JP6783894B2 - Meter reader, meter reading method and computer program - Google Patents

Description

The present invention relates to a meter reading device for reading a pointer of an analog meter, a meter reading method, and a computer program.

As an instrument used in an IoT system, a type of digital sensor that outputs a measurement result by a digital signal such as a digital thermometer, a hygrometer, or a vibrometer is often used. This is because it is easy to have the communication device transmit a numerical value indicating the measurement result. On the other hand, there are mechanical instruments in which it is not easy to convert the information obtained by measurement into a digital signal. For example, a pressure gauge using a bourdon, a diaphragm, a bellows, a water level gauge using a buoy, and the like. These mechanical instruments are of the type that visually check the dial and do not output analog signals. In order to use the information measured by these instruments in the IoT system, a method has been proposed in which the pointer on the scale board visually confirmed by the person in charge is imaged with a camera and the measured value is read.

In Patent Document 1, for a single-needle rotation type analog meter, a reference image obtained by imaging a scale board in a state where the pointer points to a known scale is used, and the measured value is read by analyzing the brightness value in the range in which the pointer moves. A method has been proposed. In Patent Document 1, it is estimated that the pointer exists in the portion of the arcuate scale plate where the luminance value is the lowest and the change in the luminance value in the radial direction is small, and the measured value is read from the portion having a high correlation with the reference image. ..

Patent Document 2 discloses a technique for removing a background, removing noise, and the like in order to specify a portion of a brightness value set with respect to a pointer by image recognition.

Japanese Unexamined Patent Publication No. 2004-133560 JP-A-2002-188939

In the conventional method such as Patent Document 1 or Patent Document 2, on the premise that the brightness value of the region in the captured image in which the pointer is captured is lower than that of the other regions, the portion where the brightness value lower than the predetermined value appears is imaged. Extracted from the image. In Patent Document 1, a method is adopted in which a captured image in which a pointer is copied in advance is used, frequency conversion is performed together with the captured image of the dial, and a portion having a high correlation is specified. It is difficult to identify the high frequency. The place where the instrument is installed is affected by the windows of the factory, light from other equipment, etc., and the dial may show clear shadows different from letters, dirt, etc. If the pointer continues to swing, the image of the pointer reflected in the captured image is unclear and may be confused with a clear shadow or the like and erroneously detected.

The present invention has been made in view of such circumstances, and an object of the present invention is to provide a meter reading device, a meter reading method, and a computer program that accurately read the pointer of an analog meter by a simple method.

The meter reading device according to one aspect of the present disclosure includes a reference position of the scale plate in an image captured by imaging the scale plate of the meter, positions of a plurality of main scales of the scale plate associated with each numerical value, and the meter. A storage unit that stores information indicating the shape and size of the pointer, a reference position of the scale plate that stores a newly captured image of the scale plate of the meter, and the positions of the plurality of main scales. Based on the above, a first creating unit that scans in a direction orthogonal to the scale in the image to create a scanned image, and a second creating unit that creates an image of the pointer based on the information indicating the shape of the pointer are created. A third creation unit that scans the pointer image in a direction orthogonal to the scale in the image based on the stored reference position and size of the scale, and creates a scanning image of the pointer, and the created scale. A calculation unit that calculates the distribution of likelihood indicating the high possibility that the pointer is reflected in the direction orthogonal to the scale in the scan image of the scale board by comparing the scanned image and the scanned image of the pointer, and the calculation unit. It is provided with a specific unit that specifies a numerical value indicated by the pointer of the meter based on the distribution in the direction orthogonal to the scale of the likelihood calculated by.

The meter reading method according to one aspect of the present disclosure includes a reference position of the scale plate in an image captured by imaging the scale plate of the meter, positions of a plurality of main scales of the scale plate associated with each numerical value, and the meter. Information indicating the shape and size of the pointer is stored in a storage medium, and the captured image newly captured by the scale plate of the meter is stored as a reference position of the stored scale plate and the positions of the plurality of main scales. To create a scanned image by scanning in a direction orthogonal to the scale in the image, create a pointer image based on the information indicating the shape of the pointer of the meter, and store the created pointer image. A scale scan image is created by scanning in a direction orthogonal to the scale in the image based on the reference position and size of a scale, and the scale board is compared with the created scale scan image and the pointer scan image. The distribution of the likelihood indicating the high possibility that the pointer is reflected in the direction orthogonal to the scale in the scanned image of the above is calculated, and the distribution of the meter in the direction orthogonal to the calculated scale of the likelihood is used. Includes processing to identify the numerical values indicated by the guidelines.

In the computer program according to one aspect of the present disclosure, a computer provided with a storage unit has a plurality of main scales of the scale plate in which a reference position of the scale plate in an image captured by imaging the scale plate of a meter and a numerical value are associated with each other. The position of the meter and information indicating the shape and size of the pointer of the meter are stored in the storage unit, and an image captured by newly capturing the scale plate of the meter is stored in the stored reference position of the scale plate. A scanning image is created by scanning in a direction orthogonal to the scale in the image based on the positions of the plurality of main scales, and an image of the pointer is created based on the information indicating the shape of the pointer of the meter. The image of is scanned in the direction orthogonal to the scale in the image based on the stored reference position and size of the scale to create a scanning image of the pointer, and the scanned image of the created scale and scanning of the pointer are created. By comparing the images, the distribution of the likelihood indicating the high possibility that the pointer is reflected in the direction orthogonal to the scale in the scanned image of the scale board is calculated, and the distribution of the likelihood is calculated with respect to the direction orthogonal to the calculated scale of the likelihood. The process of specifying the numerical value indicated by the pointer of the meter based on the distribution is executed.

In one aspect of the present disclosure, an image captured by an image of a scale is scanned in a direction orthogonal to the scale based on a stored reference position of the scale, positions of a plurality of main scales, and a shape and size of a pointer. A scanned image is created. A likelihood distribution indicating the high possibility that the pointer is shown in the scanned image is obtained by using the scanned image and the image obtained by performing the same operation on the pointer image. The position of the pointer, that is, the numerical value indicated by the pointer on the scale is specified based on the likelihood distribution. Findings that can be identified with higher accuracy than when comparing images containing noise by recreating the pointer image from the stored shape and size instead of the captured pointer image. was gotten.

In one aspect of the present disclosure, the meter of interest can be applied not only to a meter having a pointer that rotates about a circular scale as a fulcrum, but also to a meter in which the pointer moves horizontally or vertically in a straight line. It is also possible to apply.

