JPH09280826A - Calibration jig and method for image recognition device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To form the calibration jig at a low cost, in which the calibration of the correspondence relationship between picture elements and an object is precisely and easily performed, by placing an approximately complete spherical mark body in the recessed part which is formed at the center section of a positioning member. SOLUTION: In a positioning member 51 of a calibration jig 50, a flange section 53 and an engaging section 51a are integrally formed by a metal. A background member 54 is engaged to the central section of the section 51a and a recessed section 56 is formed at the center of the member 54. A high precision steel spherical mark body 52 having a sphericity of, for example, 3μm is placed at the section 56. An inner diameter D1 of the section 56 is set smaller than the diameter of a maximum outer radius section 52R of the body 52 so that when the jig 50 is imaged from the top, it is not photographed. Since the centering of the member 51 and the body 52 is determined by the hole location of a recessed section 56 of the member 54 which is formed by machining, the deviation is made minimum and the calibration precision at the time of a picture recognition is improved. Note that the body 52, which is made of steel and has a high precision, is easily available at a low cost in a commercial market.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention is used in an image pickup apparatus for recognizing an object by an image pickup apparatus, and shows a positional relationship between coordinates when an object is moved and coordinates of an image obtained by the image pickup apparatus. The present invention relates to a calibration jig and a calibration method used for comparison and calibration.

[0002]

2. Description of the Related Art An image recognition apparatus which is designed to measure the position, shape, size or angle of an object by imaging the object with an image pickup apparatus such as a camera, It is necessary to perform such calibration work. This calibration work is performed by measuring in advance how many mm a pixel of the camera corresponds to an actual object, how many times the camera is tilted with respect to the reference coordinate axis, and the like based on the result. The coordinate when moving is compared with the positional relationship between the coordinates of the image of the object obtained by the camera and the calibration is performed.

FIG. 18 shows an example of a commonly used image processing apparatus. This image recognition device includes an XY table 1, a camera 2, a ring light 3, a servo controller 4, an image processing unit 5, and the like. XY table 1
Are movable in the X and Y directions. Ring light 3 is X
Y is an illuminator for illuminating the table 1, and the camera 2 is X
The image of the mark jig 6 set on the Y table 1 is captured and recognized. The conventional mark jig 6 of this type has a disk-shaped metal portion 7 and a mark 8, and the metal portion 7 is positioned so as to fit into the hole 1 a of the XY table 1. By appropriately moving the mark jig 6 in the X and Y directions by the XY table 1, the position of the mark jig 6 moves with respect to the camera 2. Capture the position of in the image. The relationship between the coordinate axes of the camera 2 and the reference coordinate axes (in the X and Y directions) of the XY table 1 is obtained based on the captured images of the mark jig 6 at a plurality of positions.

[0004]

However, the use of the mark jig 6 having such a structure has the following problems. The mark jig 6 has a structure as shown in FIGS. The metal portion 7 of the mark jig 6 has a black plated portion 7a and a mark 8 on its upper surface side, and a white plastic member 7b as a background is arranged in the central portion thereof. A black-plated mark 8 is provided at the center of the background white plastic 7b. However, in the case of adopting such a structure, as shown in FIG. 20, even if the metal portion 7 is processed and the mark 8 is machined so as to obtain the roundness as much as possible, the collapse 8
a is generated. Also white plastic for background 7
When b is also machined, a burr 7d is formed. As a result, the contour of the mark 8 is blurred as shown in FIG. 23, and there is a problem that the camera cannot obtain the image of the mark as a substantially perfect circle mark, and sufficient accuracy of calibration work can be obtained. I can't.

Further, another conventional mark jig as shown in FIGS. 21 and 22 has the following problems. In this mark jig 6, a metal portion (positioning portion) 7 has a black-plated portion 7a on its upper surface, and a white mark 8 is provided at the center thereof.
e is attached. The mark 8e is a print mark. In this case, the print mark 8e is aligned with the center of the metal portion 7 so that the print mark 8e is aligned with the metal portion 7.
It is very difficult to print well on the center line of the. As described above, when the conventional mark jig 6 is used as a calibration mark for a high-magnification camera, it is difficult to secure the mark jig with improved processing accuracy.
Even if secured, it is very expensive. The present invention solves the above problems and provides a calibration jig for an image recognition apparatus and a calibration method for an image recognition apparatus that can be manufactured at low cost and that facilitates calibration of the correspondence between pixels and an object. Has an aim.

