Binocular vision-based cartridge holder positioning system and method

Abstract

The invention discloses a cartridge holder positioning system and method based on binocular vision. The cartridge holder positioning system comprises a first vision camera, a second vision camera, a three-axis mechanical arm, an industrial personal computer and a vibration disc. The first visual camera is positioned above the vibration disc and is higher than the top end of the three-axis manipulator; the second visual camera is located above the vibration disc and is higher than the top end of the three-axis manipulator; the material taking end of the three-axis mechanical arm is located above the vibration disc. And the industrial personal computer can calculate and calibrate the coordinates of the cartridge holder and control the movement of the three-axis manipulator. The coordinate position of the cartridge clip is obtained through the two visual cameras, the coordinate position of the cartridge clip in the vibration disc can be accurately obtained, then the path of grabbing the cartridge clip of the three-axis mechanical arm is accurately obtained according to the coordinate position of the three-axis mechanical arm relative to the vibration disc, and therefore the feeding positioning precision of the cartridge clip can be effectively improved, and the production efficiency is improved. And therefore, the loading efficiency of the cartridge holder is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of magazine production, and in particular to a magazine positioning system and method based on binocular vision. Background Art

[0002] In the prior art, in mechanical equipment for loading magazines, the magazine needs to be turned over by a vibration plate and then positioned by a visual camera, so that a three-axis robot can take out the magazine and put it into the processing station of the loading equipment.

[0003] The existing method of positioning the magazine is to calibrate the coordinates of the magazine in the vibration plate through a monocular camera. Due to the thickness of the magazine and the influence of the visual depth of field, the positioning of the magazine is often inaccurate, thus affecting the grasping efficiency of the three-axis manipulator.

[0004] Therefore, how to improve the positioning accuracy of the magazine to improve the grasping efficiency of the three-axis manipulator is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] One object of the present invention is to provide a magazine positioning system based on binocular vision, which can effectively improve the positioning accuracy of the magazine. Another object of the present invention is to provide a magazine positioning method based on binocular vision.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A magazine positioning system based on binocular vision, comprising: a first vision camera, a second vision camera, a three-axis manipulator, an industrial computer and a vibration plate;

[0008] The first visual camera is located above the vibration plate and is higher than the top of the three-axis manipulator. The first visual camera is used to measure and calibrate the coordinate position of the clip on the vibration plate.

[0009] The second visual camera is located above the vibration plate and is higher than the top of the three-axis manipulator. The second visual camera is used to measure and calibrate the coordinate position of the clip on the vibration plate.

[0010] The material taking end of the three-axis manipulator is located above the vibration plate;

[0011] The industrial computer is connected to the first visual camera, the second visual camera, the three-axis manipulator and the vibration plate;

[0012] The industrial computer includes a coordinate system establishment module, and the coordinate system establishment module is used to establish a first visual camera coordinate system, a second visual camera coordinate system, a three-axis manipulator coordinate system and a vibration disk coordinate system according to the left-hand rule, the coordinate origin of the first visual camera coordinate system is the projection point of the first visual camera on the vibration disk, the coordinate origin of the second visual camera coordinate system is the projection point of the second visual camera on the vibration disk, the coordinate origin of the three-axis manipulator coordinate system is the intersection of the axes of the three-axis manipulator working axes, and the coordinate origin of the vibration disk coordinate system is the geometric center point of the vibration disk;

[0013] The industrial computer further includes a coordinate processing module, which is used to obtain the coordinate position of the clip in the vibration plate coordinate system according to the coordinate position of the clip acquired by the first visual camera and the second visual camera and the vibration plate coordinate system;

[0014] The industrial computer also includes a path planning module, which is used to obtain a path for the three-axis manipulator to grab the magazine according to the coordinate values ​​of the calibrated coordinates of the three-axis manipulator coordinate system in the vibration plate coordinate system.

[0015] In some embodiments, the magazine positioning system further includes a light source module, which is disposed directly below the vibration plate and is used to provide a background light source for the first visual camera and the second visual camera.

[0016] In some embodiments, the coordinate origin of the vibration plate coordinate system is equidistant from the coordinate origin of the first visual camera coordinate system and the coordinate origin of the second visual camera coordinate system in the x-axis direction.

[0017] In some embodiments, a suction cup is provided at the material picking end of the three-axis manipulator, and the suction cup is used to absorb the magazine from the vibration plate.

[0018] In some embodiments, the second visual camera is located on the right side of the first visual camera, and the material picking end of the three-axis manipulator is located on the left side of the first visual camera.