In one aspect of the present disclosure, when there are a plurality of likelihood peaks, the numerical value indicated by the pointer is specified based on the position in the direction orthogonal to the scale corresponding to the steeper peak. This increases accuracy.

In one aspect of the present disclosure, a likelihood is calculated that indicates whether or not there is a pixel value variation similar to the pixel value variation in the pointer image. As a result, the accuracy of specifying the numerical value indicated by the pointer is improved even for images captured under various conditions.

In one aspect of the present disclosure, since the numerical value indicated by the pointer is specified by linearly interpolating for each section of the position of the plurality of main scales, the accuracy does not deteriorate even if the captured image contains distortion.

According to the meter reading device, the meter reading method, and the computer program of the present disclosure, it is possible to automatically read the pointer of the analog meter with high accuracy by a simple method. It is possible to omit the work of visually confirming the abnormality judgment of the analog meter. It is also possible to incorporate an analog meter into an IoT system.

It is explanatory drawing which shows the outline of the meter meter reading system in this embodiment. It is a schematic diagram of a camera device. It is a block diagram which shows the structure of the meter meter reading system. It is a figure which shows the content example of the information to be set. It is a figure which shows the outline of the correction of the distortion in a captured image. It is a flowchart which shows an example of the reading process procedure by a server apparatus. It is a schematic diagram which shows the content example of the captured image. It is a figure which shows the outline of the scanning method with respect to the captured image. It is a schematic diagram which shows an example of the scan image of the scale board of a meter. It is a schematic diagram which shows an example of the scanning image of a pointer. It is a figure which shows the likelihood distribution. It is a figure which shows the outline of another example of the scanning method with respect to the captured image. It is a flowchart which shows an example of the procedure of abnormality detection processing by the control part of a server device. It is a flowchart which shows an example of the reading processing procedure by the server apparatus of Embodiment 2. It is a figure which shows the outline of the scanning method with respect to the captured image in Embodiment 2. It is a schematic diagram which shows an example of the scan image of the scale board of a meter. It is a schematic diagram which shows an example of the scanning image of a pointer. It is a figure which shows the fluctuation distribution of the pixel value of the scan image of a pointer. It is a figure which shows the fluctuation distribution of the pixel value in the scan image of a scale board. It is a figure which shows the calculation method of the likelihood in Embodiment 2. FIG. It is a figure which shows the likelihood distribution in Embodiment 2.

Hereinafter, the meter reading method and the meter reading device of the present disclosure will be specifically described with reference to the drawings showing the embodiments thereof.

(Embodiment 1)
FIG. 1 is an explanatory diagram showing an outline of the meter meter reading system 100 according to the first embodiment. The meter reading system 100 includes a plurality of camera devices 1, a gateway device 2, a server device 3, and a client device 4.

The camera device 1 is provided for a plurality of meters M provided in the equipment in the factory. The gateway device 2 is installed in the factory and can communicate with a plurality of camera devices 1. The communication connection between the camera device 1 and the gateway device 2 is realized by, for example, short-range wireless communication. A wired communication connection may be possible between the camera device 1 and the gateway device 2.

The camera device 1 transmits an captured image of the scale board of the meter M to the gateway device 2 by communication. The gateway device 2 transmits captured images transmitted from each of the plurality of camera devices 1 to the server device 3 via the network N.

The server device 3 executes a process described later on the captured image transmitted from the gateway device 2, and identifies the state indicated by the position of the pointer of one or a plurality of meters M reflected in the captured image. In addition to this, the server device 3 exerts a function of receiving setting information for specifying the state on a Web basis, and issues an alarm to the manager of the factory where the meter M is provided based on the specified state. Demonstrate function. In the present embodiment, the server device 3 will be described as one server computer for ease of explanation, but it is realized by a virtual server that logically operates by a plurality of instances on one server computer. .. Further, the functions or processes may be distributed or superimposed on a plurality of server computers.

The network N includes a public network N1 and a carrier network N2. The public network N1 is the so-called Internet. The carrier network N2 is a network provided by a communication carrier that realizes wireless communication based on a standard such as a next-generation or next-generation high-speed mobile communication standard. The public network N1 includes an access point AP. The carrier network N2 includes a base station BS. The gateway device 2 can send and receive information to and from the server device 3 connected to the public network N1 by the access point AP or the base station BS.

Among the various meters installed in the equipment in the factory, the meter with the digital output function outputs the measurement result to the control device such as the center console in the factory, and the control device outputs the measurement target state. It is easy to judge the presence or absence of abnormalities in. On the other hand, for the meter M that does not have a digital output function, the factory management staff can visually check for any abnormalities, or the meter dial can be used with a camera in places where the staff cannot enter. The person in charge has taken an image and confirmed this remotely to determine the presence or absence of an abnormality. For example, with regard to the meter M, which is a diaphragm type pressure gauge, the person in charge visually checks whether the pressure is abnormally high several times a day to see if there is an abnormality in the equipment in the factory. I have judged.

In the present embodiment, the camera device 1 is attached to the meter M that does not have the digital output function, and the meter M is functioned as a meter reading device of the server device 3 based on the captured image captured by the camera device 1. The meter reading system 100 for specifying the state measured by is realized. The server device 3 can identify the state in which the pointer of the meter M is pointed with high accuracy by the processing contents shown below. As a result, it is possible to omit the visual work of the person in charge several times a day by a simple procedure of installing the camera device 1 on the existing analog meter M and installing the gateway device 2 in the factory. ..

FIG. 2 is a schematic view of the camera device 1. FIG. 2A is a schematic perspective view, and FIG. 2B is a schematic cross-sectional view. The camera device 1 is provided with an imaging unit 11 and a light source 12 on one surface of a strip-shaped extending substrate 10f extending from the substrate 10, a communication unit 13 and a control unit 14 are mounted on the substrate 10, and a battery box 16 is connected. It is composed of. The light source 12 is preferably removable because it may not be necessary depending on the installation location. The camera device 1 is attached so that the surface on which the image pickup unit 11 of the extension board 10f is mounted faces the viewing window of the scale plate of the meter M. The camera device 1 is positioned with respect to the meter M by the adapter 17. The adapter 17 has a circular transparent resin cover 15 having a larger outer diameter of the meter M and a main body of the adapter 17 fixed to one end of the cover 15. By fixing the board 10 together with the battery box 16 to the main body of the adapter 17, covering the cover 15 with the window of the meter M, and fixing with mounting screws or mounting brackets (not shown), the camera device 1 is attached to the meter M in FIG. It is positioned as shown in. The cover 15 is made of transparent resin, and the extension substrate 10f on which the image pickup unit 11 facing the scale plate of the meter M is mounted is strip-shaped and has a width corresponding to the size of the image pickup unit 11. Therefore, the meter M with the camera device 1 attached can also be visually recognized. Needless to say, the configurations of the camera device 1 and the adapter 17 are not limited to this.

