JP7414772B2 - Method and device for measuring displacement of object - Google Patents

Description

The present invention relates to a method and apparatus for measuring displacement of an object.

WO2017/029905A1 discloses an invention called an out-of-plane displacement distribution measuring method using a single digital camera and a method for simultaneously measuring in-plane and out-of-plane displacement using a single digital camera. According to the publication, a grating marker affixed or transferred to the surface of an object is photographed by a single digital (video) camera, and image processing is performed to determine the out-of-plane displacement of the phase of the grating pitch on the image. The amount of out-of-plane displacement is quantitatively determined from minute changes using the sampling moiré method. Similarly, the amount of out-of-plane and in-plane displacement is quantitatively determined using the sampling moiré method from minute changes due to in-plane and out-of-plane displacement of the phase of the same grating, excluding the influence of apparent in-plane displacement. It is said that the amount of three-dimensional displacement is determined.

International publication number WO2017/029905A1

By the way, the present inventor believes that in the technique disclosed in WO2017/029905A1, since the grating width is measured in units of 1 pixel in out-of-plane displacement measurement of moiré patterns, it is difficult to improve accuracy and errors are likely to occur. There is.

The method for measuring the amount of displacement of an object disclosed herein includes the following steps A to D.
(A) Step of attaching a marker having mark A and mark B placed at a predetermined distance from mark A on one plane to the measurement object (B) One plane of the marker is directed toward the imaging direction of the camera. (C) Recognizing mark A and mark B from the reference image of the measurement object by pattern matching (D) Recognizing mark A and mark B in the reference image of the measurement object obtaining a reference resolution based on the distance of

According to this displacement measurement method, the resolution of the reference image of the measurement target M is obtained as the reference resolution by image processing using pattern matching.

The distance between mark A and mark B may be determined by the distance between one point specified by mark A and one point specified by mark B. Mark A and mark B may be marked with different patterns, and mark A and mark B may be identified by pattern matching. In this case, the amount of displacement of the measurement target is obtained based on the step of obtaining a displacement image in which the measurement target has been displaced from the reference image, the amount of change in the distance between mark A and mark B in the displacement image, and the reference resolution. It may further include a step.

Alternatively, mark A and mark B may be marked with the same pattern, and mark A and mark B may be identified by pattern matching. In this case, one plane of the marker includes a mark C marked with a pattern different from the marks A and B, and the mark C may be identified by pattern matching. In this case, the method may further include a step of obtaining the amount of displacement of the measurement target based on the amount of change in the distance between mark A and mark C in the displacement image and the reference resolution. The distance between mark A and mark C may be determined by the distance between one point specified by mark A and one point specified by mark C.

In this way, a new method for measuring the amount of displacement of an object is proposed here.

Further, the displacement measurement device disclosed herein includes a camera, a marker attached to the object to be measured, and an image processing device. The marker has a mark A and a mark B placed at a predetermined distance from the mark A on one plane. The image processing device is preferably configured to execute the following processes a to c.
(a) Process of obtaining a reference image of the measurement target with one plane of the marker facing the imaging direction of the camera (b) Process of recognizing mark A and mark B from the reference image of the measurement target by pattern matching ( c) Process of obtaining a reference resolution based on the distance between mark A and mark B of the image of the measurement target

According to such a displacement measuring device, the resolution of the reference image of the measurement target M is obtained as the reference resolution by image processing using pattern matching.

The distance between mark A and mark B may be configured to be determined by the distance between one point specified by mark A and one point specified by mark B. Mark A and mark B are marked with different patterns, and mark A and mark B may be configured to be identified by pattern matching.

The image processing device calculates the amount of displacement of the measurement target based on the process of obtaining a displacement image in which the measurement target has been displaced from the reference image, the amount of change in the distance between mark A and mark B in the displacement image, and the reference resolution. The configuration may also be such that the process of obtaining the above information is further executed.

Mark A and mark B may be marked with the same pattern on one plane, and mark A and mark B may be identified by pattern matching. The marker may be composed of a sticker on which mark A and mark B are printed.

One plane includes mark C marked with a pattern different from mark A and mark B. Mark C is identified by pattern matching, and the amount of change in the distance between mark A and mark C in the displacement image is determined by pattern matching. , and the reference resolution, the displacement amount of the object to be measured may be obtained. The distance between mark A and mark C may be configured to be determined by the distance between one point specified by mark A and one point specified by mark C. The marker may be composed of a sticker on which mark A, mark B, and mark C are printed.

The displacement measurement device may include a determination unit configured to determine whether the camera is directly facing one plane.

The determination unit includes an irradiation unit that irradiates a laser that is irradiated along the photographing direction of the camera, and a light reception unit that receives the reflected laser. , it may be determined that the camera is directly facing one plane of the marker.

The determination section evaluates the accuracy of the irradiation section that irradiates a laser beam with a cross or a predetermined shape that is irradiated along the shooting direction of the camera, and the accuracy of the cross or a predetermined shape that is irradiated on one plane. Accordingly, it may be determined that the camera is directly facing one plane of the marker. The determination unit may be configured to determine whether the shape of the mark marked on the marker is accurately captured based on the captured image.

FIG. 1 is a schematic diagram of a displacement measuring device 10 disclosed herein. FIG. 2 is a schematic diagram showing an example of a change in an image taken by the camera 11 in FIG. FIG. 3 is a schematic diagram showing changes in the photographing range of the camera 11. FIG. 4 is a schematic diagram showing the movement of point Pa and point Pc when the distance between camera 11 and measurement target M changes. FIG. 5 is a schematic diagram showing changes in the photographing ranges S3 and S4 of the camera 11. FIG. 6 is a schematic diagram showing the movement of points Pd and Pe in the photographing range S4. FIG. 7 is a schematic diagram showing the amount of displacement between points Pd and Pe due to the change in the photographing range from S3 to S4. FIG. 8 is a plan view showing an example of the marker 12. FIG. 9 is a schematic diagram of a marker 12A according to another embodiment. FIG. 10 is a plan view showing a marker 12B according to another embodiment.

Hereinafter, one embodiment of the invention disclosed herein will be described. The embodiments described herein are, of course, not intended to particularly limit the invention. The invention is not limited to the embodiments described herein unless otherwise stated. Each drawing is schematic and does not necessarily reflect the actual product. In addition, members and parts that have the same function are designated by the same reference numerals as appropriate, and redundant explanations will be omitted.

FIG. 1 is a schematic diagram of a displacement measuring device 10 disclosed herein. FIG. 2 is a schematic diagram showing an example of a change in an image taken by the camera 11 in FIG.

