JP7271360B2 - State determination system - Google Patents

Description

The present invention relates to a state determination system for determining the state of structures.

Conventionally, it has been proposed to identify the vibrations at a plurality of locations of the bridge by analyzing the image of the bridge and grasp the progress of deterioration of the bridge (see, for example, Patent Document 1).

JP 2017-207339 A

Changes in vibration when an abnormality occurs in a structure such as a bridge are often local and minute. Furthermore, when observing vibrations occurring in a structure, the observed data may contain noise due to the influence of the environment and the like. Therefore, it may be difficult to accurately determine the state of the structure based on minute changes in vibration.

An object of one aspect of the present invention is to provide a state determination system capable of appropriately determining the state of a structure such as a bridge.

A state determination system according to one aspect of the present invention includes an acquisition unit that acquires a moving image of a structure, and a plurality of displacement amounts of a plurality of regions of the structure from the moving image acquired by the acquisition unit. a measuring unit that acquires displacement data; a reconstruction unit that reconstructs an attractor based on the plurality of displacement data acquired by the measuring unit; and an analysis unit that determines the state.

In this state determination system, the state of a structure is determined based on attractors reconstructed from a plurality of displacement data of the structure. In this way, since the attractor is reconstructed from a plurality of displacement data, even if a part of the displacement data contains a lot of noise, the influence of the noise on the attractor can be reduced. Therefore, it is possible to appropriately determine the state of the structure.

One aspect of the present invention can provide a state determination system that can appropriately determine the state of a structure such as a bridge.

It is a figure for demonstrating the structure of the state determination system which concerns on an example. FIG. 4 is a diagram schematically showing an example of displacement data acquired from a moving image; FIG. FIG. 10 is a diagram showing a combination of displacement data for reconstructing an attractor; FIG. 4 is a diagram for explaining filtration; FIG. 3 is a diagram showing an example of a persistent diagram; FIG. FIG. 10 is a drawing representation of a Gram matrix indicating similarities between attractors. It is a figure which shows the flow of estimation by a support vector machine. 4 is a flowchart showing an example of processing by a state determination system; . It is a figure which shows the hardware constitutions of the state determination system which concerns on embodiment of this invention.

Hereinafter, an embodiment of a state determination system according to the present invention will be described in detail with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and overlapping descriptions are omitted.

FIG. 1 shows a server 20 which is a state determination system according to this embodiment. The server 20 is a system that determines the state of the structure 2 . The structure 2 to be determined is, for example, a bridge as shown in FIG. However, the structure 2 to be determined is not limited to a bridge, and may be any structure such as a steel tower, utility pole, or building. The state of (a portion of) the structure to be determined is, for example, whether or not there is an abnormality such as damage in the structure. The result of the determination by the server 20 can be used, for example, to determine whether to reinforce or repair the structure.

The server 20 is implemented by, for example, a server device. Also, the server 20 may be realized by a plurality of server devices, that is, computer systems. The server 20 has a communication function and can transmit and receive data to and from other devices.

The server 20 determines the state of the structure using the moving image captured by the imaging device 10 . The imaging device 10 captures an image of the target structure 2 and acquires a moving image of the structure 2 as data. An example of the imaging device 10 may be a known camera (video camera) capable of capturing a moving image with a resolution that can be used to determine the state of the structure 2 . The imaging device 10 is fixedly installed in advance at a position where the structure 2 can be imaged. The imaging device 10 and the server 20 can transmit and receive data to and from each other. The imaging device 10 as an example captures an image of the structure 2 at a preset frame rate (fps) and transmits data of the captured moving image to the server 20 . The data acquired by the imaging device 10 may be loaded into the server 20 via a removable recording medium or the like.

The server 20 functionally includes an acquisition unit 21 , a measurement unit 22 , a reconstruction unit 23 , and an analysis unit 25 . The acquisition unit 21 is a functional unit that acquires a moving image of the structure 2 . The acquisition unit 21 acquires a moving image of the whole or part of the structure 2 . In one example, the moving image acquired by the acquiring unit 21 is a moving image having a rectangular image area defined by image width and image height. The image areas in each frame forming the moving image match each other. In the present embodiment, the acquisition unit 21 acquires data of moving images captured by the imaging device 10 from the imaging device 10 . The acquiring unit 21 outputs the acquired moving image data to the measuring unit 22 .

