JP2017208014A - Needle type meter detection device, method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately detect an indicated value of a needle type meter, a value related to it, or abnormality of them, even when the contrast between the needle and the background is small or the width of the needle is narrow.SOLUTION: A needle type meter detection device includes: linear image generating means 101 that, upon receiving an image obtained by photographing a needle type meter as a detection object, at least binarizes the received image and generates a linear image; line extracting means 102 for extracting a straight line or a line having a prescribed shape from the linear image; and needle line selecting means 103 for selecting a needle line as a line equivalent to the needle from the extracted line as the extracted straight line or line having the prescribed shape.SELECTED DRAWING: Figure 17

Description

  The present invention relates to a needle-type meter detection device, a needle-type meter detection method, and a needle-type meter detection program for detecting an indication value of a needle-type meter or a value related thereto and correctness / incorrectness thereof.

  As a means for recognizing an indication value of a needle meter (also called an analog meter), a calculation device that obtains an angle of a needle with respect to an appropriate angle reference line in the image with respect to an image obtained by photographing the needle meter with a camera. Proposed. An example of this calculation apparatus is described in Patent Document 1.

  The calculation device described in Patent Literature 1 detects an edge in an image that seems to be a needle from a captured image of a needle-type meter acquired via an imaging device and an acquisition unit, and Hough transforms the detected edge. To extract a plurality of lines (edge lines), and calculate the angle of the needle based on the plurality of lines.

Japanese Patent No. 5609183

  The first problem is that when the contrast between the needle and the background is small, the accuracy of needle extraction decreases.

  This is because the edge detection accuracy is lowered. An edge is usually a location where the difference in pixel value between adjacent pixels in an image is large. Such a part is normally extracted using a differential filter, as exemplified in Patent Document 1. Therefore, when the contrast between the needle and the background is small (when the difference between the pixel values of the needle and the background is small), false edges detected due to illumination fluctuations, various noises included in the image, etc. There is a problem that the detection accuracy is lowered because it cannot be distinguished from the needle edge. If the edge detection accuracy falls, the needle edge line is not correctly extracted, and the needle angle calculation accuracy falls. Note that if the needle edge line is not extracted, or if only one needle edge line is extracted, the result may be that the needle angle cannot be calculated.

  The second problem is that the angle cannot be calculated when the needle in the image is thin, especially when the line width of the needle is only one pixel.

  The reason for this is that when edge lines are extracted using a differential filter, the number of pixels whose pixel value increases (determines that they are edges) after applying the filter is one from the line whose line width is only one pixel. This is because the needle angle cannot be calculated without extracting a plurality of needle edge lines.

  Accordingly, the present invention provides a needle meter detection device capable of accurately detecting the indication value of the needle meter, a value related thereto, or an abnormality thereof even when the contrast between the needle and the background is small or the width of the needle is small. An object of the present invention is to provide a needle meter detection method and a needle meter detection program.

  The needle meter detection device according to the present invention generates a linear image by generating at least a binarized image by binarizing the input image when an image obtained by photographing a needle meter to be detected is input. Means, a line extracting means for extracting a straight line or a line having a predetermined shape from the linear image, and a needle line for selecting a needle line corresponding to the needle from the extracted straight line or a line having a predetermined shape And a selection unit.

  In the needle meter detection method according to the present invention, when an image obtained by photographing a needle meter to be detected is input, at least binarization is performed on the input image to generate a linear image. A straight line or a line having a predetermined shape is extracted from the extracted line, and a needle line corresponding to a needle is selected from the extracted lines that are the extracted straight line or the predetermined shape.

  The needle meter detection program according to the present invention is a line for generating a linear image by at least binarizing an input image when an image of a needle meter to be detected is input to a computer. A needle line that is a line corresponding to a needle is selected from a line image generation process, a line extraction process that extracts a straight line or a predetermined shape line from a line image, and an extracted line that is an extracted straight line or a predetermined shape line The needle line selection process is executed.

  According to the present invention, even when the contrast between the needle and the background is small or when the width of the needle is small, it is possible to accurately detect the indication value of the needle meter, the value related thereto, or the abnormality thereof.

It is a block diagram which shows the structural example of the needle | hook type meter detection apparatus of 1st Embodiment. It is explanatory drawing which shows the effect of thinning. It is explanatory drawing which shows the other example of thinning. It is explanatory drawing which shows an example of a needle type meter. It is explanatory drawing which shows the example of the extraction line L, the rotation center point (gamma), the extended extraction line L ', the distance (alpha), and the distance (beta). It is a flowchart which shows an example of operation | movement of the needle | hook type meter detection apparatus of 1st Embodiment. It is a flowchart which shows the example of the more detailed process flow of a linear image generation process. It is a block diagram which shows the structural example of the needle | hook type meter detection apparatus of 2nd Embodiment. It is a flowchart which shows an example of operation | movement of the needle | hook type meter detection apparatus of 2nd Embodiment. It is a block diagram which shows the structural example of the needle | hook type meter detection apparatus of 3rd Embodiment. It is a flowchart which shows an example of operation | movement of the needle | hook type meter detection apparatus of 3rd Embodiment. It is a block diagram which shows the structural example of the needle | hook type meter detection apparatus of 4th Embodiment. It is explanatory drawing which shows the example of verification of a needle | hook line position. It is a flowchart which shows an example of operation | movement of the needle | hook type meter detection apparatus of 4th Embodiment. It is a block diagram which shows the structural example of the needle | hook type meter detection apparatus of 5th Embodiment. It is a schematic block diagram which shows the structural example of the computer concerning each embodiment of this invention. It is a block diagram which shows the outline | summary of this invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following, for simplicity of explanation, it is assumed that the needle color is black and the background color is white, but the combination of the needle color and the background color is not limited to this. In the case of other combinations, the pixel value close to the needle color is read as “black”, and the pixel value close to the background color is read as “white”.