<Displacement measuring device 10>
The displacement measuring device 10 includes a camera 11 , a marker 12 attached to the object M to be measured, and an image processing device 13 .

<Camera 11>
The camera 11 is a photographing device for photographing the object M to be measured. As shown in FIG. 1, the camera 11 is preferably arranged so that the photographing direction is directed toward the measurement target M. Although not shown, the camera 11 includes, for example, an image sensor and a lens, and preferably includes a focus adjustment mechanism. As such a camera 11, a commercially available camera may be adopted as appropriate. The camera 11 may be a single monocular camera. The image sensor of the camera 11 may be a CCD or a CMOS sensor.

The present inventor is considering photographing the measurement object M with the camera 11 and analyzing the displacement of the measurement object M based on the image of the measurement object M photographed with the camera 11. In order to obtain the displacement of the measurement object M with high accuracy, it is necessary to calculate the displacement of the measurement object M in consideration of changes in the photographing range of the camera 11.

For example, as shown in FIGS. 1 and 2, when the measurement object M is displaced in the out-of-plane direction z of the image photographed by the camera 11, the photographing range of the camera 11 changes according to the displacement of the measurement object M. changes. When the measurement target M moves relative to the camera 11, the photographing range of the camera 11 changes depending on the distance between the camera 11 and the measurement target M. In other words, when the object M to be measured is focused, the photographing range changes. When the photographing range changes, the position of the measuring object M in the image photographed by the camera 11 changes. However, the shooting range may change on the same plane of the measurement object M, for example, when the relative position of the camera 11 and the measurement object M changes. In order to accurately obtain the displacement of the measurement target M based on the image photographed by the camera 11, it is necessary to analyze the displacement in consideration of changes in the photographing range of the camera 11.

FIG. 3 is a schematic diagram showing changes in the photographing range of the camera 11. FIG. 4 is a schematic diagram showing the movement of point Pa and point Pc when the distance between camera 11 and measurement target M changes. In FIG. 3, the photographing range S1 when the distance (photographing distance) between the camera 11 and the object to be measured M is long is shown by a thick line, and the photographing range S2 when the photographing distance is short is shown by a two-dot chain line. Furthermore, the scale of the photographing range S2 when the distance between the camera 11 and the object to be measured M is short is shown by a thin line. In FIG. 4, in the photographing range S2 after the distance between the camera 11 and the object to be measured M has become close, the position Pa2 of the point Pa and the position Pa2 of the point Pa and the position Pc1 of the point Pc before the photographing distance have become close are shown. The position Pc2 of C is shown.

As shown in FIGS. 3 and 4, as the distance between the camera 11 and the object M to be measured changes, the photographing range changes from S1 to S2. When the photographing range changes from S1 to S2, as shown in FIG. 4, the positions of point Pa and point Pc move in the photographed image. The actual distance between point Pa and point Pc remains unchanged. However, as shown in FIG. 3, when the shooting distance changes, the shooting ranges S1 and S2 of the camera 11 change. Therefore, in the image taken by the camera 11, the distance between the point Pa and the point Pc changes from K1 to K2. However, the change in distance from K1 to K2 also causes a change in the photographing range from S1 to S2. Therefore, the displacement of point Pa (displacement of marker 12) is unknown.

The in-plane coordinates of a point Pa in the photographing range of the camera 11 are represented by orthogonal XY coordinates. The in-plane coordinates of the position Pa1 of the point Pa before the distance between the camera 11 and the measurement target M become close are (X1, Y1). Assume that the number of pixels between points Pa and Pc in the photographed image is a. Also, assume that the actual distance between points Pa and Pc is s. It can be calculated as s=a×q. Here, q is the resolution of the image. The resolution q can be calculated as q=s/a. That is, if the actual distance s between points Pa and Pc is known in advance, the resolution q can be calculated.

The in-plane coordinates of the position Pa2 of the point Pa after the distance between the camera 11 and the measurement target M become close are (X2, Y2). If the actual distance s between two points in the captured image is known, and the coordinates of the two points in the captured image are known, the number of pixels in the x-axis direction and the number of pixels in the y-axis direction between the coordinates of the two points in the captured image can be calculated. is obtained. When the number of pixels in the x-axis direction and the number of pixels in the y-axis direction between the coordinates of two points in the photographed image are obtained, the distance between the two points in the photographed image can be obtained in terms of the number of pixels. Since the actual distance between two points in the photographed image is known, the resolution of the image can be determined by obtaining the distance between the two points in the photographed image in terms of the number of pixels. If the actual distance s between two of the markers 12 in the photographed image is known, it is possible to know the change in resolution of the image and further determine the displacement of the point Pa. Further, when two points among the markers 12 can be identified by pattern matching processing, the displacement of the marker 12 and the displacement of the measurement target M are determined from the image taken by the camera 11 through image processing by a computer. Further, two of the markers 12 are preferably provided on one plane.

FIGS. 5 to 7 are diagrams further illustrating events when the photographing range changes. FIG. 5 is a schematic diagram showing changes in the photographing ranges S3 and S4 of the camera 11. FIG. 6 is a schematic diagram showing the movement of points Pd and Pe in the photographing range S4. FIG. 7 is a schematic diagram showing the amount of displacement between points Pd and Pe due to the change in the photographing range from S3 to S4. In the example shown in FIGS. 5 to 7, point Pd moves from Pd1 to Pd2. Point Pe moves from Pe1 to Pe2.

As shown in FIG. 5, the point Pd and the point Pe change by u1 in the X direction and v1 in the Y direction in the photographing range of the camera 11, respectively. For example, when point Pd and point Pe are attached to measurement target M and marked on the same plane of marker 12 (see FIG. 1), point Pd and point Pe are displaced by the same amount in the X direction and the Y direction, respectively. do.

As shown in FIG. 5, the source position of point Pd is Pd1, and its coordinates are (d1x, d1y). The destination position of point Pd is Pd2, and its coordinates are (d2x, d2y). The source position of point Pe is Pe1, and its coordinates are (e1x, e1y). The destination position of point Pe is Pe2, and its coordinates are (e2x, e2y).

As shown in FIG. 5, when the shooting range S3 does not change, even if the points Pd and Pe move, the apparent distance t3 between the points Pd and Pe does not change. That is, the distance between the positions Pd1 and Pe1 before the movement and the distance between the positions Pd2 and Pe2 after the movement shown in FIG. 5 do not seem to change in the shooting range S3, and both are t3.

When point Pd and point Pe move to Pd2 and Pe2, respectively, the shooting range can change from S3 to S4. When the photographing range changes from S3 to S4, as shown in FIG. 6, in the photographing range S4 of the camera 11 (see FIG. 1), the point Pd moves from the position Pd1 to Pd2. Point Pe moves from position Pe1 to Pe2. In FIG. 6, of the displacement amount Md of the point Pd, the displacement amount in the X direction is XdM, and the displacement amount in the Y direction is YdM. Of the displacement Me of the point Pe, the displacement in the X direction is XeM, and the displacement in the Y direction is YeM.

