CN114986520A - Four-axis parallel robot sorting system and method based on machine vision - Google Patents
Four-axis parallel robot sorting system and method based on machine vision Download PDFInfo
- Publication number
- CN114986520A CN114986520A CN202210896881.4A CN202210896881A CN114986520A CN 114986520 A CN114986520 A CN 114986520A CN 202210896881 A CN202210896881 A CN 202210896881A CN 114986520 A CN114986520 A CN 114986520A
- Authority
- CN
- China
- Prior art keywords
- sorted
- workpieces
- workpiece
- image
- same
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention relates to the technical field of robots, and provides a four-axis parallel robot sorting system and a method based on machine vision, wherein the four-axis parallel robot sorting system comprises: the image acquisition module is used for acquiring an image of a workpiece to be sorted, preprocessing the image of the workpiece to be sorted and acquiring an image contour line of the workpiece to be sorted; the type and model identification module is used for identifying the type and model of the workpiece to be sorted according to the image contour line of the workpiece to be sorted; and the at least two delta robots are used for acquiring the types and models of the workpieces to be sorted and sorting the workpieces to be sorted of the same type and different models into different packaging boxes. The automatic workpiece sorting robot system can simultaneously sort a large number of workpieces of various types, and solves the problem that the existing automatic workpiece sorting robot system based on machine vision can not sort the workpieces of the same type and different types to different places according to the type and the model of the workpieces to be sorted.
Description
Technical Field
The invention relates to the technical field of robots, in particular to a four-axis parallel robot sorting system and method based on machine vision.
Background
In the modern industry, robots refer to artificial machines that automatically perform tasks to replace or assist human work. The control system of the mobile sorting robot based on the visual algorithm is created by combining a sorting and carrying control system based on a PLC system, a mobile sorting robot control system based on a microprocessor and a visual system. With the appearance of big data and the development of the technology of the internet of things, more advanced mobile logistics sorting robot control systems based on the internet of things are generated. From the above-mentioned several stages, it can be seen that the mobile sorting robot develops towards the direction that the physique is more flexible, the function is stronger, and the efficiency is higher.
With the development of machine learning techniques, machine learning begins to be used in the field of workpiece sorting. The Chinese patent with the application number of 201910618348.X discloses a parallel robot sorting system and method based on machine vision, wherein a parallel mechanical arm is controlled by STM32 to grab workpieces meeting preset conditions, the workpieces can be directly sorted into packing boxes according to the preset conditions, sorting is accurate, and production efficiency is improved. However, in the parallel robot sorting system and method based on machine vision, the grabbing and sorting of the workpieces are completed by analyzing the color information and the position information of the workpieces, the workpieces of the same type and different types cannot be sorted to different places according to the type and the model of the workpieces to be sorted, and the sorting function needs to be improved.
Disclosure of Invention
Based on the technical scheme, the invention provides a four-axis parallel robot sorting system and method based on machine vision, which aim to solve the problem that the existing automatic workpiece sorting robot system based on machine vision cannot sort workpieces of the same type and different types to different places according to the type and the model of the workpieces to be sorted, and the specific technical scheme is as follows:
a four-axis parallel robot sorting system based on machine vision comprises a conveying belt used for conveying workpieces to be sorted, an image acquisition module, a category and model identification module and at least two delta robots.
The image acquisition module is used for acquiring an image of a workpiece to be sorted, preprocessing the image of the workpiece to be sorted and acquiring an image contour line of the workpiece to be sorted.
The type and model identification module is used for identifying the type and model of the workpiece to be sorted according to the image contour line of the workpiece to be sorted.
The delta robot is used for acquiring the types and models of workpieces to be sorted and sorting the workpieces to be sorted of the same type and different models into different packaging boxes.
Four-axis parallel robot letter sorting system based on machine vision waits to sort the model of work piece in order to calculate through discernment to wait to sort the model of work piece to through two at least delta robots with the work piece of waiting to sort to different packing carton of same classification different models, can sort simultaneously to the work piece of a plurality of classifications in batches, solved present workpiece automatic sorting robot system based on machine vision can't be according to waiting to sort the class and the model of work piece, with the work piece letter sorting of same classification different models to the problem in different places.
