Identification system and material picking mechanism

Abstract

The present invention discloses an identification system, including a lifting mechanism, a visual system, and a control box. The visual system is arranged on the lifting mechanism and rises and falls with the lifting mechanism. The control box controls the lifting of the lifting mechanism and controls the visual system to collect images and judge whether the images are clear. A material picking mechanism includes the above-mentioned identification system, a manipulator, a cargo loading mechanism, and a depth of field calibration column. The depth of field calibration column is provided with a calibration circle. The number of the depth of field calibration columns is at least four. The height of the calibration circle on each depth of field calibration column is the same. The calibration circle is set within the depth of field range of the camera. The control box controls the movement of the manipulator. The cargo loading mechanism is set below the manipulator, and the depth of field calibration column is set beside the cargo loading mechanism. A relatively low-priced fixed-focus camera is used to adapt to the change in depth of field by automatically lifting and lowering the camera; combined with the setting of the calibration circle, the adaptive calibration of the visual system is realized, which has universal applicability in solving the problem of adaptive depth of field and ensures accurate and reliable recognition of the photographed object.

Description

Technical Field

[0001] The present invention relates to the field of robot recognition, and in particular to a recognition system and a material picking mechanism. Background Art

[0002] The depth of field of a camera refers to the range within which the subject in the shooting scene presents a clear image. When the distance between the subject and the camera focal plane is less than the minimum depth of field or greater than the maximum depth of field, the camera cannot capture a clear image of the subject. Factors that affect the depth of field include the diameter of the permissible circle of confusion, focal length, the aperture value of the lens, and the focus distance.

[0003] The hand-eye collaborative robot uses a camera to identify materials. The recognition modes include EYE-TO-HAND mode and EYE-IN-HAND mode. Among them, the EYE-TO-HAND mode is more convenient to arrange, and the object image can be captured by using the gap between the robot operation, which is more efficient and has more industrial applications. However, the depth of field of the EYE-TO-HAND mode is easily affected by environmental conditions, resulting in unclear imaging. For example, when the EYE-TO-HAND mode is used to identify boxed materials, the distance between the material in the box and the camera will change as the material is taken and placed. When the distance between the material and the camera exceeds the depth of field range for clear imaging, the material image will be blurred, and the hand-eye collaborative robot will not be able to determine the shape and position of the material, resulting in the failure of the robot to grasp. In order to deal with this problem, a camera equipped with an automatic zoom system can be used to identify the material, and the depth of field can be adjusted by automatically stretching the lens, but this camera is expensive and has few practical applications. Summary of the invention

[0004] The technical problems to be solved by the present invention are: 1. The existing recognition system cannot automatically adjust the depth of field to adapt to the change in the distance between the object being photographed and the camera; 2. In the existing material picking mechanism, the distance between the material and the camera will change. When the distance between the material and the camera exceeds the depth of field range of the camera, the material recognition will fail and the material cannot be picked up.

[0005] The solution of the present invention to solve its technical problem is:

[0006] The recognition system includes a lifting mechanism, a visual system, and a control box. The visual system is arranged on the lifting mechanism and rises and falls with the lifting mechanism. The control box controls the lifting and falling of the lifting mechanism. The control box controls the visual system to collect images. The control box recognizes the images collected by the visual system and determines whether the images are clear.

[0007] The identification method of the identification system comprises the following steps:

[0008] S1, the visual system collects the image of the external target object and transmits the image to the control box;

[0009] S2, the control box recognizes the picture and determines whether the picture is clear;

[0010] S3, if the picture is clear, the recognition is completed; if the picture is not clear, the control box controls the lifting mechanism to rise or fall, and then returns to S1.

[0011] The recognition system of the present invention can adjust the distance between the visual system and the object by adjusting the height of the visual system, and finally adjust the distance between the object and the visual system to within the depth of field of the visual system, so as to capture a clear image of the object.

[0012] The prior art provides feasible technical solutions for determining whether the image collected by the visual system is clear. For example, the Chinese patent with the patent number CN201710178827.5 and the name of an image clarity recognition method, identity authentication method and device proposes an image clarity recognition method, identity authentication method and device, which collects a facial image when the image acquisition conditions are met, calculates the clarity index of the facial image, and if the clarity is less than or equal to the first threshold, it means that the facial image is clear, and then sends the facial image to the identity authentication device for subsequent image comparison to authenticate the user's identity; if the clarity is greater than the first threshold, it means that the facial image is not clear enough and cannot be used as a basis for facial image comparison, and then it is necessary to re-collect the facial image. In this application, the images of the two end values ​​of the subject at the depth of field range are recorded, and the clarity of the above two images is used as the clarity threshold.

[0013] Furthermore, the visual system includes two cameras arranged at the same height, so as to form a dual-camera recognition system to improve recognition accuracy.

