Control device and detection system

Abstract

The control device (20) is provided with: an image acquisition unit (121) that acquires, from a vision sensor, a plurality of images obtained by continuously capturing a workpiece; and an object determination unit (122) that determines, on the basis of the plurality of images, the workpiece in the stationary state as an object of the work performed by the industrial machine.

Description

Technical Field

[0001] The invention relates to a control device and a detection system. Background Art

[0002] There is known a robot system configured to use a robot to take out an object conveyed on a conveying device and arrange it at a predetermined position, or to perform an operation of taking out a bulk object. For example, Patent Document 1 describes the following content regarding a robot-based loading and unloading system: "In the second and subsequent picking processes, the control device 30 performs a differential check to detect an object W whose change amount between a new RGB image 40b obtained from the camera 20 after the start of the previous selection process and an RGB image 40a used in the previous recognition process is less than a threshold value, performs a selection process to select an object W to be moved next from the objects W whose change amount is less than the threshold value, and then performs a moving process." (Paragraph 0148).

[0003] Patent document 2 describes the structure of a robot-based storage device as follows: "The camera 29 photographs the object 21 continuously transported on the conveyor 23, and identifies the position and posture of the object through image processing. In addition, the conveying distance is detected by an encoder provided on the conveyor 23. Based on the identified position and posture of the object and the detected conveying distance, the movement data of the robot is generated, the posture of the robot is changed, and the object is grasped and stored in the storage body 49." (Abstract).

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2021-146404

[0007] Patent Document 2: Japanese Patent Application Publication No. 2001-277165 Summary of the invention

[0008] Problems to be solved by the invention

[0009] In a robot-based bulk take-out system, or a take-out system that uses a visual sensor to detect workpieces that flow in a scattered manner on a conveyor and take them out, some workpieces that are to be taken out, such as tablets of medicine, require time to stabilize their position and posture after being introduced into a container or a conveyor. In a take-out system that targets such workpieces, if the robot performs an action to take out the workpiece before the position and posture are stabilized, it will become a major cause of the failure of the take-out and the generation of useless time.

[0010] Means for solving problems

[0011] One aspect of the present disclosure is a control device including: an image acquisition unit that acquires a plurality of images obtained by continuously photographing a workpiece from a visual sensor; and an object determination unit that determines a stationary workpiece as an object of a work performed by an industrial machine based on the plurality of images.

[0012] Another embodiment of the present disclosure is a detection system comprising: a visual sensor; an image acquisition unit that acquires a plurality of images of a workpiece continuously photographed by the visual sensor from the visual sensor; and an object determination unit that determines a workpiece in a stationary state as an object of an operation to be performed by an industrial machine based on the plurality of images.

[0013] Effects of the Invention

[0014] According to the above configuration, a workpiece in a stationary state can be taken out, thereby reducing the possibility of taking out failure and shortening the cycle time of the operation of the industrial machine.

[0015] These and other objects, features and advantages of the present invention will become more apparent from the detailed description of typical embodiments of the present invention as shown in the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a diagram showing the equipment configuration of a detection system according to one embodiment.

[0017] Figure 2 This is a diagram showing a hardware configuration example of a vision sensor control device, a robot control device, and a teaching pendant.

[0018] Figure 3 This is a functional block diagram related to the vision sensor control device and the robot control device.

[0019] Figure 4 This is a diagram for explaining the image processing in which the object determination unit of the first embodiment determines a workpiece in a stationary state as a removal object.

[0020] Figure 5 This is a diagram for explaining the image processing in which the object determination unit of the first embodiment determines a workpiece in a stationary state as a removal object.

[0021] Figure 6 This is a flowchart showing the operation of determining the extraction target according to the first embodiment.

[0022] Figure 7 This is a diagram for explaining the image processing in which the object determination unit of the second embodiment determines a workpiece in a stationary state as a removal object.

[0023] Figure 8This is a flowchart showing the operation of determining the extraction target according to the second embodiment.

[0024] Fig. 9 This is a diagram showing an example of a UI screen provided by the setting unit. DETAILED DESCRIPTION

[0025] Next, the embodiments of the present disclosure are described with reference to the accompanying drawings. In the referenced drawings, the same structural parts or functional parts are marked with the same reference symbols. For easy understanding, the scales of these drawings are appropriately changed. In addition, the method shown in the drawings is an example for implementing the present invention, and the present invention is not limited to the method shown in the drawings.