Further, four-axis parallel robot letter sorting system still includes the defect detecting module.
The defect detection module is used for detecting the defects of the workpieces to be sorted according to the preprocessed images of the workpieces to be sorted and judging whether the workpieces to be sorted have defects or not.
The delta robot is used for screening the workpieces to be sorted with defects before sorting the workpieces to be sorted with the same category and different models into different packaging boxes.
Further, the four-axis parallel robot sorting system further comprises a gray average value calculating module and a quality grade dividing module.
The gray average value calculation module is used for carrying out gray processing on the image of the workpiece to be sorted and calculating the gray value of pixel points of the image of the workpiece to be sorted after the gray processing.
The quality grading module is used for grading the quality of the workpieces to be sorted according to the gray value of the pixel points of the images of the workpieces to be sorted.
Further, the delta robot is also used for sorting the workpieces to be sorted which belong to the same category, the same model and the same quality grade to the same packaging box.
A four-axis parallel robot sorting method based on machine vision comprises the following steps:
and S1, acquiring the image of the workpiece to be sorted, preprocessing the image of the workpiece to be sorted and acquiring the image contour line of the workpiece to be sorted.
And S2, identifying the type and model of the workpiece to be sorted according to the image contour line of the workpiece to be sorted.
And S3, sorting the workpieces to be sorted with the same category and different models into different packaging boxes by at least two delta robots.
Further, in step S3, before the workpieces to be sorted of the same category and different models are sorted into different packaging boxes by at least two delta robots, the workpieces to be sorted having defects are screened.
Further, the specific method for screening the workpieces to be sorted with defects comprises the following steps:
detecting defects of the workpieces to be sorted according to the preprocessed images of the workpieces to be sorted, and judging whether the workpieces to be sorted have defects or not;
and if the workpieces to be sorted have defects, screening the workpieces to be sorted with the defects.
Further, the four-axis parallel robot sorting method further comprises the following steps:
carrying out gray processing on an image of a workpiece to be sorted;
calculating gray values of pixel points of the image of the workpiece to be sorted after graying processing;
and performing quality grade division on the workpiece to be sorted according to the gray value of the pixel point of the image of the workpiece to be sorted.
Further, the specific method for performing quality grade division on the workpiece to be sorted according to the gray value of the pixel point of the image of the workpiece to be sorted comprises the following steps:
calculating the total average value of the gray values of pixel points of the image of the workpiece to be sorted;
carrying out equal-area region division on the image of the workpiece to be sorted, and calculating the region average value of the gray values of pixel points of the image of the workpiece to be sorted in different regions;
and for the workpieces to be sorted of the same type and the same model, performing quality grade division according to the total average value and the area average value.
Further, the specific method for classifying the quality grades of the workpieces to be sorted of the same type and the same model according to the total average value and the area average value comprises the following steps:
dividing a plurality of pixel point gray value ranges and a plurality of region area ranges;
calculating the area sum of a first region corresponding to all region average values in the gray value range of the pixel point where the minimum region average value is located;
and dividing the workpieces to be sorted, of which the first area sum is in the same area range, the minimum area average values are equal, and the total average values are in the same total preset range, into the same quality grade.
Drawings
The invention will be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
Fig. 1 is a schematic diagram of an overall structure of a four-axis parallel robot sorting system based on machine vision according to an embodiment of the present invention;
fig. 2 is a schematic overall flow chart of a four-axis parallel robot sorting method based on machine vision according to an embodiment of the present invention.
Description of reference numerals:
1. a conveyor belt; 2. an image acquisition module; 3. a category and model identification module; 4. a delta robot.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to embodiments thereof. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only and do not represent the only embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The terms "first" and "second" used herein do not denote any particular order or quantity, but rather are used to distinguish one element from another.
As shown in fig. 1, a four-axis parallel robot sorting system based on machine vision in an embodiment of the present invention includes a conveyor belt 1 for conveying workpieces to be sorted, an image capturing module 2, a category and model identifying module 3, and at least two delta robots 4.
The image acquisition module is used for acquiring an image of a workpiece to be sorted, preprocessing the image of the workpiece to be sorted and acquiring an image contour line of the workpiece to be sorted. The image acquisition module can be a camera, which is mounted above the conveyor belt and is in communication connection with the category and model identification module.