The measurement unit 22 is a functional unit that measures (calculates) displacement amounts for each of a plurality of regions of the structure 2 from the moving image data acquired by the acquisition unit 21, and acquires displacement data indicating the displacement amounts. be. An example of the measurement unit 22 detects the displacement in sub-pixel units from the acquired moving image by conventional techniques such as POC (Phase Only Correlation), optical flow method, sampling moire method, etc., and measures a plurality of structures Vibration (displacement) is detected at the point. For example, the measurement unit 22 extracts a vibration measurement target area from the acquired moving image. The region is a region of interest (ROI) in the structure. Such an ROI may be automatically extracted by the measurement unit 22 or preset by the user. In the illustrated example, five regions 2a, 2b, 2c, 2d, and 2e including part of the structure 2 are set as ROIs in the image of the structure (bridge) 2 captured.

The measurement unit 22 calculates positional deviations of the common areas 2a, 2b, 2c, 2d, and 2e between the preceding and succeeding frames with sub-pixel accuracy. For example, since deterioration of a bridge progresses according to vibration in the longitudinal direction (vertical direction), the measurement unit 22 calculates the displacement in the vertical direction of the moving image when judging the state of the bridge. The measurement unit 22 calculates the positional deviation between the front and rear frames for each of the regions 2a, 2b, 2c, 2d, and 2e based on the moving image as the vibration of the structure, and uses the calculated vibration data as the displacement data. get. FIG. 2 is a diagram schematically showing an example of displacement data acquired from a moving image. In FIG. 2, five types of displacement data are indicated by different types of lines. An example of displacement data is vibration data with time on the horizontal axis and amplitude on the vertical axis. For example, vibration data may be obtained as a car passes over a bridge. Vibration data may reflect the influence of noise caused by the imaging environment. The measurement unit 22 outputs vibration data for each region obtained from the moving image to the reconstruction unit 23 as displacement data.

The reconstruction unit 23 is a functional unit that reconstructs the attractor based on the plurality of displacement data acquired by the measurement unit 22 . In this embodiment, the reconstruction unit 23 reconstructs a plurality of attractors based on different combinations of a plurality of displacement data. The number of displacement data for reconstructing one attractor is, for example, the minimum integer number that is at least twice the fractal dimension of the displacement data.

The reconstruction unit 23 as an example derives the fractal dimension N of each of the plurality of input displacement data (vibration observation data). The fractal dimension N may be derived based on conventional techniques such as Higuchi's method, box-counting method. The reconstruction unit 23 reconstructs the attractor using displacement data whose number is at least twice the maximum value of the derived fractal dimension N. In this case, if the number of displacement data acquired by the measurement unit 22 is m, and the smallest integer that is two or more times the fractal dimension N is n, the reconstruction unit 23 reconstructs _m C _n attractors. Can be configured.

In this embodiment, five pieces of displacement data are obtained by measuring displacements (vibrations) in the five regions 2a, 2b, 2c, 2d, and 2e. Further, in the present embodiment, the value of the fractal dimension N calculated from the displacement data is about 1.6, and twice the maximum value of the fractal dimension N is less than 4. Therefore, using four displacement data, the attractor can be reconstructed. In this case, since four out of five displacement data are used to reconstruct one attractor, the number of attractors that can be reconstructed is the number of combinations for selecting four types out of five types. be. That is, in this case, ₅ C ₄ (five) attractors can be reconstructed.