The image pickup unit 11 includes an image pickup element for visible light or infrared light, a memory, and the like, and executes imaging in response to a control signal of the control unit 14. The light source 12 includes, for example, an LED (Light Emitting Diode), and emits white light or infrared light at the time of imaging according to the control signal of the control unit 14. An illuminance sensor may be used for the light source 12, and the light source 12 may be turned on according to the ambient light, such as not being turned on when it is sufficiently bright by the ambient light. The communication unit 13 realizes a communication connection with the gateway device 2. The communication unit 13 includes, for example, a short-range wireless communication module such as Bluetooth (registered trademark), particularly 2.4 GHz BLE (Bluetooth Low Energy).

The control unit 14 includes a processor and a memory, and controls imaging execution by the imaging unit 11, lighting and extinguishing of the light source 12, and transmission / reception by the communication unit 13 based on the program and setting information stored in the memory. In the setting information stored in the memory, identification information for distinguishing the camera device 1 from others is stored in advance, and the control unit 14 stores the captured image in the memory when transmitting the captured image from the communication unit 13. The identification information provided is associated and transmitted. The control unit 14 executes imaging in the imaging unit 11 based on the cycle included in the setting information or in response to an instruction from the gateway device 2, and reads out the captured image temporarily stored in the built-in memory of the imaging unit 11. It is given to the communication unit 13 and transmitted to the gateway device 2.

The camera device 1 may include other sensors in addition to the image pickup unit 11. The camera device 1 may include, for example, a temperature sensor and a humidity sensor. The camera device 1 may include, for example, a sensor that acquires information about the imaging environment, such as its own battery voltage and illuminance sensor. The control unit 14 can include the information measured by these sensors in the metadata description portion of the captured image and transmit it from the communication unit 13 together with the captured image.

FIG. 3 is a block diagram showing the configuration of the meter meter reading system 100. The gateway device 2 uses a device called a so-called IoT gateway including a first communication unit 22 and a second communication unit 23 having different protocols. The gateway device 2 includes a control unit 20 and a storage unit 21. The control unit 20 performs a transmission process of a captured image transmitted from the camera device 1 to the server device 3 based on a program and setting information stored in advance using a CPU, a clock, or the like. The first communication unit 22 includes a short-range wireless communication module such as BLE for communication with the camera device 1. The second communication unit 23 includes a communication module for the next-generation mobile communication standard that realizes communication via the carrier network N2 included in the network N. The gateway device 2 may also include a device for Ethernet (registered trademark) and a communication module for wireless LAN.

The server device 3 uses a server computer. The server device 3 includes a control unit 30, a storage unit 31, and a communication unit 32. The control unit 30 is a processor using a CPU (Central Processing Unit) or a GPU (Graphical Processing Unit), and includes a built-in volatile memory, a clock, and the like. Since the control unit 30 executes image processing as described later, it is preferable to use a GPU or a separate graphic card. The control unit 30 executes each process based on the server program 30P stored in the storage unit 31 and causes the general-purpose server computer to function as a specific meter reading device that processes information related to the captured image of the meter M described later.

The storage unit 31 stores the information referred to by the control unit 30 in addition to the server program 30P using the hard disk. The storage unit 31 stores the setting information for each meter M referred to by the control unit 30 when processing the captured image, which will be described later, in association with the identification information of the meter M. The server program 30P stored in the storage unit 31 may be acquired and stored from the outside by the communication unit 32.

The communication unit 32 includes a network card. The control unit 30 can send and receive information to and from the client device 4 via the network N by the communication unit 32.

The client device 4 includes a control unit 40, a storage unit 41, a display unit 42, an operation unit 43, a voice input / output unit 44, and a communication unit 45. The control unit 40 includes a processor such as a CPU or GPU and a memory or the like. The control unit 40 may be configured as one piece of hardware (SoC: System On a Chip) in which a processor, a memory, a storage unit 41, and a communication unit 45 are integrated. The control unit 40 causes a general-purpose computer to function as a client device 4 for the user of the meter meter reading system 100 of the present embodiment based on the application program 40P stored in the storage unit 41.

The storage unit 41 includes a non-volatile memory such as a flash memory. The storage unit 41 stores the application program 40P. The application program 40P may include a Web browser function. A general-purpose Web browser program stored in the storage unit 41 may be used. The storage unit 41 stores the data referred to by the control unit 40. The application program 40P may be one in which the application program 49P stored in the storage medium 49 is read by the control unit 40 by a reading unit (not shown) and installed in the storage unit 41. The application program 40P may be one in which the control unit 40 receives the application program (not shown) distributed by any server device via the network N by the communication unit 45 and installs it in the storage unit 41.

The display unit 42 includes a display device such as a liquid crystal panel or an organic EL display. The operation unit 43 is an interface that accepts user operations, and includes physical buttons and a touch panel device with a built-in display. The operation unit 43 can accept an operation on the screen displayed on the display unit 42 by a physical button or a touch panel.

The audio input / output unit 44 includes a speaker, a microphone, and the like. The voice input / output unit 44 includes a voice recognition unit, and can recognize the operation content from the input voice with a microphone and accept the operation.

The communication unit 45 is a wireless communication module that realizes transmission / reception of information to / from the server device 3 via the network N. The communication unit 45 may perform communication via the network N by wire using a network card.

The meter reading method of the meter M in the meter meter reading system 100 configured as described above will be described. In the present embodiment, the gateway device 2 stores in advance the device identification information of the camera device 1 that can be connected to the communication in the storage unit 21. The device identification information may be, for example, a MAC address, or may be information previously assigned to and stored in the camera device 1. The gateway identification information of the gateway device 2 itself may be additionally stored in the storage unit 21. The gateway device 2 establishes pairing for a plurality of camera devices 1 by the first communication unit 22 for the camera device 1, and temporarily assigns a different address to each of the camera devices 1 for which the pairing has been established. The control unit 20 of the gateway device 2 instructs a plurality of camera devices 1 to execute imaging and transmit captured images in order in association with the device identification information stored in the storage unit 21.