The preprocessing includes, but is not limited to, noise reduction, enhancement, graying, and the like of the image.
The type and model identification module is used for identifying the type and model of the workpiece to be sorted according to the image contour line of the workpiece to be sorted.
In the type and model identification module, a plurality of image contour lines of standard workpieces of different types and different models are stored in advance. Each class of workpieces comprises at least one model.
The image contour of the standard workpiece is obtained by photographing different types of workpieces from different angles. The type and model identification module judges the type of the workpiece to be sorted by comparing the similarity between the image contour line of the workpiece to be sorted and the image contour line of the standard workpiece. And if the similarity between the image contour line of the workpiece to be sorted and the image contour line of a certain standard workpiece is greater than a first similarity threshold value, judging that the category of the workpiece to be sorted is the same as that of the certain standard workpiece.
For the model of the workpiece to be sorted, the top view and the side views of the workpiece to be sorted can be obtained, then the parameters such as the perimeter or the radius of the contour line of the top view and the side views are obtained, and finally the model of the workpiece to be sorted is calculated according to the parameters.
Specifically, the type and model identification module also stores standard parameters corresponding to different types of workpieces of different types in advance. For the same type of workpieces, actual parameters such as the perimeter or the radius of the contour line of the top view and the side view are obtained, and then the actual parameters are matched with standard parameters of workpieces of different models to obtain corresponding models.
The delta robot is used for acquiring the type and the model of the workpieces to be sorted and sorting the workpieces to be sorted of the same type and different models to different packaging boxes.
Wherein, on the delta robot, install anchor clamps. The Delta robot carries out picking and placing operation on the workpiece to be sorted through the clamp.
The four-axis parallel robot sorting system based on machine vision can sort workpieces of multiple categories in batches simultaneously by identifying the categories of the workpieces to be sorted and sorting the workpieces of the same category and different models to different packaging boxes through at least two delta robots, and solves the problem that the existing automatic workpiece sorting robot system based on machine vision can not sort the workpieces of the same category and different models to different places according to the categories and the models of the workpieces to be sorted.
In one embodiment, the four-axis parallel robot sorting system further comprises a defect detection module.
The defect detection module is used for detecting defects of the workpiece to be sorted according to the preprocessed image of the workpiece to be sorted, and judging whether the workpiece to be sorted has defects (including but not limited to damage, depression and the like).
The delta robot firstly screens the workpieces to be sorted with defects before sorting the workpieces to be sorted of the same category and different models into different packaging boxes.
The workpieces to be sorted with defects are firstly screened and processed, and then the delta robot sorts the workpieces to be sorted with the same category and different models to different packaging boxes, so that the sorting quality of the workpieces to be sorted can be improved.
In one embodiment, the four-axis parallel robot sorting system further comprises a gray average calculation module and a quality grade division module.
The gray average value calculating module is used for carrying out gray processing on the image of the workpiece to be sorted and calculating the gray value of the pixel point of the image of the workpiece to be sorted after the gray processing.
The quality grading module is used for grading the quality of the workpieces to be sorted according to the gray value of the pixel points of the images of the workpieces to be sorted.
After the workpieces to be sorted are subjected to quality grade division, the delta robot is also used for sorting the workpieces to be sorted belonging to the same category, the same model and the same quality grade to the same packaging box.
In many cases, due to different parameters such as grinding depth, temperature rise and cooling temperature, speed of temperature rise and cooling, baking temperature and time, spraying flow rate and speed, even if workpieces of the same type and the same size are used, the size of the dark and light areas on the surface and the number of the areas with different colors are different. The difference of the surface color of the workpiece generally does not influence the use function of the workpiece. If the quality grades of the workpieces can be classified according to the color difference of the surfaces of the workpieces, the classification and the subsequent sale are facilitated.
In the prior art, the quality grade of a workpiece is often divided according to the average value of the gray value of the total pixel points on the surface of the workpiece or the difference between the HSV value and the standard color data. In this method, the quality of the workpiece can be roughly classified only, and it is difficult to classify the quality grade of the workpiece more finely.
