Image processing apparatus and machine tool

Abstract

An image processing apparatus includes a photographing execution section that photographs a first partial image containing a part of a tool by a camera, a position determination section that determines a next photographing position based on a partial shape of the tool contained in the first partial image, and a position control section that changes a relative position of the tool and the camera to the determined photographing position. The photographing execution section photographs a second partial image containing a part of the tool at the next photographing position.

Description

Technical Field

[0001] This invention relates to a technique for managing the shape of tools in machine tools. Background Technology

[0002] Machine tools include devices for cutting workpieces into desired shapes and devices for manufacturing workpieces by stacking metal powders. Among cutting machine tools, there are rotation centers that machine workpieces by bringing a cutting tool into contact with a rotating workpiece, machining centers that machine workpieces by bringing a rotating cutting tool into contact with a workpiece, and composite machining centers that combine these functions.

[0003] The tool is fixed to a tool holder such as a spindle or tool post. The machine tool, according to a pre-prepared machining program, moves the tool post or similar device to select the tool to contact the workpiece while machining the workpiece.

[0004] When moving tool holders and other equipment in three dimensions within a confined machining room, control is essential to prevent the tool from contacting the workpiece itself, the tailstock supporting the workpiece, and vibration damping devices. Because tools come in a wide variety of shapes and sizes, there are situations where other tools may make contact even at positions where one tool would not. Therefore, when registering tools in a machine tool, it is necessary to establish a correspondence between the tool ID and the tool shape (for example, see Patent Document 1).

[0005] Existing technical documents

[0006] Patent documents

[0007] Patent Document 1: Japanese Patent Application Publication No. 2016-218550 Summary of the Invention

[0008] The technical problem that the invention aims to solve

[0009] In most cases, tool shape data is downloaded from the tool manufacturer's website and input into the machine tool to establish a correspondence between the tool ID and the tool shape. However, this registration method is computationally intensive, and the verification process to prevent input errors is also very demanding.

[0010] Methods for solving technical problems

[0011] An image processing apparatus according to one aspect of the present invention includes: a shooting execution unit that captures a first partial image including a portion of a tool using a camera; a position determination unit that determines a next shooting position based on a partial shape of the tool included in the first partial image; and a position control unit that changes the relative position of the tool and the camera to the determined shooting position.

[0012] The shooting unit then takes a second partial image containing a portion of the tool at the next shooting position.

[0013] Another aspect of the image processing apparatus of the present invention includes: a receiving unit that receives (1) a first partial image containing a portion of a tool captured by a camera, and (2) a second partial image containing a portion of a tool captured by changing the relative position of the tool and the camera to the determined shooting position based on the partial shape of the tool contained in the first partial image; and an image processing unit that extracts first contour data of a portion of the tool from the first partial image and extracts second contour data of a portion of the tool from the second partial image, and generates tool shape data of the tool based on the first contour data and the second contour data.

[0014] One aspect of the machine tool of the present invention includes: a camera; a tool holding unit capable of mounting a tool; a machining control unit for machining a workpiece using the tool according to a machining program; an image capturing unit for capturing a first partial image including a portion of the tool using the camera; a position determining unit for determining a next shooting position based on the partial shape of the tool included in the first partial image; and a position control unit for changing the relative position of the tool and the camera to the next shooting position.

[0015] The shooting unit then takes a second partial image containing a portion of the tool at the next shooting position.

[0016] Invention Effects

[0017] According to the present invention, tool shape image recognition can be performed easily and effectively. Attached Figure Description

[0018] Figure 1 This is an external view of the machine tool.

[0019] Figure 2 This is a schematic diagram showing the positional relationship between the tools, camera, and lighting device in the tool recognition area.

[0020] Figure 3 It is a hardware structure diagram of the machine tool and image processing device.

[0021] Figure 4 This is a functional block diagram of an image processing device.

[0022] Figure 5 This is a schematic diagram showing the positional relationship between the tool and the shooting area.

[0023] Figure 6 This is a schematic diagram illustrating the relationship between the tool and the local image.

[0024] Figure 7 This is a flowchart illustrating the process of tool registration.

[0025] Figure 8 It is shown Figure 7 The flowchart of shape recognition processing in S12.

[0026] Figure 9 This shows a partial image during shape recognition processing.

[0027] Figure 10 This is a diagram showing the image of the first edge point.

[0028] Figure 11 This shows a partial image during the execution direction determination process.

[0029] Figure 12 This is a diagram showing the image of the second edge point.

[0030] Figure 13 It is a diagram showing the tool shape data of the tool.

[0031] Figure 14 This is a schematic diagram showing a partial image of the front end of the detection tool in Modified Example 1.

[0032] Figure 15 This is a schematic diagram showing a partial image after the tool has been moved in Variation Example 1.

[0033] Figure 16 This is a first schematic diagram showing the position control method when a second edge point is detected in the third region in Modified Example 2.

[0034] Figure 17 This is a second schematic diagram illustrating the position control method when a second edge point is detected in the third region in Modified Example 2.