In the photographing range S4, the apparent distance t3 between the point Pd and the point Pe changes to a distance t4. The distance t3 changes to the distance t4 because, as shown in FIG. 5, the point Pd and the point Pe move, and the shooting range changes from S3 to S4. Here, the apparent distance t3 between the point Pd and the point Pe before the photographing range changes is determined based on the number of pixels β3 and the resolution of the photographing range S3. The apparent distance t4 between the point Pd and the point Pe after the photographing range has changed can be obtained based on the number of pixels β4 and the resolution of the photographing range S4. The numbers β3 and β4 of pixels can be obtained based on the numbers of pixels in the X direction and the Y direction, respectively.

When the actual distance t between the point Pd and the point Pe is known, the resolution q3 of the photographing range S3 can be determined by knowing the apparent distance t3 between the point Pd and the point Pe. Furthermore, when the apparent distance t4 between the point Pd and the point Pe after the photographing range changes is known, the resolution q4 of the photographing range S4 can be found. Furthermore, the amount of change in resolution (q4-q3) between the photographing ranges S3 and S4 can be found. Further, the camera image sensor horizontal distance (isk) and the lens focal length (rsk) are obtained based on the specifications of the camera 11. The out-of-plane displacement amount Δz is expressed as Δz=(q4−q3)×(isk/rsk), where isk is the resolution change and horizontal distance of the camera image sensor, and rsk is the lens focal length.

Next, FIG. 7 will be explained. In FIG. 7, the position Pd2 (see FIG. 5) of the point Pd after movement in the photographing range S3 is indicated by Pd3 in the photographing range S4. Furthermore, the position Pe2 (see FIG. 5) of the point Pe after movement in the photographing range S3 is indicated by Pe3 in FIG. As shown in FIG. 7, the amount of displacement of point Pd due to the change in the imaging range from S3 to S4 is Md1. The amount of displacement of the point Pe due to the change in the photographing range from S3 to S4 is Me1. When the displacement amount Md1 is decomposed into the X and Y directions, the X direction component is Xd1 and the Y direction component is Yd1. In the example shown in FIG. 7, Yd1=0. When the displacement Me1 is decomposed into the XY directions, the X direction component is Xe1 and the Y direction component is Ye1.

Here, as shown in FIG. 7, XdM=u1+Xd1, YdM=v1+Yd1, XeM=u1+Xe1, and YeM=v1+Ye1. In this way, the relationship {actually measured displacement amount (XdM, YdM, etc.) = actual displacement amount (u1, v1) + displacement amount due to change in the shooting range of camera 11 (Xd1, Yd1, etc.)} holds true. Therefore, when the actually measured displacement amount (XdM, YdM, etc.) and the displacement amount (Xd1, Yd1, etc.) caused by the change in the shooting range of the camera 11 are obtained, the actual movement of points Pd and Pe can be determined. (u1, v1) (see FIG. 5) is obtained.

The displacement amount (XdM, YdM, etc.) is calculated from the coordinates of two points (Pd, Pe) in the image photographed by the camera 11. The change in the photographing range of the camera 11 (that is, the change in the photographing range Δz in the out-of-plane direction) is obtained by Δz=(q4−q3)×(isk/rsk) as described above. The distance between the two points (Pd, Pe) in the photographing range S3 is t3, and the distance between the two points (Pd, Pe) in the photographing range S4 is t4. In this case, the amount of displacement (Xd1, Yd1, etc.) due to a change in the photographing range of the camera 11 is as follows with respect to the coordinates (d1x, d1y), (e1x, e1y) of the movement source of Pd and Pe in the photographing range S3. There is a relationship of (t4/t3-1).

In the example shown in Figure 7,
Xd1=d1x(t4/t3-1);
Xe1=e1x(t4/t3-1);
Yd1=d1y(t4/t3-1);
Ye1=e1y(t4/t3-1);
becomes. Here, Xd1, Xe1, Yd1, and Ye1 are obtained by substituting the coordinates (d1x, d1y) and (e1x, e1y) of the movement source of Pd and Pe in the photographing range S3. In this way, the amount of displacement (Xd1, Yd1, etc.) caused by a change in the photographing range of the camera 11 can be calculated.

If at least two points (Pd, Pe) with known distances (t) between the two points are known in the photographed image, even if the photographing range of the camera 11 changes, the two points photographed by the camera 11 The movement of two points (Pd, Pe) whose inter-point distance (t) is known is known. The amount of displacement (XdM, YdM, etc.) actually measured is determined based on two points (Pd, Pe) determined from the image taken by the camera 11. The actual displacement amounts (u1, v1) of the two points (Pd, Pe) are the same. Further, since the distance (t) between the two points (Pd, Pe) is known, the amount of change in resolution due to change in the photographing range of the camera 11 can be known. The amount of displacement (Xd1, Yd1, etc.) caused by a change in the photographing range of the camera 11 is calculated. Furthermore, XdM=u1+Xd1, YdM=v1+Yd1, XeM=u1+Xe1, and YeM=v1+Ye1 hold true. Therefore, when the actually measured displacement amounts (XdM, YdM, etc.) and the displacement amounts (Xd1, Yd1, etc.) caused by changes in the shooting range of the camera 11 are obtained, the actual displacement amounts (u1, v1, etc.) are obtained. ) can be obtained by calculation.

In this way, if at least two points (Pd, Pe) with known distances (t) between the two points are known in the photographed image, even if the photographing range of the camera 11 changes, the camera 11 can From the movements of the two photographed points (Pd, Pe), the actual movements (u1, v1) of the points Pd and Pe are obtained (see FIG. 7).

For this reason, it is preferable to prepare a marker 12 such that at least two points (Pd, Pe) with known distances (t) between the two points can be recognized in the photographed image. As shown in FIG. 1, the marker 12 is attached to the measurement target M, and when the marker 12 and the measurement target M are photographed together, the measurement target M moves and Even when the photographing range of the camera 11 changes, the two points (Pd, Pe) attached to the marker 12 are acquired from the photographed image. Then, from the movements of the two points (Pd, Pe) photographed by the camera 11, the actual movements (u1, v1) of the points Pd and Pe are obtained (see FIG. 7).

