Sorting device and sorting method

Abstract

Provided is a sorting device comprising: a conveyance means for conveying a workpiece using a conveyance belt; a position detection means for detecting a position of the workpiece by using a difference between an image including the workpiece on the conveyance belt and a background image other than the workpiece; a determination means for determining a type of the workpiece at the position detected by the position detection means; and an update means for updating the background image.

Description

Sorting device and sorting method

[0001] The present invention relates to a sorting device and a sorting method.

[0002] There is a demand for recycling plastic products so that they can be reused as materials for resin parts. However, the plastics to be recycled are a mixture of multiple types, and specific plastics must be selected from a mixture containing various colors. For this reason, a sorting device (resin sorting device) has been developed that can separate specific plastics from a mixture containing various plastics.

[0003] For example, there is a resin sorting device that identifies the type of resin by irradiating the resin with measurement light and analyzing the reflected light. In this case, near-infrared spectroscopy is the mainstream, but carbon black, which is used to color black plastics, absorbs near-infrared light and cannot be measured. On the other hand, resin identification using Raman spectroscopy can also measure black plastics, allowing for maximum plastic reuse.

[0004] Patent Document 1 describes a method for identifying and separating types of resin by obtaining Raman scattering signals from resins flowing on a belt conveyor.

[0005] Patent Document 2 discloses a method for identifying large quantities of resin at high speed by irradiating Raman light onto the resin flowing on a conveyor belt. Measuring black plastic requires a longer measurement time than measuring plastics of other colors. By tracking the measurement light along the moving sample, the measurement time is ensured.

[0006] JP 2013-36971 A JP 2023-167533 A

[0007] The sorting device of Patent Document 2 sets a path (hereinafter referred to as a tracking path) for irradiating the workpieces with measurement light. Since the tracking path is set based on the workpieces on the conveyor belt, it is necessary to recognize the workpieces before setting the path, and the workpieces are recognized based on the difference in brightness between the conveyor belt and the workpieces. However, because there is a difference in brightness due to dirt or scratches on the conveyor belt, it may be erroneously recognized as a workpiece.

[0008] When misrecognition occurs, a tracking path is set for stains or scratches, resulting in unnecessary processing. The occurrence of unnecessary processing due to the upper limit on the number of tracking operations per hour may mean that a tracking path including the workpiece to be identified cannot be set.

[0009] By reducing the number of workpieces being transported or slowing down the transport speed, it is possible to increase the number of workpieces that can be tracked, but this reduces the number of workpieces that can be processed per hour (hereafter referred to as "throughput").To correctly recognize workpieces and increase tracking efficiency, it is necessary to prevent erroneous recognition due to dirt or scratches on the transport belt and to prevent a decrease in throughput.

[0010] An object of the present invention is to provide a sorting device that can solve the above problems, suppress erroneous recognition, and prevent a decrease in throughput.

[0011] In order to solve the above problem, the sorting device of the present invention is characterized by having a conveying means for conveying a workpiece using a conveying belt, a position detection means for detecting the position of the workpiece using the difference between an image including the workpiece on the conveying belt and a background image other than the workpiece, a discrimination means for discriminating the type of the workpiece at the position detected by the position detection means, and an update means for updating the background image.

[0012] According to the present invention, it is possible to realize a sorting device that can suppress erroneous recognition and reduce a decrease in throughput.

[0013] FIG. 1 is a diagram illustrating an example of a hardware configuration of a sorting device according to a first embodiment of the present invention. FIG. 2 is a functional block diagram illustrating an example of a functional configuration of a sorting device according to a first embodiment of the present invention. FIG. 3 is a diagram illustrating an example of a hardware configuration of a sorting system 300 according to a first embodiment of the present invention, viewed from the side. FIG. 4 is a flowchart illustrating an example of a process of a sorting system using a sorting device according to a first embodiment of the present invention. FIG. 5 is a flowchart illustrating an example of an operation flow of the work sorting process (step S404) of FIG. 4. (A) and (B) are diagrams illustrating an example of setting a tracking path according to the first embodiment of the present invention. FIG. 1 is a diagram illustrating an example of a hardware configuration of a sorting system according to a second embodiment, viewed from the side. FIG. 2 is a flowchart illustrating an example of a work sorting operation flow of a sorting device according to a third embodiment. FIG. 3 is a schematic diagram illustrating an area of ​​a conveyor belt of a sorting device according to a third embodiment. FIG. 4 is a diagram illustrating an example of a hardware configuration of a sorting system according to a fourth embodiment, viewed from the side. FIG. 5 is a flowchart illustrating an example of a work sorting operation flow of a sorting device according to a fourth embodiment.