[0035] Figure 18 This is a first schematic diagram illustrating the position control method when a second edge point is detected in the sixth region in Modified Example 2.

[0036] Figure 19 This is a second schematic diagram illustrating the position control method when a second edge point is detected in the sixth region in Modified Example 2. Detailed Implementation

[0037] Figure 1 This is an external view of machine tool 100.

[0038] The machine tool 100 in this embodiment is a multi-functional machining center for processing workpieces disposed within the processing area 200. The workpiece is fixed to a holding portion 104 and is cut by a tool 102 mounted on a spindle of another holding portion. The holding portion 104 holding the workpiece is rotated by a drive mechanism.

[0039] When tool 102 is inserted into tool recognition area 210, the lower lighting device 108 illuminates tool 102, and the upper camera 106 takes a picture of tool 102. Tool shape recognition, described later, is performed based on the image taken at this time. Regarding the structure of tool recognition area 210, refer to the following... Figure 2 To elaborate further.

[0040] The machine tool 100 has a cover 202 that shields the exterior. The cover 202 has a door 204. The user opens the door 204 to install workpieces into and remove workpieces from the machining area 200. The control panel 206 receives various operations for the machine tool 100 from the user.

[0041] The operation panel 206 is connected to the image processing device 110. In this embodiment, the machine tool 100 body and the image processing device 110 are connected via a wired cable. The image processing device 110 may also be formed inside the machine tool 100, for example, as an internal device of the operation panel 206.

[0042] The tool storage unit 130 stores multiple tools 102. A tool 102 is retrieved from the multiple tools 102 stored in the tool storage unit 130 via a tool exchange (described later) and mounted onto the spindle. Furthermore, as... Figure 1 As shown, the X and Y axes are set in the horizontal direction, and the Z axis is set in the vertical direction. The Y-axis direction corresponds to the axis direction of the spindle and the workpiece.

[0043] Figure 2 This is a schematic diagram showing the positional relationship of the tool 102, camera 106 and lighting device 108 in the tool recognition area 210.

[0044] The tool 102 includes a cutting edge 112 used in machining the workpiece and a shank 114 which is a portion of a support 118 fixed to the spindle 116. The spindle 116 holds the tool 102 and is configured to rotate and move. Furthermore, the spindle 116, which also serves as a holding portion, can rotate the held tool.

[0045] Camera 106 includes an image sensor (imaging element) such as CMOS (Complementary Metal Oxide Semiconductor) or CCD (Charge-Coupled Device). Camera 106 captures images of tool 102 mounted on spindle 116 from above (Z-axis direction). Camera 106 is fixed to tool recognition area 210. Spindle 116 can capture images of tool 102 from multiple directions by rotating tool 102 about the Y-axis. Furthermore, spindle 116 can capture images of tool 102 at multiple positions by moving tool 102 in the horizontal direction (XY direction).

[0046] A lighting device 108 is fixed at the bottom opposite to the camera 106. The lighting device 108 illuminates the tool 102 from below. Through the through-illumination based on the lighting device 108, the camera 106 can easily grasp the outline of the tool 102 and obtain a high-contrast image.

[0047] When registering a new tool 102, the user sets the operation panel 206 to tool registration mode and mounts the tool 102 onto the spindle 116. Then, any tool ID is entered. The spindle 116 moves and rotates the tool 102, and the fixed camera 106 automatically captures images of the tool 102 from various positions and directions. From the multiple images captured by the camera 106, the tool shape is identified, and the tool ID and tool shape are registered accordingly. This control method allows for automatic registration of tool shapes. Details of the tool shape recognition method will be described later.

[0048] The camera 106 in this embodiment has a resolution of approximately 1 megapixel (1224×1024). The shooting range is approximately 300 mm × 300 mm. Furthermore, the camera 106 can acquire a maximum of 80 images per second.

[0049] Figure 3 This is a hardware structure diagram of the machine tool 100 and the image processing device 110.

[0050] The machine tool 100 includes an operation control unit 120, a machining control unit 122, a machining device 124, a tool exchange unit 126, and a tool storage unit 130. The machining control unit 122, functioning as a numerical control unit, sends control signals to the machining device 124 according to the machining program. The machining device 124 moves its spindle 116 to machine the workpiece based on instructions from the machining control unit 122.

[0051] The operation control device 120 includes an operation panel 206 that controls the machining control unit 122. The tool storage unit 130 stores tools. The tool exchange unit 126 corresponds to a so-called ATC (Automatic Tool Changer). Based on exchange instructions from the machining control unit 122, the tool exchange unit 126 retrieves a tool from the tool storage unit 130 and exchanges the tool located on the spindle 116 with the retrieved tool.

[0052] The image processing apparatus 110 mainly performs image processing such as tool shape recognition. As described above, the image processing apparatus 110 may also be configured as part of the operation control apparatus 120.

[0053] Figure 4This is a functional block diagram of the image processing device 110.