<Marker 12>
The marker 12 is a member attached to the measurement target M, as shown in FIG. FIG. 8 is a plan view showing an example of the marker 12. The marker 12 has a mark A, a mark B, and a mark C, as shown in FIG. Mark A, mark B, and mark C are provided on one plane of marker 12. Here, mark A and mark B have the same pattern. Mark A and mark B, which have the same pattern, are placed at a predetermined distance s from mark A. Mark C has a different pattern from mark A and mark B. The distance between mark A and mark C does not need to be known in advance.

In the form shown in FIG. 8, the marker 12 is a rectangular mark, and sections of an 8×2 grid are set. As shown in FIG. 8, in the 8×2 grid section, square areas painted in black and square areas painted in white are arranged in a staggered manner. In this marker 12, rectangular areas 12a and 12b have square areas painted in black placed at the top left and bottom right, and rectangular areas 12a and 12b have square areas painted black at the top right and bottom left. A region 12c is generated. Here, in the rectangular areas 12a and 12b, square areas painted in black are arranged at the upper left and lower right, and can be locally recognized as the same pattern in image processing. In the rectangular area 12c, square areas painted in black are arranged at the upper right and lower left. The rectangular area 12c and the rectangular areas 12a and 12b have mirror symmetry but do not match. Therefore, the rectangular area 12c is recognized as a different pattern from the rectangular areas 12a and 12b in image processing. It is preferable that the marker 12 has grid sections arranged along two orthogonal directions, X and Y, which are set on the measurement target M.

<Measurement object M>
Here, the measurement object M may be, for example, an object to be inspected that is tested in a vibration test. In this case, it is attached to a vibrator and vibrations are applied. There are various objects to be tested in the vibration test. The object to be inspected may be a battery, equipment, device, etc. mounted on a vehicle. The object to be inspected includes an in-vehicle battery such as a battery pack incorporating a plurality of batteries. The marker 12 is preferably attached to the measurement object M as the object to be inspected. The camera 11 is preferably directed at a marker 12 attached to the measurement object M, as shown in FIG. In FIG. 1, the measurement object M moves from M1 to M2 in the photographing range of the camera 11. In FIG.

Here, as shown in FIG. 1, the measurement target M can move in any direction in the in-plane direction or in the out-of-plane direction in the photographing area of the camera 11. Here, the in-plane direction refers to movement along a horizontal plane in the imaging region, and can be expressed in the x direction and the y direction. The out-of-plane direction is a movement along the imaging direction in the imaging area, and can be represented by the z direction. The measurement object M moves in the in-plane direction and in the out-of-plane direction in the photographing area of the camera 11. In the image taken of the measurement object M, the position and size of the marker 12 change, as shown in FIG. The markers 12 may be attached to predetermined positions of the measurement object M as the object to be inspected. In this case, local displacement of the region to which the marker 12 is attached can be observed. For example, the marker 12 may be attached to the housing of the battery pack, the battery module fixed to the housing, each battery cell, etc., respectively.

<Image processing device 13>
The image processing device 13 is a device that processes an image of the measurement object M in the displacement measuring device 10. The image processing device 13 can be implemented, for example, by a computer that runs according to a predetermined program. Specifically, each function of the image processing device 13 is performed by an arithmetic unit (also referred to as a processor, a CPU (Central Processing Unit), or an MPU (Micro-processing unit)) and a memory of each computer that constitutes the image processing device 13. Processing is performed through cooperation between devices (memory, hard disk, etc.) and software. For example, each configuration and process of the image processing device 13 may include a database that stores data embodied by a computer in a predetermined format, a data structure, a processing module that performs predetermined arithmetic processing according to a predetermined program, etc. , or may be embodied as a part thereof. The processing of the image processing device 13 may be executed by one computer. Further, the processing of the image processing device 13 may be executed by multiple computers. Further, the processing of the image processing device 13 may be executed in cooperation with a computer built into the camera 11 or an external computer. For example, the information or part of the information stored in the image processing device 13 may be stored in an external computer. Further, the processing executed by the image processing device 13 or a part of the processing may be executed by an external computer.

The image processing device 13 is configured to perform processing necessary to measure the amount of displacement. The processes necessary to measure the amount of displacement include, for example, the following processes 13a to 13c. Processes 13a to 13c are processes for obtaining a reference resolution among the processes necessary to measure the amount of displacement. The processes 13a to 13c can be realized by processing by a processing module built into the image processing device 13.

<Processing 13a>
The process 13a is a process for obtaining a reference image of the measurement object M in which one plane of the marker 12 is directed in the imaging direction of the camera 11. It is preferable that the normal direction of one plane of the marker 12 is directed toward the imaging direction of the camera 11. Here, in the process 13a, for example, in FIG. 1, it is preferable that an image of the measurement object M at the initial position M1 is obtained as a reference image. In the example shown in FIG. 1, the position M1 of the measurement target M is farther from the camera 11 than the position M2 of the measurement target M after movement. Therefore, as shown in FIG. 2, the photographing range of the camera 11 is closer to one side.

<Processing 13b>
Process 13b is a process of recognizing mark A and mark B from the reference image of measurement target M by pattern matching. In the embodiments shown in FIGS. 2 and 8, the patterns of mark A and mark B are determined and stored in the image processing device 13 in advance. Mark A and mark B are marked with the same pattern and are identified by pattern matching. Therefore, in the image processing device 13, mark A and mark B can be easily specified with high accuracy. In process 13b, for example, a pattern in a rectangular area 12a from among markers 12 is recognized as mark A through image processing. Next, the pattern in the rectangular area 12b of the marker 12 with the same pattern as the mark A is recognized as the mark B by pattern matching.

<Processing 13c>
Process 13c is a process for obtaining a reference resolution based on the distance between mark A and mark B of the image of measurement target M. In process 13c, the distance between mark A and mark B of the image of the measurement target M in the photographed reference image is calculated. In the form shown in FIGS. 2 and 8, in mark A, square areas painted in black are arranged diagonally. The intersection of the square areas is configured to be recognized as the center position Pa of the mark A. Regarding mark B, the intersection point of black square areas arranged diagonally is similarly configured to be recognized as the center position Pb of mark B. The center position Pa of mark A and the center position Pb of mark B may be recognized as a point where consecutive sides of square areas painted in black arranged diagonally intersect. In this embodiment, the distance between mark A and mark B is calculated as the distance between the center position Pa of mark A and the center position Pb of mark B.

In the process of obtaining the reference resolution, the resolution of the reference image of the measurement object M is obtained as the reference resolution by image processing using pattern matching. In the embodiments shown in FIGS. 2 and 8, the actual distance x0 between the mark A and the mark B in the marker 12 is stored in the image processing device 13 in advance. The resolution of the reference image of the measurement object M is determined by the ratio (x1/ x0). Such a resolution may also be referred to as a reference resolution or an initial resolution.

