンダード合同会社 | コンクリート構造物維持管理システム |
CN103870833B (zh) * | 2014-03-31 | 2016-03-02 | 武汉工程大学 | 基于凹性测度的路面裂缝提取与测评方法 |
CN103969337B (zh) * | 2014-05-07 | 2017-02-22 | 北京工业大学 | 一种基于矢量全聚焦成像的超声阵列裂纹类缺陷方向识别方法 |
JP5806786B1 (ja) * | 2015-04-17 | 2015-11-10 | ヴィスコ・テクノロジーズ株式会社 | 画像認識装置 |
JP6682561B2 (ja) * | 2016-01-26 | 2020-04-15 | 富士フイルム株式会社 | ひび割れ情報検出装置、ひび割れ情報検出方法およびひび割れ情報検出プログラム |
JP6315130B2 (ja) | 2017-04-28 | 2018-04-25 | 日亜化学工業株式会社 | 発光素子及び発光装置 |
EP3748283A4 (en) * | 2018-01-31 | 2020-12-30 | Fujifilm Corporation | REPAIR LENGTH DETERMINATION PROCEDURE AND REPAIR LENGTH DETERMINATION DEVICE |
JP6958435B2 (ja) | 2018-03-06 | 2021-11-02 | 東レ株式会社 | 塗布ヘッドおよび塗膜付きウェブの製造方法 |
-
2016
- 2016-11-09 JP JP2017557778A patent/JP6573986B2/ja active Active
- 2016-11-09 CN CN201680075328.7A patent/CN108431584B/zh active Active
- 2016-11-09 EP EP16878177.1A patent/EP3396359B1/en active Active
- 2016-11-09 WO PCT/JP2016/083191 patent/WO2017110279A1/ja active Application Filing
-
2018
- 2018-06-15 US US16/009,673 patent/US10942130B2/en active Active
-
2019
- 2019-08-14 JP JP2019148907A patent/JP6857218B2/ja active Active
-
2021
- 2021-03-19 JP JP2021045527A patent/JP7102569B2/ja active Active
-
2022
- 2022-07-06 JP JP2022108793A patent/JP7313517B2/ja active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH03138775A (ja) * | 1989-10-25 | 1991-06-13 | Tokyo Electric Power Co Inc:The | ひび割れ測定システム |
JPH06148089A (ja) * | 1992-05-29 | 1994-05-27 | Shimizu Corp | ひび割れ計測処理装置 |
JP2000046691A (ja) * | 1998-07-27 | 2000-02-18 | Asahi Optical Co Ltd | 光学部材検査装置,画像処理装置,及び、コンピュータ可読媒体 |
JP2002257744A (ja) * | 2001-03-02 | 2002-09-11 | Takenaka Komuten Co Ltd | コンクリートの欠陥検査方法およびコンクリートの欠陥検査装置 |
JP2013250058A (ja) * | 2012-05-30 | 2013-12-12 | Railway Technical Research Institute | コンクリート表面の線状変状検出方法 |
JP2016050887A (ja) * | 2014-09-01 | 2016-04-11 | 関西工事測量株式会社 | クラック計測システム |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019009214A1 (ja) * | 2017-07-07 | 2019-01-10 | キヤノン株式会社 | 画像から変状を検知する画像処理装置、画像処理方法及びプログラム |
JPWO2019009214A1 (ja) * | 2017-07-07 | 2020-05-21 | キヤノン株式会社 | 画像から変状を検知する画像処理装置、画像処理方法及びプログラム |
US11443500B2 (en) | 2017-07-07 | 2022-09-13 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and program for detecting defect from image |
JP7191823B2 (ja) | 2017-07-07 | 2022-12-19 | キヤノン株式会社 | 画像から変状を検知する画像処理装置、画像処理方法及びプログラム |
JP2020113052A (ja) * | 2019-01-11 | 2020-07-27 | 富士通株式会社 | ひび線抽出装置、ひび線抽出方法、及び、ひび線抽出プログラム |
JP7225810B2 (ja) | 2019-01-11 | 2023-02-21 | 富士通株式会社 | ひび線抽出装置、ひび線抽出方法、及び、ひび線抽出プログラム |
JP2021036213A (ja) * | 2019-08-30 | 2021-03-04 | 富士通株式会社 | 撮影漏れ検出装置、及び、撮影漏れ検出方法 |
JP7263983B2 (ja) | 2019-08-30 | 2023-04-25 | 富士通株式会社 | 撮影漏れ検出装置、及び、撮影漏れ検出方法 |
WO2021171839A1 (ja) * | 2020-02-28 | 2021-09-02 | 富士フイルム株式会社 | 画像表示装置、画像表示方法、及びプログラム |
WO2021187157A1 (ja) | 2020-03-16 | 2021-09-23 | 富士フイルム株式会社 | 画像処理装置、画像処理方法、及び画像処理プログラム |
Also Published As
Publication number | Publication date |
---|---|
US20180292329A1 (en) | 2018-10-11 |
JP2021101190A (ja) | 2021-07-08 |
EP3396359A1 (en) | 2018-10-31 |
JP7102569B2 (ja) | 2022-07-19 |
JPWO2017110279A1 (ja) | 2018-10-04 |
EP3396359A4 (en) | 2019-01-16 |
CN108431584A (zh) | 2018-08-21 |
JP7313517B2 (ja) | 2023-07-24 |
US10942130B2 (en) | 2021-03-09 |
JP2022137150A (ja) | 2022-09-21 |
EP3396359B1 (en) | 2021-04-28 |
JP6573986B2 (ja) | 2019-09-11 |
JP6857218B2 (ja) | 2021-04-14 |
JP2019200213A (ja) | 2019-11-21 |
CN108431584B (zh) | 2021-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6573986B2 (ja) | 損傷情報処理装置及び損傷情報処理方法 | |
WO2017130699A1 (ja) | ひび割れ情報検出装置、ひび割れ情報検出方法およびひび割れ情報検出プログラム | |
JP6576473B2 (ja) | ひび割れ情報編集装置、ひび割れ情報編集方法およびひび割れ情報編集プログラム | |
JP2022000646A (ja) | サーバ装置、画像処理方法、及び画像処理システム | |
WO2017110278A1 (ja) | 情報処理装置及び情報処理方法 | |
EP3709264B1 (en) | Information processing apparatus and accumulated images selecting method | |
WO2021014754A1 (ja) | ひび割れ評価装置、ひび割れ評価方法、及びひび割れ評価プログラム | |
US11144590B2 (en) | Similar damage search device and a similar damage search method | |
JP2018036226A (ja) | 画像処理プログラム、画像処理方法および画像処理装置 | |
Ioli et al. | UAV photogrammetry for metric evaluation of concrete bridge cracks | |
JP5218849B2 (ja) | 欠陥検査装置 | |
WO2020129554A1 (ja) | 観測方法及び観測装置 | |
Adhikari et al. | Automated bridge condition assessment with hybrid sensing | |
Moreu et al. | Bridge Cracks Monitoring: Detection, Measurement, and Comparison using Augmented Reality |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16878177 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2017557778 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2016878177 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2016878177 Country of ref document: EP Effective date: 20180725 |