When each of the camera devices 1 receives an instruction from the gateway device 2, the light source 12 is turned on, the image pickup unit 11 executes imaging, the light source 12 is turned off, and the captured image is transmitted from the communication unit 13 to the gateway device 2. When the device identification information is stored in the built-in memory in advance, the control unit 14 may transmit the device identification information together with the captured image.

Each time the control unit 20 of the gateway device 2 receives the captured image from the camera device 1 by the first communication unit 22, the control unit 20 associates the captured image with the corresponding device identification information and sends the captured image from the second communication unit 23 to the server device 3. Send. The control unit 20 may store captured images using the built-in memory. If it is difficult to transmit from the second communication unit 23, it may be stored and transmitted when communication becomes possible.

The control unit 20 of the gateway device 2 cyclically repeats the above-mentioned processing of imaging instruction, reception and transmission of captured image, with respect to one or a plurality of camera devices 1 capable of communication connection. The gateway device 2 can communicate with, for example, up to 20 camera devices 1. If it takes 10 to 20 seconds to transmit from one imaging instruction to the server device 3, each camera device 1 executes imaging once every 4 to 6 minutes.

In the server device 3, each time the captured image is transmitted from the gateway device 2, the position of the pointer is specified from the scale plate of the meter M for each meter M in association with the device identification information by the process described later, and the scale indicated by the pointer. Identify the number corresponding to. The control unit 30 stores the setting information used for specifying the position of the pointer and the numerical value in the storage unit 31 in association with the device identification information for each meter M. It is preferable to connect the client device 4 to the server device 3 and accept the processing of these information by the operation of the operator.

FIG. 4 is a diagram showing an example of the content of the set information. In FIG. 4, the position of the pointer fulcrum is indicated by the symbol O, and the positions of the plurality of main scales are indicated by the symbols P0, P1, P2, P3, P4, and P5. These positions may be selected and set by the operator on the screen. The storage unit 31 has coordinates indicating the positions of the pointer fulcrum position O shown in FIG. 4 on the captured image, and coordinates indicating the positions of the positions P0, P1, P2, P3, P4, P5, ... Of the plurality of main scales. Each is remembered.

Further, in FIG. 4, the contour C corresponding to the shape of the pointer adjusted and determined with respect to the contour drawn based on the general contour information of the stored pointer is shown. Information indicating a general outline as the shape of the pointer is stored in advance in the storage unit 31. The contour C is determined by the operator designating the tip, expanding / contracting the width, and adjusting the length of the contour drawn based on the information indicating the contour stored in advance. The storage unit 31 stores the determined length and width of the contour C and the relative position of the pointer fulcrum position O with respect to the contour C. It is preferable that the needle color is also selected and stored in the storage unit 31.

Further, it is preferable that the storage unit 31 is preset with distortion correction of the captured image. In distortion correction, for example, since the distance between the image pickup unit 11 of the camera device 1 and the meter M is short, distortion occurs when the image pickup unit 11 is not strictly perpendicular to the scale plate of the meter M, that is, does not face each other. growing. There is other distortion due to the characteristics of the lens. FIG. 5 is a diagram showing an outline of distortion correction in a captured image. In FIG. 5, the distortion of the captured image is represented by a grid. As shown in FIG. 5, the grids that originally intersect each other vertically are distorted and imaged as shown in FIG. 5A depending on the angle of the imaging direction, the lens characteristics, and the like. The control unit 30 of the server device 3 may automatically identify and correct the distortion by using the image analysis function, display a screen for previewing the captured image, and the operator confirms the corrected captured image. However, the distortion may be corrected. FIG. 5B shows the corrected grid. The correction parameter group is stored in the storage unit 31 as setting information. Based on the setting information, the control unit 30 can correct the captured image captured by the same camera device 1 at a stage prior to the reading process described later.

Next, the reading process based on the setting information set as shown in FIGS. 4 and 5 will be described. The reading process is executed by the server device 3 for the captured image transmitted from the camera device 1 based on the setting information received via the client device 4.

FIG. 6 is a flowchart showing an example of the reading processing procedure by the server device 3. The server device 3 executes the following processing each time the captured image is received from the gateway device 2.

The control unit 30 of the server device 3 identifies the device identification information corresponding to the received captured image (step S201), and reads out the setting information associated with the device identification information from the storage unit 31 (step S202).

The control unit 30 first executes distortion correction processing on the received captured image based on the read setting information (step S203). In step S203, for example, as described above, the control unit 30 reads out and applies the parameter group of the correction by the operation of the person in charge on the preview screen 422 including the captured image in the setting information reception screen 420. The control unit 30 may automatically specify the distortion correction parameter in advance and store it in the storage unit 31 for use.

The control unit 30 secondly executes the equalization process on the captured image (step S204). The equalization process in step S204 is an image process that reduces the influence of noise elements such as shadows and reflections by correcting the gradation of the image.

Next, the control unit 30 selects one meter M shown in the captured images after the processing of steps S203 and S204 (step S205), and the following steps are taken based on the setting information stored for the selected meter M. The process of step S214 is executed from S206.

The control unit 30 performs a process of scanning the captured image with pixels in a range corresponding to the length of the pointer along the length direction of the pointer with reference to the position of the pointer fulcrum, to be 0 (0) among the plurality of scale positions. Zero) From the scale position to the maximum scale position, the process proceeds sequentially in the direction orthogonal to the scale (or the direction in which the pointer advances) (step S206). A scanned image of the dial is created using the pixel values of the referenced pixels each time the reference process is performed (step S207).

The control unit 30 creates an image of the pointer based on the contour information of the shape of the pointer and the needle color included in the read setting information (step S208). In step S208, for example, the control unit 30 draws a background image that is sufficiently larger than the length and width of the pointer with the color of the dial included in the setting information, and is based on the contour information at the center of the background image. The outline of the pointer corresponding to the length and width is drawn, and the inside of the outline is drawn with the needle color of the setting information. Pixels having a width corresponding to the length of the pointer are scanned in a direction orthogonal to the scale (step S209), and a scanned image of the pointer is created using the pixel values of the scanned pixels (step S210).

The control unit 30 uses the scanned image of the pointer created in step S210 along the direction orthogonal to the scale in the scanned image of the scale board created in step S207, and distributes the high possibility that the pointer is reflected ( (Likelihood distribution) is calculated (step S211).