[0026] Figure 1 FIG. 1 is a diagram showing the device configuration of a detection system 100 according to an embodiment. The detection system 100 is configured as a robot system that detects a workpiece using a visual sensor 70 and performs processing on the workpiece. Figure 1 As shown, the inspection system 100 includes: a robot 30, a robot control device 50 for controlling the robot 30, a teaching operation panel 10 connected to the robot control device 50, a visual sensor 70, and a visual sensor control device 20 for controlling the visual sensor 70. The visual sensor control device 20 is connected to the robot control device 50. In addition, a peripheral device 80 is arranged in the inspection system 100. The peripheral device 80 is, for example, a container for placing a workpiece, a conveying device for conveying a workpiece, and the like.

[0027] Here, the robot 30 is described as an example of a vertical multi-joint robot, but various types of robots such as a parallel link robot and a dual-arm robot can be used as the robot 30 depending on the work object. The robot 30 can perform the desired work through the end effector installed on the wrist. The end effector is an external device that can be replaced according to the purpose, such as a manipulator, a tool, etc. Figure 1 , an example of using a manipulator 33 as an example of an end effector is shown. The manipulator may be a structure that grips an object with a gripping claw, or a structure that adsorbs and holds the object with an adsorption portion. In the detection system 100, the robot 30 uses the manipulator 33 to perform processing on the workpiece. In addition, the processing may include various operations based on the robot, such as picking and placing, storage in containers and containers, and palletizing.

[0028] In this embodiment, the visual sensor 70 is a camera capable of capturing a two-dimensional image, and is fixed at a position in the workspace where the workpiece can be captured. In addition, a three-dimensional sensor capable of obtaining a distance image or a three-dimensional point group may also be used as the visual sensor 70. The visual sensor 70 may also be mounted on the front end of the arm of the robot 30.

[0029] The visual sensor control device 20 has the function of controlling the visual sensor 70 and performing image processing on the image captured by the visual sensor 70. The visual sensor control device 20 has the following functions: retaining model data of the object and performing detection processing to detect the object by pattern matching between the image of the object in the photographic image and the model data.

[0030] exist Figure 1 2 shows an example in which the vision sensor control device 20 is configured as a device separate from the robot control device 50 , but the functions of the vision sensor control device 20 may also be mounted in the robot control device 50 .

[0031] Among the workpieces to be processed by the robot 30, there are some workpieces such as medicine tablets, whose position / posture is not immediately stable after being placed in a container or introduced into a conveyor, but becomes stable after a certain period of time. It is preferable to remove the workpiece when the workpiece is in a stable state. In the detection system 100 of this embodiment, for the workpieces placed in a container or introduced into a conveyor, the workpieces in a stable state are taken out, which can achieve the efficiency of the removal operation.

[0032] Figure 2 1 is a diagram showing an example of the hardware configuration of the visual sensor control device 20, the robot control device 50, and the teaching operation panel 10. Figure 2 As shown, the visual sensor control device 20 may also have a general computer structure connected to the processor 21 via a bus, including a memory 22 (ROM, RAM, non-volatile memory, etc.), a display unit 23, an operation unit 24 including various input devices, an input / output interface 25, etc. The input / output interface 25 may include various input / output interfaces such as a network interface, a serial communication interface, and a memory card interface. The visual sensor control device 20 may be configured as a dedicated device dedicated to the function of the visual sensor control device, or may be configured by a general-purpose computer such as a personal computer.

[0033] The robot control device 50 may also have a general computer structure having a memory 52 (ROM, RAM, nonvolatile memory, etc.), an input / output interface 53, an operation unit 54 including various operation switches, etc. connected to the processor 51 via a bus. The input / output interface 53 may include various input / output interfaces such as a network interface, a serial communication interface, and a memory card interface.

[0034] The teaching operation panel 10 is used as a device for teaching the robot 30, or for inputting operations for making various settings and displaying screens. The teaching operation panel 10 may also have a general computer structure connected to the processor 11 via a bus, such as a memory 12 (ROM, RAM, non-volatile memory, etc.), a display unit 13, an operation unit 14 composed of input devices such as a keyboard (or software keys), and an input / output interface 15. The input / output interface 15 may include various input / output interfaces such as a network interface, a serial communication interface, and a memory card interface. The teaching operation panel 10 may also be composed of an information processing device such as a tablet terminal or a smart phone.