[0019] A method for locating a magazine based on binocular vision comprises the following steps:

[0020] Step S1: The vibration plate vibrates to turn the magazine over, and performs matching calculation based on the magazine contour template to form a matching array [d 1, d 2 ,d 3 ........], each matching array contains the angle θ 1i , coordinates (x 1i o 1i y 1i z 1i), coordinates (x 2i o 2i y 2i z 2i )、matching success rate k 1 , where: matching array d 1 Contains {θ 1i , coordinates (x 1i o 1i y 1i z 1i ), coordinates (x 2i o 2i y 2i z 2i )、k 1}Three parameters;

[0021] Step S2: Based on the success rate k 1 Sort the matching array and put k 1 The magazines with a value of less than 0.8 are discarded, and the priority of grabbing the flipped magazines is determined based on the sorting of the matching array;

[0022] Step S3: Extract the captured clip in the coordinate system (x 1i o 1i y 1i z 1i ) and the coordinate system (x 2i o 2i y 2i z 2i ) in the coordinate system (x 4i o 4i y 4i z 4i ) in the value;

[0023] Step S4: Determine the coordinate value of the captured clip at x 4i The positive and negative values ​​of the direction, if it is a positive value, the clip position is in the vibration plate B area, if it is a negative value, the clip position is in the vibration plate A area;

[0024] Step S5: According to the depth of field principle, if the clip is in area A, the first visual camera obtains point A and point B in the coordinate system (x 4i o 4i y 4i z 4i ) is the calibration value, and the coordinate values ​​of point A and point B obtained by the second vision camera are the calibration values; if the clip is in area B, the coordinate system (x 4i o 4i y 4i z 4i ) are the calibration values, and the coordinate values ​​of point A and point B obtained by the first visual camera are the calibration values;

[0025] Step S6: Calculate the calibration error of the magazine. If it is in area A, the difference between the absolute value of the coordinates of point A and point B of the magazine obtained by the second visual camera and the absolute value of the coordinates of point A and point B of the magazine obtained by the first visual camera is the error correction value; if it is in area B, the difference between the absolute value of the coordinates of point A and point B of the magazine obtained by the first visual camera and the absolute value of the coordinates of point A and point B of the magazine obtained by the second visual camera is the error correction value;

[0026] Step S7: Solve the three-axis manipulator coordinate system (x 3 o 3 y 3 z 3 ) is calibrated in the vibration plate coordinate system (x 4 o 4 y 4 z 4 ) and plan the grabbing path from the three-axis manipulator to points A and B of the magazine;

[0027] Step S8: Repeat the above steps until the clips in the matching array are captured.

[0028] Compared with the prior art, the above technical solution has the following advantages:

[0029] The present invention provides a binocular vision-based magazine positioning system, comprising: a first visual camera, a second visual camera, a three-axis manipulator, an industrial computer and a vibration plate. The industrial computer can calculate and calibrate the coordinates of the magazine and control the movement of the three-axis manipulator. The present invention obtains the coordinate position of the magazine through two visual cameras, and can accurately obtain the coordinate position of the magazine in the vibration plate, and then accurately obtain the path of the three-axis manipulator to grab the magazine according to the coordinate position of the three-axis manipulator relative to the vibration plate, so that the positioning accuracy of the magazine feeding can be effectively improved, thereby improving the magazine feeding efficiency.

[0030] The magazine positioning method provided by the present invention is not affected by the thickness of the magazine and the visual depth of field, and can accurately obtain the coordinate position of the magazine in the vibration plate, thereby enabling the three-axis manipulator to accurately grasp the magazine, thereby effectively improving the magazine loading positioning accuracy and thereby improving the magazine loading efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0032] Figure 1 A schematic structural diagram of a magazine positioning system based on binocular vision provided in a specific embodiment of the present invention;

[0033] Figure 2 A schematic diagram of the coordinate system and partitions of a magazine positioning system based on binocular vision provided by a specific embodiment of the present invention;

[0034] Figure 3 A clip pattern matching parameter diagram of a clip positioning system based on binocular vision provided in a specific embodiment of the present invention.

[0035] The reference numerals are as follows:

[0036] 1-first vision camera, 2-second vision camera, 3-three-axis manipulator, 4-vibration plate, 5-clip, 51-clip contour template. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Please refer to Figure 1-Figure 3 .