In step S211 the control unit 30 superimposes the scanned image of the pointer created in step S210 along the direction orthogonal to the scale in the scanned image (rectangular image) of the scale board in accordance with the direction of the pointer, and the corresponding pixels are overlapped with each other. The likelihood is calculated based on the numerical value obtained by calculating the difference between. The control unit 30 may use the sum of the differences between the corresponding pixels in the entire size range of the scanned image of the pointer, or may calculate the average value of the sum. The control unit 30 calculates the likelihood that the smaller the total value or the average value of the differences, the higher the possibility that the pointer appears in the scanned image of the dial on which the scanned image of the pointer is located. Preferably, for the center line of the pointer and the pixels having a predetermined width from the center line in the scanned image of the pointer, the likelihood may be calculated by weighting the difference so that the smaller the difference is, the larger the likelihood is.

The control unit 30 corrects the likelihood distribution using the direction orthogonal to the scale calculated in step S211 that is, the differential value of the likelihood distribution with respect to the scale position (step S212). This is because in step S212, the control unit 30 adopts a steeper peak among the peaks in the likelihood distribution for peaks having the same likelihood.

The control unit 30 identifies the position on the scanned image of the dial having the maximum likelihood based on the corrected likelihood distribution in step S212 (step S213), and determines the numerical value indicated by the pointer corresponding to the specified position. It is calculated and stored in the storage unit 31 in association with the device identification information and the meter identification information (step S214). The storage in step S214 may be stored and stored as a log in association with the time information indicating the time when the captured image was acquired, or only the latest numerical information may be stored.

The control unit 30 determines whether or not all the processes of the monitored meter M shown in the received captured image have been executed (step S215), and when it is determined that all the processes have not been executed (S215). : NO), the process is returned to step S205, the next meter M is selected (S205), and the process is continued.

When it is determined in step S215 that all the processes have been executed (S215: YES), the control unit 30 ends the processes.

When scanning in step S206, if the pointer is expected to swing beyond the upper and lower limits (zero and maximum scale positions) of the scale range, the portion exceeding the upper and lower limits is set as the "outside reading range area". You may execute it including the range. In step S206, the control unit 30 may proceed with scanning based on the setting of whether or not the “out-of-reading area” is the target of the scanned image. When the "out-of-reading area" is not targeted, the control unit 30 scans only from the zero scale position to the maximum scale position as shown in S206 to create a scanned image. When the "outside reading range area" is targeted, the control unit 30 advances scanning including the "outside reading range area", creates a scanned image, and the pointer exists in the "outside reading range area" in the processing after S211. In a state where it can be estimated that the image is being performed, a process such as avoiding the specific process of S213 may be performed.

The processing procedure shown in the flowchart of FIG. 6 will be specifically described with reference to an example of the contents of the captured image. FIG. 7 is a schematic view showing an example of the contents of the captured image. FIG. 7 shows an example in which the meter M, which is a pressure gauge, is imaged as shown in FIG. FIG. 8 is a diagram showing an outline of a scanning method for captured images. In FIG. 8, with respect to the captured image shown in FIG. 7, the pointer fulcrum position set by the process described with reference to FIG. 4 is indicated by reference numeral O, and the positions of the plurality of main scales are indicated by reference numerals P0, P1, P2, P3, and so on. It is indicated by P4 and P5. In FIG. 8, the traveling direction of the scan for creating the scan image of the scale is indicated by a white arrow, and the range corresponding to the length of the pointer referred to in one scan (main scan) is indicated by a broken line. It is shown by a rectangle L. The rectangle L passes through the pixel at the fulcrum position of the pointer, which is the reference position of the pointer, and has a width range of 1 to 2 pixels for the length of the pointer, so that the pixel can be referred to. In step S207 (the same applies to step S210), the control unit 30 creates a scanned image by referring to the pixel values while rotating the rectangle L little by little at the pointer fulcrum position O.

FIG. 9 is a schematic view showing an example of a scanned image of the scale plate of the meter M. In FIG. 9, the scanned image is shown as a diagram, and the positions of the main scales identified by the symbols O, P0, P1, P2, P3, P4, and P5 shown in FIG. 8 in the scanned image are indicated by the symbols. As shown in FIG. 9, the scanned image is created as a rectangular image. In the example shown in FIG. 9, the line segment Q that crosses the rectangular image corresponds to the position of the pointer fulcrum. The long side direction corresponds to the rotation angle of the rectangle L during scanning. As shown in FIG. 9, the length differs for each section between the main scales due to the distortion of the meter M in the captured image. Therefore, when reading the numerical value indicated by the guideline later, it is specified based on the distribution of the scales among the main scales, which are different for each section. In addition, in order to make the length of the section uniform, the scanned image may be stretched or shortened by a different coefficient for each section.

FIG. 10 is a schematic view showing an example of a scanned image of the pointer. In order to create a scanning image similar to the scanning image of the dial by the method shown in FIG. 8, the image is created as an image in which the lower part of the pointer is expanded.

FIG. 11 is a diagram showing a likelihood distribution. The horizontal axis shows the scanning traveling direction of the scanned image of the dial, and the vertical axis shows the likelihood. FIG. 11 shows the likelihood distribution superimposed on the scanned image of the scale shown in FIG. FIG. 11 shows the distribution of the high possibility that the scanned image of the pointer of FIG. 10 matches the scanned image of the scale of FIG. 9, that is, the pointer is reflected. In the example of FIG. 11, the likelihood peak is on the left side of the scanned image of the dial. The control unit 30 can identify that the pointer indicates the vicinity of 3.4 based on the position of the peak and the position of the main scale on the scanned image.

The above-mentioned processing has been described by taking a meter M having a rotating pointer as an example, but the same processing is not limited to this, and the same processing is applied to a meter M having a pointer that moves up and down or a pointer that moves left and right (indicator not limited to a needle). Can be read by. At this time, the direction in which the scanning proceeds does not change in the direction orthogonal to the scale (the direction in which the pointer moves up and down). However, for such a meter M, the reference position (for example, the center) of the pointer is received and stored as setting information instead of the pointer fulcrum position, and a scanned image is created using the reference position in the reading process. FIG. 12 is a diagram showing an outline of another example of the scanning method for the captured image. In the example shown in FIG. 12, an image taken by a water level gauge whose pointer moves up and down in the vertical direction is used. Even with such a water level gauge, the same applies by sequentially creating a scanned image in the direction orthogonal to the scale (the direction in which the pointer or the water surface, the boundary surface, etc. travels) by referring to the pixel values in the range L including the pointer. Processing can be applied.

The read numerical values can be used for detecting abnormalities in the state of the measurement target of the meter M, respectively. In the following processing, the server device 3 determines whether or not the read numerical value is within the preset range, and only when it is determined that the read numerical value is out of the range, the client device 4 of the meter reading system 100 is used. Notify the person in charge of use and realize a safety monitoring service.

FIG. 13 is a flowchart showing an example of a procedure for abnormality detection processing by the control unit 30 of the server device 3. The control unit 30 executes the following processing procedure each time the reading process shown in the flowchart of FIG. 6 is executed, or at a predetermined cycle such as once every few minutes or once every few hours.

The control unit 30 selects the device identification information (step S301), and reads out the numerical value indicated by the pointer for each meter M stored in association with the selected device identification information (step S302). The control unit 30 reads out a predetermined safety range for each meter M corresponding to the selected device identification information (step S303), and determines whether or not the numerical value read in step S302 is within the predetermined safety range read out in step S303. Determine (step S304).

When it is determined in step S304 that the safety range is within the range (S304: YES), the control unit 30 determines whether or not all the device identification information corresponding to the meter M to be monitored has been selected (step S305). When it is determined that all have been selected (S305: YES), the control unit 30 ends the process.

When it is determined in step S304 that the safety range is out of range (S304: NO), the control unit 330 issues a notification to the person in charge based on the account information associated with the device identification information selected in step S301. (Step S306), and the process proceeds to step S305.

If it is determined in step S305 that all have not been selected (S305: NO), the control unit 30 returns the process to step S301.

Conventionally, a person in charge patrols the factory and visually checks the meter M, which is an analog meter, to determine the presence or absence of an abnormality. However, the function of the server device 3 of the present disclosure enables highly accurate automatic reading. The camera device 1 is positioned and attached to the meter M, the gateway device 2 is set and installed, and only the initial settings as shown in FIG. 4 are performed for each camera device 1, and then the operation of abnormality detection is automated. be able to. For example, even for a meter installed in a place where it is difficult for the person in charge to enter due to high temperature, handling of dangerous gas, etc., it is possible to automate the meter reading by using the camera device 1 using the adapter 17 for high temperature. is there.

(Embodiment 2)
The configuration of the meter meter reading system 100 in the second embodiment is the same as the configuration in the first embodiment except for the details of the reading process as the meter reading device of the server device 3. In the following description of the second embodiment, the same reference numerals are given to the configurations common to the first embodiment, and detailed description thereof will be omitted.

The reading processing procedure according to the second embodiment will be described. FIG. 14 is a flowchart showing an example of the reading processing procedure by the server device 3 of the second embodiment. Among the processing procedures shown in the flowchart of FIG. 14, the procedures common to the processing procedures shown in the flowchart of FIG. 6 of the first embodiment are given the same step numbers and detailed description thereof will be omitted.

The control unit 30 of the server device 3 identifies the device identification information corresponding to the received captured image (S201), and reads out the setting information corresponding to the device identification information (S202). The control unit 30 executes distortion correction processing on the received captured image (S203). In the second embodiment, the equalization process is not executed.

The control unit 30 selects one meter M shown in the captured image (S205), and executes the following processing based on the setting information for the selected meter M.

The control unit 30 sequentially advances the process of scanning the pixels with reference to the pointer fulcrum position on the captured image in the direction orthogonal to the scale (or the direction in which the pointer advances) with respect to the entire area of the scale plate (step S226). ). In the second embodiment, the “scanning of pixels based on the pointer fulcrum position” in step S226 is performed not only on the pixels in the range of the length from the needle tail to the needle tip of the pointer, but also in the region outside the needle tail. It may reach.

The control unit 30 creates a scanned image of the dial using the pixel values of the referenced pixels each time the reference process in step S226 is performed (S207).

The control unit 30 creates an image of the pointer of the selected meter M (S208), scans the created image with pixels based on the pointer fulcrum position in the same manner as in step S226 (S209), and operates. A scanned image of the pointer is created using the pixel values of the pixels (S210).

The control unit 30 calculates the variation distribution of the pixel values within the range of the scanned image with respect to the scanned image of the pointer created in step S210 (step S221). Here, the pixel value may be a value corresponding to brightness (luminance) or may be a value for each of RGB.

The control unit 30 may capture the pointer along the direction orthogonal to the scale in the scan image of the scale board created in step S207 by using the variation distribution of the pixel values of the scan image of the pointer created in step S221. The distribution of high sex (probability distribution) is calculated (step S222).

In step S222, the control unit 30 sequentially shifts the range corresponding to the scanned image of the pointer created in step S210 along the direction orthogonal to the scale in the scanned image (rectangular image) of the scale board, and the pixel values in each range. Is extracted. The control unit 30 calculates the fluctuation distribution of the pixel values in the extracted range, and calculates the likelihood based on the numerical value indicating the similarity with the fluctuation distribution calculated in step S221. Since the image of the pointer basically shows a pointer with a clear outline, the fluctuation of the pixel value is large in the outline portion. Since the scale board is usually the background color, the fluctuation should be small if there is no influence such as reflection and reflection. The control unit 30 calculates the sum of products of derivatives (described later) corresponding to the similarity of the fluctuation distribution of the pixel values in each range with the fluctuation distribution of the pixel values in the scanned image of the pointer as the likelihood. The fluctuation distribution of the pixel value is calculated as a fluctuation distribution obtained by scanning the range in at least one direction, but in order to improve the accuracy of the likelihood, the results of scanning in different directions may be summed. The fluctuation distributions in different directions may be weighted and added up as the likelihood. Details will be described later with reference to the diagram.

Based on the likelihood distribution calculated in step S222, the control unit 30 identifies the position on the scanned image of the scale board having the maximum likelihood (S213), and calculates the numerical value indicated by the guideline corresponding to the specified position. Then, it is stored in the storage unit 31 in association with the device identification information and the meter identification information (S214).

The control unit 30 determines whether or not all the processes of the monitored meter M shown in the received captured image have been executed (S215), and when it is determined that all the processes have not been executed (S215:). NO), the process is returned to step S205, the next meter M is selected (S205), and the process is continued.

When it is determined in step S215 that all the processes have been executed (S215: YES), the control unit 30 ends the processes.

The processing procedure shown in the flowchart of FIG. 14 of the second embodiment will be specifically described. Also in the second embodiment, when the meter M is imaged, the captured image as shown in FIG. 7 is acquired. The reading procedure in the second embodiment will be specifically described by taking the captured image shown in FIG. 7 as an example.

FIG. 15 is a diagram showing an outline of a scanning method for a captured image according to the second embodiment. In FIG. 15, with respect to the captured image shown in FIG. 7, the pointer fulcrum position set by the process described with reference to FIG. 4 is designated by reference numeral O, and the positions of the plurality of main scales are designated by reference numerals P0, P1, P2, P3, and so on. It is indicated by P4 and P5. In FIG. 15, a white arrow indicates the traveling direction of the scan for creating a scan image of the scale board, and the pixel group referred to in one scan (main scan) is a scale centered on the pointer fulcrum position. It is shown by a line segment L2 that is twice as long as the distance to. The line segment L2 is a line segment having a length that passes through the pixel at the fulcrum position of the pointer, which is the reference position of the pointer. In step S207 (the same applies to step S210), the control unit 30 creates a scanned image by referring to the pixel values on the line segment L2 for 360 degrees while rotating the line segment L2 little by little at the pointer fulcrum position O. The line segment L2 may have a width of 1 to 2 pixels and may refer to the pixels in L2.

FIG. 16 is a schematic view showing an example of a scanned image of the scale plate of the meter M. In FIG. 16, the scanned image is shown as a diagram, and the positions of the main scales identified by the symbols O, P0, P1, P2, P3, P4, and P5 shown in FIG. 15 in the scanned image are indicated by the symbols. As shown in FIG. 16, the scanned image is created as a rectangular image. In the example shown in FIG. 16, the line segment Q that crosses the rectangular image corresponds to the pointer fulcrum position O. The long side direction corresponds to the rotation angle of the rectangle L during scanning. In the scanned image of the dial in the second embodiment shown in FIG. 16, the reference reference line segment L2 extends to the blank on the needle tail portion side of the pointer as compared with FIG. In this case, by extending the line segment L2 from the needle tail side first, it is likely that the region at the tip of the needle tail has a small variation in the pixel value. That is, the likelihood can be calculated based on the amount of correlation with the pointer image including the tip of the needle tail.

FIG. 17 is a schematic view showing an example of a scanned image of the pointer. In order to create a scanning image similar to the scanning image of the dial by the method shown in FIG. 15, it is created as an image in which the needle tail portion of the pointer is expanded, and the reference reference line segment L2 extends over the blank of the needle tail portion. There is.

FIG. 18 is a diagram showing a variation distribution of pixel values of the scanned image of the pointer. The control unit 30 distributes the pixel values in the scanning direction (horizontal direction in FIGS. 17 and 18, in this case, the width direction of the scanning image of the pointer) of the scanning image of the pointer by one line (width of 1 to several pixels). The fluctuation distribution is calculated by acquiring and differentiating the acquired pixel values in units of one pixel. While shifting the fluctuation distribution in the direction orthogonal to the scanning direction, the height of the scanned image is calculated and stored. In FIG. 18, the distribution of pixel values B2 (h1) with respect to the scanning direction when the height y in the scanned image is y = h1, and the distribution B2 (h2) of the pixel values with respect to the scanning direction when the height y is y = h2. Has been obtained. When each distribution is differentiated in units of one pixel (x) in the scanning direction, it is expressed as the following equation (1). Here, "B" of B2 indicates the distribution in the scanning direction, and "2" indicates the distribution in the scanned image of the pointer.

As shown in FIG. 18, it can be seen that the variation distribution of the pixel values in the range in which the pointer is captured includes a portion where the pixel value (brightness, luminance value, RGB value) in the central portion is low in the scanning direction.

FIG. 19 is a diagram showing a variation distribution of pixel values in a scanned image of a dial. As shown in FIG. 19, the control unit 30 extracts the scanned image of the scale board in predetermined pixel units in the scanning direction, and extracts only the range that matches the scanned image of the pointer, and distributes the pixel values in the extracted range. It is calculated in the same manner as in FIG. 18 and differentiated to calculate the fluctuation distribution. The image shown in FIG. 19 shows the range indicated by the broken line when the position X in the scanning direction is X = α in the scanned image of the scale plate shown in FIG.

The control unit 30 distributes the pixel values in the scanning direction (horizontal direction in FIG. 19, in this case, the width direction of the extraction range) with respect to the range in the scanned image as shown in FIG. 19, as in the method shown in FIG. Is acquired for each line (width of 1 to several pixels), and the acquired pixel value is differentiated in 1-pixel units to calculate the fluctuation distribution. The variation distribution of the pixel values in the scanning direction in the scanned image of the scale board is expressed by the following equation (2). Here, "B" indicates the distribution in the scanning direction, and "1" indicates the distribution in the scanned image of the dial.

FIG. 20 is a diagram showing a method of calculating the likelihood according to the second embodiment. In the second embodiment, the likelihood is the change in the pixel value in the range extracted from the scanning image on the scale as shown in FIG. 19 centered on the position X in the scanning direction, which is the image of the pointer shown in FIG. It is calculated by the sum of products of fluctuation similarity of how similar it is to the fluctuation of the pixel value in. The variation similarity is calculated as follows for each line in the scanning direction in the extraction range and the pointer image.

The control unit 30 calculates a multiplication value of the variation distribution for each change in the scanning direction in the extraction range and the variation distribution for each change in the scanning direction in the pointer image for each change. The multiplication value is calculated as a positive value if the fluctuation distribution has a positive correlation, that is, a high score if the peaks and valleys in the fluctuation distribution are the same, and a low score if the phases are opposite. To. The control unit 30 takes the sum of the multiplication values calculated for each change in the scanning direction (dx) (Equation (3)).

The control unit 30 sets the sum of products of fluctuation similarity of pixel values in the scanning direction between the extraction range (partial image) calculated for each line and the scanning image of the pointer in the direction orthogonal to the scanning direction (scanning of the pointer). The result of integration in the height direction of the image) is calculated as the likelihood (Equation (4)).

By shifting the position of X little by little in the scanning direction in this likelihood distribution, the position in the scanning direction where the pointer is likely to be reflected (likelihood) can be specified. FIG. 21 is a diagram showing the likelihood distribution in the second embodiment. The horizontal axis shows the scanning traveling direction of the scanned image of the dial, and the vertical axis shows the likelihood. FIG. 21 shows the likelihood distribution superimposed on the scanned image of the scale shown in FIG. FIG. 21 shows the distribution of the height of similarity with the pointer image of FIG. 17 with respect to the scanned image of the scale of FIG. In the example of FIG. 21, since the scanned image is created by scanning 360 degrees or more, the inverted pointer image is also shown on the right side of the drawing, but the degree of similarity with the pointer image of FIG. 17 is high. Therefore, the peak likelihood is unique and can be identified without error.

In the calculation of the likelihood of the second embodiment, the pixel values are referred to in the width direction in the extracted range as shown in FIGS. 18 to 20, the fluctuation distribution is calculated, and the product-sum is calculated to obtain the likelihood. Was calculated. However, in order to improve the accuracy of the likelihood, the fluctuation distribution in a direction different from the width direction, for example, the fluctuation distribution in the height direction of the extracted range and the scanned image of the pointer is calculated, and the calculated fluctuation distribution is made in the same manner. It may be integrated and added to the likelihood calculated based on the fluctuation distribution in the width direction. At the time of summarization, the value based on the fluctuation distribution in the width direction and the value based on the fluctuation distribution in the height direction may be weighted and summed up. The different directions are not limited to the orthogonal width direction or height direction, and may be calculated by taking the variation distribution of the pixel values in any direction in which the characteristics of the pointer image can be easily captured.

Regarding the process described in the second embodiment, the meter M having a pointer moving up and down or a pointer moving left and right (indicator not limited to the needle) can be read by the same process, and the process described in the second embodiment can be read by the same process. Similarly, it can be applied to the realization of a safety monitoring service for abnormality detection and notification based on the read numerical value.

The embodiments disclosed as described above should be considered in all respects as exemplary and not restrictive. The scope of the present invention is indicated by the scope of claims, not the above-mentioned meaning, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

1 Camera device 11 Imaging unit 13 Communication unit 14 Control unit 2 Gateway device 3 Server device (meter reader)
30 Control unit 31 Storage unit 30P Server program 4 Client device 40 Control unit 40P App program 42 Display unit 43 Operation unit

Claims (8)

Stores information indicating the reference position of the scale plate in the captured image obtained by capturing the scale plate of the meter, the positions of a plurality of main scales of the scale plate associated with each numerical value, and the shape and size of the pointer of the meter. The memory part to keep and
A scanned image is created by scanning an image captured by newly capturing the scale plate of the meter in a direction orthogonal to the scale in the image based on the stored reference position of the scale plate and the positions of the plurality of main scales. The first creation part to do and
A second creation unit that creates an image of the pointer based on the information indicating the shape of the pointer, and
A third creation unit that scans the created pointer image in a direction orthogonal to the scale in the image based on the stored reference position and size of the scale board to create a scanned image of the pointer.
Calculation to calculate the distribution of likelihood indicating the high possibility that the pointer is reflected in the direction orthogonal to the scale in the scanned image of the scale by comparing the scanned image of the created scale and the scanned image of the pointer. Department and
A meter reading device including a specific unit that specifies a numerical value indicated by a pointer of the meter based on a distribution in a direction orthogonal to the likelihood scale calculated by the calculation unit. The scale plate has a circular shape, and the reference position of the scale plate stored in the storage unit indicates the position of the fulcrum of the rotating pointer, and the direction orthogonal to the scale is the rotation direction centered on the fulcrum. The meter reading device according to claim 1. The scale is rectangular, and the reference position of the scale stored in the storage unit indicates a position corresponding to a specific position of the pointer moving on a straight line, and the direction orthogonal to the scale is the pointer. The meter reading device according to claim 1, which is the moving direction of the above. The calculation unit determines the fluctuation of the pixel value in the range corresponding to the scanned image of the pointer in the scanned image created by the first creation unit and the pixel value in the scanned image of the pointer created by the third creation unit. The meter reading device according to any one of claims 1 to 3, wherein the likelihood is calculated by the sum of products in a scanning direction of numerical values indicating similarity to fluctuations and in a direction orthogonal to the scale. The specific part is
One or more likelihood peaks are identified based on the distribution in the direction orthogonal to the likelihood scale.
If multiple peaks are identified, select the peak with a steeper likelihood change and
The meter reading device according to any one of claims 1 to 3, wherein a numerical value indicated by a pointer is specified based on a position in a direction orthogonal to the scale of the selected peak and the positions of the plurality of scales. When a peak exists in any of the sections between the positions of the plurality of main scales stored in the storage unit in the direction orthogonal to the scale of the scanned image of the scale plate, the specific unit is used for each section. The meter reading device according to any one of claims 1 to 5, which complements the scales to specify a numerical value. Stores information indicating the reference position of the scale plate in the captured image of the scale plate of the meter, the positions of a plurality of main scales of the scale plate associated with each numerical value, and the shape and size of the pointer of the meter. Store it in the medium
A scanned image is created by scanning an image captured by newly capturing the scale plate of the meter in a direction orthogonal to the scale in the image based on the stored reference position of the scale plate and the positions of the plurality of main scales. And
An image of the pointer is created based on the information indicating the shape of the pointer of the meter.
The created pointer image is scanned in a direction orthogonal to the scale in the image based on the stored reference position and size of the scale board to create a scanned image of the pointer.
By comparing the scanned image of the created dial and the scanned image of the pointer, the distribution of the likelihood indicating the high possibility that the pointer is shown in the direction orthogonal to the scale in the scanned image of the scale is calculated.
A meter reading method including a process of specifying a numerical value indicated by a pointer of the meter based on a distribution in a direction orthogonal to the calculated likelihood scale. For computers equipped with a storage unit
The information indicating the reference position of the scale plate in the captured image of the scale plate of the meter, the positions of a plurality of main scales of the scale plate associated with each numerical value, and the shape and size of the pointer of the meter are described. Store it in the memory
A scanned image is created by scanning an image captured by newly capturing the scale plate of the meter in a direction orthogonal to the scale in the image based on the stored reference position of the scale plate and the positions of the plurality of main scales. And
An image of the pointer is created based on the information indicating the shape of the pointer of the meter.
The created pointer image is scanned in a direction orthogonal to the scale in the image based on the stored reference position and size of the scale board to create a scanned image of the pointer.
By comparing the scanned image of the created dial and the scanned image of the pointer, the distribution of the likelihood indicating the high possibility that the pointer is shown in the direction orthogonal to the scale in the scanned image of the scale is calculated.
A computer program that executes a process of specifying a numerical value indicated by a pointer of the meter based on a distribution in a direction orthogonal to the calculated likelihood scale.

Images