[0035] Figure 3 is a functional block diagram related to the visual sensor control device 20 and the robot control device 50. Figure 3 As shown, the visual sensor control device 20 includes an image acquisition unit 121, an object determination unit 122, and a setting unit 123. The robot control device 50 includes an operation control unit 151 that controls the operation of the robot 30 according to an operation program.

[0036] The image acquisition unit 121 controls the visual sensor 70 to acquire the image captured by the visual sensor 70. In the present embodiment, the image acquisition unit 121 acquires a plurality of images obtained by the visual sensor 70 continuously capturing images of the workpiece.

[0037] The object determination unit 122 extracts a stationary workpiece based on a plurality of images acquired from the visual sensor 70 and determines it as a target for the work to be performed by the robot 30. The object determination unit 122 notifies the robot control device 50 of the workpiece determined as a target for the work to be performed by the robot.

[0038] The setting unit 123 receives input of various settings (for example, parameters for image processing) from the object determination unit 122 for extracting a workpiece in a stationary state.

[0039] Two examples are described below with respect to specific embodiments of the operation in which the object determination unit 122 determines a stationary workpiece as a pick-up object by the robot 30. In these embodiments, the workpiece is a tablet of medicine, and the peripheral device 80 is a container into which the workpiece is placed.

[0040] First embodiment

[0041] Below, refer to Figures 4 to 6 A first embodiment will be described. Figure 4 and Figure 5 This is a diagram for explaining the image processing in which the object determination unit 122 determines a workpiece in a stationary state as a removal object in the first embodiment. Figure 6 This is a flowchart showing the operation of determining the extraction target in the first embodiment. Figure 6 The flowchart of the first embodiment describes the operation of determining the extraction target.

[0042] First, the user sets an operation for removing a moving workpiece as a target of the robot 30's picking operation (ie, setting a stationary workpiece as a pick-up target) (step S1). This setting is accepted via a UI (user interface) screen provided by the setting unit 123, for example.

[0043] Then, if Figure 4 As shown, a workpiece W, which is a tablet of medicine, is put into the peripheral device (container) 80 (step S2). The visual sensor 70 is arranged at a position where it can photograph the workpiece W on the peripheral device (container) 80. The visual sensor 70 continuously photographs the workpiece W. Thus, the first photographing (step S3) and the second photographing (step S4) of the workpiece W are performed. Figure 4 As shown in FIG. 1 , an image obtained by the first shooting is referred to as image M1 , and an image obtained by the second shooting is referred to as image M2 . Seven workpieces W1 to W7 appear in images M1 and M2 , respectively.

[0044] The object determination unit 122 compares the two images M1 and M2 and extracts the area where the pixel value changes between the two images as the area where there is activity on the image (step S5). In this example, the pixel area of ​​the four workpieces W2 to W5 is extracted as the area where there is a change between the two images. The object determination unit 122 adds a predetermined margin to the pixel area of ​​the workpiece where there is activity, and determines the detection non-target area D1 as the area including the four workpieces W2 to W5. The detection non-target area D1 refers to an area that is not the object of the detection process for detecting the workpiece.

[0045] Furthermore, in a situation where the visual sensor 70 is mounted on the robot 30 and the robot 30 photographs the workpiece while moving, before comparing the pixel values ​​of the two images photographed continuously in step S5, as a preprocessing thereof, image conversion (image translation, rotation, etc.) may be performed according to the photographing position of the visual sensor 70 during photographing so that the two images are in a state where the same photographing area is reflected. Furthermore, in a situation where the workpiece is transported on a conveying device and the workpiece transported on the conveying device is photographed by the visual sensor 70 fixed to the workspace, before comparing the pixel values ​​of the two images photographed continuously in step S5, as a preprocessing thereof, image conversion (image translation, rotation, etc.) may be performed according to the conveying speed of the conveying device, etc. so that the two images are in a state where the same area on the conveyor belt is reflected.

[0046] The object determination unit 122 performs a process of excluding the detection non-object area D1 from the image M2, which is the latest image (step S6). Here, the process of excluding the detection non-object area D1 from the image M2 refers to a process for setting the detection non-object area D1 as an invalid pixel in the image M2, or a process for applying a masking process to the pixels included in the detection non-object area D1 in the image M2. In the case of performing the former process, the object determination unit 122 may also perform a detection process on the remaining image area in the state where the detection non-object area is removed from the image M2 (step S7). In this case, the detection non-object area D1 is removed from the object of the detection process, so that the time required for the detection process can be shortened.