According to the invention, the workpieces to be sorted are subjected to quality grade division according to the pixel point gray value of the image of the workpieces to be sorted, so that more specific and detailed quality grade division can be performed on the workpieces of the same type and the same model, and the classification and subsequent sale of the workpieces are facilitated.
As shown in fig. 2, a four-axis parallel robot sorting method based on machine vision is applied to the four-axis parallel robot sorting system based on machine vision, and includes the following steps:
and S1, acquiring the image of the workpiece to be sorted, preprocessing the image of the workpiece to be sorted and acquiring the image contour line of the workpiece to be sorted.
And S2, identifying the type and model of the workpiece to be sorted according to the image contour line of the workpiece to be sorted.
Specifically, based on the neural network technology, after the neural network is trained and learned by using a large number of different workpiece image contour lines, the category of the workpiece to be sorted can be identified through the trained neural network.
And S3, sorting the workpieces to be sorted with the same category and different models into different packaging boxes by at least two delta robots.
The four-axis parallel robot sorting method based on the machine vision can simultaneously sort a large number of workpieces of various categories by identifying the categories and the models of the workpieces to be sorted and sorting the workpieces to be sorted of the same category and different models to different packing boxes by at least two delta robots, and solves the problem that the existing automatic workpiece sorting robot system based on the machine vision can not sort the workpieces of the same category and different models to different places according to the categories and the models of the workpieces to be sorted.
In one embodiment, in step S3, before sorting the workpieces to be sorted of the same category and different models into different packaging boxes by at least two delta robots, the workpieces to be sorted having defects are screened.
Specifically, the specific method for screening the workpieces to be sorted with defects comprises the following steps:
detecting defects of the workpieces to be sorted according to the preprocessed images of the workpieces to be sorted, and judging whether the workpieces to be sorted have defects or not; and if the workpieces to be sorted have defects, screening the workpieces to be sorted with the defects.
The workpieces to be sorted with defects are firstly screened, and then the delta robot sorts the workpieces to be sorted of the same category and different models to different packaging boxes, so that the sorting quality of the workpieces to be sorted can be improved.
In one embodiment, the four-axis parallel robot sorting method further includes the following steps:
carrying out gray processing on the image of the workpiece to be sorted;
calculating gray values of pixel points of the image of the workpiece to be sorted after graying processing;
and performing quality grade division on the workpiece to be sorted according to the gray value of the pixel point of the image of the workpiece to be sorted.
The specific method for classifying the quality grades of the workpieces to be sorted according to the gray value of the pixel points of the images of the workpieces to be sorted comprises the following steps:
calculating the total average value of the gray values of pixel points of the image of the workpiece to be sorted;
carrying out equal-area region division on the image of the workpiece to be sorted, and calculating the region average value of the gray values of pixel points of the image of the workpiece to be sorted in different regions;
and for the workpieces to be sorted of the same type and the same model, performing quality grade division according to the total average value and the area average value.
The specific method for classifying the quality grades of the workpieces to be sorted in the same category and the same model according to the total average value and the area average value comprises the following steps of:
dividing a plurality of pixel point gray value ranges and a plurality of region area ranges;
calculating the area sum of a first region corresponding to all region average values in the gray value range of the pixel point where the minimum region average value is located;
and dividing the workpieces to be sorted, of which the first area sum is in the same area range, the minimum area average values are equal, and the total average values are in the same total preset range, into the same quality grade.
The total preset range is provided with a plurality of total preset ranges which are different. The total average value can represent the overall color condition of the surface of the workpiece. The purpose of setting a plurality of different total preset ranges is to perform preliminary quality grading on workpieces with approximately the same overall color. After the workpieces are subjected to preliminary quality grade division, the workpieces to be sorted, of which the first area sum is in the same area range, the minimum area average value is equal, and the total average value is in the same total preset range, are divided into the same quality grade.
In many cases, due to the difference of parameters such as grinding depth, temperature rise and cooling temperature, speed of temperature rise and cooling, baking temperature and time, spraying flow and speed, even if workpieces of the same type and the same size are different, the size of the dark and light areas on the surface and the number of the areas with different colors are different. The difference of the color of the surface of the workpiece generally does not influence the use function of the workpiece.