Embodiment 1. FIG.
FIG. 1 is a block diagram illustrating a configuration example of a needle meter detection device according to a first embodiment of the present invention. A needle meter detection device 10 shown in FIG. 1 includes a linear image generation unit 11, a line extraction unit 12, a needle line selection unit 13, and a needle angle calculation unit 14.

  When an image obtained by photographing a needle meter to be detected is input, the needle meter detection device of the present embodiment outputs the angle of the needle of the needle meter.

  The linear image generation unit 11 performs predetermined image processing on the input image to generate a linear image.

  The image processing performed by the linear image generation unit 11 may be binarization processing, for example. As a binarization method, for example, discrimination binarization generally used in character recognition, adaptive binarization implemented in an open library OpenCV (Open source Computer Vision library) can be used. However, the binarization method is not limited to these. Further, the linear image generation unit 11 may perform thinning in addition to binarization as image processing. That is, after binarization, thinning processing is performed on a pixel having a pixel value corresponding to the color of the needle in the image (for example, if the needle is black, the pixel is classified as black by binarization). You may give it. The thinning process may be, for example, a process for obtaining a center line of a connected area in a binary image. As the thinning method, existing methods (for example, the Hildic method, the Deutsch method, the Tamura method, the Tsuruoka method, etc.) can be used.

  FIG. 2 is an explanatory diagram showing the effect of thinning. For example, when a line is extracted from a region having a certain thickness, such as a connected component in the figure, various lines may be detected even if Hough transform or the like is performed. For this reason, it may be difficult to accurately obtain the optimum line among them. In such a case, by reducing the line width of the connected component after binarization, a straight line or a line having a predetermined shape can be stably extracted.

  The linear image generated by the linear image generation unit 11 is, for example, a line in which the line width of a pixel having a pixel value corresponding to the color of the needle in the target image is equal to or smaller than a predetermined value (preferably one pixel). The image is preferably configured (drawn). As a method for obtaining such a linear image, in addition to the above-described binarization or a combination of binarization and thinning, for example, the following method is also exemplified.

  FIG. 3 is an explanatory diagram showing another example of thinning. For example, as illustrated in FIG. 3, the linear image generation unit 11 performs straight line fitting on a connected component obtained by binarization, and a portion included in a circumscribed rectangle of the connected component among the obtained straight lines. May be extracted. In that case, an image composed only of the extracted straight lines may be a linear image. Note that the fitting to the connected component is not limited to a straight line, but a figure that can be represented by a line in the image (for example, a waveform represented by a polynomial, a free line represented by an arbitrary mathematical expression, a straight line and / or surrounded by them) Arbitrary graphics etc.) can also be used.

  The line extraction unit 12 performs predetermined image processing on the linear image obtained by the linear image generation unit 11 and extracts lines from the image. The line extracted here (hereinafter referred to as “extraction line L”) may be a straight line having no end point in the image, a line segment having an end point in the image, or an arbitrary shape. It may be a line. In the case of a straight line having no end point in the image, the end of the image may be set as the end point. Hereinafter, a straight line having a length is referred to as a straight line regardless of whether or not there is an end point in the image. In this example, the extraction line L is a straight line, but if the shape of the needle is known in advance, it may be a line having a predetermined shape that is the same as or similar to the needle shape. The extraction line L preferably includes the center line of the needle.

  The image processing performed by the line extraction unit 12 may be, for example, a Hough transform or a probabilistic Hough transform. The Hough transform is a technique for detecting a straight line or an arc from image data.

  For example, assume that there is an arbitrary straight line passing through the point P = (x, y). If the length of the perpendicular to the straight line from the origin is ρ, and the angle formed by the perpendicular is θ, the relationship of the following equation (1) holds.

ρ = x · cos θ + y · sin θ (1)

  If there is another point P ′ on the straight line, θ and ρ for the point P ′ are the same as those for the point P. Therefore, the points where θ and ρ are the same are counted, and if the number is equal to or greater than a predetermined threshold, it can be derived that a straight line exists there.