[0014] Optionally, the lifting mechanism includes a vertically arranged bracket, a mounting frame slidably connected to the bracket, a screw rod drivingly connected to the mounting frame, and a first motor drivingly connected to the screw rod, the first motor is fixedly connected to the bracket, the control box controls the start or stop of the first motor, and the control box controls the rotation direction of the power output by the first motor. If the rotation direction of the first motor output is different, the rotation direction of the screw rod is different, and the mounting frame connected to the screw rod can move up or down along the screw rod and the bracket, thereby driving the visual system to move up and down.

[0015] Optionally, the apparatus further comprises a translation mechanism, a second motor is disposed on the mounting frame, and a horizontal conveyor belt is connected to the second motor in a transmission manner, a camera carrier is fixedly connected to the conveyor belt, and the camera is disposed on the camera carrier. The position of the visual system can be adjusted horizontally, and the distance between the visual system and the object can be adjusted, so that the object can be included in the depth of field range of the visual system.

[0016] Furthermore, the translation mechanism includes two limit blocks fixedly connected to the mounting frame, and the two limit blocks are respectively arranged on the left and right sides of the camera carrier. This structure is used to prevent the camera carrier from falling off the mounting frame.

[0017] The present invention also provides a material picking mechanism, including the above-mentioned identification system, and also including a manipulator, a cargo loading mechanism, and a depth of field calibration column, wherein a calibration circle is provided on the depth of field calibration column, and the number of the depth of field calibration columns is at least four, and the height of the calibration circle on each depth of field calibration column is the same, and the calibration circle is set within the depth of field range of the camera, the control box controls the movement of the manipulator, the cargo loading mechanism is set below the manipulator, and the depth of field calibration column is set beside the cargo loading mechanism.

[0018] In the material picking mechanism, the number of calibration circles is preferably six, which can reduce the coordinate conversion process. The center of a calibration circle is taken as the origin to establish a world coordinate system, and the world coordinates of the centers of the remaining five circles are measured. The manipulator has its own coordinate system, which is called the machine coordinate system. The machine coordinates of the centers of the six calibration circles are measured by the manipulator. Since the world coordinates of the centers of the six calibration circles are known, the conversion relationship between the world coordinate system and the machine coordinate system can be established.

[0019] The coordinate system with the camera itself as the center is called the camera coordinates. When the position of the visual system has been adjusted so that a clear image of the object can be captured, the visual system is used to sense the position of the object and the calibration circle to obtain the camera coordinates of the object and the calibration circle. Since the machine coordinates of the calibration circle are known, the conversion relationship between the camera coordinate system and the machine coordinate system can be calculated, so that the machine coordinates of the object can be calculated based on the camera coordinates of the object. The control box adjusts the manipulator according to the machine coordinates of the object to achieve the function of accurately grasping the object, that is, grasping the goods in the cargo loading mechanism.

[0020] The relationship between the world coordinate system and the camera coordinate system can be described by a rotation matrix and a translation vector. The translation vector is a 3*1 row vector, and the rotation matrix is ​​a 3*3 unit orthogonal matrix. There are twelve unknowns in the rotation matrix and the translation vector. One corresponding point in space can get three equations, so four corresponding points can be used to calculate the rotation matrix and the translation vector. Therefore, the number of calibration circles is at least four. Given the three-dimensional coordinates of the centers of the six calibration circles in the camera coordinate system and the world coordinate system, the transformation from the camera coordinate system to the world coordinate system can be calculated. Six points are used instead of four points to calculate the transformation relationship because more points can make the result more accurate.

[0021] Furthermore, the height of the calibration circle is between the heights of the highest point and the lowest point of the cargo loading mechanism. The cargo needs to be located near the calibration circle to ensure that the camera can simultaneously recognize a clear cargo image and a calibration circle image to obtain the camera's world coordinates and the cargo's camera coordinates.

[0022] Optionally, the cargo loading mechanism is an AGV, and the control box controls the movement of the AGV. AGV: Automated Guided Vehicle, refers to a transport vehicle equipped with an electromagnetic or optical automatic guidance device that can travel along a specified guidance path. It is a transport vehicle that does not require a driver in industrial applications and uses a rechargeable battery as a power source.

[0023] The beneficial effects of the present invention are: 1. The visual system can automatically adjust the height, using a relatively low-priced fixed-focus camera to adapt to changes in depth of field by automatically raising and lowering the camera; 2. The lifting and lowering freedom of the visual system, combined with the setting of the calibration circle, realizes the adaptive calibration of the visual system, which has universal applicability in solving the problem of adaptive depth of field and ensures accurate and reliable recognition of the photographed objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly describes the drawings required for use in the description of the embodiments. Obviously, the drawings described are only part of the embodiments of the present invention, not all of the embodiments, and those skilled in the art can also obtain other design solutions and drawings based on these drawings without creative work.

[0025] Figure 1 is a front view of the present invention;

[0026] Figure 2 It is a top view of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the concept, specific structure and technical effects of the present invention in combination with the embodiments and drawings, so as to fully understand the purpose, characteristics and effects of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, other embodiments obtained by technicians in this field without creative work are all within the scope of protection of the present invention. In addition, all the connection relationships mentioned in the text do not refer to the direct connection of components, but refer to the fact that a better connection structure can be formed by adding or reducing connecting accessories according to the specific implementation situation. The various technical features in the invention can be combined interchangeably without conflicting with each other.

[0028] Reference Figure 1 to Figure 2 , which is an embodiment of the present invention, specifically:

[0029] Identification system: includes a lifting mechanism, a visual system, and a control box 6. The visual system is arranged on the lifting mechanism and rises and falls with the lifting mechanism. The control box 6 controls the lifting mechanism to rise and fall. The control box 6 controls the visual system to collect images. The control box 6 identifies the images collected by the visual system and determines whether the images are clear. The visual system includes two cameras 21 arranged at the same height. The lifting mechanism includes a vertically arranged bracket 11, a mounting frame 12 slidably connected to the bracket 11, a screw rod 13 connected to the mounting frame 12 in a transmission manner, and a first motor 10 connected to the screw rod 13 in a transmission manner. The first motor 10 is fixedly connected to the bracket 11. The control box 6 controls the first motor 10 to start or stop, and the control box 6 controls the rotation direction of the power output by the first motor 10. It also includes a translation mechanism, a second motor 70 is arranged on the mounting frame 12, and a horizontal conveyor belt 71 connected to the second motor 70 in a transmission manner. A camera carrier 22 is fixedly connected to the conveyor belt 71, and the camera 21 is arranged on the camera carrier 22. The two limit blocks 72 are respectively disposed on the left and right sides of the camera carrier 22 .

[0030] Material picking mechanism: including the identification system, and also including a manipulator 4, a cargo loading mechanism 5, and a depth of field calibration column 3. The depth of field calibration column 3 is provided with a calibration circle. The number of the depth of field calibration columns 3 is at least four. The height of the calibration circle on each depth of field calibration column 3 is the same. The calibration circle is set within the depth of field range of the camera 21. The control box 6 controls the movement of the manipulator 4. The cargo loading mechanism 5 is set below the manipulator 4, and the depth of field calibration column 3 is set beside the cargo loading mechanism 5. The height of the calibration circle is between the highest point and the lowest point of the cargo loading mechanism 5. The cargo loading mechanism 5 is an AGV trolley, and the control box 6 controls the movement of the AGV trolley.

[0031] The preferred embodiments of the present invention are specifically described above, but the invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. Material picking mechanism, characterized by: The invention comprises an identification system, a manipulator (4), a cargo loading mechanism (5), and a depth of field calibration column (3), wherein the depth of field calibration column (3) is provided with a calibration circle, the number of the depth of field calibration columns (3) is at least four, the height of the calibration circle on each depth of field calibration column (3) is the same, the calibration circle is set within the depth of field range of the camera (21), a control box (6) controls the movement of the manipulator (4), the cargo loading mechanism (5) is arranged below the manipulator (4), and the depth of field calibration column (3) is arranged beside the cargo loading mechanism (5); The recognition system comprises a lifting mechanism, a visual system, and a control box (6); the visual system is arranged on the lifting mechanism and is lifted and lowered together with the lifting mechanism; the control box (6) controls the lifting and lowering of the lifting mechanism; the control box (6) controls the visual system to collect images; the control box (6) identifies the images collected by the visual system and determines whether the images are clear; the visual system comprises two cameras (21) arranged at the same height; the height of the calibration circle is between the height of the highest point and the lowest point of the cargo loading mechanism (5); The lifting mechanism comprises a vertically arranged bracket (11), a mounting frame (12) slidably connected to the bracket (11), a screw rod (13) drivingly connected to the mounting frame (12), and a first motor (10) drivingly connected to the screw rod (13); the first motor (10) is fixedly connected to the bracket (11); the control box (6) controls the start or stop of the first motor (10), and the control box (6) controls the rotation direction of the power output by the first motor (10); The identification system further comprises a translation mechanism, the mounting frame (12) being provided with a second motor (70), and further comprising a horizontal conveyor belt (71) drivingly connected to the second motor (70), the conveyor belt (71) being fixedly connected to a camera carrier (22), and the camera (21) being arranged on the camera carrier (22); The identification method of the identification system comprises the following steps: S1, the visual system collects images of external target objects and transmits the images to the control box (6); S2, the control box (6) identifies the image and determines whether the image is clear; S3, if the picture is clear, the recognition is completed; if the picture is not clear, the control box (6) controls the lifting mechanism to rise or fall, and then returns to S1; When a clear image of the object can be captured, the control box (6) uses the visual system to sense the positions of the object and the calibration circle, and adjusts the manipulator (4) according to the machine coordinates of the object, thereby achieving the function of accurately grasping the object.

2. The material picking mechanism according to claim 1, characterized in that: The translation mechanism comprises two limit blocks (72) fixedly connected to the mounting frame (12), and the two limit blocks (72) are respectively arranged on the left side and the right side of the camera carrier (22).

3. The material picking mechanism according to claim 1, characterized in that: The cargo loading mechanism (5) is an AGV trolley, and the control box (6) controls the movement of the AGV trolley.

Images