In the prior art, the quality grade of a workpiece is often divided according to the average value of the gray value of the total pixel points on the surface of the workpiece or the difference between the HSV value and the standard color data. In this method, the quality of the workpiece can be roughly classified, and it is difficult to finely classify the quality grade of the workpiece.
In the invention, the workpieces to be sorted, of which the first area sum is in the same area range, the minimum area average value is equal and the total average value is in the same total preset range, are classified into the same quality grade by calculating the first area sum corresponding to all the area average values in the pixel gray value range in which the minimum area average value is located and judging whether the area ranges in which the first area sum of the workpieces to be sorted is located are the same, the minimum area average value and the total average value are equal, so that the workpieces to be sorted, of which the first area sum is in the same area range, the minimum area average value is equal and the total average value is in the same total preset range, can be classified into the same quality grade in a more specific and detailed manner.
The sorting method of the four-axis parallel robot further comprises the following steps: after more specific and detailed quality grade division is carried out on the workpieces with the same category and the same model, the workpieces to be sorted with the same category, the same model and the same quality grade are sorted into the same packaging boxes.
In addition, the method of the invention also comprises the following steps: the second area sum corresponding to all the area average values in the pixel gray value range where the maximum area average value is located is calculated, whether the area areas where the second area sum of the workpieces to be sorted is located are the same, and whether the maximum area average value and the total average value are equal are judged, and then the workpieces to be sorted, which have the second area sum in the same area range, the maximum area average value and the total average value in the same total preset range, are divided into the same quality grade, so that the workpieces of the same category and the same model can be subjected to more specific and detailed quality grade division.
Therefore, workpieces of the same type and the same model can be subjected to more specific and detailed quality grade division according to different color depths of the regions.
In one embodiment, the four-axis parallel robot sorting method further includes the following steps:
the method comprises the steps of firstly, comparing similarity between an image contour line of a workpiece to be sorted and a standard image contour line of a standard workpiece for workpieces to be sorted of the same type, the same model and the same quality grade, and judging whether burrs and/or deformation exist on the edge of the workpiece to be sorted if the similarity is larger than a first similarity threshold value and smaller than or equal to a second similarity threshold value. Here, the first similarity threshold is smaller than the second similarity threshold.
And secondly, judging the workpiece to be sorted as a defective product if burrs and/or deformation exist on the edge of the workpiece to be sorted.
And thirdly, screening the workpieces to be sorted which are judged to be defective by the delta robot before sorting the workpieces to be sorted which belong to the same category, the same model and the same quality grade into the same packaging box.
For some workpieces, such as bearings, nozzles, nuts, gaskets and the like in hardware fittings, burrs and deformation of edges do not affect the actual use function in many times, but affect the appearance performance of the workpieces. The workpieces with burrs and/or deformation at the edges are judged to be inferior products through detecting the burrs and the deformation at the edges of the workpieces, so that the quality of the workpieces to be sorted is divided more finely.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. The utility model provides a four-axis parallel robot letter sorting system based on machine vision, is including being used for carrying the conveyer belt of waiting to sort the work piece, its characterized in that, four-axis parallel robot letter sorting system still includes:
the image acquisition module is used for acquiring an image of a workpiece to be sorted, preprocessing the image of the workpiece to be sorted and acquiring an image contour line of the workpiece to be sorted;
the type and model identification module is used for identifying the type and model of the workpiece to be sorted according to the image contour line of the workpiece to be sorted;
and the delta robots are used for acquiring the types and models of the workpieces to be sorted and sorting the workpieces to be sorted of the same type and different models into different packaging boxes.
2. The machine vision based four axis parallel robot sorting system of claim 1, further comprising:
the defect detection module is used for detecting the defects of the workpieces to be sorted according to the preprocessed images of the workpieces to be sorted and judging whether the workpieces to be sorted have defects or not;
the delta robot is used for screening the workpieces to be sorted with defects before sorting the workpieces to be sorted with the same category and different models into different packaging boxes.
3. The machine vision based four axis parallel robot sorting system of claim 2, further comprising:
the gray average value calculating module is used for carrying out gray processing on the image of the workpiece to be sorted and calculating the gray value of a pixel point of the image of the workpiece to be sorted after the gray processing;
and the quality grading module is used for grading the quality of the workpiece to be sorted according to the gray value of the pixel point of the image of the workpiece to be sorted.