In this embodiment, one point Pa specified by mark A is defined by the center position of mark A. One point Pb specified by mark B is defined by the center position of mark B. In mark A and mark B, one point that can be recognized by image processing is preferably identified. The distance between mark A and mark B is preferably configured to be determined by the distance between one point specified by mark A and one point specified by mark B. From this point of view, one point Pa specified by mark A may not be defined by the center position of mark A. Moreover, one point Pb specified by mark B does not have to be defined by the center position of mark B. The actual distance s between the mark A and the mark B in the marker 12 (see FIG. 8) is preferably known and preferably stored in the image processing device 13 in advance.

Next, a mark C, which is different from marks A and B, is searched for in the reference image of the measurement object M. In the rectangular area 12c as mark C, square areas painted in black are arranged at the upper right and lower left. The rectangular area 12c has mirror symmetry with the rectangular areas 12a and 12b. Therefore, the rectangular area 12c is recognized as having a different pattern from the rectangular areas 12a and 12b in image processing. Further, the rectangular area 12c as the mark C can be searched by pattern matching as a pattern having mirror symmetry with respect to the rectangular areas 12a and 12b. It is preferable that the intersection point of black square areas arranged diagonally among the searched marks C be recognized as the center position Pc of the mark C. The distance x2 between mark A and mark C is preferably configured to be determined by the distance between one point Pa specified by mark A and one point Pc specified by mark C. It is preferable that the distance between the mark A and the mark C be recorded as α1 in the reference image of the measurement object M.

Note that the patterns that can be searched for by pattern matching for the rectangular areas 12a and 12b are not limited to the patterns that have mirror symmetry mentioned here. For example, a pattern that can be searched for by pattern matching for the rectangular areas 12a, 12b may be a pattern that has rotational symmetry of less than 180 degrees with respect to the rectangular areas 12a, 12b. Further, the image processing device 13 may store image data of a pattern adopted for each mark in advance. In this case, since each mark can be searched by pattern matching processing, any pattern may be adopted. For example, each mark may have a non-identical irregular shape and may have no relationship such as symmetry.

Next, the image of the object M to be measured changes by applying vibration with a vibrator or the like. At this time, by attaching the marker 12 to the measurement object M, the displacement of the measurement object M can be obtained. However, when the object M to be measured is focused, the photographing range of the camera 11 changes depending on the distance L1 between the camera 11 and the object M. For this reason, the displacement of the measurement target M cannot be simply obtained from the photographed image.

In the embodiments shown in FIGS. 2 and 8, one plane of the marker 12 includes a mark C with a pattern different from that of the marks A and B. As described above, mark C is identified by pattern matching. The image of the object M to be measured changes by applying vibration with a vibrator or the like. In other words, the position of the measurement target M in the image taken by the camera 11 is determined by the direction of the camera 11, the distance L1 between the camera 11 and the measurement target M, the focal length of the camera 11, the angle of view, and the image sensor. Depends on the size of. Among these, assuming that the direction of the camera 11, the focal length of the camera 11, the angle of view, and the size of the image sensor are constant, the position of the measurement target M in the image taken by the camera 11 is It changes depending on the displacement of the measurement object M relative to the target object M.

In accordance with the displacement of the marker 12 in the out-of-plane direction of the image taken by the camera 11, the distance between the mark A and the mark C changes from α1 to α2 in the image taken by the camera 11. The displacement of the marker 12 in the out-of-plane direction can be obtained from the change in the distance between the mark A and the mark C in the image taken by the camera 11. According to the marker 12 shown in FIG. 8, one plane includes a mark C marked with a pattern different from the marks A and B, and the mark C is identified by pattern matching. Then, the amount of displacement of the marker 12 is obtained based on the amount of change in the distance between mark A and mark C in the displacement image and the reference resolution. In this way, the displacement (in-plane displacement and out-of-plane displacement) of the measurement target M is grasped based on the change in the position of mark A and the change in the distance between mark A and mark C.

In this way, the displacement measurement method proposed here preferably includes the following steps (A) to (C).
(A) A marker 12 having a mark A and a mark B disposed at a predetermined distance from the mark A on one plane is attached to an object M to be measured.
(B) Obtain a reference image of the measurement object M in which one plane of the marker 12 is directed in the imaging direction of the camera 11.
(C) Mark A and mark B are recognized from the reference image of the measurement target M by pattern matching.
(D) A reference resolution is obtained based on the distance between mark A and mark B in the reference image of measurement target M.

In this way, according to the displacement measuring device and the displacement measuring method, the resolution of the reference image of the measurement target M is obtained as the reference resolution through image processing using pattern matching. In this embodiment, a marker 12 having a mark A and a mark B disposed at a predetermined distance from the mark A on one plane is attached to an object M to be measured. One plane of the marker 12 is directed toward the imaging direction of the camera 11, and a reference image is obtained by the camera 11. Mark A and mark B of the marker 12 are recognized by pattern matching. The reference resolution can be obtained with high accuracy based on the distance between mark A and mark B in the reference image.

In this case, the distance between mark A and mark B may be determined by the distance between one point specified by mark A and one point specified by mark B. Mark A and mark B may be marked in the same pattern on one plane of the marker 12. In this case, mark A and mark B may be identified by pattern matching. Furthermore, one plane may include a mark C with a pattern different from the marks A and B. Mark C may be identified by pattern matching. Further, it is preferable that the amount of displacement of the measurement target M be obtained based on the amount of change in the distance between the mark A and the mark C in the displacement image and the reference resolution. According to the displacement measuring method proposed here, a marker 12 is attached to the measurement target M, and mark A, mark B, and mark C marked on the marker 12 are identified by pattern matching. Then, based on the image taken by the camera 11, the reference resolution and the amount of displacement of the measurement object M can be obtained with high accuracy. In other words, the amount of in-plane movement and out-of-plane movement of the measurement target M can be obtained with high accuracy.

According to the displacement measurement device and displacement measurement method, the marker 12 is attached to the measurement object M and the image is photographed by the camera 11, thereby obtaining the displacement of the measurement object M from the image. For example, by attaching the markers 12 to each of a plurality of predetermined positions on the measurement target M, local displacements at each position of the measurement target M can be obtained. For example, when a plurality of battery cells are housed in a housing like a battery pack or a battery module, markers 12 may be attached to each battery cell and at a plurality of positions on the housing. Then, by photographing an image including the marker 12 and performing image processing according to a predetermined program in the image processing device 13, the displacement of each battery cell and each of the plurality of positions of the casing can be obtained. . Therefore, the degree of fixation of each battery cell to the casing can be appropriately acquired through image processing.

<Marker 12A>
FIG. 9 is a schematic diagram of a marker 12A according to another embodiment. In the embodiments shown in FIGS. 2 and 8, one embodiment of the marker 12 attached to the measurement target M is illustrated. The marker 12 is not limited to this form. For example, marker 12 shown in FIGS. 2 and 8 may be replaced with marker 12A shown in FIG. 9.

As shown in FIG. 9, the marker 12A has a mark A, a mark B having the same pattern as the mark A, and a mark C having a different pattern from the marks A and B on one plane of the marker 12. It is formed. Mark A and mark B have rectangular areas 12a and 12b in which black square areas are arranged at the upper left and lower right. The center positions Pa and Pb of the rectangular areas 12a and 12b of the marks A and B, which have the same pattern, are arranged at a predetermined distance. Mark C has a rectangular area 12c in which square areas painted in black are arranged at the lower left and upper right. The rectangular area 12c of mark C and the rectangular areas 12a and 12b of marks A and B have mirror symmetry but do not match. Therefore, the rectangular area 12c is recognized as having a different pattern from the rectangular areas 12a and 12b in image processing.

In this way, the markers 12A are not provided in the 8×2 grid sections like the markers 12 shown in FIGS. 2 and 8. However, the marker 12A has rectangular areas 12a, 12b, and 12c similar to the marker 12, respectively, and functions similarly to the marker 12. That is, the marker 12A is attached to the object M to be measured. Then, it is used to obtain the reference resolution of the photographed image and to obtain the displacement of the measurement object M from the photographed image.

According to the marker 12A, the distance between the mark A and the mark B is stored in advance in the image processing device 13. The reference resolution q0 is obtained from the distance s0 between mark A and mark B on the reference image. Here, the distance between two points on the image can be converted into the number of pixels between the two points. Mark A and mark B have the same pattern and are identified by pattern matching, and their center positions Pa and Pb are identified. When the number of pixels between the center positions Pa and Pb of mark A and mark B is a, the distance s between mark A and mark B can be calculated as s=a×q. Here, q is the resolution of the image and can be calculated as q=s/a. That is, if the distance s between mark A and mark B is known in advance, the resolution q can be calculated.

Mark A and mark C are different patterns having mirror symmetry, and are identified by pattern matching. In this embodiment, the mark C has a different pattern with mirror symmetry, but the pattern of the mark C may be stored in the image processing device 13 in advance. The distance t between the center positions Pa and Pc of mark A and mark C has a relationship of q=t/β=s/a. Here, β is the number of pixels between the center positions Pa and Pc of mark A and mark C.

When the resolution q changes, such as when the measurement target M is displaced in an out-of-plane direction, the image range changes. For example, assume that the resolution q changes from q1 to q2, and the distance t between the center positions Pa and Pb of mark A and mark B in the captured image changes from t1 to t2. The number β of pixels between the center positions Pa and Pb of mark A and mark C in the photographed image changes from β1 to β2. The respective relationships are t1/q1=β1, t2/q1=β2, and t1/β2=q2.
t2/q1=β2 indicates a pixel change due to a change in distance between two points with the resolution as an initial reference. Since the actual distance between two points is constant, t1/β2=q2 shows a calculation formula for calculating the changed resolution when the number of pixels is changed.

The amount of displacement Δz in the out-of-plane direction is determined by the change in resolution Δq=(q2−q1), the horizontal distance (isk) of the image sensor of the camera 11, and the focal length (rsk) of the camera 11 (lens). It is obtained by (q2-q1)×(isk/rsk).

<Marker 12B>
FIG. 10 is a plan view showing a marker 12B according to another embodiment. As shown in FIG. 10, the marker 12B has a mark A and a mark B provided on one plane. Here, mark A has square areas painted in black arranged at the upper left and lower right. Mark B has square areas painted in black arranged at the upper right and lower left. Mark A and mark B have mirror symmetry and are recognized as different patterns in image processing. Further, in this embodiment, the mark B has a pattern having mirror symmetry with respect to the mark A, and can be searched for by pattern matching based on the mark A. In this way, in the marker 12B, the mark A and the mark B are marked with different patterns. Further, mark A and mark B are identified by pattern matching. Furthermore, in this embodiment, marks A and B are arranged so that the square area of mark A painted black and the square area of mark B painted black do not overlap. Specifically, a square area painted black at the bottom left of mark B is arranged in the top right area of mark A. Thereby, the marker 12B is housed compactly as a whole, and space saving is achieved.

For mark A and mark B, the intersections of black square areas arranged diagonally are recognized as the center positions Pa and Pb of the marks. Mark B is placed at a predetermined distance from mark A. The distances between the center positions Pa and Pb of the marks A and B are stored in advance in the image processing device 13.

This marker 12B is attached to the measurement target M as shown in FIG. Then, a reference image of the measurement target M in which one plane of the marker 12 is directed in the imaging direction of the camera 11 is obtained. Mark A and mark B are recognized from the reference image of the measurement object M by pattern matching. The reference resolution is obtained based on the distance between the mark A and the mark B in the reference image of the measurement object M. Further, when the measurement target is displaced from the reference image, a displacement image is obtained. The amount of displacement of the object to be measured is obtained based on the amount of change in the distance between mark A and mark B in the displacement image and the reference resolution. In this way, also in the marker 12B, the mark A and the mark B are recognized by pattern matching in the image processing device 13, and the reference resolution is obtained. Furthermore, when the measurement target object is displaced from the reference image, the amount of displacement of the measurement target object is obtained. In other words, the amount of in-plane movement and out-of-plane movement of the measurement target M can be obtained.

Here, the positions of mark A and mark B can be obtained as (XA, YA) and (XB, YB), respectively, in orthogonal coordinates in the reference image. It is preferable that the coordinates of each point be configured so that they can be obtained in advance by an image processing program. The distance u between mark A and mark B in the x direction can be obtained as u=|XB−XA|. The distance v in the y direction between mark A and mark B can be obtained as v=|YB−YA|.

Let the distance t between mark A and mark B in the reference image be t0. The distance between mark A and mark B can be converted by the number of pixels β0. Further, assuming that the resolution of the reference image is the reference resolution q0, t0=β0×q0. The image processing device 13 may be configured to obtain the distance t0 between the mark A and the mark B by obtaining the distance between the mark A and the mark B with the number of pixels β0 and obtaining the reference resolution q0.

When the marker 12B moves in the out-of-plane direction z of the photographed image by the camera 11, the distance between the mark A and the mark B changes in the photographed image as described above. In the image processing device 13, mark A and mark B are acquired by pattern matching as described above, and the distance between mark A and mark B after displacement is acquired by the number of pixels β1. Here, the actual distance t between mark A and mark B does not change. Therefore, the resolution q1 of the captured image after displacement is obtained by, for example, q1=t/β1. The displacement amount Δz in the out-of-plane direction is obtained by Δz=(q2−q1)×(isk/rsk) as described above.