  In addition to the straight line, a line segment may be extracted. For the extraction of the line segment, a probabilistic Hough transform can be used. For example, Randomized or Probabilistic Hough Transform: United Performance Evaluation; Nahum Kiryati et al., Pattern Recognition Letters, 2 May 2000, and `` A Probabilistic Hough Transform; N. Kiryati et al., Pattern Recognition, Vol. 24 , pp. 303-316, 1991 ”.

  The needle line selection unit 13 is based on the rotation center point γ of the needle meter in the image and the information (position and length or shape) of the extraction line L extracted by the line extraction unit 12. A line corresponding to the needle (hereinafter referred to as a needle line) is selected. As the rotation center point γ, a predetermined one may be used, or one extracted by analyzing an input image may be used.

  Examples of the method for selecting the needle line include the following methods. Hereinafter, the length of the perpendicular line drawn from the rotation center point γ to the extraction line L or the extension extraction line L ′ obtained by extending the extraction line L in the direction of the rotation center point γ, that is, the rotation center point γ and the extraction line L or extended extraction The distance from the position on the line L ′ is a distance α. Further, the distance between the end point farther from the rotation center point γ of the extraction line L and the rotation center point γ is a distance β. In such a case, for example, as a first method, the extraction line L whose distance α is not more than a certain value and whose one end point is farthest from the rotation center point of the needle meter is selected as the needle line. May be. For example, as the second method, the longest extraction line L may be selected as the needle line from the extraction lines L whose distance α is equal to or smaller than a certain value and whose distance β is equal to or larger than a certain value. Furthermore, in the first and second methods described above, the extraction line L that is separated from the rotation center point α by both of the end points may be excluded from the needle line candidates.

Hereinafter, the method of selecting a needle line will be referred to using the example of the needle type meter shown in FIG. The needle meter shown in FIG. 4 has a single background color, one needle, a white background color, and a black needle color. Further, as prior knowledge, it is assumed that the needle meter is given information that there is no long line segment other than the needle. FIG. 5 is an explanatory diagram illustrating an example of the extraction line L, the rotation center point γ, the extended extraction line L ′, the distance α, and the distance β. FIG. 5A is an explanatory diagram illustrating an example of the extraction line L. For example, FIG. 5A shows an example of five extraction lines L _{1 to} L ₅ . FIG. 5B is an explanatory diagram showing an example of the rotation center point γ. FIG. 5C is an explanatory diagram showing an example of the extended extraction line L ′. In FIG. 5C, the solid line portion represents the extraction line L, and the broken line portion represents the extended extraction line L ′. For example, in FIG. 5 (c), _{L 1} is an extension extraction line _{L 1} ', _{L 2} is an extension extraction line _{L 2', L 4} is an extension extraction line _{L 4} ', the extension of the _{L 5} An example of L ₅ ′ that is an extraction line is shown. Incidentally, extraction line L ₃ is due to the position contacting the perpendicular and straight from the rotational center point, extension is not. FIG. 7D is an explanatory diagram showing examples of the distance α and the distance β. In FIG. 7 (d), the distance α and distance β is shown for extraction line L ₅ shown in Figure 7 (a).

  The needle angle calculation unit 14 calculates the angle of the needle line selected by the needle line selection unit 13. The needle angle calculation unit 14 may analyze the image and calculate the angle of the needle line with respect to a predetermined reference line in an image system in which the width direction and the height direction of the image are x-coordinate and y-coordinate. For example, when the angle of the line parallel to the y-axis is set to 0 degrees, the needle angle calculation unit 14 may calculate a value from −180 degrees to 180 degrees.

  Next, the operation of this embodiment will be described.

  FIG. 6 is a flowchart showing an example of the operation of the needle meter detection device of the present embodiment. In the example illustrated in FIG. 6, first, the linear image generation unit 11 generates a linear image from the input image (step S11).

  FIG. 7 is a flowchart illustrating an example of a more detailed processing flow of the linear image generation processing. As shown in FIG. 7, the linear image generation unit 11 first binarizes an input image as a linear image generation process (step S111). An existing method may be used for binarization, a method by comparing a predetermined threshold value with a pixel value, discrimination binarization, adaptive binarization (the pixel value of the target pixel is a pixel around the target pixel) Depending on whether the value is larger than the value determined based on the statistic calculated from the value, it is possible to use a method of allocating whether the value is binary or not.

  Next, the linear image generation unit 11 may thin the black pixels of the binary image as a linear image generation process (step S112). For thinning, an existing method or the method described above can be used.

  When the line image is generated, the line extraction unit 12 extracts a line from the line image (step S12 in FIG. 6). For example, the line extraction unit 12 may extract a straight line or a line having a predetermined shape (extraction line L) by performing Hough transformation or probabilistic Hough transformation on the linear image as described above.

  Next, the needle line selection unit 13 selects a needle line from the extracted lines L (step S13). The needle line selection unit 13 selects a needle line from the extraction line L according to a predetermined condition.

  The needle line selection unit 13 uses, for example, a predetermined rotation center point γ of the meter, and, as described above, the extraction line having the largest distance β and the distance α being equal to or smaller than a predetermined value. L may be selected as a needle line.