[0054] The components of the image processing apparatus 110 are implemented through hardware including an arithmetic logic unit (ALU) such as a CPU (Central Processing Unit) and various computer processors, a storage device such as a memory or storage device, wired or wireless communication lines connecting them, and software stored in the storage device that supplies processing commands to the ALU. Computer programs may also consist of device drivers, operating systems, various application programs located at their upper layers, or libraries that provide common functions to these programs. The blocks described below are not structures of hardware units, but rather blocks representing functional units.

[0055] In addition, the operation control device 120 and the processing control unit 122 may be a storage device including an arithmetic unit such as a processor, a memory or storage device, wired or wireless communication lines connecting them, or software or programs that provide processing commands to the arithmetic unit stored in the storage device and implemented on a separate operating system from the image processing device 110.

[0056] The image processing apparatus 110 includes a user interface processing unit 140, a data processing unit 142, and a data storage unit 144.

[0057] In addition to receiving user input, the user interface processing unit 140 is responsible for user interface-related processing such as image display and sound output. The data processing unit 142 performs various processes based on data acquired by the user interface processing unit 140 and data stored in the data storage unit 144. The data processing unit 142 also functions as the interface between the user interface processing unit 140 and the data storage unit 144. The data storage unit 144 stores various programs and settings data.

[0058] The user interface processing unit 140 includes an input unit 146 and an output unit 148.

[0059] The input unit 146 receives input from the user via hardware such as a touch panel or a gamepad. The output unit 148 provides various information to the user via image display or sound output. The input unit 146 includes an ID receiving unit 150 that receives tool ID input.

[0060] The data processing unit 142 includes a shooting execution unit 152, a position determination unit 154, a position control unit 156, a shape reproduction unit 158, a first edge detection unit 160, a second edge detection unit 162, an image conversion unit 164, a tool registration unit 166, and a movable adjustment unit 168.

[0061] The imaging execution unit 152 instructs the camera 106 to acquire an image. The position determination unit 154 calculates the movement direction of the spindle 116 during the imaging of the tool 102 using a method described later. The position control unit 156 moves the spindle 116 during the imaging of the tool 102. The shape reproduction unit 158 ​​generates data representing the three-dimensional shape of the tool 102, i.e., "tool shape data," based on the captured image. The first edge detection unit 160 detects a "first edge point" representing the contour position of the tool 102. The second edge detection unit 162 also detects a "second edge point" representing the contour position of the tool 102. The image conversion unit 164 changes the resolution of the captured image.

[0062] The tool registration unit 166 registers the tool ID and tool shape data in the data storage unit 144. The tool ID and tool shape data can also be provided from the image processing device 110 to the operation control device 120. The movable adjustment unit 168, a so-called interference detection module, determines the movable range (range of movement) of the spindle 116 based on the type of machine tool 100, the shape of the workpiece, and the tool shape data of the tool 102 in use. Depending on the shape and size of the tool 102, the position where the spindle 116 interferes with the workpiece or other objects varies. The movable adjustment unit 168 determines the movable range of the spindle 116 accordingly to the tool in use based on the tool shape data. The machine tool 100 moves the spindle 116 within its movable range.

[0063] Figure 5 This is a schematic diagram showing the positional relationship between tool 102 and shooting area 170.

[0064] The shooting area 170 is located directly below the light-receiving surface of the camera 106. The camera 106 photographs objects within the shooting area 170. The position control unit 156 inserts the tool 102 into the shooting area 170 by moving the main spindle 116. Because the shooting area 170 is smaller than the tool 102, the entire tool 102 cannot be photographed at once.

[0065] Increasing the lens of the camera 106 to increase the shooting area 170 would increase the cost of the camera 106. Furthermore, if a large camera 106 is used in the tool recognition area 210, the space in the processing area 200 would be compressed, which is undesirable. Therefore, in this embodiment, the method employed is to take multiple shots of the tool 102 using a relatively small camera 106, and to recognize the overall shape of the tool 102 based on the multiple captured images.

[0066] If the number of times the tool 102 moves and the number of images acquired increases, time will be spent on the tool shape recognition processing (hereinafter referred to as "shape recognition processing"). In order for shape recognition processing to be effective, the tool 102 needs to be moved effectively in a way that does not acquire images that are not needed in terms of recognizing the tool shape, specifically, images that do not reflect the outline of the tool 102 are not acquired.

[0067] Hereinafter, the image captured by the camera 106 and the photographing tool 102 will be referred to as a "partial image".

[0068] Figure 6 This is a schematic diagram illustrating the relationship between tool 102 and the local image.

[0069] When registering the tool, the position control unit 156 moves the tool 102 (spindle 116) at a certain speed in the negative Y-axis direction, that is, in the direction away from the front end of the tool 102 from the shooting area 170. The shooting execution unit 152 constantly monitors the shooting area 170. The live view image in the shooting area 170 is transmitted from the camera 106 to the image processing device 110. When the shooting execution unit 152 detects the front end of the blade 112 in the shooting area 170 (live view image), it instructs the camera 106 to acquire a shooting image (partial image). Upon receiving the instruction, the camera 106 acquires the first partial image and stores it in memory. Figure 6 First, the local image P1 is acquired.

[0070] Next, the position control unit 156 further moves the tool 102 (spindle 116) in the negative Y-axis direction. At this time, the position control unit 156 moves the spindle 116 slightly in the negative X-axis direction so that the outline of the tool 102 does not detach from the shooting area 170 (details will be described later). After the movement, the shooting execution unit 152 instructs the camera 106 to acquire a partial image, and the camera 106 saves the second partial image P2 in its memory. Thus, the position control unit 156 moves the spindle 116 moderately to the left and right (X direction) and moves the spindle 116 little by little in the negative Y-axis direction.

[0071] The imaging execution unit 152, in coordination with the movement of the main axis 116, instructs the camera 106 to capture (acquire local images), acquiring local images P1 to P8. Based on the multiple local images P1 to P8, the shape reproduction unit 158 ​​generates the outline of the tool 102, that is, generates tool shape data of the tool 102. By appropriately moving the main axis 116, the number of times local images are acquired can be reduced, and image recognition of the outline of the tool 102 can be appropriately performed.

[0072] Figure 7 This is a flowchart illustrating the process of tool registration.

[0073] Tool registration is performed after the user inputs a tool ID. When the user inputs the tool ID, the position control unit 156 sets the rotation angle of the spindle 116 (e.g., 0 degrees) after mounting the tool 102 to be registered on the spindle 116 (S10). Hereinafter, the rotation angle of the spindle 116 will be referred to as the "spindle rotation angle". In this embodiment, shape recognition processing is performed for a total of 30 angles (=360÷12) by rotating the tool 102 in 12-degree increments.

[0074] After setting the spindle rotation angle, the position control unit 156 moves the spindle 116 in the XY direction, and the image capture execution unit 152 performs shape recognition processing (S12) by acquiring multiple local images. Details of the shape recognition processing will be provided below. Figure 8 As described later. In the shape recognition process, the contour of tool 102 is determined as dot matrix data at the set spindle rotation angle. If there is an unset spindle rotation angle (N in S14), the process returns to S10, and the next rotation angle is set (e.g., 12 degrees). When shape recognition processing is performed for all 30 spindle rotation angles (Y in S14), the shape reproduction unit 158 ​​generates tool shape data representing the three-dimensional shape of tool 102 based on the dot matrix data obtained for multiple spindle rotation angles (S16). The tool registration unit 166 registers the tool ID and tool shape data in the data storage unit 144 in a corresponding manner (S18).

[0075] Figure 8 It is shown Figure 7 The flowchart of shape recognition processing in S12.

[0076] After setting the spindle rotation angle, the position control unit 156 moves the spindle 116 in the negative Y-axis direction, and the image capture execution unit 152 captures a partial image (S20). The first edge detection unit 160 detects the first edge points of the outline of the representation tool 102 from the partial image (in conjunction with...). Figure 9 (As described below), the shape position in the partial image of the identification tool 102 is identified (S22). Next, the position determination unit 154 determines the next shooting position based on the partial image of the tool 102, in other words, determines the movement direction of the main axis 116 (S24). The method for determining the movement direction will be discussed in conjunction with... Figure 11 This will be discussed later.

[0077] When it is necessary to capture the next partial image (S26, N), the position control unit 156 moves the tool 102 (spindle 116) in the movement direction determined in S24 (S28). When the spindle 116 has moved a predetermined distance in the negative Y-axis direction, the image capture is completed (S26, Y), and processing is moved to... Figure 7 S14.

[0078] As described above, the shape recognition process includes S22, which performs image recognition on the contour of the tool 102 (hereinafter referred to as "shape recognition process"), and S24, which determines the next moving direction of the tool 102 (hereinafter referred to as "direction determination process"). Next, the shape recognition process and the direction determination process will be described.

[0079] Figure 9 A partial image 290 is shown during the shape recognition process. Figure 10 This is a diagram showing the first edge point image 190.

[0080] In partial image 290, the silhouette of tool 102 projected from below by illumination device 108 is shown. First edge detection unit 160 sets a scan line 180a in the positive X-axis direction and detects points located at the boundary between dark region 182 (the silhouette area where tool 102 exists) and bright region 184 (the area where tool 102 does not exist) as first edge points 192. First edge detection unit 160 detects multiple first edge points 192 while shifting scan line 180a at certain intervals.

[0081] Similarly, the first edge detection unit 160 sets a scan line 180b in the negative Y-axis direction and detects first edge points 192 located at the boundary between the dark region 182 and the bright region 184. The first edge detection unit 160 detects multiple first edge points 192 while shifting the scan line 180b at certain intervals.

[0082] Furthermore, the first edge detection unit 160 sets a scan line 180c in the positive Y-axis direction and detects first edge points 192 located at the boundary between the dark region 182 and the bright region 184. The first edge detection unit 160 detects multiple first edge points 192 while shifting the scan line 180c at certain intervals.

[0083] In this way, by setting scan lines 180a, 180b, and 180c from three directions, multiple first edge points 192 are detected, and the data is obtained. Figure 10 The first edge point image 190 is shown. Dot matrix data representing the contour of the tool 102 is obtained from the plurality of first edge points 192 contained in the first edge point image 190. In this embodiment, the processing time required for shape recognition processing of each local image is approximately 200-250 milliseconds.

[0084] Figure 11 A partial image 290 is shown during the execution direction determination process. Figure 12 This is a diagram showing the second edge point image 260.

[0085] During orientation determination processing, the image conversion unit 164 sets the resolution of the local image 290 to one-eighth lower. Lowering the resolution reduces the number of pixels being processed, thus reducing the workload and increasing the speed of orientation determination processing. While high-resolution local image 290 is preferred for shape recognition processing to identify the shape of tool 102, using a low-resolution local image 290 is appropriate as long as the orientation determination processing can determine the next shooting position.

[0086] A reference point 250 is set at a predetermined position in the local image 290. In this embodiment, the reference point 250 is set at the center of the local image. Furthermore, an arbitrary reference line 252 is set passing through the reference point 250. In this embodiment, the reference line 252 is set in the first quadrant of the XY plane with the reference point 250 as the origin.

[0087] The second edge detection unit 162 sets a scan line 254a in the positive X-axis direction and detects points located at the boundary between the dark region 182 and the bright region 184 as second edge points 194. The second edge detection unit 162 detects multiple second edge points 194 while shifting the scan line 254a at regular intervals. Similarly, the second edge detection unit 162 sets a scan line 254b in the negative X-axis direction and detects points located at the boundary between the dark region 182 and the bright region 184 as second edge points 194. The second edge detection unit 162 detects multiple second edge points 194 while shifting the scan line 254b at regular intervals.

[0088] The second edge detection unit 162 sets a scan line 254c in the negative Y-axis direction, and detects multiple second edge points 194 while shifting the scan line 254c at certain intervals. The second edge detection unit 162 sets a scan line 254d in the positive Y-axis direction, and detects multiple second edge points 194 while shifting the scan line 254d at certain intervals.

[0089] In this way, by setting scan lines 254a, 254b, 254c, and 254d from four directions to detect multiple second edge points 194, the following can be obtained: Figure 12 The second edge point image 260 is shown. To reduce the resolution of the local image, the number of second edge points 194 is less than the number of first edge points 192.

[0090] Next, the position determination unit 154 sets a verification line 262 connecting the reference point 250 and the second edge point 194. The position determination unit 154 calculates the angle formed by the verification line 262 and the reference line 252 (hereinafter referred to as the "edge angle"), and determines the second edge point 194A with the smallest edge angle as the "selected second edge point". In the second edge point image 260, when the second edge point 194A is selected, the edge angle is the smallest. The position determination unit 154 determines the next shooting position based on the verification line 262A at this time.

[0091] like Figure 12 As shown, the second edge point 194A (selected second edge point) selected by the positioning unit 154 based on the edge angle is set on the side farther from the front end of the tool 102. In other words, viewed from the reference point 250 set in the second edge point image 260, it is set on the base end side of the tool 102. Next, the positioning unit 154 moves from the second edge point 194A along the tool length direction of the tool 102 (…). Figure 12 The position determination unit 154 determines the next shooting position by moving the lower half of the tool 102 (the front end side of the tool 102) up and down (upper: the base end side of the tool 102, lower: the front end side of the tool 102) in the Y-axis direction. Furthermore, the position determination unit 154 moves from the second edge point 194A towards the tool diameter direction of the tool 102. Figure 12 The way the camera moves along the central side (in the X-axis direction) determines the position of the next shot. Figure 12 In the image 260, the second edge point 194A (selected second edge point) is located on the positive Y-axis direction side (upper side) and the negative X-axis direction side (left side). Therefore, the position determination unit 154 moves the tool 102 along the movement vector 264 (negative Y-axis direction and positive X-axis direction), and changes the relative position of the shooting area 170 and the tool 102 by moving the second edge point 194A (selected second edge point) downward and centrally.

[0092] That is, the positioning unit 154 causes the tool 102 (spindle 116) to move along the verification line 262A. Figure 12The tool 102 moves in the direction indicated by the movement vector 264. At this time, the Y component (insertion direction) of the movement vector 264 of the tool 102 can be set to a constant. That is, the position control unit 156 adjusts the magnitude of the X component of the movement vector 264 of the tool 102 based on the magnitude of the minimum edge angle. When the tool 102 moves in the direction of the movement vector 264, in the next local image 290, the second edge point 194A (the point representing the contour line) moves towards the center. With this control method, control can be achieved in a way that the contour line of the tool 102 does not detach in the shooting area 170; in other words, control can be achieved in a way that local images without the contour line are not captured. In this embodiment, the processing time required for determining the direction of each local image is approximately 10 to 20 milliseconds.

[0093] Figure 13 This is a diagram showing the tool shape data of tool 102.

[0094] The position control unit 156 sets the spindle rotation angle centered on the Y-axis of the tool 102, then moves the tool 102 in the negative Y-axis direction and moves it in the X-axis direction according to the edge angle. A partial image 290 is acquired in the imaging area 170, and a first edge point 192 is detected from the partial image 290, thereby determining the shape of the tool 102. After detecting the first edge point 192, a second edge point 194 is detected to adjust the next imaging position. Multiple partial images are acquired for each spindle rotation angle. Next, the position control unit 156 rotates the tool 102 by 12 degrees and performs the same process for the next spindle rotation angle.

[0095] If 10 local images 290 are acquired for each principal axis rotation angle, then a total of 300 local images 290 can be obtained based on 30 principal axis rotation angle settings. The dot matrix data shown in the first edge point image 190 is obtained from these local images 290. The shape reproduction unit 158 ​​generates a shape by integrating the dot matrix data of each local image 290. Figure 13 The tool shape data shown is, that is, the bitmap data that generates the three-dimensional shape of tool 102.

[0096] [Summary]

[0097] The above description pertains to the image processing apparatus 110 and the machine tool 100 based on the embodiments.

[0098] According to this embodiment, the user mounts the tool 102 onto the spindle 116, inputs the tool ID, and automatically generates tool shape data, then registers the tool ID and tool shape data in a corresponding manner. Dozens of tools 102 are registered in the tool storage unit 130. Therefore, the automation of tool shape data registration significantly improves the operating efficiency of the machine tool 100.

[0099] In this embodiment, a small camera 106 is used to photograph only a portion of the tool 102. Using a small camera 106 reduces the cost of the camera 106 and also helps save space in the processing area 200. By performing direction determination processing on the second edge point image 260, the number of times the local image 290 is acquired can be reduced while appropriately identifying the shape of the tool 102. The local image 290, which is not needed for shape confirmation of the tool 102, is an image that does not reflect the outline of the tool 102. The position determination unit 154 controls the local image to always capture the shape of the tool 102 by adjusting the amount of movement of the camera 106 in the X-axis direction according to the edge angle.

[0100] Furthermore, by reducing the resolution of the local image used in the orientation determination process compared to the local image used in the shape recognition process, the orientation determination process is accelerated. By recognizing the shape of the tool 102 using a high-resolution local image and determining the movement direction of the tool 102 using a low-resolution local image, a balance between image recognition accuracy and speed is achieved.

[0101] Furthermore, the present invention is not limited to the above-described embodiments or modifications, and the constituent elements can be modified and embodied without departing from the spirit of the invention. Various inventions can be formed by appropriately combining the multiple constituent elements disclosed in the above-described embodiments or modifications. In addition, several constituent elements may be deleted from all the constituent elements shown in the above-described embodiments or modifications.

[0102] [Variation Example]

[0103] The shape reproduction unit 158 ​​generates tool shape data in the form of bitmap data (see reference). Figure 13 The situation was explained. The shape reproduction unit 158 ​​can also generate tool shape data in a polygonal manner by attaching textures to the bit data.

[0104] In this embodiment, the case where the camera 106 is fixed and the tool 102 (spindle 116) is moved has been described. As a variation, the tool 102 (spindle 116) may also be fixed and the camera 106 moved. Alternatively, both the camera 106 and the tool 102 (spindle 116) may be moved. In any case, a partial image can be acquired while the relative positions of the camera 106 and the tool 102 change.

[0105] In this embodiment, the case where orientation determination processing is performed after shape recognition processing is described. As a variation, shape recognition processing and orientation determination processing can also be performed in parallel.

[0106] In this embodiment, the case where the first edge point 192 is detected for shape recognition of the tool 102, and the second edge point 194 is detected for direction control of the tool 102 (spindle 116) is described. As a variation, the position determination unit 154 may also determine the moving direction of the tool 102 by calculating the verification line 262 and the edge angle based on the first edge point 192.

[0107] The image processing apparatus 110 may also be configured to include a receiving unit and an image processing unit. The receiving unit of the image processing apparatus machine tool 100 receives a first partial image containing a portion of the tool 102 from the camera 106. Similarly, it receives a second partial image containing another portion of the tool 102 from the camera 106. That is, the camera 106 or the image processing apparatus equipped with the camera 106 may be configured to have the functions of an image execution unit 152, a position determination unit 154, a position control unit 156, a second edge detection unit 162, and an image conversion unit 164. The image processing unit of the image processing apparatus 110 has the functions of a shape reproduction unit 158 ​​and a first edge detection unit 160.

[0108] The image processing unit of the image processing apparatus 110 acquires a first partial image from the camera 106, etc. (e.g., Figure 6 A partial image P1) and a second partial image corresponding to its next shooting position (e.g., Figure 6 The same applies to subsequent local images (local image P3). The image processing unit extracts first contour data representing the contour of tool 102 from the first local image and extracts second contour data representing the contour of tool 102 from the second local image. The method for extracting contour data and its combination... Figure 11 , Figure 12 The method described is the same. Furthermore, the image processing unit can also reproduce the tool contour data of tool 102 based on the contour data (point group) obtained from multiple local images.

[0109] In this embodiment, the process of setting the spindle rotation angle to a predetermined angle and then sequentially photographing the tool 102 from the front end to the base end, followed by changing the spindle rotation angle after the photographing is completed, is described. However, this is not a limitation; the tool 102 can also be rotated while the camera 106 continuously photographs the tool 102. For example, the rotation timing of the spindle 116 can be synchronized with the photographing timing of the camera 106 by gradually rotating the tool 102 at a predetermined angle every t seconds and photographing the tool 102 by the camera 106 every t seconds, thereby rotating the camera 106 and photographing the camera 106 from multiple angles. Alternatively, when the camera 106 rotates once at a predetermined position, the camera 106 can be moved horizontally in the XY direction to photograph other positions of the camera 106 from multiple angles.

[0110] The camera 106 can also take pictures of the tool 102 at certain time intervals. At this time, the camera 106 can send a synchronization signal to the image processing device 110 in coordination with the shooting timing. The image processing device 110 can control the timing of the movement or rotation of the tool 102 in coordination with the synchronization signal.

[0111] The possibility that the shooting timing of camera 106 may not be perfectly synchronized with the rotation timing of the spindle rotation angle is also considered. Camera 106 can send a synchronization signal to machining control unit 122 and image processing device 110 at the shooting timing, and image processing device 110 measures the spindle rotation angle of spindle 116 when the synchronization signal is received. For example, the tool 102 is photographed by camera 106 at a timing when the spindle rotation angle is set to 36 degrees. However, the rotation of spindle 116 may not be completely finished, for example, the shooting may be performed when the spindle rotation angle is 35.99 degrees. Therefore, machining control unit 122 measures the actual spindle rotation angle at the shooting timing, and shooting execution unit 152 can save the partial image corresponding to the actual spindle rotation angle. According to such a control method, the actual spindle rotation angle of the partial image (the captured image) can be recorded correctly, thus making it easier to accurately reproduce the tool contour data.

[0112] The image processing apparatus 110 performs the following steps: capturing a partial image of a portion of the tool 102 using the camera 106; determining the next shooting position based on the shape of the portion of the tool 102 contained in the partial image; and changing the relative position of the tool 102 and the camera 106 to the determined shooting position; and may further perform the step of capturing a partial image of a portion of the tool 102 at the next shooting position.

[0113] The various computers exemplified by the image processing apparatus 110 can execute computer programs that perform the following functions: capturing a partial image of a portion of the tool 102 by the camera 106; determining the next shooting position based on the shape of the portion of the tool 102 contained in the partial image; changing the relative position of the tool 102 and the camera 106 to the determined shooting position; and capturing a partial image of a portion of the tool 102 at the next shooting position.

[0114] Figure 14 This is a schematic diagram showing a partial image when the tool tip is detected in Modified Example 1.

[0115] In partial image 290 (capture area 170), the position determining unit 154 determines the front end of tool 102 (hereinafter referred to as the "tool tip"). The center of partial image 290 is reference point 250. Within partial image 290, in... Figure 14In Chinese, the lower side of the paper (the side with the positive Y-axis) is called the "lower side," and the upper side of the paper (the side with the negative Y-axis) is called the "upper side."

[0116] The direction in which tool 102 extends is called the "tool length direction", and the radial direction (short side direction) of tool 102 is called the "tool radial direction". The line passing through the Y-axis direction of reference point 250 is called the "center line 292". In addition, in the tool radial direction, the direction close to the center line 292 is called the "center side", and the direction away from the center line 292 is called the "end side".

[0117] When the local image 290 is divided into four equal parts with reference point 250 as the center, the upper right region is called the first region C1, the upper left region is called the second region C2, the lower left region is called the third region C3, and the lower right region is called the fourth region C4.

[0118] Through combination Figure 11 , Figure 12 Using the same method described, the position determination unit 154 determines a plurality of second edge points 194. In Modification 2, the position determination unit 154 selects the second edge point 194 that is farthest from the reference point 250. Figure 14 In the middle, the second edge point 194 farthest from the reference point 250 is the second edge point 194B and the second edge point 194C. The position determination unit 154 selects the second edge point 194, which is located on the first region C1 or the center line 292, from among the second edge points 194B and 194C. Figure 14 In the first region C1, the second edge point 194B is selected. The position control unit 156 instructs the machining control unit 122 on the movement direction of the tool 102 in such a way that the selected second edge point 194B (selected second edge point) coincides with the reference point 250.

[0119] Figure 15 This is a schematic diagram showing a partial image after the tool has been moved in Variation Example 1.

[0120] As the tool 102 moves, the second edge point 194B aligns with the reference point 250. The position control unit 156 then selects the second edge point 194E, which is furthest from the reference point 250. However, the second edge point 194E does not satisfy the condition of being "on the first region C1 or the center line 292". At this time, the position control unit 156 selects the second edge point 194D, which is the second furthest from the second edge point 194E. The second edge point 194D is on the center line 292, thus satisfying the above condition. At this time, the position control unit 156 instructs the machining control unit 122 to move in a manner in which the second edge point 194D (selected second edge point) coincides with the reference point 250. In Modification 1, by repeating this control, multiple local images 290 are acquired from the tool 102.

