Machine vision practical training sample piece

Abstract

A machine vision practical training sample piece comprises a plurality of battery blocks and a charging tray, the plurality of battery blocks are provided with information identification parts used for machine vision information identification training, the charging tray is provided with battery grooves matched with the battery blocks, and the battery blocks are provided with first positioning holes used for battery block distance calculation training; the battery jar is provided with a second positioning hole for calculating the central point of the battery jar. The beneficial effects of the utility model lie in that the battery block integrates various characteristics for machine vision identification, can adapt to various application scenes, is rich in teaching content and function, and does not need to select different practical training samples and carriers according to different application scenes.

Description

Technical Field

[0001] The utility model belongs to the technical field of machine learning, and in particular relates to a machine vision training sample. Background Art

[0002] The existing machine vision training samples can realize applications such as hand-eye calibration, guided grasping, sorting and assembly, character recognition, dimension measurement, defect detection, etc. It can also be used for machine vision system hardware selection, lighting and imaging, programming and other training, and is suitable for teaching and training, engineering training and skills competitions in colleges and universities for majors such as electrical automation, mechatronics, and industrial robots.

[0003] The existing machine vision training samples have relatively simple functions and can only realize measurement, recognition, detection or guidance of one or two applications; the corresponding structures of the training samples for some application scenarios are relatively large and cannot be compatible with multiple uses and small size at the same time; when you want to realize multiple applications, you often need to equip multiple samples, which increases costs and requires replacing the carrier. The operation process is cumbersome and the cost-effectiveness is not high. Utility Model Content

[0004] In order to solve the defects of the prior art, this invention provides a machine vision training sample, and its technical solution is as follows:

[0005] A machine vision training sample comprises a battery block and a material tray, wherein the number of the battery blocks is multiple, and each of the multiple battery blocks is provided with an information recognition unit for machine vision information recognition training; the material tray is provided with a battery slot matching the battery block; the battery block is provided with a first positioning hole for distance calculation training of the battery block; the battery slot is provided with a second positioning hole for calculating the center point of the battery slot.

[0006] Specifically, the information recognition unit includes a QR code and / or characters for machine vision recognition.

[0007] Specifically, the plurality of battery blocks are classified into non-notch battery blocks, single-notch battery blocks, and double-notch battery blocks based on their outer shapes.

[0008] Specifically, the number of the material trays is three, and the three material trays are respectively provided with battery slots matching the no-notch battery, the single-notch battery block, and the double-notch battery block.

[0009] Specifically, the notch of the single-notch battery block is located on the right side of the battery block, and the notches of the double-notch battery block are located on the upper and lower sides of the battery block.

[0010] Specifically, at least one of the battery blocks is a rectangular parallelepiped, and its dimensions are: length×width×thickness=34mm×23mm×8mm.

[0011] Specifically, the width of one battery block is smaller than that of the other battery blocks, and its size is: length×width×thickness=34mm×22mm×8mm.

[0012] Specifically, the first positioning hole is circular, and the first positioning holes of the plurality of battery blocks have the same diameter.

[0013] Specifically, the information identification part is provided on both sides of the battery block.

[0014] Specifically, the material tray is circular in shape.

[0015] The utility model is beneficial in that it integrates multiple features for machine vision recognition through the battery block, can adapt to a variety of application scenarios, has rich teaching content and functions, and does not require the selection of different training samples and vehicles according to different application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A three-dimensional diagram of the machine vision training sample of the utility model;

[0017] Figure 2 for Figure 1 Front view of the machine vision training sample.

[0018] In the figure: 11, battery block without notch; 12, battery block with single notch; 13, battery block with double notch; 14, first positioning hole; 15, information identification part; 21, first material tray; 211, first battery slot; 22, second material tray; 221, second battery slot; 23, third material tray; 231, third battery slot; 24, second positioning hole. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the utility model.

[0020] The following is an example and combined with the attached Figure 1-2 The utility model is described in further detail.

[0021] A machine vision training sample; including a battery block and a material tray. Specifically, in this embodiment, the number of battery blocks is multiple, and the number of material trays is three. The battery blocks are divided into no-notch battery blocks 11, single-notch battery blocks 12, and double-notch battery blocks 13 according to the outer shape. Specifically, in this embodiment, the notch of the single-notch battery block 12 is located on the right side of the battery block, and the notch of the double-notch battery block 13 is located on the upper and lower sides of the battery block. It is used for machine vision appearance defect and type detection applications, and the battery block is provided with a first positioning hole 14.

[0022] The material tray includes a first material tray 21, a second material tray 22, and a third material tray 23. The material tray is provided with a battery slot and a second positioning hole 24. The first battery slot 211 matches the shape of the no-notch battery block 11, the second battery slot 221 matches the shape of the single-notch battery block 12, and the third battery slot 231 matches the shape of the double-notch battery block 13. Specifically, in this embodiment, the first material tray 21, the second material tray 22 and the third material tray 23 are circular in shape.