4. The machine vision-based four-axis parallel robot sorting system as claimed in claim 3, wherein said delta robot is further adapted to sort the workpieces to be sorted belonging to the same category, the same model and the same quality class into the same packing boxes.
5. A four-axis parallel robot sorting method based on machine vision is characterized by comprising the following steps:
s1, acquiring an image of the workpiece to be sorted, preprocessing the image of the workpiece to be sorted and acquiring an image contour line of the workpiece to be sorted;
s2, identifying the type and model of the workpiece to be sorted according to the image contour line of the workpiece to be sorted;
and S3, sorting the workpieces to be sorted with the same category and different models into different packaging boxes by at least two delta robots.
6. The four-axis parallel robot sorting method based on machine vision as claimed in claim 5, wherein in step S3, before sorting the workpieces to be sorted of the same category and different models into different packaging boxes by at least two delta robots, the workpieces to be sorted with defects are screened.
7. The machine vision-based four-axis parallel robot sorting method according to claim 6, wherein the specific method for screening the workpieces to be sorted with defects comprises the following steps:
detecting defects of the workpieces to be sorted according to the preprocessed images of the workpieces to be sorted, and judging whether the workpieces to be sorted have defects or not;
and if the workpieces to be sorted have defects, screening the workpieces to be sorted with the defects.
8. The machine vision based four-axis parallel robot sorting method according to claim 7, wherein the four-axis parallel robot sorting method further comprises the steps of:
carrying out gray processing on an image of a workpiece to be sorted;
calculating gray values of pixel points of the image of the workpiece to be sorted after graying processing;
and performing quality grade division on the workpiece to be sorted according to the gray value of the pixel point of the image of the workpiece to be sorted.
9. The machine vision-based four-axis parallel robot sorting method as claimed in claim 8, wherein the specific method for performing quality classification on the workpieces to be sorted according to the gray pixel values of the images of the workpieces to be sorted comprises the following steps:
calculating the total average value of the gray values of pixel points of the image of the workpiece to be sorted;
carrying out equal-area region division on the image of the workpiece to be sorted, and calculating the region average value of the gray values of pixel points of the image of the workpiece to be sorted in different regions;
and for the workpieces to be sorted of the same type and the same model, performing quality grade division according to the total average value and the area average value.
10. The machine vision-based four-axis parallel robot sorting method according to claim 9, wherein the specific method for performing quality grade division according to the total average value and the area average value for the workpieces to be sorted of the same category and the same model comprises the following steps:
dividing a plurality of pixel point gray value ranges and a plurality of region area ranges;
calculating the area sum of a first region corresponding to all region average values in the gray value range of the pixel point where the minimum region average value is located;
and dividing the workpieces to be sorted, of which the first area sum is in the same area range, the minimum area average values are equal, and the total average values are in the same total preset range, into the same quality grade.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210896881.4A CN114986520B (en) | 2022-07-28 | 2022-07-28 | Four-axis parallel robot sorting system and method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210896881.4A CN114986520B (en) | 2022-07-28 | 2022-07-28 | Four-axis parallel robot sorting system and method based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114986520A true CN114986520A (en) | 2022-09-02 |
CN114986520B CN114986520B (en) | 2022-10-28 |
Family
ID=83021074
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210896881.4A Active CN114986520B (en) | 2022-07-28 | 2022-07-28 | Four-axis parallel robot sorting system and method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114986520B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117991825A (en) * | 2024-02-02 | 2024-05-07 | 华南理工大学 | PTZ structure and PTZ method based on deep learning and depth information detection and positioning |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106737664A (en) * | 2016-11-25 | 2017-05-31 | 中国科学院自动化研究所 | Sort the Delta robot control methods and system of multiclass workpiece |