FIG. 3 is a diagram showing an example of a combination of displacement data for reconstructing an attractor. In FIG. 3, five indices identify the five attractors for convenience. As shown in FIG. 3, when the displacement data corresponding to the five regions 2a, 2b, 2c, 2d, and 2e are a, b, c, d, and e, respectively, the indices 0, 1, 2, 3, and 4 are Combinations of the displacement data Xl, Xm, Xn, and Xo for reconstructing the corresponding five types of attractors are (a, b, c, d), (a, b, c, e), (a, b, d , e), (a, c, d, e), (b, c, d, e). In the present embodiment, the reconstruction unit 23 reconstructs attractors using a conventional embedding method. That is, the reconstruction unit 23 plots the time-series data of the displacement data Xl, Xm, Xn, and Xo in a multidimensional coordinate space (four-dimensional coordinate space in the embodiment) corresponding to the number of displacement data for reconstructing the attractor. do. In this embodiment, since the attractors are reconstructed in the four-dimensional coordinate space, illustration of the attractors is omitted.

The analysis unit 25 is a functional unit that determines the state of the structure based on the attractors reconstructed by the reconstruction unit 23 . The analysis unit 25 as an example identifies attractors with different characteristics from among the plurality of reconstructed attractors, and determines the state of the structure based on the identified attractors. For example, the analysis unit 25 may identify an attractor with different characteristics from among the plurality of attractors based on the degree of similarity between the reconstructed plurality of attractors. Then, the analysis unit 25 may identify the region related to the abnormal location of the structure based on the displacement data forming the attractors with different characteristics.

The analysis unit 25 as an example first obtains a persistent diagram (PD) expressing persistent homology for each attractor. The persistent diagram shows the topological features of the attractor obtained by filtering the points plotted as the attractor. FIG. 4 is a schematic diagram for explaining filtration. In FIG. 4, for easy understanding, points plotted as attractors are shown two-dimensionally. FIG. 5 is a diagram showing an example of a persistent diagram.

As shown in FIG. 4, the analysis unit 25 increases the size of each point plotted as an attractor, that is, while increasing the radius ε of the circle centered at each point, the topological feature amount of the attractor. Analyze the occurrence and disappearance of The feature amount in the present embodiment includes a connected component whose dimension of homology is 0th order and a hole whose dimension of homology is 1st order. Note that the feature quantity may include a cavity whose homology dimension is second order. A primary hole is an annulus shape generated by connecting points as the radius ε increases. In the primary hole, the size of the radius ε when the ring shape is formed is defined as Birth, and the size of the radius ε when the inner side of the ring shape is filled is defined as Death. FIG. 4 shows a state in which each point has increased to the size indicated by the dashed line. This example shows a primary hole HA that maintains its annular shape and a hole HB that has already been filled and disappeared. A connected component of order 0 is a non-circular shape and is composed of a single point or a plurality of connected points. The 0th order connected component occurs with a radius ε of zero. Also, in the 0th-order connected component, one connected component disappears when it comes into contact with adjacent points as the radius ε increases.

The analysis unit 25 derives the occurrence and disappearance of the topological features of the attractor as a persistent diagram. In the persistent diagram, the feature quantity is shown with the horizontal axis representing the occurrence time of the feature quantity when the rate of increase of the radius ε is constant, and the vertical axis representing the disappearance time of the feature quantity. In the example of FIG. 5, a persistent diagram showing connected components (dark dots in the figure) and a persistent diagram showing holes (light dots in the figure) are shown. The dashed line shown in the upper end of the figure indicates that the extinction time is infinite. The connected components gradually disappear as the radius ε increases and finally converge to one. Therefore, one connected component is plotted at a position where the disappearance time is infinite. A first-order hole appears with increasing radius ε and then disappears. For example, the longer the shape of the hole is maintained, the more the hole can be said to have a shape that exhibits the essential features of the attractor. A feature amount with a long time from appearance to disappearance is plotted at a position away from the dashed line with a slope of 1 shown in the drawing. In this embodiment, a persistent diagram is derived for each of the five attractors reconstructed by the reconstruction unit 23 .

