Three-dimensional measuring device and three-dimensional measuring method

Abstract

The distance range used to calculate grayscale is appropriately set according to the height of the workpiece. A three-dimensional measurement device includes: a three-dimensional sensor that images the workpiece to acquire three-dimensional information; a setting unit that sets a reference position serving as a reference for the height direction of the workpiece based on the acquired three-dimensional information, and sets a height margin for the grayscale in a grayscale image based on the reference position, thereby setting a distance range corresponding to the grayscale in the grayscale image; an image conversion unit that converts the acquired three-dimensional information into the grayscale image based on the distance range; and a detection unit that uses the grayscale image to three-dimensionally determine the shape and / or position of the workpiece.

Description

Technical Field

[0001] The present invention relates to a three-dimensional measuring device and a three-dimensional measuring method. Background Art

[0002] By capturing images of a workpiece using a 3D sensor such as a stereo camera and acquiring 3D information, the workpiece's shape and position can be determined three-dimensionally. However, object recognition based on 3D information suffers from high computational complexity and time-consuming processing. For example, when detecting a workpiece based on a pre-taught model representing its 3D shape, comparing the 3D information with the model takes significantly longer than processing 2D information.

[0003] In this regard, a technique is known in which a distance value calculated based on acquired three-dimensional information is converted into a shading value and a detection process is performed based on the obtained shading image.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Laid-Open No. 2012-021909 Summary of the Invention

[0007] Problems to be solved by the invention

[0008] In a shading image, which uses distance values ​​calculated based on 3D information acquired by a 3D sensor, the shading values ​​vary depending on the height of the workpiece. For example, in a shading image with 256 grayscale values, the distances corresponding to the shading value "0" (representing black) and the shading value "255" (representing white) are predetermined based on the distance from a plane perpendicular to the optical axis of the 3D sensor. Within this range, the shading values ​​vary depending on the distance. Therefore, depending on the size of the workpiece, the distance range may be exceeded.

[0009] Figure 10 This figure shows an example of a shading image of a workpiece having a size within a range of distance based on a three-dimensional sensor, and a histogram with the horizontal axis representing shading values ​​and the vertical axis representing the number of pixels. Figure 11 This is a diagram showing an example of a shading image of a workpiece whose size does not fit within the range of the distance based on the three-dimensional sensor, and a histogram with the horizontal axis being the shading value and the vertical axis being the number of pixels. Figure 10 and Figure 11 In the example, the white density value is set to "255" at a distance H1 from the three-dimensional sensor, and the black density value is set to "0" at a distance H2. Figure 10In FIG, a workpiece having a semicircular groove in the Y-axis direction is shown. Figure 11 In the middle, it means that Figure 10 The workpiece has the same semicircular groove and has a ratio Figure 10 The higher the workpiece is, the higher the Z-axis height of the workpiece is.

[0010] like Figure 10 As shown, since the height of the workpiece falls within the range of the distance H1 and the distance H2 , a shaded image reflecting the shape of the workpiece can be obtained. Figure 10 The right side of represents a histogram of gradation values ​​in the workpiece region after removing background portions (eg, a region where the workpiece is placed) having gradation values ​​of “1” or less in the gradation image.

[0011] On the other hand, Figure 11 As shown in FIG, since the upper surface of the workpiece extends further toward the 3D sensor than the distance H1, a shading image with a whitened area larger than the upper surface of the workpiece can be obtained. Therefore, the obtained shading image does not accurately reflect the shape of the workpiece. In addition, Figure 11 In the histogram on the right, the number of pixels with a gradation value of "255" increases due to whitening.

[0012] As described above, even on the same workpiece surface, the histogram varies significantly depending on the height of the workpiece, making it impossible to directly compare with the histogram of the pre-taught model, and processing may become complicated.

[0013] Therefore, it is desirable to appropriately set the distance range for calculating grayscale according to the height of the workpiece.

[0014] Means for solving problems

[0015] (1) One embodiment of the three-dimensional measuring device disclosed herein comprises: a three-dimensional sensor that captures a workpiece to obtain three-dimensional information; a setting unit that sets a reference position serving as a reference for the height direction of the workpiece based on the acquired three-dimensional information, and sets a margin in the height direction of the grayscale in a grayscale image based on the reference position, thereby setting a distance range corresponding to the grayscale of the grayscale image; an image conversion unit that converts the acquired three-dimensional information into the grayscale image based on the distance range; and a detection unit that uses the grayscale image to three-dimensionally determine the shape and / or position posture of the workpiece.