CN109978839A (en) * | 2019-03-08 | 2019-07-05 | 浙江大学 | The detection method of the low texture defect of wafer |
CN110813778A (en) * | 2019-11-21 | 2020-02-21 | 蓝思智能机器人(长沙)有限公司 | Workpiece classification method, workpiece classification system and workpiece transmission system |
CN111445434A (en) * | 2019-10-17 | 2020-07-24 | 烟台艾易新能源有限公司 | Image processing method of metal workpiece grade sorting system |
CN111871841A (en) * | 2020-08-12 | 2020-11-03 | 安徽信息工程学院 | Rotary classification machine vision part sorting system, method and device |
CN114299051A (en) * | 2021-12-31 | 2022-04-08 | 南京工程学院 | Leather material surface defect detection method based on feature modeling significance detection |
KR20220055356A (en) * | 2020-10-26 | 2022-05-03 | 에스케이텔레콤 주식회사 | Method of extracting characters from license plate, and license plate character extracting device performing |
-
2022
- 2022-07-28 CN CN202210896881.4A patent/CN114986520B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106737664A (en) * | 2016-11-25 | 2017-05-31 | 中国科学院自动化研究所 | Sort the Delta robot control methods and system of multiclass workpiece |
CN109978839A (en) * | 2019-03-08 | 2019-07-05 | 浙江大学 | The detection method of the low texture defect of wafer |
CN111445434A (en) * | 2019-10-17 | 2020-07-24 | 烟台艾易新能源有限公司 | Image processing method of metal workpiece grade sorting system |
CN110813778A (en) * | 2019-11-21 | 2020-02-21 | 蓝思智能机器人(长沙)有限公司 | Workpiece classification method, workpiece classification system and workpiece transmission system |
CN111871841A (en) * | 2020-08-12 | 2020-11-03 | 安徽信息工程学院 | Rotary classification machine vision part sorting system, method and device |
KR20220055356A (en) * | 2020-10-26 | 2022-05-03 | 에스케이텔레콤 주식회사 | Method of extracting characters from license plate, and license plate character extracting device performing |
CN114299051A (en) * | 2021-12-31 | 2022-04-08 | 南京工程学院 | Leather material surface defect detection method based on feature modeling significance detection |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117991825A (en) * | 2024-02-02 | 2024-05-07 | 华南理工大学 | PTZ structure and PTZ method based on deep learning and depth information detection and positioning |
Also Published As
Publication number | Publication date |
---|---|
CN114986520B (en) | 2022-10-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107486415B (en) | Thin bamboo strip defect online detection system and detection method based on machine vision | |
CN110314854B (en) | Workpiece detecting and sorting device and method based on visual robot | |
CN112232399B (en) | Automobile seat defect detection method based on multi-feature fusion machine learning | |
CN110610141A (en) | Logistics storage regular shape goods recognition system | |
CN111127571A (en) | Small sample defect classification method and device | |
CN114986520B (en) | Four-axis parallel robot sorting system and method based on machine vision | |
CN207238542U (en) | A kind of thin bamboo strip defect on-line detecting system based on machine vision | |
CN113070240A (en) | Copper plate surface defect detection and automatic classification method based on machine vision and deep learning | |
CN112304957A (en) | Machine vision-based intelligent detection method and system for appearance defects | |
CN106780437B (en) | A kind of quick QFN chip plastic packaging image obtains and amplification method | |
CN111968082A (en) | Product packaging defect detection and identification method based on machine vision | |
CN113894055A (en) | Hardware surface defect detection and classification system and method based on machine vision | |
CN113751332A (en) | Visual inspection system and method of inspecting parts | |
CN114332622A (en) | Label detection method based on machine vision | |
CN111539927A (en) | Detection process and algorithm of automobile plastic assembly fastening buckle lack-assembly detection device | |
CN117094609B (en) | Intelligent management system for aluminum profile production quality based on machine vision | |
CN113139943B (en) | Method and system for detecting appearance defects of open circular ring workpiece and computer storage medium | |
CN116823771A (en) | ZARA defect specification detection method, system and storage medium | |
Hashim et al. | Automated visual inspection for metal parts based on morphology and fuzzy rules | |
CN107833222A (en) | A kind of non-metal workpiece fifth wheel detection means and method | |
Tatari et al. | Automatic recognition of defects in wood | |
CN112184665A (en) | Artificial intelligence defect detecting system applied to paper-plastic industry | |
CN113591923A (en) | Engine rocker arm part classification method based on image feature extraction and template matching | |
CN118334039B (en) | Sagging identification method and system | |
CN113516610A (en) | Workpiece detection counting method based on industrial vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |