AI vision integration and application device

Abstract

The utility model discloses an AI vision integration and application device, which comprises a rack, a plurality of AI vision modules, a plurality of AI vision modules and a plurality of AI vision modules, the visual camera is correspondingly arranged above the flexible vibration disc; a suction cup is arranged at the tail end of the four-axis robot; and the feeding frame is arranged on one side of the four-axis robot. Compared with the prior art, the problem that a conventional visual camera is difficult to effectively cooperate with an industrial robot to carry out machine learning model training in AI vision is solved.

Description

Technical Field

[0001] The utility model relates to the technical field of visual recognition, in particular to an AI visual integration and application device. Background Technique

[0002] When using the method of AI visual analysis for image recognition, the recognition accuracy can be effectively improved. For example, Chinese Patent No. 202410161880.4 discloses an industrial control visual motion control system and method based on AI visual analysis; the automated workshop where the industrial robot is located is divided into n areas; when an employee enters the automated workshop, the employee images in the automated workshop are collected in real time; the employee images collected in real time are analyzed to determine whether the items carried by the employee are large items; if the items carried by the employee are large items, then the employee images collected in real time are further analyzed to determine the area where the items carried by the employee are located; according to the area where the items carried by the employee are located, a corresponding risk instruction is generated; according to the risk instruction, the industrial robot is decelerated or stopped.

[0003] When using the method of AI visual analysis for recognition, in order to ensure the accuracy of real-time image analysis by the machine learning model, it is necessary to effectively train the machine learning model. In the prior art, there is a problem that the vision camera is difficult to effectively cooperate with the industrial robot for training the machine learning model in AI vision. Summary of the Utility Model

[0004] The purpose of the utility model is to provide an AI visual integration and application device to solve the problem that the existing vision camera is difficult to effectively cooperate with the industrial robot for training the machine learning model in AI vision.

[0005] In order to achieve the above purpose, the utility model adopts the following technical scheme: an AI visual integration and application device, including:

[0006] A frame on which a flexible vibrating disk is arranged;

[0007] A vision camera, whose position is correspondingly arranged above the flexible vibrating disk;

[0008] A four-axis robot, with a suction cup arranged at its end;

[0009] A loading rack, which is arranged on one side of the four-axis robot.

[0010] As a further description of the above technical scheme:

[0011] The vision camera is fixedly installed on a support frame, which includes a support column and a support beam. The support column is fixedly installed on the frame, the support beam is fixedly installed on the support column, a connecting seat is arranged on the support beam, and the vision camera is fixedly installed on the connecting seat.

[0012] As a further description of the above technical solution:

[0013] The support beam is a circular rod.

[0014] As a further description of the above technical solution:

[0015] Three loading racks are arranged circumferentially along the four-axis robot.

[0016] As a further description of the above technical solution:

[0017] The loading rack is detachably installed on the frame 1.

[0018] As a further description of the above technical solution:

[0019] The loading rack includes an upper supporting plate, a bottom plate and columns. The upper supporting plate is parallel to the bottom plate. One end of the column is fixedly installed on the upper supporting plate, and the opposite end is fixedly installed on the bottom plate. The bottom plate is fixedly installed on the frame through bolt connectors.

[0020] In summary, due to the adoption of the above technical solution, the beneficial effects of the present utility model are as follows:

[0021] 1. In the present utility model, a product to be identified is set on the loading rack. The four-axis robot picks and places the product to be identified through a suction cup. After the four-axis robot places the product to be identified into the disk body of the flexible vibrating disk, the vision camera collects the image of the product to be identified on the flexible vibrating disk and transmits it to the computer, and real-time image analysis is performed through the machine learning model in the computer. The product to be identified in the flexible vibrating disk can adjust its posture flexibly through vibration, which is convenient for training the machine learning model for a single product to be identified and improving the accuracy of subsequent AI vision analysis.

[0022] 2. In the present utility model, the product to be identified is placed on the upper supporting plate of the loading rack. The loading rack is fixed to the frame through the bolt connectors between the upper supporting plate and the bottom plate. On the one hand, it is convenient to disassemble and move the loading rack. On the other hand, the bolt connectors are arranged in the cavity between the upper supporting plate and the bottom plate separated by the columns, which is convenient for operating the bolt connectors and avoiding the bolt connectors from affecting the picking and placing of the product to be identified. Description of the Drawings

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present utility model, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present utility model, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0024] Figure 1Schematic structure of an AI vision integration and application device Figure 1 。

[0025] Figure 2 Schematic structure of an AI vision integration and application device Figure 2 。

[0026] Legend:

[0027] 1. Frame; 11. Flexible vibrating bowl; 2. Vision camera; 3. Four-axis robot; 31. Suction cup; 4. Loading rack; 41. Upper supporting plate; 42. Bottom plate; 421. Bolt connection; 43. Column; 5. Support frame; 51. Support column; 52. Support beam; 521. Connection seat. Detailed implementation mode

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0029] Embodiment 1

[0030] Please refer to Figure 1-2 , the present invention provides a technical solution: an AI vision integration and application device, including:

[0031] Frame 1, on which a flexible vibrating bowl 11 is provided;

[0032] Vision camera 2, whose position is correspondingly set above the flexible vibrating bowl 11;

[0033] Four-axis robot 3, with a suction cup 31 at its end;

[0034] Loading rack 4, which is arranged on one side of the four-axis robot 3.

[0035] The vision camera 2 is fixedly installed on the support frame 5. The support frame 5 includes a support column 51 and a support beam 52. The support column 51 is fixedly installed on the frame 1, the support beam 52 is fixedly installed on the support column 51, a connection seat 521 is arranged on the support beam 52, and the vision camera 2 is fixedly installed on the connection seat 521 to fix the position of the vision camera 2.

[0036] The support beam 52 is a circular rod, so that the connection seat 521 is convenient to slide along the support beam 52 to adjust the position. After the adjustment is in place, the position of the connection seat 521 is fixed to realize the position fixation of the vision camera 2, which is convenient to flexibly adjust the vision camera 2.

[0037] Three loading racks 4 are arranged circumferentially around the four-axis robot 3, and different loading racks 4 place different products to be identified, further meeting the training requirements of the machine learning model.

[0038] The loading rack 4 is detachably installed on the frame 1. The loading rack 4 includes an upper supporting plate 41, a bottom plate 42 and a column 43. The upper supporting plate 41 is parallel to the bottom plate 42. One end of the column 43 is fixedly installed on the upper supporting plate 41, and the opposite end is fixedly installed on the bottom plate 42. The bottom plate 42 is fixedly installed on the frame 1 through a bolt connecting piece 421. The product to be identified is placed on the upper supporting plate 41 of the loading rack 4. The loading rack 4 is fixed to the frame 1 through the bolt connecting piece 421 between the upper supporting plate 41 and the bottom plate 42. On the one hand, it is convenient to disassemble and move the loading rack 4. On the other hand, the bolt connecting piece 421 is arranged in the cavity between the upper supporting plate 41 and the bottom plate 42 separated by the column 43, which is convenient to operate the bolt connecting piece 421 and avoid the bolt connecting piece affecting the picking and placing of the product to be identified.

[0039] Working principle: The product to be identified is set on the loading rack 4. The four-axis robot 3 picks and places the product to be identified through the suction cup 31. After the four-axis robot 3 puts the product to be identified into the disk body of the flexible vibrating disk 11, the vision camera 2 collects the image of the product to be identified on the flexible vibrating disk 11 and transmits it to the computer, and real-time image analysis is carried out through the machine learning model in the computer. The products to be identified in the flexible vibrating disk 11 can adjust their postures flexibly through vibration, which is convenient for training the machine learning model for a single product to be identified and improving the accuracy of subsequent Al visual analysis.

[0040] The above is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and all should be covered within the protection scope of the present invention.

Claims

1. An AI vision integration and application device, characterized in that, Comprising: A frame, on which a flexible vibrating bowl is provided; A vision camera, whose position is correspondingly arranged above the flexible vibrating bowl; A four-axis robot, with a suction cup provided at its end; A loading rack, which is arranged on one side of the four-axis robot.

2. The AI vision integration and application device according to claim 1, characterized in that The vision camera is fixedly installed on a support frame, the support frame includes a support column and a support beam, the support column is fixedly installed on the frame, the support beam is fixedly installed on the support column, a connecting seat is arranged on the support beam, and the vision camera is fixedly installed on the connecting seat.

3. An AI vision integration and application device according to claim 2, characterized in that, The support beam is a circular rod.

4. An AI vision integration and application device according to claim 1, characterized in that, 3 of the loading racks are arranged circumferentially along the four-axis robot.

5. An AI vision integration and application device according to claim 1, characterized in that, The loading rack is detachably installed on the frame.

6. An AI vision integration and application device according to claim 1, characterized in that, The loading rack includes an upper supporting plate, a bottom plate and a column, the upper supporting plate is parallel to the bottom plate, one end of the column is fixedly installed on the upper supporting plate, and the opposite end is fixedly installed on the bottom plate, and the bottom plate is fixedly installed on the frame through bolt connectors.

Images