[0016] (2) One mode of the three-dimensional measurement method disclosed herein is to obtain three-dimensional information by photographing a workpiece using a three-dimensional sensor, set a reference position serving as a reference for the height direction of the workpiece based on the obtained three-dimensional information, set a margin in the height direction of the grayscale in a grayscale image based on the reference position, set a distance range corresponding to the grayscale of the grayscale image, convert the obtained three-dimensional information into the grayscale image based on the distance range, and use the grayscale image to three-dimensionally determine the shape and / or position posture of the workpiece.

[0017] Effects of the Invention

[0018] According to one embodiment, the distance range for grayscale calculation can be appropriately set according to the height of the workpiece. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a block diagram showing a configuration example of a three-dimensional measuring device according to one embodiment.

[0020] Figure 2 This is a diagram showing an example of a reference position and a distance range.

[0021] Figure 3 This is a diagram showing an example of the relationship among a workpiece, a distance range, and shading values.

[0022] Figure 4A This is a diagram showing an example of a shaded image of a workpiece.

[0023] Figure 4B This is a diagram showing an example of a shaded image of a workpiece.

[0024] Figure 5 This is a diagram showing an example of a histogram of a grayscale image.

[0025] Figure 6 This is a diagram showing an example of a grayscale image and a histogram when the back side of the workpiece is arranged as the upper surface.

[0026] Figure 7 This is a flowchart illustrating measurement processing by the three-dimensional measuring device.

[0027] Figure 8A This figure shows an example of two-dimensional images of six workpieces captured by a three-dimensional sensor.

[0028] Figure 8B This is a diagram showing an example of a shaded image of a workpiece.

[0029] Figure 9A This is a diagram showing an example of a histogram of a grayscale image on the front side of a workpiece.

[0030] Figure 9BThis is a diagram showing an example of a histogram of a grayscale image on the back side of a workpiece.

[0031] Figure 10 This figure shows an example of a shading image of a workpiece having a size within a range of distance based on a three-dimensional sensor, and a histogram with the horizontal axis representing shading values ​​and the vertical axis representing the number of pixels.

[0032] Figure 11 This figure shows an example of a shading image of a workpiece whose size does not fit within the range of the distance based on the three-dimensional sensor, and a histogram with the horizontal axis representing shading values ​​and the vertical axis representing the number of pixels. DETAILED DESCRIPTION

[0033] The following describes an embodiment of the present invention in detail using the accompanying drawings. Here, a black and white image is used as an example of a grayscale image. The present invention is not limited to black and white images and can also be applied to grayscale images of any of red, green, and blue, for example.

[0034] Figure 1 This is a block diagram showing a configuration example of a three-dimensional measuring device according to one embodiment.

[0035] like Figure 1 As shown, the three-dimensional measuring device 10 includes a three-dimensional sensor 101 , a workpiece detection unit 102 , a setting unit 103 , an image conversion unit 104 , and a detection unit 105 .

[0036] like Figure 1 As shown, the three-dimensional sensor 101 captures the workpiece 20 and the mounting surface 30 on which the workpiece 20 is placed, and obtains three-dimensional information in which the distances between the plane perpendicular to the optical axis of the three-dimensional sensor 101 and each point on the surface of the workpiece 20 and the mounting surface 30 are set as pixel values. Figure 1 As shown in FIG. 1 , the pixel value of point A on workpiece 20 in the three-dimensional information is the distance D between the three-dimensional sensor 101 and point A on workpiece 20 in the Z-axis direction of the three-dimensional coordinate system (X, Y, Z) of the three-dimensional sensor 101. The Z-axis direction of the three-dimensional coordinate system corresponds to the optical axis direction of the three-dimensional sensor 101. In the following description, distance refers to the distance in the Z-axis direction of the three-dimensional coordinate system (X, Y, Z) of the three-dimensional sensor 101.

[0037] In addition, the three-dimensional sensor 101 may acquire a two-dimensional image such as an RGB image together with the three-dimensional information.