  If the meter has a circular shape, the center point of the circle extracted by using the generalized Hough transform may be used instead of the rotation center point γ given in advance. When a plurality of circles are detected, the relative positions of the center points of the plurality of circles may be analyzed, and the positions of the center points within a predetermined range may be averaged to obtain the rotation center point γ. Further, the center point of the circle having the most votes may be set as the rotation center point γ using the voting result of the generalized Hough transform.

Finally, the needle angle calculation unit 14 calculates the needle angle (step S14). For example, the needle angle calculation unit 14 uses the coordinates (x ₁ , y ₁ ) and (x ₂ , y ₂ ) of any two points on the detected needle line as shown in the following formula (2). What is necessary is just to obtain | require which (theta).

tan θ = (x ₂ −x ₁ ) / (y ₂ −y ₁ ) (2)

  As described above, according to the present embodiment, since it is configured to detect needle lines (extraction and selection of lines including needle lines) based on binarization, even a needle with a narrow line width can be used. Needle lines can be extracted with high accuracy. In addition, according to the present embodiment, since a line having a long connected component by binarization can be extracted as a needle line, even if the contrast between the needle and the background is small and a lot of noise components are included, a fake attributed to noise is generated. The needle line can be detected with high accuracy without being affected by the line. Therefore, the needle meter can be detected with high accuracy.

  For example, when binarization is performed on a captured image of a needle meter as shown in FIG. 6, a connected component of black pixels is extracted from a numeric part, a circular arc part, a needle part, and the like. In some cases, the connected component is obtained in the form of overlapping arcs and needles. For needle meters that do not have an arc in the background, the connected components of the needle are extracted without overlapping other connected components. For example, how long the obtained connected components are on the image. Analysis may be performed to select a needle line.

  However, not only the arc but also other figures or characters exist in the background, the connected component may be extracted in a form in which they and the needle are not correctly separated. Even in such a case, conversion to a space suitable for extracting a straight line from each black pixel of the connected component by Hough transformation or probabilistic Hough transformation (for example, transformation based on Equation (1)) is performed. A portion having a strong linearity in the black pixel region of the connected component can be obtained stably. In this way, a relatively long line segment in the meter in the image can be extracted from the needle portion, not from a relatively small number or a curved portion such as an arc. If a line corresponding to the needle line can be extracted from the image, then the needle line may be selected by comparison with other extracted lines. If thinning is performed after binarization, the needle line can be detected more stably.

Embodiment 2. FIG.
Next, a second embodiment of the present invention will be described. FIG. 8 is a block diagram illustrating a configuration example of the needle meter detection device according to the second embodiment of the present invention. The needle type meter detection apparatus 10 shown in FIG. 8 is different from the configuration of the first embodiment shown in FIG. 1 in that it further includes a meter image matching unit 15 and an image storage unit 16. In addition, the processing content of the needle angle calculation unit 14 is different. In the following, differences from the first embodiment will be mainly described.

  The image storage unit 16 stores a needle meter image in advance. The needle meter image stored in the image storage unit 16 may be an image of the needle meter to be detected when the needle meter to be detected is known in advance. Note that the image storage unit 16 may store images of a plurality of types of needle meters including images of needle meters other than the needle meters that are to be detected. Hereinafter, the needle meter image stored in the image storage unit 16 is referred to as a DB image.

  The DB image may be, for example, a photograph taken from the front of a needle meter. At this time, it is preferable that the region other than the meter is processed and stored so as not to be included as much as possible. Note that the DB image may be, for example, an image including information (such as a base line of the inclination, such as a base portion) that indicates the inclination of the needle meter in the DB image, in addition to the image taken from the front. Alternatively, an image to which such tilt information is given may be used.

  The meter image collation unit 15 collates the input image and the DB image, thereby specifying a meter region in the input image and obtaining parameters for correcting the inclination of the input image.

  The most suitable process for realizing these components is, for example, a method for obtaining a combination of feature points extracted from an image by comparing it with a DB image. For example, the correspondence between feature points obtained from an image such as SIFT (Sclase-Invariant Feature Transform) feature points, SURF (Speeded Up Robust Features) feature points, and corner feature points may be used. As an example, the method described in International Publication No. 2015/064107, the method described in International Publication No. 2013/089004, or the method described in US Pat. No. 6,711,293 may be used. For example, International Publication No. 2013/089004 pamphlet describes an example of a local feature point based method.

  In addition, for example, in the pamphlet of International Publication No. 2015/064107, a method for extracting a label image and correcting the inclination of the input image by comparing the input image with a label image registered by a method designated in advance. Is described. This can be realized by replacing the label image in this method with a DB image.

  Further, the needle angle calculation unit 14 of the present embodiment performs image inclination correction using an inclination parameter (homography matrix, F matrix, etc.) indicating the inclination degree of the input image obtained by the meter image matching unit 15. After that, the needle angle is calculated.

  Next, the operation of this embodiment will be described.

  FIG. 9 is a flowchart showing an example of the operation of the needle meter detection device of the present embodiment. Since the operations in steps S11 to S13 are the same as those in the first embodiment, the description thereof is omitted.