The analysis unit 25 obtains the degree of similarity between attractors based on the plurality of derived persistent diagrams. The analysis unit 25 as an example calculates the similarity between attractors according to the dimension of homology as a Gram matrix. As an example, the analysis unit 25 obtains the degree of similarity between persistent diagrams using, for example, PWGK (Persistence Weighted Gaussian Kernel). FIG. 6 is a graphical representation of a Gram matrix indicating similarities between attractors. In FIG. 6, the rows and columns indicate the index of the combination, and the degree of similarity between the corresponding attractors is indicated by shading. In the illustrated example, the greater the degree of similarity between corresponding attractors, the darker the color. In FIG. 6, the entire structure has a degree of deterioration that cannot be said to be abnormal (normal aging deterioration), noise is included in the detected vibration (displacement data), and region 2c (that is, c Figure 2 shows the Gram matrix when only the displacement data) has anomalies other than normal aging. Further, (a) of FIG. 6 shows the similarity between attractors for 0th-order connected components, and (b) of FIG. 6 shows the similarity between attractors for 1st-order holes. . Note that FIG. 6 is based on simulation results.

The analysis unit 25 identifies attractors with different features from among a plurality of attractors based on the Gram matrix indicating the degree of similarity between attractors. The analysis unit 25 as an example identifies attractors with different features using a so-called machine learning technique. The analysis unit 25 uses, for example, a support vector machine (SVM) technique to estimate indices corresponding to attractors having different features from the input gram matrix. As an example, by inputting a Gram matrix to be subjected to anomaly detection to a support vector machine given a Gram matrix without anomalies, the presence or absence of anomalies can be known.

FIG. 7 is a diagram showing the flow of estimation by the support vector machine. In this embodiment, the analysis unit 25 provides the support vector machine 25a with a Gram matrix indicating the similarity between attractors for the 0th-order connected components shown in FIG. A Gram matrix is input that indicates gender. As a result, the analysis unit 25 acquires the result of estimating the presence or absence of abnormality for each index corresponding to the attractor. In FIG. 7, "1" indicates that there is no abnormality, and "-1" indicates that there is an abnormality. That is, in FIG. 7, it is estimated that the attractor corresponding to index 2 is abnormal. In other words, it is estimated that the features of the attractor corresponding to index 2 are different from the other attractors. Note that, for example, when the features of the attractor are more likely to be reflected in the persistent diagram for the first-order hole than in the persistent diagram for the zero-order connected component, the Gram matrix input to the support vector machine is It may be just a Gram matrix that indicates the similarity between attractors for holes of first order.

The analysis unit 25 identifies an area related to the abnormal location of the structure based on the displacement data forming the attractors with different characteristics (the attractor corresponding to index 2 in the illustrated example). In the above embodiment, since displacement data c is included in all attractors other than index 2, it is estimated that region 2c associated with displacement data c is abnormal. Thus, when the number of ROIs is small, the majority of attractors include displacement data of abnormal regions. Determine that there is.

In the above-described embodiment, an example in which five ROIs are set is shown for ease of understanding, but more ROIs may be set in order to improve the accuracy of identifying an abnormal location. When the number of ROIs is large, the displacement data for reconstructing the attractor is randomly selected without duplication from the displacement data corresponding to all the ROIs. Therefore, the number of attractors containing displacement data obtained from regions containing structural anomalies is reduced. In this case, the analysis unit 25 identifies displacement data commonly used by attractors corresponding to a plurality of indices estimated to have different features, and determines that there is an abnormality in the region corresponding to the displacement data.

For example, when there are displacement data a to j obtained from 10 ROIs, assume that displacement data c is data based on an abnormality. In this case, the combinations of displacement data used to reconstruct the five attractors are (a, f, b, i), (b, g, c, j), (c, h, d, f), ( d, i, e, g) and (e, j, a, h), the reconstructed 2 The features of one attractor are determined to be different from other attractors. In this case, it is determined that there is an abnormality in the area related to the displacement data c common to the two attractors.

It should be noted that when the number of ROIs increases, it is conceivable that the number of combinations of displacement data for reconstructing attractors will become enormous. Therefore, for example, if the user can set a region (ROI) to verify the presence or absence of an abnormality and a plurality of regions that are considered to have no abnormality, at least one attractor including the ROI to be verified is reconfigured, Other attractors may be reconstructed from a plurality of regions that appear to be free of anomalies. In this case, the number of attractors to be reconstructed can be reduced, and the amount of calculation in the server 20 can be reduced.