[0038] The workpiece 20 is an object to be detected. The mounting surface 30 is, for example, a surface of a workbench on which the workpiece 20 is mounted. Figure 1 As shown, the workpiece 20 is arranged on the optical axis of the three-dimensional sensor 101. Here, the workpiece 20 is exemplified as a rectangular parallelepiped having a semicircular groove in the Y-axis direction.

[0039] As the three-dimensional sensor 101, for example, a stereo camera that measures the distance to the workpiece 20 to be inspected by matching images from two cameras, or a stereo camera that measures the distance to the workpiece 20 to be inspected by matching an image of a pattern projected from a projector with an image from a camera. Alternatively, the three-dimensional sensor 101 may be a stereo camera that measures the distance to the workpiece 20 to be inspected by matching images from two cameras under the condition that a pattern is projected from a projector.

[0040] The workpiece detection unit 102 detects the position of the workpiece 20 by performing pattern matching, for example, based on the two-dimensional image obtained by the three-dimensional sensor 101 and a two-dimensional model representing the shape of the workpiece 20 pre-stored in a storage unit (not shown) such as an HDD (Hard Disk Drive) included in the three-dimensional measuring device 10.

[0041] In addition, the workpiece detection unit 102 can also detect the position of the workpiece 20 by, for example, pattern matching based on the three-dimensional information obtained by the three-dimensional sensor 101 and three-dimensional information representing the shape of the workpiece 20 pre-stored in the storage unit (not shown) of the three-dimensional measuring device 10.

[0042] The setting unit 103 sets a reference position serving as a reference in the height direction (Z-axis direction) of the workpiece 20 based on the three-dimensional information obtained by the three-dimensional sensor 101 and the position of the workpiece 20 detected by the workpiece detection unit 102, and sets a predetermined distance range including the reference position in the Z-axis direction.

[0043] Specifically, the setting unit 103 sets, for example, the point closest to the three-dimensional sensor 101 among the distances in the Z-axis direction of each point on the surface of the workpiece 20 in the three-dimensional information as a reference position serving as a reference in the Z-axis direction. Figure 1 In the case of , since each point on the upper surface of the workpiece 20 is closest to the three-dimensional sensor 101, the setting unit 103 sets, for example, point A included in the upper surface as the reference position. Figure 2 As shown, the setting unit 103 sets a margin D1 in the Z-axis direction on the side of the three-dimensional sensor 101, which serves as a white reference for the grayscale image converted from the three-dimensional information by the image conversion unit 104 described later, and sets a margin D2 in the Z-axis direction on the opposite side of the three-dimensional sensor 101, which serves as a black reference, based on the set reference position. In other words, Figure 3 As shown, the setting unit 103 sets the gradation values ​​from “255” to “0” within the distance range from the distance (D-D1) to the distance (D+D2) including the reference position in the Z-axis direction.

[0044] The image conversion unit 104 converts the image into a shaded image using the distance values ​​of each surface point of the workpiece 20 in the three-dimensional information as the shade values ​​based on the shade values ​​in the distance range from (D-D1) to (D+D2) set by the setting unit 103.

[0045] Specifically, for example Figure 4A As shown, the image conversion unit 104 is based on Figure 3 The lightness value set in this way will have the same Figure 10 The three-dimensional information of the workpiece 20 of the same shape is converted into a 256-grayscale shading image.

[0046] Thus, even if the workpiece 20 has Figure 11 In the case of the same shape, such as Figure 4B As shown, the setting unit 103 can also appropriately set the grayscale within the distance range of (D'-D1) and (D'+D2) according to the height of the workpiece 20. Thus, the image conversion unit 104 can convert the three-dimensional information into a grayscale image without whitening.

[0047] In addition, D' is the distance in the Z-axis direction between the three-dimensional sensor 101 and the point A' of the workpiece 20. Figure 4B The distance D' is greater than Figure 4A The distance D is short, so Figure 4A compared to, Figure 4B The workpiece 20 in the shaded image is captured by the three-dimensional sensor 101 to appear larger.

[0048] The detection unit 105 performs image processing on the converted grayscale image to obtain the shape and / or position and posture of the workpiece 20 in three dimensions.

[0049] Specifically, the detection unit 105 generates a histogram with the horizontal axis representing the gradation value and the vertical axis representing the number of pixels, using the gradation value of the region corresponding to the workpiece 20 in the converted gradation image, for example.

[0050] Figure 5 Yes Figure 4A An example of a histogram of a grayscale image is shown in FIG. Figure 5 , a histogram of the gradation values ​​in the workpiece 20 is shown after removing the background of the mounting surface 30 having a gradation value of “1” or less.

[0051] like Figure 5 As shown, the histogram is Figure 3 As shown in FIG. 1 , since the area R1 of the upper surface of the workpiece 20 is large, the number of pixels with a gradation value of 160 to 165 is the largest. In the histogram, the area of ​​the area R3 corresponding to the bottom portion of the semicircular groove is the second largest, so the number of pixels with a gradation value of 85 to 120 is the second largest. On the other hand, as shown in FIG. Figure 3As shown, the area of ​​region R2 corresponding to the side surface of the semicircular groove is the smallest, and therefore the number of pixels with gradation values ​​of 120 to 160 is the smallest.

[0052] The detection unit 105 generates Figure 5 The histogram is compared with a model of a histogram representing the light and dark of the front and back sides of the workpiece 20, which is pre-stored in the storage unit (not shown) of the three-dimensional measuring device 10, to determine whether the upper surface of the workpiece 20 arranged on the loading surface 30 is the front side or the back side, and to detect the orientation of the workpiece 20.

[0053] Figure 6 : is a diagram showing an example of a grayscale image and a histogram when the back side of the workpiece 20 is arranged as the upper surface. Figure 6 The left side of represents the positional relationship between the reference position set on the upper surface of the workpiece 20 and the margins D1 and D2. Figure 6 The center of represents the shaded image of the back side of the workpiece 20. Figure 6 The right side of shows a histogram in which the horizontal axis of the back side of the workpiece 20 is set to the shading value and the vertical axis is set to the number of pixels. Figure 6 The histogram of Figure 5 , which is the same as the case of , indicates the gradation value in the workpiece 20 after removing the background of the mounting surface 30 having a gradation value of “1” or less.

[0054] like Figure 6 As shown in the center of the image, the dark and light image indicates that the back side of the workpiece 20 is a flat surface, so the image has few unevenness and a constant dark and light image. Figure 6 As shown on the right side of FIG, the histogram on the back side of the workpiece 20 is distributed with only pixels having a gradation value α.

[0055] Therefore, if Figure 4A (or Figure 4B )and Figure 6 As shown, since the shapes of the histograms differ greatly between the front side and the back side of the workpiece 20 , the three-dimensional measuring apparatus 10 can determine whether the workpiece 20 on the placement surface 30 is on the front side or the back side based on the histogram.

[0056] In order to achieve Figure 1The three-dimensional measuring device 10 shown includes functional blocks other than the three-dimensional sensor 101. The three-dimensional measuring device 10 can be configured as a computer equipped with a CPU (Central Processing Unit) or other arithmetic processing unit. Furthermore, the three-dimensional measuring device 10 includes auxiliary storage devices such as an HDD for storing various control programs, including application software and an OS (Operating System), and main storage devices such as RAM (Random Access Memory) for temporarily storing data required by the arithmetic processing unit while executing these programs.

[0057] Furthermore, in the three-dimensional measuring device 10, the processing unit reads application software or an operating system from the auxiliary storage device, expands the read application software or OS on the main storage device, and performs processing based on the application software or OS. Furthermore, based on the results of these calculations, the processing unit controls the various hardware components of the three-dimensional measuring device 10. This implements the functional blocks of this embodiment. In other words, this embodiment can be implemented through the collaboration of hardware and software.

[0058] <Measurement Processing by Three-Dimensional Measuring Device 10>

[0059] Next, operations related to the measurement process of the three-dimensional measuring device 10 according to this embodiment will be described.

[0060] Figure 7 1 is a flowchart illustrating the measurement process of the three-dimensional measuring device 10 .

[0061] In step S11, the three-dimensional sensor 101 images the workpiece 20 and the mounting surface 30 on which the workpiece 20 is placed, obtaining three-dimensional information, in which the distances between the three-dimensional sensor 101 and each point on the surface of the workpiece 20 and the mounting surface 30 are expressed as pixel values, and a two-dimensional image, such as an RGB image. The three-dimensional sensor 101 outputs the two-dimensional image to the workpiece detection unit 102 and the three-dimensional information to the setting unit 103.

[0062] In step S12 , the workpiece detection unit 102 detects the position of the workpiece 20 by pattern matching or the like based on the two-dimensional image acquired in step S11 and a two-dimensional model of the workpiece 20 stored in advance in a storage unit (not shown) of the three-dimensional measuring device 10 .

[0063] In step S13, the setting unit 103 sets a reference position and margins D1 and D2 serving as a reference in the Z-axis direction of the workpiece 20 based on the three-dimensional information obtained in step S11 and the position of the workpiece 20 detected in step S12, and sets a distance range corresponding to the shading value of the shading image.

[0064] In step S14 , the image conversion unit 104 converts the three-dimensional information into a grayscale image based on the distance range set in step S13 .

[0065] In step S15 , the detection unit 105 generates a histogram with the horizontal axis representing the gradation value and the vertical axis representing the number of pixels, using the gradation value of the gradation image converted in step S14 .

[0066] In step S16, the detection unit 105 compares the histogram generated in step S15 with a model of the histogram of the light and dark values ​​on the front side and the back side of the workpiece 20 pre-stored in the storage unit (not shown) of the three-dimensional measuring device 10, determines whether the upper surface of the workpiece 20 arranged on the mounting surface 30 is the front side or the back side, and detects the orientation of the workpiece 20.

[0067] As described above, a three-dimensional measuring device 10 according to one embodiment acquires three-dimensional information including the distance in the Z-axis direction to each point on the surface of a workpiece 20 captured by a three-dimensional sensor 101. Based on the acquired three-dimensional information, the three-dimensional measuring device 10 sets a reference position D, which serves as a reference in the Z-axis direction, on the workpiece 20, as well as margins D1 and D2, and sets a distance range corresponding to the shading values ​​of the shading image. This allows the three-dimensional measuring device 10 to appropriately set the distance range used for grayscale calculation based on the height of the workpiece 20, and to generate a shading image without whitening, using the distance values ​​of the three-dimensional information as shading values. Furthermore, the shading values ​​in the shading image do not change significantly even if the height of the workpiece 20 changes. Therefore, the three-dimensional measuring device 10 can use shading values, such as a histogram, to determine whether the workpiece 20 is facing the front or back side, making it easier to detect the orientation of the workpiece 20.

[0068] In addition, based on the detection results, the three-dimensional measuring device 10 can confirm whether there are objects of a height around the workpiece 20 that may collide when the workpiece 20 is taken out by the robot, for example, when the position (height) of the workpiece 20 grasped on the front and back sides changes.

[0069] Although one embodiment has been described above, the three-dimensional measuring device 10 is not limited to the above embodiment, and includes modifications and improvements within a range that can achieve the purpose.

[0070] <Variation 1>

[0071] In the above embodiment, the three-dimensional measuring device 10 sets margins D1 and D2 along with a reference position serving as a reference in the Z-axis direction of the workpiece 20. However, this is not limiting. For example, the reference position is set to the point closest to the three-dimensional sensor 101 among the distances between points on the surface of the workpiece 20 in the three-dimensional information. Therefore, the three-dimensional measuring device 10 may set only margin D2. In other words, the three-dimensional measuring device 10 may set gradation values ​​from "255" to "0" within the distance range from distance D to distance (D + D2).

[0072] <Variation 2>

[0073] Furthermore, for example, in the above embodiment, the three-dimensional measuring device 10 uses a histogram to determine whether the workpiece 20 is facing the front or back, thereby detecting the orientation of the workpiece 20. However, this is not limiting. For example, the three-dimensional measuring device 10 may pre-store models of each posture of the workpiece 20 in the shading image in a storage unit (not shown), and perform shape comparison (matching) between the converted shading image and the stored models of each posture to determine the three-dimensional position and posture of the workpiece 20.

[0074] Figure 8A 1 is a diagram showing an example of a two-dimensional image of six workpieces 20a(1) to 20a(6) captured by the three-dimensional sensor 101. Figure 8A In the figure, the front side of the workpieces 20a(1), 20a(3), and 20a(5) is the upper surface, and the back side of the workpieces 20a(2), 20a(4), and 20a(6) is the upper surface.

[0075] Figure 8B express Figure 8A Light and dark images of workpieces 20a(1)-20a(6).

[0076] The three-dimensional measuring device 10 is based on Figure 8B Template matching is performed on the edges of the shaded image, and the position and posture (XYZWPR) of each workpiece 20a(1)-20a(6) can be detected on the shaded image.

[0077] In addition, the three-dimensional measuring device 10 can also use the template matching after the template matching. Figure 9A as well as Figure 9B The histogram shown is used to determine the front and back of each workpiece 20a(1)-20a(6), thereby obtaining a more accurate three-dimensional position and posture of the workpiece 20.

[0078] Figure 9A This is a diagram showing an example of a histogram of a grayscale image on the front side of the workpiece 20a (1). Figure 9B : is a diagram showing an example of a histogram of a shading image on the back side of the workpiece 20a(2). Figure 9A as well as Figure 9B The histogram excludes backgrounds with gradation values ​​of "1" or less (ie, the placement surface 30). The number of pixels in the histogram is normalized to "1" by taking the number of pixels with the highest gradation value.

[0079] In addition, the histogram of the front side of the workpiece 20a(3) and 20a(5) is also the same as Figure 9A The histogram of the workpiece 20a(1) is the same as that of the workpiece 20a(4) and 20a(6). Figure 9B The histogram of workpiece 20a(2) is the same.

[0080] Here, it is possible to detect the posture including the orientation only by using the grayscale image, but it requires comparison processing including the change of rotation around the Z axis (R direction), which takes processing time. Figure 9A as well as Figure 9B As shown, the same histogram can be obtained even when the workpiece changes in the R direction. Therefore, the three-dimensional measuring device 10 can obtain a more accurate three-dimensional position and posture of the workpiece 20 in a short time by using the histogram after performing template matching as described above.

[0081] <Variation 3>

[0082] In addition, for example, in the above-described embodiment, the grayscale image is a black and white image, but the present invention is not limited thereto. For example, the grayscale image may be a grayscale image using any color of red, green, or blue.

[0083] In addition, each function included in the three-dimensional measuring device 10 in one embodiment can be realized by hardware, software, or a combination thereof. Here, realization by software means realization by having a computer read a program and execute it.

[0084] The program can be stored using various types of non-transitory computer-readable media and provided to the computer. Non-transitory computer-readable media include various types of tangible recording media (Tangible storage medium). Examples of non-transitory computer-readable media include magnetic recording media (e.g., floppy disks, magnetic tapes, hard disk drives), optical magnetic recording media (e.g., optical magnetic disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, RAMs). In addition, the program can also be provided to the computer via various types of transient computer-readable media (Transitory computer readable media). Examples of transient computer-readable media include electric signals, optical signals, and electromagnetic waves. Transient computer-readable media can provide the program to the computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths.

[0085] Furthermore, the steps describing the program recorded in the recording medium include not only processes that are performed in time series according to the order thereof but also processes that are not necessarily performed in time series but are executed in parallel or individually.

[0086] In other words, the three-dimensional measuring device and the three-dimensional measuring method of the present disclosure can take various embodiments having the following structures.

[0087] (1) The three-dimensional measuring device 10 disclosed in the present invention comprises: a three-dimensional sensor 101 that images a workpiece 20 to obtain three-dimensional information; a setting unit 103 that sets a reference position D serving as a reference for the height direction of the workpiece 20 based on the obtained three-dimensional information, and sets margins D1 and D2 in the height direction of the grayscale in the grayscale image based on the reference position D, thereby setting a distance range corresponding to the grayscale of the grayscale image; an image conversion unit 104 that converts the obtained three-dimensional information into a grayscale image based on the distance range; and a detection unit 105 that uses the grayscale image to three-dimensionally determine the shape and / or position and posture of the workpiece 20.

[0088] According to the three-dimensional measuring device 10, the distance range for calculating the grayscale can be appropriately set according to the height of the workpiece.

[0089] (2) According to the three-dimensional measuring device 10 described in (1), the detection unit 105 may generate a histogram using the grayscale of the grayscale image and three-dimensionally determine the shape and / or position and posture of the workpiece 20 based on the generated histogram.

[0090] Thus, the three-dimensional measuring device 10 can reduce the amount of calculation compared to the case of using grayscale images.

[0091] (3) In the three-dimensional measuring device 10 described in (1) or (2), the shape of the workpiece 20 may be the front surface or the back surface of the workpiece 20 .

[0092] Thus, when the robot takes out the workpiece 20 , the three-dimensional measuring device 10 can check whether there is an object around the workpiece 20 that is high enough to cause a collision.

[0093] (4) The three-dimensional measurement method disclosed in the present invention obtains three-dimensional information by photographing the workpiece 20 with a three-dimensional sensor 101, sets a reference position D serving as a reference for the height direction of the workpiece 20 based on the obtained three-dimensional information, and sets margins D1 and D2 for the height direction of the grayscale in the grayscale image based on the reference position D to set a distance range corresponding to the grayscale of the grayscale image, converts the obtained three-dimensional information into a grayscale image based on the distance range, and uses the grayscale image to three-dimensionally determine the shape and / or position posture of the workpiece 20.

[0094] According to this three-dimensional measurement method, the same effect as (1) can be achieved.

[0095] (5) According to the three-dimensional measurement method described in (4), a histogram may be generated using the grayscale of the grayscale image, and the shape and / or position and posture of the workpiece 20 may be three-dimensionally determined based on the generated histogram.

[0096] Therefore, the three-dimensional measurement method can achieve the same effect as (2).

[0097] (6) In the three-dimensional measurement method described in (4) or (5), the shape of the workpiece 20 may be the front surface or the back surface of the workpiece 20 .

[0098] Therefore, the three-dimensional measurement method can achieve the same effect as (3).

[0099] Description of Reference Signs

[0100] 10. Three-dimensional measuring device,

[0101] 20 workpieces,

[0102] 30 loading surface,

[0103] 101 3D sensor,

[0104] 102 Workpiece detection department,

[0105] 103 Setting Department,

[0106] 104 image conversion unit,

[0107] 105 Detection Department.

Claims

1. A three-dimensional measuring device, characterized in that: The three-dimensional measuring device has: A three-dimensional sensor that photographs the workpiece to obtain three-dimensional information; a setting unit that sets, based on the acquired three-dimensional information, a point of the workpiece that is closest to the three-dimensional sensor as a reference position serving as a reference in a height direction, sets a first margin in the height direction toward the three-dimensional sensor of grayscale in a grayscale image with the reference position as a reference, sets a second margin in the height direction away from the three-dimensional sensor with the reference position as a reference, and sets a distance range from the first margin to the second margin corresponding to the grayscale in the grayscale image; an image conversion unit, configured to convert the acquired three-dimensional information into the grayscale image according to the distance range; as well as A detection unit is configured to obtain a three-dimensional shape and / or position and posture of the workpiece using the grayscale image.

2. The three-dimensional measuring device according to claim 1, wherein: The detection unit generates a histogram using the grayscale of the grayscale image, and three-dimensionally obtains the shape and / or position and posture of the workpiece based on the generated histogram.

3. The three-dimensional measuring device according to claim 1 or 2, characterized in that: The shape of the workpiece is the front side or the back side of the workpiece.

4. A three-dimensional measurement method, characterized in that: Use a 3D sensor to capture the workpiece to obtain 3D information. Based on the acquired three-dimensional information, a point of the workpiece that is closest to the three-dimensional sensor is set as a reference position serving as a reference in the height direction; a first margin in the height direction of the grayscale in the grayscale image toward the three-dimensional sensor is set based on the reference position; and a second margin in the height direction away from the three-dimensional sensor is set based on the reference position; and a distance range from the first margin to the second margin is set corresponding to the grayscale of the grayscale image. According to the distance range, the obtained three-dimensional information is converted into the grayscale image, The grayscale image is used to three-dimensionally determine the shape and / or position and posture of the workpiece.

5. The three-dimensional measurement method according to claim 4, characterized in that: generating a histogram using the grayscale of the grayscale image, Based on the generated histogram, the shape and / or position and posture of the workpiece are three-dimensionally determined.

6. The three-dimensional measurement method according to claim 4 or 5, characterized in that: The shape of the workpiece is the front side or the back side of the workpiece.

Images