  When the needle line is selected in step S13, the meter image collating unit 15 collates the input image with the DB image to identify the DB image most similar to the input image, and parameters related to the tilt of the input image (tilt parameter). ) Is calculated (step S21).

Finally, the needle angle calculation unit 14 calculates the needle angle (step S22). The needle angle calculation unit 14 calculates, for example, the needle angle after converting (correcting) the position information of the needle line using the inclination parameter obtained by the meter image matching unit 15. For example, when using the two points (x ₁ , y ₁ ) and (x ₂ , y ₂ ) on the needle line output in the needle line selection process in step S21, the needle angle calculation unit 14 performs the needle angle as follows. You may ask for. That is, the point (x ₁ , y ₁ ) and the point (x ₂ , y ₂ ) are respectively transformed using a slope parameter (for example, a homography matrix), and the point (x ₁ , y ₁ ) and the point (x ₂ , y point after conversion to _{2) (a} 1, _{b 1)} and a point _(a 2, _b and may be obtained θ as shown by ₂₎ to replace the above equation (2).

  As described above, according to the present embodiment, it is configured to obtain the needle angle after correcting the inclination of the meter in the input image. Therefore, for an input image in which the meter is not necessarily photographed from the front. However, the needle angle corresponding to the case of shooting from the front can be calculated.

Embodiment 3. FIG.
Next, a third embodiment of the present invention will be described. FIG. 10 is a block diagram illustrating a configuration example of the needle meter detection device according to the third embodiment of the present invention. The needle-type meter detection device 10 shown in FIG. 10 is different from the configuration of the second embodiment shown in FIG. 8 in that an angle / instruction value conversion unit 17 is further provided.

  Note that the needle meter detection device of the present embodiment outputs an instruction value of the needle of the needle meter when an image obtained by photographing the needle meter to be detected is input.

  The angle / instruction value conversion unit 17 refers to meter information that is determined in advance or the meter information associated with the DB image specified by the meter image collation unit 15, and converts the needle angle into the instruction value. . Here, the meter information may be information indicating a correspondence rule between the needle angle and the instruction value. For example, the meter information may be a mathematical expression for calculating the instruction value from the needle angle or a parameter representing it.

  In the present embodiment, the meter image matching unit 15 may have a function equivalent to that of the device specifying unit that the monitoring unit 16 of the fifth embodiment described later has. In addition to the calculation of the inclination parameter, the meter image collation unit 15 identifies a device using, for example, the same method as the means, and the identification result (device number, device type number, etc.) 17 may be provided. In such a case, the angle / instruction value conversion unit 17 may convert the needle angle into the instruction value by referring to the meter information corresponding to the information provided by the meter image matching unit 15. In addition, when reading a character, a figure, or the like from the input image, the meter image matching unit 15 may detect the inclination in the input image from the reading result, and in that case, the DB image matching process may be omitted.

  Next, the operation of this embodiment will be described.

  FIG. 11 is a flowchart showing an example of the operation of the needle meter detection device of the present embodiment. Since the operations of Step S11 to Step S13, Step S21 and Step S22 are the same as those in the first and second embodiments, description thereof will be omitted.

  In the present embodiment, when the needle angle is calculated in step S22, the angle / instruction value converter 17 converts the needle angle information output in the needle angle calculation process in step S22 into an instruction value based on the meter information. (Step S31).

  As described above, according to the present embodiment, since the needle angle is converted into the indicated value, the indicated value of the needle type meter can be obtained.

Embodiment 4 FIG.
Next, a fourth embodiment of the present invention will be described. FIG. 12 is a block diagram illustrating a configuration example of the needle meter detection device according to the fourth embodiment of the present invention. The needle type meter detection apparatus 10 shown in FIG. 12 includes a needle line position verification unit 18 instead of the needle angle calculation unit 14 and the angle / instruction value conversion unit 17 in the configuration of the third embodiment shown in FIG. The point is different.

  In the needle meter detection device according to the present embodiment, when an image obtained by photographing a needle meter that is a detection target is input, whether or not the needle state (pointed state) of the needle meter is normal. Output the verification result.

  The needle line position verification unit 18 indicates the needle line selected by the needle line selection unit 13 based on the DB image specified by the meter image verification unit 15 or the meter information determined in advance or specified by the meter image verification unit 15. Verify whether the position is normal. For example, the needle position verification unit 18 converts the position of the needle line (corrects the tilt) using the tilt parameter calculated by the meter image matching unit 15 in the same manner as the needle angle calculation unit 14 of the second embodiment. It may be determined whether or not the position of the converted needle line is included in the normal range by determining whether or not the position of the converted needle line is included in the region representing the normal range indicated by the DB image or the meter information.

  It should be noted that the DB image stored in the image storage unit 16 of the present embodiment is given information indicating the normal range of the indicated position of the needle line of the needle meter in the image, or is drawn to indicate the normal range. It shall be. Or the meter information of this embodiment shall contain the information regarding the normal range of the needle | hook line position in a meter.

  Moreover, the meter image collation part 15 may have the function of an apparatus identification means similarly to 3rd Embodiment. In that case, the meter image collation unit 15 identifies the device using the same method as that means, and acquires meter information predetermined for each device or model from the identification result (device number, device type number, etc.). Then, the normal range of the position of the needle line may be specified. If the DB image stored in the image storage unit 16 of the present embodiment is specified, the normal range of the position of the needle line can be specified from the DB image, but the meter image verification unit 15 specifies the DB image ( Instead of the collation), the normal range of the position of the needle line may be specified by acquiring meter information using the above-described device specifying means. The needle line position verification unit 18 may verify whether or not the indicated position of the needle line selected by the needle line selection unit 13 is normal based on the normal range specified by the meter image matching unit 15.

  FIG. 13 is an explanatory diagram showing a verification example of the needle line position. As shown in FIG. 13, an area indicating a normal range (area indicated by a triangle in the figure) in the meter by the front view preset for the DB image is applied to the meter in the input image. Thus, it may be determined as normal if the converted needle line indicating part or main part is included in the normal range after application, and abnormal otherwise. Here, the normal range is applied to the meter in the input image by, for example, expanding the input image or its coordinate system so that the meter in the DB image and the meter in the input image have substantially the same size and orientation. It can be expanded or rotated. Further, the instruction portion of the needle line may be, for example, an end point far from the rotation center point γ. Further, the unnecessary portion of the needle line may be, for example, 50% or more of the line segment from the rotation center point γ to the designated portion. In this example, as the meter information attached to the DB image, information on the partial area in the DB image representing the normal range is given. In the example shown in FIG. 13, since the instruction portion of the needle line is included in the normal range, it is determined as normal.

  Next, the operation of this embodiment will be described.

  FIG. 14 is a flowchart showing an example of the operation of the needle meter detection device of the present embodiment. Since the operations in steps S11 to S13 and step S21 are the same as those in the first and second embodiments, description thereof will be omitted.

  In the present embodiment, when a needle line is selected in step S13 and a DB image is specified in step S21, the needle line position verification unit 18 verifies the position of the needle line (step S41).

  As described above, according to the present embodiment, since the needle line and the normal range associated with the specified DB image are compared on the image, the correctness of the needle line position is determined. For example, when it is desired to detect the abnormality only when the value indicated by the needle is abnormal, it is possible to carry out the process without associating the needle angle with the instruction value in advance.

  In the fourth embodiment, whether or not the needle state is normal is determined from the position of the needle line and information indicating the region of the normal range in the DB image. The same can be done based on the value. In such a case, the needle meter detection device 10 may further include a needle angle calculation unit 14 and an angle / instruction value conversion unit 17. Then, after obtaining the needle angle and the indicated value based on the position of the needle line by the method of the second and third embodiments, whether or not the value is within the normal range based on the information indicating the normal range stored in advance. What is necessary is just to judge.

  The area indicating the normal range is the area connecting the two points detected by image analysis and the rotation center point when two marks indicating the normal range are physically attached in the meter. Also good.

  In addition, when inputting a region indicating a normal range, for example, using a tablet terminal that accepts a touch operation, a user may input a vertex of a polygon indicating a normal range while displaying a DB image on the display. Various functions may be added. A similar example is described in WO 2012/053626 and may be used.

Embodiment 5. FIG.
Next, a fifth embodiment of the present invention will be described. FIG. 15 is a block diagram illustrating a configuration example of the needle meter detection device according to the fifth embodiment of the present invention. The needle meter detection device 10 shown in FIG. 15 is different from the configuration of the fourth embodiment shown in FIG. 12 in that it further includes a monitoring unit 19.

  The monitoring unit 19 monitors the presence or absence of abnormality determination by the needle line position verification unit 18. For example, when the needle position verification unit 18 determines that there is an abnormality, the monitoring unit 19 may perform an operation such as an emergency stop of the apparatus, a report to a management center or the like having jurisdiction over the work, and the like. Moreover, you may make it show the information which alerts the worker who performs a maintenance check.

  At this time, the monitoring unit 19 may include device specifying means (not shown) for specifying a device (a needle meter to be detected) from information (including an input image) input from the outside. The device specifying unit is, for example, a character recognition unit, and may specify a device by obtaining a device number, a device model number, and the like from an input image. Further, the device specifying means is, for example, an ID reading means, which reads a barcode, a two-dimensional barcode, RFID, etc. (hereinafter simply referred to as ID etc.) attached to the device from an input image. The device may be specified by obtaining a model number or the like. Note that the reading method of the ID or the like is not limited to the above, and for example, a device placed at a predetermined position at a predetermined timing or directly held may be read. Further, the device specifying unit is, for example, a user input receiving unit, and may specify the device by allowing the user to input a device number, a device model number, or the like. In such a case, the needle line position verification unit 18 can also determine whether or not there is an abnormality by using an abnormal state determination criterion according to the obtained device number, device model number, or the like. Further, when the angle / instruction value conversion unit 17 is provided, the angle / instruction value conversion unit 17 converts the needle angle into the instruction value by using a conversion parameter corresponding to the obtained device number, device model number, and the like. Also good. Moreover, the monitoring part 19 may transmit the information containing the value of the acquired apparatus number and instruction value, when notifying an abnormal condition to a management center etc. FIG. In the above description, the method of specifying the device by the device number, the device model number, etc. has been described. However, the specification of the device is not limited to these, for example, an arbitrary one uniquely assigned by the instrument installer, administrator, etc. Character strings, symbol strings, figures, etc. may be recognized.