[0047] The case of performing the latter operation will be described. Figure 5 Indicates a state in which the detection non-object area D1 is shielded (for example, painted with a background color) in the image M2. The object determination unit 122 performs, for example, a detection process for detecting a workpiece on the image M2 that has been shielded (step S7). In this way, the detection process is applied to the image M2 in a state in which the area including the workpiece accompanied by the activity is shielded, thereby shortening the time required for the detection process. More specifically, the area including the workpiece accompanied by the activity is shielded, thereby not generating a processing load such as calculating a score value (a calculated value of the similarity between the object in the image and the model data) in the detection process for the pixels in the shielded area, thereby shortening the time required for the detection process.

[0048] The workpieces W1, W6, and W7 are determined as the workpieces to be removed by the detection process, and are notified to the robot controller 50. The motion control unit 151 of the robot controller 50 performs the removal operation on the workpieces W1, W6, and W7 notified from the target determination unit 122 (step S8).

[0049] Thus, according to the first embodiment, by excluding the region containing the workpiece accompanied by movement from the image where the workpiece is projected and performing the detection process, the workpiece in a stationary state can be determined as the object to be picked up by the robot 30. That is, the possibility that the robot 30 fails in trying to pick up the workpiece accompanied by movement can be reduced, and the overall cycle time of the picking operation can be shortened. In addition, by excluding the region containing the workpiece accompanied by movement from the image where the workpiece is projected and performing the detection process, the time for the detection process can be shortened, and the overall cycle time of the picking operation can be shortened.

[0050] Second embodiment

[0051] Below, refer to Figure 7 and Figure 8 The second embodiment will be described. Figure 7This is a diagram for explaining the image processing in which the object determination unit 122 of the second embodiment determines a workpiece in a stationary state as a removal object. Figure 8 This is a flowchart showing the operation of determining the extraction target in the second embodiment. Figure 8 The flowchart of the second embodiment is used to illustrate the action of determining the removal object. Figure 8 In the flowchart of FIG. 1 , steps S11 to S14 are the same as steps S1 to S4 in the first embodiment.

[0052] First, the user sets the robot 30 to remove workpieces excluding moving workpieces (ie, to remove workpieces in a stationary state) (step S11 ). This setting is accepted via a UI screen provided by the setting unit 123 , for example.

[0053] Then, if Figure 7 As shown, a workpiece W, which is a tablet of medicine, is put into the peripheral device (container) 80 (step S12). The visual sensor 70 is arranged at a position where it can photograph the workpiece W on the peripheral device (container) 80. The visual sensor 70 continuously photographs the workpiece W. Thus, the first photographing (step S13) and the second photographing (step S14) of the workpiece W are performed. Figure 7 As shown in FIG. 1 , an image obtained by the first shooting is referred to as image M11 , and an image obtained by the second shooting is referred to as image M12 . Seven workpieces W1 to W7 appear in images M11 and M12 , respectively.

[0054] The object determination unit 122 performs detection processing for detecting the workpieces on each of the image M11 and the image M12 (step S15 ), thereby obtaining the positions of the workpieces W1 to W7 in the image M11 and the positions of the workpieces W1 to W7 in the image M12 as detection results.

[0055] In addition, in a situation where the visual sensor 70 is mounted on the robot 30 and the robot 30 photographs the workpiece while moving, the photographing position of the visual sensor 70 during photographing changes, and the position of the object (stationary object) in the image changes between two images photographed continuously. Therefore, in such a situation, when calculating the position of the workpiece as the detection result in step S15, the change in the photographing position can also be considered, and the calculation is performed in a manner that the position of the stationary object in the image is the same. In addition, regarding the workpiece being transported on the conveying device, the visual sensor 70 fixed to the working space is used to photograph the workpiece transported on the conveying device, and the position of the stationary object on the conveyor belt also changes between two images photographed continuously. Therefore, in such a situation, when calculating the position of the workpiece as the detection result in step S15, the conveying speed of the conveying device can also be considered, and the calculation is performed in a manner that the position of the stationary object on the conveyor belt in the image is the same.

[0056] Based on these detection results, the object determination unit 122 extracts, among the workpieces W1 to W7 , workpieces whose positions do not change between the image M11 and the image M12 as workpieces in a stationary state (step S16 ).

[0057] In this example, the positions of the workpieces W2 to W5 change, while the positions of the workpieces W1, W6, and W7 do not change. In this case, in step S16, the workpieces W1, W6, and W7 are extracted as workpieces in a stationary state and notified to the robot control device 50 as the removal targets. The motion control unit 151 of the robot control device 50 performs the removal operation on the workpieces W1, W6, and W7 notified from the target determination unit 122 (step S17).

[0058] Thus, according to the second embodiment, a stationary workpiece can be determined as a pick-up target by the robot 30. That is, the possibility of the robot 30 failing to pick up a moving workpiece can be reduced, and the overall cycle time of the picking operation can be shortened.

[0059] Next, refer to Fig. 9 An example of a UI screen for making settings related to an operation for determining a workpiece in a stationary state as a picking target of the robot 30 will be described. Fig. 9 1 shows an example of such a UI screen 90. The UI screen 90 may be generated by the setting unit 123 and displayed on the display screen of the display unit 13 of the teaching operation panel 10. In this case, operation input to the UI screen 90 may be performed via the operation unit 14 of the teaching operation panel 10.

[0060] like Fig. 9As shown, the UI screen 90 includes a check box 91 for causing the detection system 100 to perform a take-out operation by excluding the active workpiece. By checking the check box 91, the operation of removing the workpiece by excluding the active workpiece as described in the first embodiment and the second embodiment can be performed. In addition, a selection bar for specifying which of the operations of the first embodiment and the second embodiment is to be performed can also be provided in the UI screen 90.

[0061] The UI screen 90 may further include a designation field 92 for designating the size (number of pixels) of the margin when setting the detection non-target area by adding a margin to the pixel area of ​​the workpiece having movement in the operation of the first embodiment.

[0062] The UI screen 90 may also have: a designation column 93, which is used to designate that the workpiece is excluded from the work object when the workpiece moves by more than a few pixels between the continuously captured images. The designation column 93 can be applied to any of the cases of excluding the workpiece that changes between the image M1 and the image M2 in the first embodiment and excluding the workpiece that changes between the image M11 and the image M12 in the second embodiment. In addition, in the designation column 93 illustrated here, the amount of movement of the workpiece excluded from the work object is specified as a position in the image (number of pixels), but the amount of movement of the workpiece excluded from the work object can also be specified as a position in the actual space (for example, millimeters). Alternatively, when the amount of movement of the workpiece to be excluded is entered in the number of pixels in the designation column 93, the value converted from the number of pixels to the amount of movement in the actual space is displayed, and the amount of movement in the actual space can be confirmed.

[0063] As described above, according to this embodiment, it is possible to prevent the robot from performing an action to remove a workpiece before the position / posture is stabilized, and wasteful time due to failure in removal. That is, a workpiece in a stationary state can be used as the object of removal, thereby reducing the possibility of removal failure and shortening the cycle time of the robot's operation.

[0064] Although the present invention has been described above using typical embodiments, it will be understood by those skilled in the art that changes to the above-described embodiments and various other changes, omissions, and additions may be made without departing from the scope of the present invention.

[0065] The above-described embodiment can be applied not only to a robot processing system but also to various industrial machine systems that can improve the efficiency of work by making a workpiece in a stationary state the object of work.

[0066] The above-mentioned embodiment describes an example of extracting a workpiece such as a tablet whose position / posture is stable as the removal object, but the above-mentioned embodiment can also be applied to operations such as extracting a container (bottle, etc.) whose position / posture is stable conveyed on a conveying device and loading the workpiece into the container by a robot.

[0067] In the detection system 100 described in the first embodiment or the second embodiment, the visual sensor 70 may be configured to continuously capture images of the workpiece W, and the object determination unit 122 may automatically extract the workpiece in a stationary state based on the continuous images obtained from the visual sensor 70 and remove the workpiece by the robot 30. In this case, when the workpiece is put into a container or the like, the user does not need to perform an operation for generating a trigger signal that activates the visual sensor 70 to perform the removal operation.

[0068] In the first and second embodiments described above, an example of extracting a workpiece in a stationary state from two images taken continuously is described, but it is also possible to extract a workpiece in a stationary state from three or more images taken continuously. In the case of extracting a workpiece in a stationary state from three images taken continuously, for example, a workpiece with movement may be extracted between the first and third images and between the second and third images, and the extracted workpiece may be excluded from the latest image (the third image) to perform detection processing.

[0069] In reference Fig. 9 The UI screen described above may include the setting of the imaging cycle when the workpiece is continuously imaged using the visual sensor. In this case, the user can set an appropriate imaging cycle according to the nature of the workpiece to be worked on.

[0070] Figure 3 The configuration of the functional blocks in the functional block diagram is an example, and there may be various modifications of the configuration of the functional blocks. For example, at least one of the image acquisition unit, the object determination unit, and the setting unit configured in the visual sensor control device 20 may be configured on the robot control device 50 side.

[0071] Figure 3 The functional blocks of the visual sensor and robot control device shown can be implemented by the processor of the visual sensor and robot control device executing various software stored in the storage device, or can also be implemented by a structure mainly composed of hardware such as ASIC (Application Specific Integrated Circuit).

[0072] Execute the decision operation of taking out the object in the above-mentioned embodiment ( Figure 6 , Figure 8 ) and other processing programs can be recorded in various computer-readable recording media (for example, semiconductor memories such as ROM, EEPROM, and flash memory, magnetic recording media, and optical disks such as CD-ROM and DVD-ROM).

[0073] Explanation of symbols

[0074] 10 Teaching operation panel;

[0075] 20. Visual sensor control device;

[0076] 30 Robots;

[0077] 33 Manipulator;

[0078] 50 Robot control device;

[0079] 70 Vision Sensors;

[0080] 80 peripheral equipment;

[0081] 100 Detection system;

[0082] 11, 21, 51 processors;

[0083] 12, 22, 52 memory;

[0084] 13, 23 display unit;

[0085] 14, 24, 54 operation units;

[0086] 15, 53, 25 input and output interfaces;

[0087] 121 image acquisition unit;

[0088] 122 Object Determination Department;

[0089] 123 Setting Department;

[0090] 151 Motion Control Unit.

Claims

1. A control device, characterized in that: have: an image acquisition unit that acquires a plurality of images obtained by continuously photographing the workpiece from a visual sensor; and The object determination unit determines, based on the plurality of images, a workpiece in a stationary state as an object of work to be performed by the industrial machine.

2. The control device according to claim 1, characterized in that: The object determination unit extracts an active workpiece based on the multiple images, performs image processing to exclude the active workpiece from the latest image among the multiple images, performs detection processing for detecting the workpiece on the latest image from which the active workpiece is excluded, and determines the workpiece detected by the detection processing as an object for the operation.

3. The control device according to claim 2, characterized in that: The image processing includes masking the area of ​​the latest image containing the active workpiece, The object determination unit performs the detection process on the latest image that has been subjected to the masking process.

4. The control device according to claim 2 or 3, characterized in that: The control device further comprises: a setting unit for setting parameters used in the image processing; The parameters include at least one of a first parameter and a second parameter, wherein the first parameter is used to set the extraction of the active workpiece when the workpiece moves more than a few pixels between consecutive images among the multiple images, and the second parameter is used to set the size of a margin area that should be added around the pixel area of ​​the active workpiece as an area excluded from the latest image.

5. The control device according to claim 1, characterized in that: The object determination unit performs a detection process for detecting a workpiece on each of the plurality of images, and extracts the workpiece in the stationary state based on the position of the workpiece detected in the detection process for each of the plurality of images and determines the workpiece as an object of the operation.

6. A detection system, characterized in that: have: Vision sensors; an image acquisition unit that acquires, from the visual sensor, a plurality of images obtained by the visual sensor continuously photographing the workpiece; and The object determination unit determines, based on the plurality of images, a workpiece in a stationary state as an object of work to be performed by the industrial machine.

7. The detection system according to claim 6, characterized in that: The object determination unit extracts an active workpiece based on the multiple images, performs image processing to exclude the active workpiece from the latest image among the multiple images, performs detection processing for detecting the workpiece on the latest image from which the active workpiece is excluded, and determines the workpiece detected by the detection processing as an object for the operation.

8. The detection system according to claim 7, characterized in that: The image processing includes masking the area of ​​the latest image containing the active workpiece, The object determination unit performs the detection process on the latest image that has been subjected to the masking process.

9. The detection system according to claim 7 or 8, characterized in that: The detection system further comprises: a setting unit for setting parameters used in the image processing; The parameters include at least one of a first parameter and a second parameter, wherein the first parameter is used to set the extraction of the active workpiece when the workpiece moves more than a few pixels between consecutive images among the multiple images, and the second parameter is used to set the size of a margin area that should be added around the pixel area of ​​the active workpiece as an area excluded from the latest image.

10. The detection system according to claim 6, characterized in that: The object determination unit performs a detection process for detecting a workpiece on each of the plurality of images, and extracts the workpiece in the stationary state based on the position of the workpiece detected in the detection process for each of the plurality of images and determines the workpiece as an object of the operation.

Images