Next, an example of processing executed by the server 20 will be described with reference to FIG. First, the imaging device 10 captures an image of the structure 2 whose state is to be determined to obtain a moving image. In one example, the entire structure 2 is imaged so that all locations for determining the state are captured. The acquisition unit 21 of the server 20 acquires data of the captured moving image from the imaging device 10 (S21). Subsequently, the measurement unit 22 sets a plurality of regions (ROI) in the moving image of the structure 2, and acquires vibration data (displacement data) of the structure 2 in each set region (S22 ).

Subsequently, the reconstruction unit 23 calculates the fractal dimension of each displacement data (S23). Then, the reconstruction unit 23 reconstructs the attractor based on the plurality of displacement data (S24). The number of displacement data used for attractor reconstruction is the smallest integer value greater than or equal to twice the value of the largest fractal dimension. When reconstructing attractors, all displacement data are used to reconstruct at least one attractor. That is, there is no displacement data that is not used to reconstruct the attractor.

Subsequently, the analyzing unit 25 obtains a persistent diagram for each of the reconstructed attractors (S25), and obtains a Gram matrix indicating the degree of similarity between the attractors based on the obtained plurality of persistent diagrams (S26 ). Then, the analysis unit 25 identifies attractors with different characteristics based on a harm learning method such as a support vector machine using a Gram matrix, and identifies an abnormal region based on the identified attractors (S26). .

As described above, in the state determination system, an attractor is reconstructed using a plurality of pieces of displacement data acquired from moving images of the structure 2 . Based on the attractors, the state of the structure 2 can be determined, since the reconstructed attractors can reflect features of the dynamic system behind the displacement data. Also, since the attractor is reconstructed using a plurality of displacement data, even if a part of the displacement data contains a lot of noise, the influence of the noise on the attractor can be reduced. Therefore, the state of the structure 2 can be appropriately determined.

Further, the reconstruction unit 23 reconstructs a plurality of attractors based on mutually different combinations of the plurality of displacement data. The analysis unit 25 identifies attractors with different characteristics from among the plurality of attractors, and determines the state of the structure 2 based on the identified attractors. In this configuration, each attractor is reconfigured with a different combination of displacement data. Therefore, by specifying attractors with different characteristics, it is possible to easily specify the displacement data measured from the abnormal ROI.

Also, the number of displacement data for reconstructing one attractor is a minimum integer that is at least twice the fractal dimension of the displacement data. In this configuration, since the attractor is reconstructed using displacement data that is twice or more the fractal dimension, the attractor can be reconstructed with an accuracy that can be used for analysis. In addition, by minimizing the number of displacement data required for one attractor, it is possible to reduce the computational load when reconstructing the attractor.

Further, the analysis unit 25 obtains a persistent diagram corresponding to the attractor, and calculates the similarity between the attractors according to the dimension of homology. In this embodiment, since the displacement data is calculated based on the moving image of the structure 2, noise is likely to be included in the displacement data. In the above configuration, by obtaining the persistent diagram, the essential features of the attractor appear by filtering, thereby reducing the influence of noise components contained in the displacement data. As a result, analysis can be performed with higher accuracy.

In the above embodiment, the displacement data of the ROI is obtained based on the moving image of the structure 2. For example, the displacement data can be obtained by installing a plurality of vibration sensors or the like on the structure 2. is also possible. However, in order to analyze an abnormal portion of a structure with high accuracy, it is necessary to install a large number of vibration sensors, which is not realistic. In this embodiment, highly accurate analysis can be easily realized by using displacement data acquired based on moving images.

It should be noted that the block diagrams used in the description of the above embodiments show blocks in units of functions. These functional blocks (components) are realized by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be implemented using one device that is physically or logically coupled, or directly or indirectly using two or more devices that are physically or logically separated (e.g. , wired, wireless, etc.) and may be implemented using these multiple devices. A functional block may be implemented by combining software in the one device or the plurality of devices.

Functions include judging, determining, determining, calculating, calculating, processing, deriving, investigating, searching, checking, receiving, transmitting, outputting, accessing, resolving, selecting, choosing, establishing, comparing, assuming, expecting, assuming, Broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, assigning, etc. can't For example, a functional block (component) that makes transmission work is called a transmitting unit or a transmitter. In either case, as described above, the implementation method is not particularly limited.