[0121] Figure 16 This is a first schematic diagram showing the position control method when a second edge point is detected in the third region in Modified Example 2.

[0122] In variation example 2, local image 290 is as follows: Figure 16 The area is divided into six parts, from the first region D1 to the sixth region D6. Here, the second edge point 194F (the second edge point 194 furthest from the reference point 250) is detected in the third region D3 in the upper left.

[0123] Figure 17 This is a second schematic diagram illustrating the position control method when a second edge point is detected in the third region in Modified Example 2.

[0124] In Modification 2, the position control unit 156 instructs the machining control unit 122 on the direction of movement of the tool 102, with the second edge point 194F included in the fifth region D5. For example... Figure 17 As shown, when the second edge point 194E is detected in the third region D3, the tool 102 moves in both the Y direction (tool length direction) and the X direction (tool diameter direction).

[0125] Figure 18 This is a first schematic diagram illustrating the position control method when a second edge point is detected in the sixth region in Modified Example 2.

[0126] Here, in the sixth region D6 in the lower left, the second edge point 194G (the second edge point 194 furthest from the reference point 250) was detected.

[0127] Figure 19 This is a second schematic diagram illustrating the position control method when a second edge point is detected in the sixth region in Modified Example 2.

[0128] and Figure 16 , Figure 17 Similarly, the position control unit 156 instructs the machining control unit 122 on the direction of movement of the tool 102, with the second edge point 194G included in the fifth region D5. For example... Figure 19 As shown, when the second edge point 194G is detected in the sixth region D6, the tool 102 moves in the X direction (tool radial direction).

[0129] Thus, the location determination unit 154 detects multiple second edge points 194 and selects the second edge point 194 located in the upper half of the local image 290 (shooting area 170) (first region D1 to third region D3). Figures 17 to 19The text describes selecting the second edge point 194 that is furthest from the reference point 250, but it can also be any second edge point 194 located in the upper half. The position control unit 156 instructs the machining control unit 122 on the direction of movement of the tool 102 so that the selected second edge point 194 is located in the middle region (fifth region D4) that divides the lower half into three parts.

Claims

1. An image processing apparatus, comprising: The second edge detection unit detects a plurality of second edge points representing the shape and position of the tool in a first local image containing a portion of the tool. The movement determination unit selects a second edge point located farther from the front end of the tool from a subset of the plurality of second edge points to determine the next shooting position. The selected second edge point is positioned in the lower half of the tool's length direction and at the center of the tool's diameter direction in the first partial image. The unit then determines the direction of movement of the relative position of the camera and the tool. The position control unit changes the relative position of the tool and the camera according to the direction of movement; The camera captures a second partial image at the next shooting position, which includes the selected second edge point and a portion of the tool.

2. The image processing apparatus according to claim 1, The second edge point with the smallest relative angle between the specified baseline extending from the specified reference point in the first local image and the verification line connecting the reference point and the second edge point is selected as the second edge point. The direction of movement of the relative position of the camera and the tool is determined as the direction in which the selected second edge point approaches the reference point.

3. The image processing apparatus according to claim 1, further comprising: The ID receiving unit receives the tool ID used to identify the tool; The first edge detection unit detects a plurality of first edge points in the first local image that represent the shape and position of the tool; The shape reproduction unit forms tool shape data representing the shape of the tool based on multiple first edge points detected from multiple first local images; as well as The tool registration department establishes a corresponding registration system for tool IDs and tool shape data.

4. An image processing apparatus, comprising: The second edge detection unit detects a plurality of second edge points representing the shape and position of the tool in a first local image containing a portion of the tool. The position determination unit selects the second edge point as the smallest relative angle between the second edge points and the verification line connecting the reference point and the second edge point, based on a predetermined baseline extending from a predetermined reference point in the first partial image. It then determines the direction of movement of the relative position of the camera and the tool as the direction in which the selected second edge point approaches the reference point. The position control unit changes the relative position of the tool and the camera according to the direction of movement; The camera captures a second partial image at the next shooting position, which includes the selected second edge point and a portion of the tool.

5. The image processing apparatus according to claim 1 or 4, When the camera moves relative to the tool, the shooting execution unit detects the front end of the tool within the shooting range and captures an initial partial image of the tool.

6. The image processing apparatus according to claim 1 or 4, The position control unit also changes the relative angle between the tool and the camera. The filming team took partial videos from various relative angles.

7. The image processing apparatus according to claim 1 or 4, further comprising: The first edge detection unit detects a plurality of first edge points in the first local image that represent the shape and position of the tool; as well as The shape reproduction unit forms tool shape data representing the shape of the tool based on a plurality of first edge points detected from the first local image.

8. The image processing apparatus according to claim 7, It also includes an image conversion unit that converts the first local image into a low-resolution image. The second edge detection unit detects second edge points from the low-resolution first local image.

Images