[0039] A binocular vision-based magazine 5 positioning system provided in an embodiment of the present invention comprises: a first vision camera 1, a second vision camera 2, a three-axis manipulator 3, an industrial computer and a vibration disk 4; wherein the first vision camera 1 is located above the vibration disk 4, and its position height is higher than the top of the three-axis manipulator 3, and the first vision camera 1 is used to measure, calibrate and calibrate the coordinate position of the magazine 5 on the vibration disk 4; the second vision camera 2 is located above the vibration disk 4, and its position height is higher than the top of the three-axis manipulator 3, and the second vision camera 2 is used to measure, calibrate and calibrate the coordinate position of the magazine 5 on the vibration disk 4, and the magazine 5 positioning system further comprises a light source module, which is arranged directly below the vibration disk 4 and is used to provide a background light source for the first vision camera 1 and the second vision camera 2; the material picking end of the three-axis manipulator 3 is located above the vibration disk 4, the second vision camera 2 is located on the right side of the first vision camera 1, and the material picking end of the three-axis manipulator 3 is located on the left side of the first vision camera 1 On the left side, a suction cup is provided at the material-picking end of the three-axis manipulator 3, which is used to absorb the clip 5 from the vibration disk 4; the industrial computer is connected to the first visual camera 1, the second visual camera 2, the three-axis manipulator 3 and the vibration disk 4; the industrial computer includes a coordinate system establishment module, which is used to establish the first visual camera coordinate system, the second visual camera coordinate system, the three-axis manipulator coordinate system and the vibration disk coordinate system according to the left-hand rule, the coordinate origin of the first visual camera 1 coordinate system is the projection point of the first visual camera 1 on the vibration disk 4, the coordinate origin of the second visual camera coordinate system is the projection point of the second visual camera 2 on the vibration disk 4, the coordinate origin of the three-axis manipulator coordinate system is the intersection of the axes of the working axes of the three-axis manipulator 3, the coordinate origin of the vibration disk coordinate system is the geometric center point of the vibration disk 4, and the coordinate origin of the vibration disk coordinate system is equidistant from the coordinate origin of the first visual camera 1 coordinate system and the coordinate origin of the second visual camera coordinate system in the x-axis direction.

[0040] The industrial computer also includes a coordinate processing module, which is used to obtain the coordinate position of the clip 5 in the vibration disk coordinate system based on the coordinate position of the clip 5 obtained by the first visual camera 1 and the second visual camera 2 and the vibration disk coordinate system; the industrial computer also includes a path planning module, which is used to obtain the path of the three-axis manipulator 3 to grasp the clip 5 based on the coordinate value of the calibrated coordinates of the three-axis manipulator coordinate system in the vibration disk coordinate system.

[0041] The present invention uses two visual cameras to obtain the coordinate position of the clip 5, and can accurately obtain the coordinate position of the clip 5 in the vibration plate 4, and then accurately obtain the path of the three-axis manipulator 3 to grab the clip 5 according to the coordinate position of the three-axis manipulator 3 relative to the vibration plate 4, thereby effectively improving the loading positioning accuracy of the clip 5, thereby improving the loading efficiency of the clip 5.

[0042] Please refer to Figure 1-Figure 3 .

[0043] An embodiment of the present invention provides a binocular vision-based magazine positioning method, comprising the following steps:

[0044] Step S1: The vibration plate 4 vibrates to turn over the magazine 5, and performs matching calculation according to the magazine contour template 51 to form a matching array [d 1, d 2 ,d 3 ........], each matching array contains the angle θ 1i , coordinates (x 1i o 1i y 1i z 1i ), coordinates (x 2i o 2i y 2i z 2i )、matching success rate k 1 , where: matching array d 1 Contains {θ 1i , coordinates (x 1i o 1i y 1i z 1i ),, coordinates (x 2i o 2i y 2i z 2i )、k 1}Three parameters;

[0045] Step S2: Based on the success rate k 1 Sort the matching array and put k 1 Clip 5 with a value less than 0.8 is discarded, and the priority of grabbing the flipped clip 5 is determined based on the sorting of the matching array;

[0046] Step S3: Extract the captured clip 5 in the coordinate system (x 1i o 1i y 1i z 1i ) and the coordinate system (x 2i o 2i y 2i z 2i ) in the coordinate system (x 4i o 4i y 4i z 4i ) in the value;

[0047] Step S4: Determine the coordinate value of the captured clip at x 4i The positive and negative values ​​of the direction, if it is a positive value, the clip position is in the vibration plate 4B area, if it is a negative value, the clip position is in the vibration plate 4A area;