For example, the server 20 in one embodiment of the present disclosure may function as a computer that performs information processing of the present disclosure. FIG. 9 is a diagram illustrating an example of a hardware configuration of server 20 according to an embodiment of the present disclosure. The server 20 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

Note that in the following description, the term "apparatus" can be read as a circuit, device, unit, or the like. The hardware configuration of the server 20 may be configured to include one or more of each device shown in the figure, or may be configured without some of the devices.

Each function in the server 20 is performed by causing the processor 1001 to perform calculations, controlling communication by the communication device 1004, controlling communication by the communication device 1004, and controlling the communication by the memory 1002 and It is realized by controlling at least one of data reading and writing in the storage 1003 .

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like. For example, the server 20 described above may be implemented by the processor 1001 .

The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 to the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least part of the operations described in the above embodiments is used. For example, server 20 may be implemented by a control program stored in memory 1002 and running on processor 1001 . Although it has been explained that the above-described various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. FIG. Processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via an electric communication line.

The memory 1002 is a computer-readable recording medium, and is composed of at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), and RAM (Random Access Memory). may be The memory 1002 may also be called a register, cache, main memory (main storage device), or the like. The memory 1002 can store executable programs (program code), software modules, etc. for performing information processing according to an embodiment of the present disclosure.

The storage 1003 is a computer-readable recording medium, for example, an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disc, a magneto-optical disc (for example, a compact disc, a digital versatile disc, a Blu-ray disk), smart card, flash memory (eg, card, stick, key drive), floppy disk, magnetic strip, and/or the like. Storage 1003 may also be called an auxiliary storage device. The storage medium provided by the server 20 may be, for example, a database including at least one of the memory 1002 and the storage 1003, a server, or other suitable medium.

The communication device 1004 is hardware (transmitting/receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also called a network device, a network controller, a network card, a communication module, or the like.

The input device 1005 is an input device (for example, keyboard, mouse, microphone, switch, button, sensor, etc.) that receives input from the outside. The output device 1006 is an output device (eg, display, speaker, LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated (for example, a touch panel).

Devices such as the processor 1001 and the memory 1002 are connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between devices.

The server 20 includes hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). A part or all of each functional block may be implemented by the hardware. For example, processor 1001 may be implemented using at least one of these pieces of hardware.

The processing procedures, sequences, flowcharts, etc. of each aspect/embodiment described in this disclosure may be rearranged as long as there is no contradiction. For example, the methods described in this disclosure present elements of the various steps using a sample order, and are not limited to the specific order presented.

Input/output information and the like may be stored in a specific location (for example, memory), or may be managed using a management table. Input/output information and the like can be overwritten, updated, or appended. The output information and the like may be deleted. The entered information and the like may be transmitted to another device.

The determination may be made by a value represented by one bit (0 or 1), by a true/false value (Boolean: true or false), or by numerical comparison (for example, a predetermined value).

Each aspect/embodiment described in the present disclosure may be used alone, may be used in combination, or may be used by switching according to execution. In addition, the notification of predetermined information (for example, notification of “being X”) is not limited to being performed explicitly, but may be performed implicitly (for example, not notifying the predetermined information). good too.

Although the present disclosure has been described in detail above, it should be apparent to those skilled in the art that the present disclosure is not limited to the embodiments described in this disclosure. The present disclosure can be practiced with modifications and variations without departing from the spirit and scope of the present disclosure as defined by the claims. Accordingly, the description of the present disclosure is for illustrative purposes and is not meant to be limiting in any way.

Software, whether referred to as software, firmware, middleware, microcode, hardware description language or otherwise, includes instructions, instruction sets, code, code segments, program code, programs, subprograms, and software modules. , applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.

Software, instructions, information, etc. may also be sent and received over a transmission medium. For example, the software uses wired technology (coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), etc.) and/or wireless technology (infrared, microwave, etc.) to create websites, Wired and/or wireless technologies are included within the definition of transmission medium when sent from a server or other remote source.

As used in this disclosure, the terms "system" and "network" are used interchangeably.