[0006]

According to the present invention, the above object is used in an image recognition apparatus for recognizing an object, the coordinates when the object is moved, and the coordinates of the image obtained by the image pickup apparatus. In a calibration jig used for comparing and calibrating the positional relationships of the above, a calibration jig for an image recognition apparatus including a positioning member having a concave portion and a substantially spherical mark body held in the concave portion of the positioning member. Achieved by tools. According to the present invention, when the image recognition device recognizes an object, the concave portion of the positioning member is used when the positional relationship between the coordinate when the object is moved and the coordinate of the image obtained by the image capturing device is compared and calibrated. On the other hand, a substantially spherical mark body is held.
As a result, the image processing apparatus can easily perform the calibration operation of the correspondence relationship between the pixel and the object by capturing and recognizing only the image of the true spherical mark body.

The mark body has a metallic luster, and the peripheral portion which defines the concave portion of the positioning member is white, and if the central portion of the mark body is reflected on the projection surface, light is reflected. The image of the peripheral part of the body can be clearly obtained, and the calibration work can be made more reliable. In this case, if the size of the recess is smaller than the diameter of the mark,
Since the recess is hidden by the mark body, the existence of the recess can be ignored. The focus of the image pickup device is aligned with the maximum outer diameter portion of the mark body so that the concave portion of the positioning member is hidden from the maximum outer diameter portion of the mark body, so that the presence of the concave portion of the positioning member can be ignored. . The background of the mark body can be captured more clearly by changing the mark body from a material having metallic luster to white.

[0008]

Preferred embodiments of the present invention will be described below in detail with reference to the accompanying drawings. Note that the embodiments described below are preferred specific examples of the present invention,
Although various technically preferable limitations are given, the scope of the present invention is not limited to these modes unless otherwise specified to limit the present invention. FIG. 1 shows an example of an image recognition device provided with a calibration jig for the image recognition device of the present invention. Image recognition device 10
Includes a camera 11, a ring light 12, a table moving unit 20, a servo controller 30, an image processing unit 40, a calibration jig 50, and the like.

As the camera 11, for example, a CCD (charge coupled device) camera or the like can be adopted, and its lens barrel portion 11 is used.
a is oriented vertically downward. Ring light 12
It is, for example, a ring-shaped fluorescent lamp that is turned on by the power supply 12a. The ring light 12 is a lens barrel portion 11a of the camera 11.
It is located in the surrounding area. The ring light 12 irradiates the surface of the table 21 of the table moving means 20 with light. The table moving means 20 moves the table 21
It is means for appropriately moving and positioning in the X and Y directions.
The table moving means 20 includes a table 21, a base 22,
23. The base 22 is a motor 24 for the X axis.
And a ball screw 25. Ball screw 25
It engages with a nut (not shown) provided on the base 23, and when the ball screw 25 is rotated by the drive of the motor 24, the ball screw 25 moves the base 23 along the linear guide 26 in the X direction. It can be positioned.

Similarly, the base 23 has a motor 27 for the Y direction and a ball screw 28. Ball screw 28
Engages with a nut (not shown) provided under the table 21, and when the ball screw 28 is rotated by the drive of the motor 27, the table 21 is moved by the linear guide 29.
Can be positioned by moving in the Y direction. In this way, the table 21 can be appropriately moved and positioned in the X and Y directions.

The servo controller 30 controls the driving of the above-mentioned motors 24 and 27. Servo controller 3
0, the image processing unit 30, and the power supply 12a are controlled by the control unit 100. The image processing unit 40 is a device that processes an image of the calibration jig 50 on the table 21 captured by the camera 11. The servo controller 30 sends the XY coordinate position of the table to the image processing unit 40.