[0014] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the present invention is not limited to the following embodiments. In each drawing, the same members or elements are given the same reference numerals, and duplicate descriptions will be omitted or simplified. <Embodiment 1>

[0015] 1 is a diagram showing an example of the hardware configuration of a sorting apparatus according to embodiment 1 of the present invention. The sorting apparatus 100 includes a CPU 101, an input / output I / F 102 for an external storage device, a ROM 104, and a RAM 105, which exchange data via a bus 103.

[0016] A touch panel 106 and a control unit 107 are connected to the sorting device 100, and data is exchanged via a bus 103. The touch panel 106 and the control unit 107 may be disposed in the housing of the sorting device, or may be provided in a housing separate from the sorting device.

[0017] Fig. 2 is a functional block diagram showing an example of the functional configuration of the sorting device according to the first embodiment of the present invention. Note that some of the functional blocks shown in Fig. 2 are realized by causing a CPU 101, which serves as a computer included in the sorting device, to execute a computer program stored in a memory, which serves as a storage medium.

[0018] However, some or all of these functions may be implemented by hardware, such as a dedicated circuit (ASIC) or a processor (a reconfigurable processor, DSP). Furthermore, the functional blocks shown in Fig. 2 do not have to be housed in the same housing, and may be configured as separate devices connected to each other via signal paths.

[0019] The control unit 107 also has a built-in CPU and the like as a computer, and functions as a control means for controlling the operation of each part of the sorting device and the entire sorting system based on a computer program stored in a memory as a storage medium.

[0020] For example, external units included in the sorting system, such as a near-infrared light or laser light irradiation unit, a camera, and an air jet, are controlled by the control unit 107. The touch panel 106 is used to give instructions to start / stop the sorting device 100 and to output the current status.

[0021] The sorting device operates as a device that sequentially identifies the workpieces on the workpiece conveying section and separates them according to the identification results. In this embodiment, the objects conveyed as the workpieces are not limited, but an example in which resin is conveyed as the workpiece will be described here.

[0022] The sorting device 100 includes a workpiece transport unit 201. The workpiece transport unit is, for example, a belt conveyor that transports resin. Here, the workpiece transport unit 201 functions as a transport means that executes a transport step of transporting the workpiece using a transport belt.

[0023] The work position, which is the position of a work such as resin transported by the work transport unit, is detected by the work position detection unit 202. At that time, the work position is detected, for example, by the difference between a background image of the belt transport surface on which no work is placed and an image including the work on the transport belt. Here, the work position detection unit 202 functions as a position detection means that detects the position of the work using the difference between the image including the work on the transport belt and a background image other than the work.

[0024] The type of resin of the workpiece at the detected workpiece position is identified by the workpiece identification unit 203. For example, the type of resin is identified by sequentially irradiating the workpiece, such as resin, with a laser along a predetermined tracking path and obtaining a Raman scattering signal.

[0025] Alternatively, the type of resin may be identified by irradiating the resin with near-infrared light and analyzing the reflected and transmitted light. In this embodiment, these identification means are not limited to these. Here, the workpiece identification unit 203 functions as an identification means for identifying the type of workpiece at the position detected by the position detection means.

[0026] When the workpiece identification unit 203 completes the identification process, the workpiece separation unit 204 receives the results of the workpiece identification unit and separates the resins to be identified from the resins that are not. For example, the resins are separated according to their types and stored in boxes where the resins to be identified should be stored.