  With such a configuration, it is possible to substitute or assist a worker who performs equipment inspection.

  Further, the monitoring unit 19 may notify a predetermined server of a value (angle information or instruction value) detected from the input image regardless of whether there is an abnormality determination. At that time, the monitoring unit 19 may notify the device number given together with the input image or obtained by image analysis together with the detected numerical value. In such a case, the needle meter detection device 10 may include an imaging unit, take an image of a needle meter that is a detection target at a constant period, and input the image to the linear image generation unit 11. In that case, it is preferable that the imaging unit is installed at a position and an angle suitable for reading the needle.

  With such a configuration, the needle meter detection device 10 can be used as a smart meter that performs continuous reading uploading.

  Next, a configuration example of a computer according to each embodiment of the present invention will be shown. FIG. 16 is a schematic block diagram illustrating a configuration example of a computer according to each embodiment of the present invention. The computer 1000 includes a CPU 1001, a main storage device 1002, an auxiliary storage device 1003, an interface 1004, a display device 1005, and an input device 1006.

  The needle meter detection device of each embodiment described above may be implemented in the computer 1000. In this case, the operation of the needle type meter detection device may be stored in the auxiliary storage device 1003 in the form of a program. The CPU 1001 reads a program from the auxiliary storage device 1003 and develops it in the main storage device 1002, and executes predetermined processing in each embodiment according to the program.

  The auxiliary storage device 1003 is an example of a tangible medium that is not temporary. Other examples of the tangible medium that is not temporary include a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, and a semiconductor memory connected via the interface 1004. When this program is distributed to the computer 1000 via a communication line, the computer that has received the distribution may develop the program in the main storage device 1002 and execute the predetermined processing in each embodiment.

  The program may be for realizing a part of predetermined processing in each embodiment. Furthermore, the program may be a difference program that realizes predetermined processing in each embodiment in combination with another program already stored in the auxiliary storage device 1003.

  Further, depending on the processing contents in the embodiment, some elements of the computer 1000 may be omitted. For example, if the needle meter detection device does not present information to the user, the display device 1005 can be omitted. For example, if the needle meter detection device does not input information from the user, the input device 1006 can be omitted. In this case, however, at least means for inputting an image is provided separately.

  In addition, some or all of the constituent elements of each device are implemented by general-purpose or dedicated circuits (Circuitry), processors, and the like or combinations thereof. These may be constituted by a single chip or may be constituted by a plurality of chips connected via a bus. Moreover, a part or all of each component of each device may be realized by a combination of the above-described circuit and the like and a program.

  When some or all of the constituent elements of each device are realized by a plurality of information processing devices and circuits, the plurality of information processing devices and circuits may be centrally arranged or distributedly arranged. Also good. For example, the information processing apparatus, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client and server system and a cloud computing system.

  Next, the outline of the present invention will be described. FIG. 17 is a block diagram showing an outline of the present invention. As shown in FIG. 17, the needle meter detection device of the present invention includes a linear image generation unit 101, a line extraction unit 102, and a needle line selection unit 103.

  When an image obtained by photographing a needle meter that is a detection target is input, the linear image generation unit 101 (for example, the linear image generation unit 11) performs at least binarization on the input image and performs linear processing. Generate an image.

  The line extraction unit 102 (for example, the line extraction unit 12) extracts a straight line or a line having a predetermined shape from the generated linear image.

  The needle line selection unit 103 (for example, the needle line selection unit 13) selects a needle line that is a line corresponding to the needle from the extracted straight lines or the extracted lines that are lines having a predetermined shape.

  According to such a configuration, the needle line can be detected from the input image with high accuracy, and accordingly, the indication value of the needle meter or the value related thereto and the correctness / incorrectness thereof can be detected with high accuracy.

  Note that the needle meter detection device may further include angle calculation means for calculating the angle of the needle line with respect to a predetermined angle reference line.

  In addition, the needle meter detection device stores in advance an image storage device that stores one or more types of needle meter images in such a manner that the inclination angle of the needle meter in the image can be specified, an input image, and an image storage A meter image collating unit that collates a DB image that is a needle meter image stored in the unit and identifies a DB image that is most similar to the input image, and the angle calculating unit is identified as a result of the collation. The angle of the needle line with respect to a predetermined angle reference line may be calculated after correcting the inclination of the needle type meter in the input image based on an angle parameter representing the degree of inclination of the needle type meter in the input image. Here, the aspect in which the inclination angle of the needle type meter in the image can be specified may be, for example, a rule set to a fixed value (0 degree) in advance, or the inclination angle of the meter in the image may be determined. Information to be displayed may be attached to the image, or a specific mark or coloring that can calculate the inclination angle of the meter may be added to the image.