[0023] The battery block surface is provided with an information identification part 15. Specifically, in this embodiment, the content of the information identification part 15 is a two-dimensional code and / or characters, which is used for machine vision barcode and character recognition applications; the information identification part 15 is provided on both sides of the battery block. The first positioning hole 14 is circular in shape, and the diameters of multiple first positioning holes 14 are the same, which is used to calculate the distance from the center of the first positioning hole 14 to the center point of the battery block or to calculate the distance from the center of the first positioning hole 14 to the two sides of the battery block. The second positioning hole 24 is circular in shape and is used to calculate the position of the center point of the battery block.

[0024] The battery block has a variety of colors. Specifically, in this embodiment, the battery block colors are divided into red and black for use in machine vision color detection applications.

[0025] The battery block is a rectangular parallelepiped structure, and its standard size is: length × width × thickness = 34mm × 23mm × 8mm. A battery block has different sizes. Specifically, in this embodiment, the width of the battery block is smaller than that of other battery blocks, and its size is: length × width × thickness = 34mm × 22mm × 8mm.

[0026] The application process of a visual training sample:

[0027] By identifying the QR code and characters and comparing whether the information of the two is consistent, it can determine whether the product information is qualified, thus realizing the application of machine vision barcode and character recognition;

[0028] By detecting the color of the battery block, black and red can be distinguished, and machine vision color detection applications;

[0029] By identifying the shape of the battery block, the defective single-notch battery blocks 12 and double-notch battery blocks 13 are screened out, the notch-free battery blocks 11 are retained, and the categories are recorded, so as to realize the application of machine vision appearance defect and category detection; the machine vision measures the length and width of the battery block, calculates the center point position of the battery block, calculates the distance from the center of the first positioning hole 14 to the center point or calculates the distance from the center of the first positioning hole 14 to the two sides of the battery block, and screens out the battery blocks with unqualified dimensions through their size data and tolerance requirements, so as to realize the application of machine vision size measurement; through the center point position of the battery block, hand-eye calibration and standard position teaching are performed to realize the guided grasping of fixed cameras and mobile cameras, so as to realize the application of machine vision guided grasping. Through the above process, different categories of battery blocks are assembled into corresponding types of trays, so as to realize the application of machine vision sorting and assembly.

[0030] Use a 3D camera to measure the thickness of the battery block, learn and practice the application of 3D vision technology, and realize the application of machine vision 3D dimension measurement.

[0031] The utility model is beneficial in that it can adapt to various application scenarios by integrating multiple features for machine vision recognition through the battery block, and has rich teaching content and functions, and does not need to select different training samples and carriers according to different application scenarios. At the same time, the battery block and the tray are compact in structure and small in size without reducing the content and functions, which has higher cost performance and convenience.

[0032] The above embodiment only expresses one implementation method of the utility model, but it cannot be understood as limiting the scope of the utility model patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the utility model, several modifications and improvements can be made, which are equivalent modifications and improvements made to the above embodiment based on the essential technology of the utility model, and all of them belong to the protection scope of the utility model.

Claims

1. A machine vision training sample, characterized by: It includes a battery block and a material tray, wherein there are multiple battery blocks, each of which is provided with an information identification unit for machine vision information recognition training, the material tray is provided with a battery slot matching the battery block, the battery block is provided with a first positioning hole for mechanical recognition distance calculation training, and the battery slot is provided with a second positioning hole for calculating the center point of the battery slot.

2. The machine vision training sample according to claim 1, characterized in that: The information recognition unit includes a QR code and / or characters for machine vision recognition.

3. The machine vision training sample according to claim 1, characterized in that: The plurality of battery blocks are classified into non-notch battery blocks, single-notch battery blocks, and double-notch battery blocks based on their outer shapes.

4. The machine vision training sample according to claim 3, characterized in that: The number of the material trays is three, and the three material trays are respectively provided with battery slots matching the no-notch battery, the single-notch battery block, and the double-notch battery block.

5. The machine vision training sample according to claim 3, characterized in that: The notch of the single-notch battery block is located on the right side of the battery block, and the notches of the double-notch battery block are located on the upper and lower sides of the battery block.

6. The machine vision training sample according to claim 1, characterized in that: At least one of the battery blocks is a rectangular parallelepiped with dimensions of: length×width×thickness=34mm×23mm×8mm.

7. The machine vision training sample according to claim 6, characterized in that: The width of one of the battery blocks is smaller than that of the other battery blocks, and its dimensions are: length×width×thickness=34mm×22mm×8mm.

8. The machine vision training sample according to claim 7, characterized in that: The first positioning hole is circular, and the first positioning holes of the plurality of battery blocks have the same diameter.

9. The machine vision training sample according to claim 1, characterized in that: The information identification part is disposed on both sides of the battery block.

10. The machine vision training sample according to claim 1, characterized in that: The shape of the material tray is circular.

Images