Next, referring to FIG. 2, the image recognition apparatus 10 can be used, for example, in a mounting apparatus for an electronic component PA. The mounting apparatus in FIG. 2 includes the above-described table moving means 20, and the table moving means 20 is set on the base 31. Table 21 that is the object
A printed wiring board OB, for example, can be detachably set on the upper side. The head 32 can mount the component PA on the printed wiring board OB. This head 3
2 holds the component PA by vacuum suction, for example, and the head 32 moves the moving operation means 33 in response to a command from the controller 100.
By this, it is possible to move and position in the Z direction.

Next, the structure of the calibration jig 50 shown in FIGS. 1 and 2 will be described. The calibration jig 50 includes a positioning member 51 and a substantially spherical mark body 52. First, the positioning member 51 has a fitting portion 51 a and a flange portion 53, as shown in FIGS. 1, 3 and 4. The fitting portion 51a is adapted to fit into the hole 21a of the table 21 shown in FIG. That is, the inner diameter of the hole 21a is substantially the same as the outer diameter of the fitting portion 51a. The outer diameter of the flange portion 53 is larger than the outer diameter of the indented portion 51a, and the background member 54 is insetly attached to the central portion thereof. This background member 54 is
For example, it is white plastic, and methacrylic can be used as the plastic.

On the other hand, the flange portion 53 and the indented portion 51a are integrated and are made of, for example, metal, and the kind of metal is carbon steel S for machine structure.
45C can be used. A recess 56 is formed in the center of the background member 54. Inner diameter D1 of the recess 56 of FIG.
Is smaller than the diameter L of the maximum outer diameter portion of the mark body 52 described above.

The upper surface 53 of the flange portion 53 as shown in FIG.
a is plated black, for example. Therefore, the background member 54 is white plastic and has an upper surface 53a.
Is black-plated, the ring-shaped outer contour of the background member 54 is clearly highlighted by the color coding of black and white. The substantially spherical mark body 52 is placed in the recess 56 in the center of the background member 54. For the mark body 52, for example, a steel ball can be used. As this steel ball, for example, a commonly used carbon steel steel ball or a stainless steel steel ball can be used. The roundness of this type of steel ball is as high as 3 μm, for example, whereas the roundness of the conventionally used printing mark body is about 20 μm at most. As this type of steel ball, it is possible to practically use a steel ball for a ball bearing, for example.

As shown in FIG. 3, the inner diameter D1 of the concave portion 56 is set smaller than the diameter L of the maximum outer diameter portion of the mark body 52 because the camera 11 of FIG. 1 images the calibration jig 50 from above. In this case, the concave portion 56 has the maximum outer diameter portion 52 of the mark body 52.
This is to prevent the image from being hidden by R. The background member 54 is white because the camera 11 can catch the background member 54 white, and the outer peripheral portion 52g of the mark body 52 seen from above is mirror-reflected so that the illumination light of the ring light 12 is reflected by the camera 11. By not returning to the side, the outer peripheral portion 52g of the mark body 52 can be imaged with a black camera as shown in FIG. When the calibration work is performed in this manner, the mark body 52 appears black and the background member 54 around the mark body 52 appears.
Is white, and the image of the mark body 52 that is black on a white background can be captured with a clean circular contour as shown in FIG.

More specifically, as shown in FIG. 6, the light LT from the ring light 12 is emitted from the center axis CL of the mark body 52.
Is reflected in a region R1 centered on the center, and the reflected light LT returns to the camera 11 side, but a region R2 in the peripheral portion is further reflected obliquely upward, and a further outer region R3 (maximum outer diameter The light LT reflected by the portion 52R) is reflected laterally. Therefore, as shown in FIG.
In the camera 11, the central portion of the mark body 52 appears white and the black appears toward the periphery. Then, the maximum outer diameter portion 52R of the mark body 52 can make a substantially circular outline stand out with a strong contrast with respect to the white of the background member 54. To get these results,
It is preferable that the mark body 52 has a metallic luster like a steel ball for a normal bearing.

Next, an example of a calibration method using such a calibration jig 50 will be described. 7 to 9 show the kl coordinate system J of the image IM for capturing by the camera 11 and the xy coordinate system H of the table 21 in FIG. This coordinate system J
And the coordinate system H are inclined by an arbitrary angle θ. That is, it is shown as an example that the orientation of the camera 11 and the orientation of the table 21 do not match. The coordinate system J of the camera, the coordinate system H of the table 21, and the coordinate system (unit pixel) kl of the camera 11 are shown in FIG. FIG.
1, the coordinate system H and the coordinate system J have a unit of mm, and the coordinate system kl of the unit pixel is the α-β coordinate system J.
Is a coordinate system that expands and contracts along the α and β coordinate axes.

In FIG. 11, OR represents the origin coordinates (x0, y0) of the camera. Further, θ indicates the tilt angle of the coordinate system H and the coordinate system J. An explanation of each element shown in FIG. 11 is shown in FIG. In FIG. 12, a vector Xi is a vector representing the position of the mark body 52 in the coordinate system H of the table 21. The vector Xa is a vector representing the origin coordinate OR (x0, y0) of the camera 11 in the coordinate system H of the table 21. Vector Xb is
It is a vector that represents from the origin coordinate OR (x0, y0) of the camera 11 to the position coordinate (Xi, Yi) of the mark body 52 in the coordinate system H of the table 21. The vector P is a vector representing the vector Xb in the coordinate system J of the camera 11. Therefore, the vector Xb is equal to the vector P. The vector R is a vector that represents the vector P in the pixel coordinate system kl of the camera 11.

FIG. 13 shows the relationship between the vector Xi and the vector R. The vector Xi is (xa, ya),
It can be represented by α, β, xp, yp and the like. FIG.
Indicates the vector Xi of the coordinates of the first, second, and third mark bodies 52 when captured by the camera 11, and also indicates the vector R. Other vectors Xa, Xb
A similar expression can be made for. The coordinate Xi1 of the first mark body 52 is shown in FIG. 7, the coordinate Xi2 of the second mark body is shown in FIG. 8, and the coordinate Xi3 of the third mark body is shown in FIG. ing. The vector Xi1, the vector Xi2, and the vector Xi3 are taken in primary independent positions.

Here, as shown in FIG. 15, xa, ya,
Since S, t, and θ are fixed values, the equation as shown in FIG. 15 is established. It should be noted that θ is the tilt angle as described above, and t is the magnification of how many mm one pixel in the β direction of the camera image corresponds to. It is. S is a magnification of how many mm one pixel in the α direction of the camera image corresponds to.

FIG. 16 shows a coordinate transformation matrix which is the result of adding equations (6) and (7) in FIG. In FIG. 17, the coordinate transformation matrix of FIG. 16 is substituted into the equation (1) of FIG.
a, ya) and the coordinate transformation matrix (FIG. 10) of FIG. 14 and the origin coordinate OR of the camera 11 are obtained. As a result, arbitrary pixel coordinates on the camera are converted to (0) of FIG.
It is shown that the coordinate system is converted to the coordinate system H of the table 21 by an expression.

Next, referring to FIGS. 7 to 9, the camera 11
Is the first mark body 52, the second mark body 52 and 3
The position of the dot mark body 52 is detected, the coordinate transformation matrix (0) formula and the origin coordinate OR of the camera 11 are obtained,
An arbitrary pixel coordinate system (k-1) of the camera is converted into the XY table coordinate system H by the equation (0). In steps S1 to S9 shown in FIG. 10, the servomotor 30 controls the motors 24 and 27 of the table moving means 20, and the image processing unit 40 sets the center position of the mark body 52 of the calibration jig 50 captured by the camera 11. Ask.

In step S1 of FIG. 10, the camera 11 is moved to a position where the mark body 52 is imaged. As a result, the camera 11 takes in the coordinates P1 (vector Xi1) (xi1, yi1) of the first point of the mark body 52 in FIG. 7 (step S2). Then, in step S3 of FIG. 10, the image processing unit 40 obtains the center position of the mark body 52 at the coordinate P1 of the first point by image processing. This corresponds to the pixel (x1p, y1p) on the camera 11.

Next, the table 21 is moved to move the camera 1
1, the camera 11 takes in the coordinates P2 (vector Xi2) (xi2, yi2) of the second point of the mark body 52 as shown in FIG. 8 (step S5). Then, the image processing unit 40 obtains the center position of the second mark body 52 by image processing. The center position of the mark body 52 is the pixel (x2p, y2
p) (step S6).

Next, as shown in FIG. 9, the table 21 is moved and the coordinate P3 (vector Xi) of the third point of the mark body 52 is moved.
3) Take in (xi3, yi3) as an image (step S7). Then, the center position of the mark body 52 is obtained by image processing (step S9). The center position of the mark body 52 corresponds to the pixel (x3p, y3p).

Then, as shown in step S10, if the processing of the equations (0) to (11) in FIGS. 15 to 17 is performed, one pixel (pixel) of the camera is a table which is an actual object. Before the measurement by the image recognition of the object, how many mm on 21 or how many times the camera 11 is tilted as shown by θ in FIG. 7 is calibrated. You can That is, it is possible to determine how many millimeters the pixel is intended to be placed on the table 21, for example, the printed wiring board.

In the present invention, the substantially spherical mark body 52 is used.
Can be used for the recess of the positioning member as a mark close to a perfect circle at a low price by using, for example, a high-precision steel ball that is commercially available. As a result, the calibration accuracy at the time of image recognition can be improved.
Since the centering of the positioning member 51 and the substantially spherical mark body 52 of FIG. 3 is determined by the hole position of the concave portion 56 of the background member 54 opened by machining, it can be suppressed to a minimum deviation. The calibration accuracy at the time of image recognition can be improved.

In the case of a mark made by machining as in the prior art, the accuracy of the calibration is deteriorated due to the slack of the edge portion having burrs around the mark. However, the calibration correction as shown in FIG. 3 of the present invention is performed. By using the tool 50, such a problem is eliminated. The background member 54 is on the rear side of the mark body 52 when viewed from the camera 11 side, and the upper surface of the background member 54, which is the background surface, is the focal height F of the camera 11.
Since it is on the rear side (lower side) of PP, the background member 54
The camera 11 does not focus on dust and scratches attached to the image, and an image with less noise can be obtained as compared with the conventional jig, and the calibration accuracy can be improved. That is,
The focal height FPP of the camera 11 is preferably located at the maximum outer diameter portion 52R of the mark body 52.

The present invention is not limited to the above embodiment. For example, the background member 54 of FIG.
It is made of white plastic and is embedded in the flange part 53 so that the outer peripheral part of the mark body 52 appears black (see FIG. 5).
The mark object 52 is image-recognized as a circular mark based on the black-and-white contrast and calibrated. However, the invention is not limited to this. May be plated with black. Instead of embedding white plastic as the background member 54, white paint may be applied to the central portion of the upper surface of the flange portion 53 (the peripheral portion of the recess 56). Further, when the background member 54 is plated with a dark color, it is of course possible to obtain the contrast of the circular mark by painting the mark body 52 with a white color or a color that appears bright on the camera image. When the background is made black, it is possible to use a highly accurate white plastic ball without using the mark body. The mark body 52 of FIG. 3 can be prevented from coming off the recess 56 by adhering it to the corner of the recess 56 with an adhesive.

In the image recognition apparatus in which the object is captured by the image of the camera as described above and the information of its shape, size and position angle is obtained by the image processing, one pixel is on the object such as a table. It is possible to highly accurately calibrate the actual number of mm, and the number of times the camera is tilted with respect to the reference coordinate axis before measuring the object.

[0032]

As described above, according to the present invention,
It can be manufactured at low cost, and the correspondence between pixels and objects can be easily calibrated.

[Brief description of drawings]

FIG. 1 is a perspective view showing an example of an image recognition apparatus having a preferred embodiment of a calibration jig of the image recognition apparatus of the present invention.

FIG. 2 is a perspective view showing an example in which the image recognition device of FIG. 1 is used for an electronic component device.

3 is a side view having a partial cross section showing the calibration jig of FIG. 1. FIG.

FIG. 4 is a plan view of the calibration jig shown in FIG.

FIG. 5 is a view showing a state of reflected light from a mark body of the calibration jig shown in FIGS. 3 and 4;

FIG. 6 is a side view showing a state of reflected light from a mark body.

FIG. 7 is a diagram showing a state in which the coordinates of the first point are captured by a camera.

FIG. 8 is a diagram showing a state in which the coordinates of a second point are captured by a camera.

FIG. 9 is a diagram showing a state in which the coordinates of a third point are captured by a camera.

FIG. 10 is a diagram showing an example of image processing when the coordinates of the first to third points are captured.

FIG. 11 is a diagram showing a relationship among a table coordinate system, a camera coordinate system, and a camera coordinate system (unit pixels).

12 is a diagram illustrating each element of FIG. 11. FIG.

FIG. 13 is a diagram showing a relationship between a vector Xi and a vector R.

FIG. 14 is a vector Xi1 to X of coordinates of first to third points.
The figure which shows i3 and vector R.

FIG. 15 is a diagram showing a relationship of coordinates of first to third points.

FIG. 16 is a diagram showing a coordinate conversion matrix.

FIG. 17 is a diagram showing how arbitrary pixel coordinates on the camera are obtained from the coordinate transformation matrix and the origin coordinates of the camera.

FIG. 18 is a perspective view showing an example of a conventional image recognition device.

FIG. 19 is a plan view showing an example of a mark body used in the conventional image recognition apparatus of FIG.

FIG. 20 is a side view of the mark in FIG.

FIG. 21 is a plan view of another conventional mark.

22 is a side view of the mark in FIG. 21. FIG.

FIG. 23 is a diagram showing the blurring of the contour of a conventional mark.

[Explanation of symbols]

11 ... Camera, 12 ... Ring light (illuminating means), 20 ... Table moving means, 21 ... Table (object), 50 ... Calibration jig, 51 ... Positioning member 52 ... ..Mark bodies, 56 ... Recesses

Claims (6)

[Claims] 1. A calibration tool used in an image recognition apparatus for recognizing an object, and used when calibrating by comparing a positional relationship between coordinates when an object is moved and coordinates of an image obtained by an image capturing apparatus. A calibrating jig for an image recognition device, comprising: a positioning member having a recess; and a substantially spherical mark body held in the recess of the positioning member. 2. The image according to claim 1, wherein the mark body has a metallic luster, a peripheral portion of the positioning member that defines the concave portion is white, and substantially the central portion of the mark body reflects light when viewed from the projection plane. Calibration jig for the recognition device. 3. The positioning member is attached to a moving means for holding and moving an object, the size of the recess is smaller than the diameter of the mark body, and the center of the mark body coincides with the central axis of the positioning means. The calibration jig for an image recognition device according to claim 2. 4. A calibration method for use in an image recognition apparatus for recognizing an object, for calibrating by comparing the positional relationship between coordinates when an object is moved and coordinates of an image obtained by the image recognition apparatus. Hold the positioning member on the object, and hold the almost spherical mark body in the recess of the positioning member,
Align the center of the substantially spherical mark with the center axis of the recess of the positioning member, and based on the reflected light of the mark, the coordinates of the moving direction of the object and the position of the coordinates of the image obtained by the image recognition device. A calibration method for an image recognition device, characterized in that the relationship is calibrated. 5. The calibration method for an image recognition device according to claim 4, wherein the focus of the image pickup device is aligned with the maximum outer diameter portion of the mark body, and the concave portion of the positioning member is hidden by the maximum outer diameter portion of the mark body. 6. The calibration method for an image recognition apparatus according to claim 5, wherein the surface of the mark body that is the back shadow is the white surface of the positioning member.