In addition, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values from a predetermined value, or may be expressed using other corresponding information. may be represented.

Servers and/or clients may also be referred to as transmitters, receivers, communication devices, and/or the like. At least one of the server and the client may be a device mounted on a mobile object, the mobile object itself, or the like. The mobile object may be a vehicle (e.g., car, airplane, etc.), an unmanned mobile object (e.g., drone, self-driving car, etc.), or a robot (manned or unmanned ). At least one of the server and the client includes devices that do not necessarily move during communication operations. For example, at least one of the server and client may be an IoT (Internet of Things) device such as a sensor.

Also, the server in the present disclosure may be read as a client terminal. For example, a configuration in which communication between a server and a client terminal is replaced with communication between a plurality of user terminals (for example, D2D (Device-to-Device), V2X (Vehicle-to-Everything), etc.) Each aspect/embodiment of the present disclosure may be applied to. In this case, the client terminal may have the functions of the server described above.

Similarly, the client terminal in the present disclosure may be read as a server. In this case, the server may have the functions that the client terminal described above has.

As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Judgement", "determining" are, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (eg, lookup in a table, database, or other data structure), ascertaining as "judged" or "determined", and the like. Also, "judgment" and "determination" are used for receiving (e.g., receiving information), transmitting (e.g., transmitting information), input, output, access (accessing) (for example, accessing data in memory) may include deeming that a "judgment" or "decision" has been made. In addition, "judgment" and "decision" are considered to be "judgment" and "decision" by resolving, selecting, choosing, establishing, comparing, etc. can contain. In other words, "judgment" and "decision" may include considering that some action is "judgment" and "decision". Also, "judgment (decision)" may be read as "assuming", "expecting", "considering", or the like.

The terms "connected", "coupled", or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, It can include the presence of one or more intermediate elements between two elements being "connected" or "coupled." Couplings or connections between elements may be physical, logical, or a combination thereof. For example, "connection" may be read as "access". As used in this disclosure, two elements are defined using at least one of one or more wires, cables, and printed electrical connections and, as some non-limiting and non-exhaustive examples, in the radio frequency domain. , electromagnetic energy having wavelengths in the microwave and optical (both visible and invisible) regions, and the like.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

Any reference to elements using the "first," "second," etc. designations used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, reference to a first and second element does not imply that only two elements can be employed or that the first element must precede the second element in any way.

Where "include," "including," and variations thereof are used in this disclosure, these terms are inclusive, as is the term "comprising." is intended. Furthermore, the term "or" as used in this disclosure is not intended to be an exclusive OR.

In this disclosure, where articles have been added by translation, such as a, an, and the in English, the disclosure may include the plural nouns following these articles.

In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean that "A and B are different from C". Terms such as "separate," "coupled," etc. may also be interpreted in the same manner as "different."

2... structure, 10... imaging device, 20... server (state determination system), 21... acquisition unit, 22... measurement unit, 23... reconstruction unit, 25... analysis unit.

Claims (3)

an acquisition unit that acquires a moving image of a structure;
a measurement unit that acquires a plurality of displacement data respectively indicating displacement amounts for a plurality of regions of a structure from the moving image acquired by the acquisition unit;
a reconstruction unit that reconstructs an attractor based on the plurality of displacement data acquired by the measurement unit;
an analysis unit that determines the state of the structure based on the attractor reconstructed by the reconstruction unit ;
The reconstruction unit reconstructs the plurality of attractors based on mutually different combinations of the plurality of displacement data,
The state determination system, wherein the analysis unit identifies an attractor having different characteristics from among the plurality of attractors, and identifies an area related to an abnormal location of the structure based on the identified attractor. 2. The state determination system according to claim 1 , wherein the number of the plurality of displacement data for reconstructing one of the attractors is a minimum integer number equal to or greater than two times the fractal dimension of the displacement data. The analysis unit obtains a persistent diagram corresponding to the attractor, calculates a degree of similarity between the attractors according to the dimension of homology, and selects attractors with different features from among the plurality of attractors based on the degree of similarity. 3. The state determination system according to claim 1 or 2 , which specifies the .

Images