Hereinafter, the markers 12, 12A, and 12B illustrated here will be generalized and explained as marker 12. The markers 12 proposed here are not limited to those shown in FIGS. 3, 9, and 10. It is preferable that each marker 12 has at least two patterns that can be recognized by the image processing device 13 through pattern matching. One of the recognized patterns is different from the other one. Two of the recognized patterns are placed at a predetermined distance. The marker 12 is attached to the measurement target M and photographed by the camera 11. In the reference image, the reference resolution is obtained based on two patterns placed at a predetermined distance. When the object to be measured is displaced from the reference image, the amount of displacement of the object to be measured is obtained. In other words, by using such a marker 12, measurements can be made by image processing using pattern matching based on the image of the measurement target M taken by the camera 11 using information about the angle of view and measurement range of the camera. The amount of in-plane movement and out-of-plane movement of the object M can be obtained with high accuracy. In contrast, it is not necessary to obtain data regarding the relationship between the image and the displacement in advance. Therefore, the amount of in-plane movement and out-of-plane movement of the measuring object M can be obtained with high accuracy by image processing the photographed image taken by the camera 11.

As shown in FIGS. 3 and 10, the pattern attached to the marker 12 may be a pattern in which the entire unit is two or more, and each unit is a black square whose corners are in contact with each other. Further, the pattern attached to the marker 12 is preferably a black square with two sides forming a cross. According to such a pattern, the pattern can be made small because it can be expressed using small dots. The plane on which the pattern is applied can be made smaller, and the flatness of the plane on which the pattern is applied can be improved. Therefore, it is possible to accurately measure even minute displacements of the object M to be measured. In addition, the pattern attached to the markers 12, 12A has a center point defined by alternating black and white. Therefore, changes in the black density of an image can be read by pattern matching. Therefore, highly accurate pattern recognition is possible through image processing by the image processing device 13 (computer), and highly accurate measurement is possible.

The marker 12 may be a tape such as a label writer with the above-mentioned pattern printed thereon. Further, the marker 12 may be a sticker printed by inkjet. In this case, the marker 12 is preferably attached to the plane of the measurement target M. In this case, since the marker 12 is light, it does not affect the displacement of the object M to be measured.

Furthermore, if the measurement object M has unevenness and flatness cannot be ensured if it is attached as is, the marker 12 is preferably attached to a metal or resin plate and attached to the measurement object M. As the metal plate, it is preferable to use a lightweight metal plate such as an aluminum plate. As the resin plate, it is preferable to attach it to a resin plate such as polystyrene or acrylic plate and attach it to the measurement target M. Note that the marker 12 may be printed directly on a metal or resin plate. Alternatively, the marker 12 may be printed directly on the flat surface of the measurement target M.

Further, as shown in FIG. 1, a determination unit 30 configured to determine whether one plane of the camera 11 and the marker 12 are directly facing each other may be provided. By providing such a determination unit 30, it can be determined that one plane of the camera 11 and the marker 12 are directly facing each other, so that the amount of displacement of the marker 12 can be measured with high accuracy.

For example, if one plane of the marker 12 reflects light, the determination unit 30 may apply a laser pointer along the photographing direction of the camera 11 to determine the laser beam reflected by one plane of the marker 12 in advance. It may be determined that the object is facing directly if the object falls within a certain range. In this case, as shown in FIG. 1, the camera 11 includes an irradiating section 31 that irradiates the laser L1 in the photographing direction of the camera 11, and a light receiving section 32 that receives the reflected laser L2. You can. Then, it is preferable that the laser L2 reflected by one plane of the marker 12 is received by the light receiving section 32, so that it can be determined that the camera 11 is directly facing one plane of the marker 12.

Further, an equilateral triangular pointer is projected onto the marker 12 along the photographing direction of the camera 11, the length of each side of the projected pointer is evaluated, and if the difference between each side is smaller than a predetermined threshold, It may be determined that one plane of the camera 11 and the marker 12 are directly facing each other. The shape of the pointer is not limited to an equilateral triangle, and may be, for example, a cross or a square pointer. By evaluating the accuracy of the irradiation part that irradiates a laser beam with a cross or a predetermined shape that is irradiated along the shooting direction of the camera, and the cross or a predetermined shape that is irradiated on one plane, the camera It may be configured such that it is determined that the marker is directly facing one plane of the marker.

Further, the determination unit 30 is not limited to this form. The function of the determination unit 30 may be incorporated into the image processing device 13. For example, in the embodiment described above, the marker 12 has several square areas painted black. In this case, based on the image taken by the camera 11, it is determined whether the difference between each side of the square area is within a predetermined threshold value, and the difference between each side is determined to be within a predetermined threshold value. If it is smaller than the threshold, it may be determined that one plane of the camera 11 and the marker 12 are directly facing each other. In this way, it may be determined based on the captured image whether the shape of the mark marked on the marker 12 is accurately captured.

Various aspects of the invention disclosed herein have been described above. Unless specifically stated, the embodiments listed herein do not limit the invention. Furthermore, the embodiments of the invention disclosed herein can be modified in various ways, and unless particular problems arise, each component and each process mentioned here can be omitted or combined as appropriate. .

10 Displacement measurement device 11 Cameras 12, 12A, 12B Markers 12a, 12b, 12c Rectangular area 13 Image processing device 30 Judgment section 31 Irradiation section 32 Light receiving section A, B, C Mark L1 Laser L2 Reflected laser M Measurement object

Claims (21)

a step of attaching a marker having a mark A and a mark B disposed at a predetermined distance from the mark A on one plane to an object to be measured;
determining that the one plane and the camera are directly facing each other;
obtaining a reference image of the measurement object in which the one plane of the marker is directed in the imaging direction of the camera;
a step of recognizing the mark A and the mark B from the reference image of the measurement object by pattern matching;
obtaining a reference resolution based on the distance between the mark A and the mark B in the reference image of the measurement object,
Here, in the step of determining whether the one plane and the camera are directly facing each other, the camera emits a laser along the photographing direction of the camera and receives the laser reflected on the one plane. A method for measuring displacement of an object, wherein it is determined that the object is directly facing the one plane. a step of attaching a marker having a mark A and a mark B disposed at a predetermined distance from the mark A on one plane to an object to be measured;
determining that the one plane and the camera are directly facing each other;
obtaining a reference image of the measurement object in which the one plane of the marker is directed in the imaging direction of the camera;
a step of recognizing the mark A and the mark B from the reference image of the measurement object by pattern matching;
obtaining a reference resolution based on the distance between the mark A and the mark B in the reference image of the measurement object,
Here, in the step of determining whether the one plane and the camera are directly facing each other, the one plane is irradiated with a cross or a laser beam of a predetermined shape that is irradiated along the photographing direction of the camera. A method for measuring the amount of displacement of an object, in which it is determined that the camera is directly facing the one plane by evaluating the accuracy of a cross or a predetermined shape irradiated on the object. a step of attaching a marker having a mark A and a mark B disposed at a predetermined distance from the mark A on one plane to an object to be measured;
determining that the one plane and the camera are directly facing each other;
obtaining a reference image of the measurement object in which the one plane of the marker is directed in the imaging direction of the camera;
a step of recognizing the mark A and the mark B from the reference image of the measurement object by pattern matching;
obtaining a reference resolution based on the distance between the mark A and the mark B in the reference image of the measurement object,
Here, the marker has several square areas,
In the step of determining whether the one plane and the camera are directly facing each other, based on the image taken by the camera, the difference between each side of the square area of the marker is within a predetermined threshold value. the amount of displacement of the object, and if the difference between each side is smaller than a predetermined threshold, it is determined that the camera is directly facing the one plane; Measuring method. Any one of claims 1 to 3, wherein the distance between the mark A and the mark B is determined by the distance between one point specified by the mark A and one point specified by the mark B. A method for measuring the amount of displacement of an object described in paragraph 1. 5. The object according to claim 1, wherein the mark A and the mark B are marked with different patterns, and the mark A and the mark B are identified by pattern matching. Displacement measurement method. obtaining a displacement image in which the measurement object is displaced from the reference image;
The object according to claim 5, further comprising the step of obtaining the displacement amount of the measurement object based on the amount of change in distance between the mark A and the mark B in the displacement image and a reference resolution. Displacement measurement method. 5. The object according to claim 1, wherein the mark A and the mark B are marked with the same pattern, and the mark A and the mark B are identified by pattern matching. Displacement measurement method. The one plane includes a mark C marked with a pattern different from the mark A and the mark B,
a step in which the mark C is identified by pattern matching;
obtaining a displacement image in which the measurement object is displaced from the reference image;
The object according to claim 7, further comprising the step of obtaining the displacement amount of the measurement object based on the amount of change in distance between the mark A and the mark C in the displacement image and a reference resolution. Displacement measurement method. 9. The object according to claim 8, wherein the distance between the mark A and the mark C is determined by the distance between one point specified by the mark A and one point specified by the mark C. Displacement measurement method. camera and
a marker attached to an object to be measured;
an image processing device;
and a determination section,
The marker has a mark A and a mark B arranged at a predetermined distance from the mark A on one plane,
The determination unit includes:
It has an irradiation unit that irradiates a laser that is irradiated along the photographing direction of the camera, and a light receiving unit that receives the reflected laser, and the laser reflected from the one plane is received by the light receiving unit, It is configured to determine that the camera is directly facing the one plane,
The image processing device includes:
obtaining a reference image of the measurement object in which the one plane of the marker is directed in the imaging direction of the camera;
A process of recognizing the mark A and the mark B from the reference image of the measurement object by pattern matching;
A displacement measuring device configured to perform a process of obtaining a reference resolution based on a distance between the mark A and the mark B of the image of the measurement object. camera and
a marker attached to an object to be measured;
an image processing device;
and a determination section,
The marker has a mark A and a mark B arranged at a predetermined distance from the mark A on one plane,
The determination unit includes:
By evaluating the accuracy of the irradiation unit that irradiates a laser beam with a cross or a predetermined shape that is irradiated along the shooting direction of the camera, and the cross or the predetermined shape that is irradiated on the one plane. , configured to determine that the camera is directly facing the one plane,
The image processing device includes:
obtaining a reference image of the measurement object in which the one plane of the marker is directed in the imaging direction of the camera;
A process of recognizing the mark A and the mark B from the reference image of the measurement object by pattern matching;
A displacement measuring device configured to perform a process of obtaining a reference resolution based on a distance between the mark A and the mark B of the image of the measurement object. camera and
a marker attached to an object to be measured;
an image processing device;
and a determination section,
The marker has a mark A and a mark B arranged at a predetermined distance from the mark A on one plane,
The marker has several square areas,
The determination unit includes:
Based on the image taken by the camera, it is determined whether the difference between each side of the square area of the marker is within a predetermined threshold, and the difference between each side is determined to be within a predetermined threshold. If the camera is smaller than a threshold, it is determined that the camera is directly facing the one plane,
The image processing device includes:
obtaining a reference image of the measurement object in which the one plane of the marker is directed in the imaging direction of the camera;
A process of recognizing the mark A and the mark B from the reference image of the measurement object by pattern matching;
A displacement measuring device configured to perform a process of obtaining a reference resolution based on a distance between the mark A and the mark B of the image of the measurement object. From claim 10, wherein the distance between the mark A and the mark B is determined by the distance between one point specified by the mark A and one point specified by the mark B. 12. The displacement measuring device according to any one of items 12 to 12. 14. The method according to claim 10, wherein the mark A and the mark B are marked with different patterns, and the mark A and the mark B are configured to be identified by pattern matching. Described displacement measuring device. a process of obtaining a displacement image in which the measurement object is displaced from the reference image;
A process of obtaining a displacement amount of the object to be measured based on a reference resolution and an amount of change in distance between the mark A and the mark B in the displacement image is configured to be further executed. 14. The displacement measuring device described in 14. The displacement amount measurement according to claim 12 or 13, wherein the mark A and the mark B are marked with the same pattern, and the mark A and the mark B are identified by pattern matching. Device. 17. The displacement measurement device according to claim 10, wherein the marker is a sticker on which the mark A and the mark B are printed. The one plane includes a mark C marked with a pattern different from the mark A and the mark B,
a process in which the mark C is identified by pattern matching;
a process of obtaining a displacement image in which the measurement object is displaced from the reference image;
A process of obtaining a displacement amount of the measurement target based on a change amount in the distance between the mark A and the mark C in the displacement image and a reference resolution,
The displacement measuring device according to claim 16 or 17, further configured to be executed. 19. The distance between the mark A and the mark C is determined by the distance between one point specified by the mark A and one point specified by the mark C. Described displacement measuring device. 20. The displacement measurement device according to claim 18, wherein the marker is a sticker on which the mark A, the mark B, and the mark C are printed. The displacement device according to any one of claims 10 to 20, wherein the determination unit is configured to determine whether the shape of the mark marked on the marker is accurately captured based on a photographed image. Quantity measuring device.

Images