  In addition, the needle meter detection device may include instruction value conversion means for converting the needle line angle into an instruction value based on information indicating a correspondence rule between the needle line angle and the instruction value.

  The needle type meter detection device is selected based on the specified normal range and the specifying means for specifying the normal range of the indicated position of the needle line in the needle type meter to be detected from the information inputted from the outside. And determining means for determining whether the state of the needle line is normal or abnormal. The specifying unit acquires, for example, information for specifying a device from information (including an input image) input to an image portion, and specifies a normal range of a needle line indication position based on meter information associated with the information. It may be a means. Further, for example, the input image may be a unit that collates a DB image that is an image of a needle meter stored in the image storage unit and identifies a DB image that is most similar to the input image. In such a case, the needle-type meter detection device stores an image of one or more types of needle-type meters in advance in such a manner that the normal range of the indicated position of the needle line of the needle-type meter in the image can be specified. It is assumed that storage means is provided. Here, the mode in which the normal range of the needle line indication position of the needle meter in the image can be specified is, for example, information indicating the normal range of the needle needle indication position in the image is attached to the image. Alternatively, a specific mark or coloring indicating the normal range of the indicated position of the needle line may be provided in the image.

  Further, the needle meter detection device may include monitoring means for outputting information including a needle line angle, an instruction value, or a needle line state to a predetermined server device.

  While the present invention has been described with reference to the present embodiment and examples, the present invention is not limited to the above embodiment and examples. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

  The present invention is applicable not only to the indication value of a needle type meter or a value related to it, but also to the detection of the correctness / incorrectness thereof, as well as to the use of monitoring abnormalities in various facilities. Further, it can be suitably applied to uses such as maintenance inspection work support.

DESCRIPTION OF SYMBOLS 10 Needle type meter detection apparatus 11 Linear image generation part 12 Line extraction part 13 Needle line selection part 14 Needle angle calculation part 15 Meter image collation part 16 Image storage part 17 Angle / instruction value conversion part 18 Needle line position verification part 19 Monitoring part 1000 Computer 1001 CPU
1002 Main storage device 1003 Auxiliary storage device 1004 Interface 1005 Display device 1006 Input device 101 Linear image generation means 102 Line extraction means 103 Needle line selection means

Claims (10)

When an image obtained by photographing a needle meter to be detected is input, linear image generation means for at least binarizing the image and generating a linear image;
Line extraction means for extracting a straight line or a line of a predetermined shape from the linear image;
A needle-type meter detection device comprising needle line selection means for selecting a needle line that is a line corresponding to a needle from the extracted straight lines or extracted lines that are lines of a predetermined shape. The needle-type meter detection device according to claim 1, further comprising angle calculation means for calculating an angle of the needle line with respect to a predetermined angle reference line. Image storage means for storing in advance an image of one or more types of needle-type meters in a manner in which the inclination angle of the needle-type meter in the image can be specified;
A meter image collating unit that collates an input image with a DB image that is an image of a needle meter stored in the image storage unit, and identifies a DB image that is most similar to the input image;
The angle calculation means corrects the inclination of the needle meter in the input image based on an angle parameter representing the inclination degree of the needle meter in the input image specified as a result of the collation, and then calculates a predetermined angle. The needle type meter detection device according to claim 2, wherein an angle of the needle line with respect to the reference line is calculated. The needle-type meter detection device according to claim 2 or 3, further comprising instruction value conversion means for converting the needle line angle into an instruction value based on information indicating a correspondence rule between the needle line angle and the instruction value. A specifying means for specifying a normal range of the indicated position of the needle line in the needle type meter to be detected from information input from the outside;
The needle-type meter detection device according to claim 1, further comprising: a determination unit that determines whether the state of the selected needle line is normal or abnormal based on the specified normal range. The needle-type meter detection device according to any one of claims 2 to 5, further comprising a monitoring unit that outputs information including a needle line angle, an instruction value, or a needle line state to a predetermined server device. When an image obtained by photographing a needle meter to be detected is input, at least binarization is performed on the image to generate a linear image,
Extract a straight line or a line of a predetermined shape from the linear image,
A needle-type meter detection method, comprising: selecting a needle line corresponding to a needle from the extracted straight lines or extracted lines that are lines having a predetermined shape. The needle meter detection method according to claim 7, wherein an angle of the selected needle line with respect to a predetermined angle reference line is calculated. On the computer,
When an image obtained by photographing a needle meter to be detected is input, at least binarization is performed on the image, and a linear image generation process for generating a linear image,
A line extraction process for extracting a straight line or a line having a predetermined shape from the linear image, and a needle line selection for selecting a needle line corresponding to a needle from the extracted extracted lines that are the straight line or the predetermined shape line Needle meter detection program to execute processing. On the computer,
The needle-type meter detection program according to claim 9, wherein an angle calculation process for calculating an angle of a selected needle line with respect to a predetermined angle reference line is executed.

Images