[0027] These functional units are realized by the CPU of the control unit 107 loading a computer program stored in ROM into RAM and executing processing in accordance with each flowchart described below. Also, for example, when configuring hardware to replace at least part of the software processing using the CPU, it is sufficient to configure a calculation unit or circuit corresponding to the processing of each functional unit described here.

[0028] Next, the configuration of a device (hereinafter referred to as a sorting system) incorporating the device of this embodiment, which sequentially identifies workpieces such as resin supplied on a belt conveyor and separates them according to the identification results, will be described.

[0029] 3 is a side view of an example of the hardware configuration of a sorting system 300 according to the first embodiment of the present invention. The sorting system 300 supplies workpieces 303 such as resins supplied from an external belt conveyor 301 to a belt conveyor 302 of the sorting system 300 to separate the resins.

[0030] The sorting system 300 is equipped with a workpiece conveying surface photographing camera 304, a conveying belt photographing camera 305, a length measuring meter 306 that measures the amount of movement of the conveying belt, a workpiece identification camera 307, and a laser irradiation device 308.

[0031] The workpiece conveyance surface photographing camera 304 is used to detect the position of a workpiece 303 such as a resin workpiece being conveyed by the belt conveyor by the workpiece position detection unit 202. The conveyor belt photographing camera 305 is used to obtain an image of the belt conveyance surface on which the workpiece 303 is not placed as a background image.

[0032] The length measuring device 306 is used to detect the amount of movement and speed of the belt. The workpiece identification camera 307 and laser irradiation device 308 are used by the workpiece identification unit 203 to identify the type of resin.

[0033] The air jet 309 ejects air toward the resin in response to the operation of the workpiece separating unit 204 of the device of this embodiment. This controls the workpieces 303, such as resin, to be collected to go into a collection box 310, and the resin to be discarded to go into another box 311.

[0034] Fig. 4 is a flowchart showing an example of processing in a sorting system using the sorting device according to the first embodiment of the present invention, and Fig. 5 is a flowchart showing an example of the operation flow of the work sorting process (step S404) in Fig. 4. Note that the operations of the steps in the flowcharts of Fig. 4 and Fig. 5 are sequentially performed by the sorting device 100 or a CPU or the like serving as a computer in the control unit 107 executing a computer program stored in memory.

[0035] The flow of the operation for separating workpieces 303 such as resin will be described with reference to Figures 4 and 5. First, when an instruction to start the operation is given on the touch panel 106, the flow shown in Figure 4 begins. In step S401, the CPU performs preparation processing. That is, it starts supplying power to each unit (air jet, camera, laser irradiation device, belt conveyor, etc.) that constitutes the separation system 300, and transitions these units to an operable state.

[0036] When the preparatory operation is completed, the CPU determines whether a stop signal has been received in step S402. The stop signal may be issued when an instruction to stop operation is given on the touch panel 106, or when a safety problem occurs in the system.

[0037] If it is determined in step S402 that a stop signal has been received, the process proceeds to step S405, where termination processing is performed, the system is immediately stopped, and the flow of FIG. 4 is terminated.

[0038] If it is not determined in step S402 that a stop signal has been received, the CPU determines in step S403 whether or not a workpiece 303 is present on the belt conveyor.

[0039] If it is determined in step S403 that no workpiece 303 is present, the process returns to step S401, and if it is determined in step S403 that a workpiece is present, the process proceeds to step S404, where the workpiece sorting process of the sorting device is carried out. Details of step S404 will be described using FIG. 5.

[0040] Fig. 5 is a flowchart showing an example of the operation flow of the workpiece sorting process (step S404) in Fig. 4. When the flow in Fig. 5 begins, a background image is acquired in step S501. That is, the background image is updated by periodically capturing an image of the conveyor belt just before the workpiece 303 is placed by the conveyor belt photographing camera 305. Here, the conveyor belt photographing camera 305 functions as an imaging means for photographing the conveying surface of the conveyor belt.

[0041] Here, step S501 functions as an updating step (updating means) that updates the background image, and updates the background image based on an image captured by the imaging means when no workpiece is loaded on the conveying surface of the conveyor belt. Note that dirt on the conveyor belt also includes, for example, partial changes in color and reflectance due to aging of the conveyor belt surface. In other words, the background image includes dirt or scratches on the conveyor belt.

[0042] After the background image is acquired, in step S502, an image of the workpiece mounting surface on which the workpiece 303 is mounted is acquired. That is, to acquire the image of the workpiece mounting surface, the workpiece conveyance surface imaging camera 304 captures an image of the workpiece 303 on the conveyance belt.

[0043] After acquiring the image of the workpiece mounting surface, in step S503, difference processing is performed to recognize the workpiece 303 by thresholding the brightness value obtained from the difference between the images of the conveyor belt and the workpiece mounting surface. Note that in order to make the brightness values ​​of the workpiece conveyance surface photographing camera 304 and the conveyor belt photographing camera 305 similar, the same lighting system is used, or the brightness levels and gains of the workpiece conveyance surface photographing camera 304 and the conveyor belt photographing camera 305 are adjusted.

[0044] In this manner, in this embodiment, the background image immediately before the workpiece 303 is placed is acquired in step S501, and the background image is used to perform background image update processing in step S503. Note that in this embodiment, the background image including dirt or scratches is updated at least once during one rotation of the conveyor belt.

[0045] Next, in step S504, the CPU performs workpiece position detection processing. That is, the size and position of the workpiece 303 are detected by comparing the brightness data obtained by the difference processing with a predetermined threshold value. Here, step S504 functions as a position detection step that detects the position of the workpiece using the difference between an image including the workpiece on the conveyor belt and a background image other than the workpiece.

[0046] Next, in step S505, the CPU sets a tracking path of the laser light by the laser irradiation device 308 based on the recognized workpiece 303. Here, step S505 functions as a tracking path setting step (tracking path setting means) that sets a tracking path based on the position of the workpiece.

[0047] 6A and 6B are diagrams showing examples of setting a tracking path according to the first embodiment of the present invention, and Fig. 6A is a diagram showing an example of a tracking path. A tracking path 603 is set, which is a path along which laser light is sequentially irradiated based on the position of the recognized workpiece 303, starting from the head in the conveyance direction.

[0048] When the recognized workpieces are lined up perpendicular to the conveyance direction, as in (2) and (2)' in Fig. 6(A), the workpiece on the upper side of Fig. 6(A) is prioritized for tracking. In this case, if dirt or scratches 602 on the conveyor belt are mistakenly recognized as a workpiece, a tracking path including the dirt or scratches will be set.

[0049] 6B is a diagram showing an example of setting a tracking path when position detection is performed using the immediately preceding background image including dirt or scratches in this embodiment. By performing a subtraction process with the immediately preceding background image including dirt or scratches 602, a path that tracks only the workpiece 303 can be generated.

[0050] As a result, even if new stains or scratches 602 occur, the stains or scratches will not be mistakenly recognized as a workpiece, and the workpiece can be tracked efficiently. Furthermore, after setting the tracking path in step S505, in step S506, the CPU performs processing to identify the type of resin of the workpiece 303.

[0051] To this end, a laser irradiation device 308 irradiates each workpiece 303 with laser light based on a set tracking path, and the type of resin is identified, for example, by capturing an image of the reflected light (Raman scattered light) with a workpiece identification camera 307.

[0052] Here, step S506 functions as a discrimination step for discriminating the type of workpiece at the position detected by the position detection step. Note that, for identifying resins using Raman scattered light, a known technique may be used, and therefore a description thereof will be omitted here.

[0053] In step S507, the CPU separates the workpieces according to the identification result of the identification process in step S506. For example, the CPU controls the air jet 309 so that the workpieces 303 are sorted and stored in the collection box 310 or another box 311 according to the identified resin type. When this series of processes is completed, the flow in FIG. 5 ends.

[0054] As described above, in this embodiment, immediately before the workpiece identification process, the background image is updated to include areas with a different brightness from the conveyor belt, such as newly occurring stains or scratches on the conveyor belt, so the identification process for stains or scratches on the conveyor belt can be reduced, thereby preventing a decrease in throughput.

[0055] Although an example in which the workpieces 303 are separated into two boxes, a recovery box and another box, has been shown, this embodiment is not limited to this example of separating into two boxes. The workpieces may be separated into three or more boxes according to the type of resin, such as ABS, polystyrene, polyethylene, or polypropylene.

[0056] <Embodiment 2> Fig. 7 is a diagram showing a hardware configuration of a sorting system according to embodiment 2 as seen from the side. The same components as in Fig. 5 are assigned the same numbers. This example differs from the example in Fig. 5 in that there is no camera for capturing background images.

[0057] Fig. 8 is a flowchart showing an example of a workpiece sorting operation flow according to embodiment 2. Note that the operations of the steps in the flowchart of Fig. 8 are performed sequentially by the sorting device 100 or a CPU or the like serving as a computer in the control unit 107 executing a computer program stored in memory.

[0058] 8 starts, the CPU acquires an image of the workpiece 303 placed on it in step S801, and then performs a difference process between the previously acquired background image and the image of the workpiece 303 placed on the conveyor belt in step S802. In addition, the CPU performs a workpiece position detection process based on the data from the difference process in step S803.

[0059] Next, in step S804, the CPU sets a tracking path for the recognized workpiece, and in step S805, performs workpiece identification processing using Raman scattered light of the laser light.

[0060] In step S806, the CPU separates the workpieces according to the identification result of the identification process. That is, the CPU controls the air jet 309 so that the resin workpieces 303 are stored in the collection box 310 or another box 311 according to the identified resin type.

[0061] Next, in step S807, the CPU determines whether new stains or scratches have occurred on the conveyor belt based on the identification results of the workpiece identification process. Even if stains or scratches are erroneously determined to be works based on the difference in brightness with the conveyor belt as in Fig. 6A, it is possible to determine that the detected stains or scratches are works because the Raman scattering signals are different between the conveyor belt and the workpiece.

[0062] If it is determined in step S807 that dirt or scratches have been detected, the CPU performs background image update processing in step S808 to include the detected dirt or scratches in the background.

[0063] Here, step S808 functions as an update step (update means) that determines whether the conveyor belt is dirty or scratched based on the Raman scattering signal from the dirt or scratch, and updates the background image based on the determined dirt or scratch. The update means periodically updates the background image. After processing step S808, or if step S807 returns No, the series of steps S801 to S808 in FIG. 8 is terminated.

[0064] As described above, in the second embodiment, by detecting stains and scratches based on the results of the workpiece identification process, the background image is updated to include areas with a different brightness from the conveyor belt, such as stains and scratches newly appearing on the conveyor belt. Therefore, the next time, identification process will not be performed on stains and scratches on the conveyor belt, making it possible to prevent a decrease in throughput.

[0065] <Embodiment 3>

[0066] Fig. 9 is a flowchart showing an example of the workpiece sorting operation of the sorting device according to embodiment 3. Note that the operation of each step in the flowchart of Fig. 9 is performed sequentially by the sorting device 100 or the CPU or the like as a computer in the control unit 107 executing a computer program stored in memory.

[0067] 9 starts, in step S901, the CPU acquires an image in which a workpiece is mounted, and in step S902, performs a difference process between the image in which the workpiece is mounted and a background image acquired in advance. In addition, in step S903, the CPU performs a workpiece position detection process based on the result of the difference process.

[0068] After the workpiece position detection process, in step S904, the CPU stores the detected positions of the workpieces 303.

[0069] Figure 10 is a schematic diagram of the area of ​​the conveying belt of the sorting device of embodiment 3. As shown in Figure 10, the area of ​​the conveying belt is set by dividing the width direction of the conveying belt into M pixels and the length direction of the belt into N pixels.

[0070] In step S904, the pixel in which the workpiece 303 was recognized is stored, and the number of times 1001 that the workpiece appeared in that pixel is stored. Next, in step S905, the CPU sets a tracking path for the detected workpiece 303, and in step S906, it performs workpiece identification processing. In step S907, the CPU separates the workpieces according to the identification results of the identification processing. For example, it controls the air jet 309 so that the workpiece 303 is stored in the collection box 310 or another box 311 according to the resin type of the identified workpiece 303.

[0071] Furthermore, in step S908, the CPU determines whether the number of times the workpiece appears in each pixel shown in Fig. 10 exceeds a predetermined threshold value. Dirt or scratches that occur on the conveyor belt and can cause erroneous recognition always appear as areas with a different brightness from the conveyor belt.

[0072] Therefore, if the answer is Yes in step S908, the CPU determines in step S909 that pixels in which the number of times the workpiece appears exceeds a predetermined threshold are stains or scratches, and registers them in the background image.

[0073] That is, the number of times an area whose brightness differs from that of the conveying belt appears is added up, and if the number of times exceeds a predetermined threshold, the result of step S908 is determined as Yes, and the process proceeds to step S909. Then, in step S909, the CPU performs background image update processing to generate a background image including an area 1002 whose brightness exceeds a threshold (for example, 2).

[0074] Here, step S909 functions as an update step (updating means) that updates the background image by regarding an area where the number of times that the area has appeared as a workpiece position is equal to or exceeds a predetermined threshold as a stain or scratch. On the other hand, if the number of times that the area has appeared does not exceed the threshold, that is, if step S908 returns No, the series of processes is completed, and the flow in FIG. 9 ends.

[0075] As described above, in the third embodiment, by detecting stains and scratches based on the number of appearances of areas recognized as workpieces, the background image is updated to include areas with a different brightness from the conveyor belt, such as newly occurring stains and scratches on the conveyor belt. Therefore, it is not necessary to perform identification processing on stains and scratches on the conveyor belt, and it is possible to prevent a decrease in throughput.

[0076] <Fourth embodiment> Fig. 11 is a side view of the hardware configuration of a sorting system according to a fourth embodiment. Components that are the same as those in Fig. 5 are assigned the same numbers. The difference from the configuration in Fig. 5 is that a three-dimensional camera 1101 is used as workpiece position detection means.

[0077] Fig. 12 is a flowchart showing an example of a workpiece sorting operation flow of the sorting device according to embodiment 4. Note that the operations of the steps in the flowchart of Fig. 12 are sequentially performed by the sorting device 100 or a CPU or the like as a computer in the control unit 107 executing a computer program stored in memory.

[0078] In step S1201, the CPU acquires three-dimensional data of the workpiece. That is, by using the three-dimensional camera 1101, height information is acquired in addition to the position and size of the workpiece.

[0079] Next, in step S1202, the CPU performs workpiece position detection processing. At this time, the height of the workpiece is compared with a predetermined threshold, and anything above the predetermined threshold is recognized as a workpiece, and the workpiece position is detected for the workpiece recognized. Here, step S1202 functions as a position detection step that detects the position of the workpiece by determining the height of the workpiece based on the predetermined threshold.

[0080] On the other hand, the background image may be updated by registering the height of an object below a predetermined threshold as, for example, a stain or a scratch in the background image. That is, step S1202 can function as an updating step (updating means) that updates the background image by registering the area where the height of an object on the conveyor belt is below a predetermined threshold as a stain or a scratch.

[0081] Next, in step S1203, the CPU sets a tracking path based on the detected workpiece position. Then, in step S1204, the CPU irradiates the workpieces on the tracking path with laser light and identifies the type of resin in the workpieces based on the Raman scattered light. Then, in step S1205, the CPU separates the workpieces according to the identified type of resin.

[0082] In this way, workpieces with heights above a predetermined threshold are recognized as workpieces made of resin or the like, and workpieces with heights below the predetermined threshold are recognized as dirt or scratches on the conveyor belt, so dirt or scratches on the conveyor belt are not mistakenly recognized as workpieces, allowing the correct tracking path to be set and reducing erroneous recognition of workpieces.

[0083] In this way, in the fourth embodiment, the workpiece is measured three-dimensionally, so that identification processing is not mistakenly performed on stains or scratches on the conveyor belt, and it is possible to prevent a decrease in throughput.

[0084] In the fourth embodiment, the height of the workpiece is acquired using a three-dimensional camera, but any sensor that can measure and acquire the height of the workpiece may be used. For example, the height of the workpiece may be acquired using a sensor such as a distance measuring sensor or a LiDAR (Light Detection and Ranging) sensor.

[0085] <Embodiment 5> Next, a method for manufacturing articles (semiconductor IC elements, liquid crystal display elements, MEMS, etc.) using the sorting apparatus or sorting system of the above-described embodiments will be described. Substrates, for example, are sorted using the sorting apparatus or sorting system according to the above-described embodiments. Then, articles are manufactured by processing the substrates, for example, through a process of applying a photosensitive material to the substrates, a process of exposing the substrates (wafers, glass substrates, etc.) coated with the photosensitive material, a process of developing the substrates (photosensitive material), or other well-known processes for processing the developed substrates.

[0086] Other well-known processes include etching, resist stripping, dicing, bonding, packaging, etc. According to such an article manufacturing method, it is possible to manufacture high-quality articles without causing a decrease in throughput compared to conventional methods.

[0087] The present invention has been described in detail above based on preferred embodiments thereof, but the present invention is not limited to the above embodiments. Various modifications and combinations of the above embodiments are possible based on the spirit of the present invention, and these are not excluded from the scope of the present invention. The present invention includes the following combinations. (Cross-reference to related applications) This application claims the benefit of Japanese Patent Application No. 2024-002274, filed January 11, 2024. The contents of the above Japanese patent application are incorporated herein by reference in their entirety.

Claims

1. A sorting device comprising: a conveying means for conveying a workpiece using a conveyor belt; a position detecting means for detecting the position of the workpiece using the difference between an image including the workpiece on the conveyor belt and a background image other than the workpiece; a discriminating means for discriminating the type of the workpiece at the position detected by the position detecting means; and an updating means for updating the background image.

2. The sorting device according to claim 1, further comprising a tracking path setting means for setting a tracking path based on the position of the workpiece.

3. The sorting device according to claim 1 or 2, including an imaging means for imaging the conveying surface of the conveyor belt, wherein the updating means updates the background image based on an image acquired by the imaging means when the workpiece is not mounted on the conveying surface of the conveyor belt.

4. The sorting device according to any one of claims 1 to 3, wherein the updating means determines the dirt or damage based on a Raman scattering signal from the dirt or damage of the conveyor belt, and periodically updates the background image based on the determined dirt or damage.

5. The sorting device according to any one of claims 1 to 4, wherein the updating means updates the background image including the dirt or damage at least once within one rotation of the conveyor belt.

6. The sorting device according to any one of claims 1 to 5, wherein the updating means updates the background image using, as the dirt or damage, a region where the number of appearances as the position of the workpiece is equal to or greater than a predetermined threshold.

7. The sorting device according to any one of claims 1 to 6, wherein the updating means updates the background image using, as the dirt or damage, a region where the height of an object on the conveyor belt is less than a predetermined threshold.

8. The sorting device according to any one of claims 1 to 7, wherein the background image includes dirt or damage of the conveyor belt.

9. The sorting device according to any one of claims 1 to 8, wherein the updating means periodically updates the background image.

10. A sorting device comprising: a conveying means for conveying a workpiece; a position detecting means for detecting the position of the workpiece; and a discriminating means for discriminating the type of the workpiece at the position of the workpiece detected by the position detecting means, wherein the position detecting means detects the position of the workpiece by discriminating the height of the workpiece based on a predetermined threshold value.

11. A sorting method comprising: a conveying step of conveying a workpiece using a conveyor belt; a position detecting step of detecting the position of the workpiece using a difference between an image including the workpiece on the conveyor belt and a background image other than the workpiece; a discriminating step of discriminating the type of the workpiece at the position detected by the position detecting step; and an updating step of updating the background image.

12. A sorting method comprising: a conveying step of conveying a workpiece; a position detecting step of detecting the position of the workpiece; and a discriminating step of discriminating the type of the workpiece at the position of the workpiece detected by the position detecting step, wherein the position detecting step detects the position of the workpiece by discriminating the height of the workpiece based on a predetermined threshold value.

Images