[0048] Step S5: According to the depth of field principle, if the clip 5 is in area A, the points A and B acquired by the first visual camera 1 are in the coordinate system (x 4i o 4i y 4i z 4i ) is the calibration value, and the coordinate values ​​of point A and point B obtained by the second visual camera 2 are the calibration values; if the clip 5 is in area B, the coordinate system (x 4i o 4i y 4i z 4i ) are calibration values, and the coordinate values ​​of point A and point B acquired by the first visual camera 1 are calibration values;

[0049] Step S6: Calculate the calibration error of the clip. If it is in area A, the difference between the absolute value of the coordinates of point A and point B of the clip obtained by the second visual camera 2 and the absolute value of the coordinates of point A and point B of the clip obtained by the first visual camera 1 is the error correction value; if it is in area B, the difference between the absolute value of the coordinates of point A and point B of the clip obtained by the first visual camera 1 and the absolute value of the coordinates of point A and point B of the clip obtained by the second visual camera 2 is the error correction value;

[0050] Step S7: Solve the coordinate system (x 3 o 3 y 3 z 3 ) is calibrated in the vibration plate 4 coordinate system (x 4 o 4 y 4 z 4 ) and plan the grabbing path from the three-axis manipulator 3 to the clip points A and B;

[0051] Step S8: Repeat the above steps until all the clips 5 in the matching array are captured.

[0052] The method for positioning the magazine 5 provided by the present invention is not affected by the thickness of the magazine 5 and the visual depth of field, and can accurately obtain the coordinate position of the magazine 5 in the vibration plate 4, thereby enabling the three-axis manipulator 3 to accurately grasp the magazine 5, thereby effectively improving the loading positioning accuracy of the magazine 5, and thereby improving the loading efficiency of the magazine 5.

[0053] It should be noted that, in this specification, relational terms such as first and second are merely used to distinguish one entity from other entities, but do not necessarily require or imply any actual relationship or order between these entities.

[0054] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0055] The above is a detailed introduction to a binocular vision-based magazine positioning system and method provided by the present invention. This article uses specific examples to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method and core ideas of the present invention. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, the present invention can also be improved and modified in a number of ways, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. A magazine positioning system based on binocular vision, characterized in that: include: First vision camera, second vision camera, three-axis manipulator, industrial computer and vibration plate; The first visual camera is located above the vibration plate and is higher than the top of the three-axis manipulator. The first visual camera is used to measure and calibrate the coordinate position of the clip on the vibration plate. The second visual camera is located above the vibration plate and is higher than the top of the three-axis manipulator. The second visual camera is used to measure and calibrate the coordinate position of the clip on the vibration plate. The material taking end of the three-axis manipulator is located above the vibration plate; The industrial computer is connected to the first visual camera, the second visual camera, the three-axis manipulator and the vibration plate; The industrial computer includes a coordinate system establishment module, and the coordinate system establishment module is used to establish a first visual camera coordinate system, a second visual camera coordinate system, a three-axis manipulator coordinate system and a vibration disk coordinate system according to the left-hand rule, the coordinate origin of the first visual camera coordinate system is the projection point of the first visual camera on the vibration disk, the coordinate origin of the second visual camera coordinate system is the projection point of the second visual camera on the vibration disk, the coordinate origin of the three-axis manipulator coordinate system is the intersection of the axes of the three-axis manipulator working axes, and the coordinate origin of the vibration disk coordinate system is the geometric center point of the vibration disk; The industrial computer further includes a coordinate processing module, which is used to obtain the coordinate position of the clip in the vibration plate coordinate system according to the coordinate position of the clip acquired by the first visual camera and the second visual camera and the vibration plate coordinate system; The industrial computer also includes a path planning module, which is used to obtain a path for the three-axis manipulator to grab the magazine according to the coordinate values ​​of the calibrated coordinates of the three-axis manipulator coordinate system in the vibration plate coordinate system.

2. The binocular vision-based magazine positioning system according to claim 1, characterized in that: It also includes a light source module, which is arranged directly below the vibration plate and is used to provide a background light source for the first visual camera and the second visual camera.

3. The binocular vision-based magazine positioning system according to claim 2, characterized in that: The coordinate origin of the vibration plate coordinate system is equidistant from the coordinate origin of the first visual camera coordinate system and the coordinate origin of the second visual camera coordinate system in the x-axis direction.

4. The binocular vision-based magazine positioning system according to claim 3, characterized in that: A suction cup is provided at the material taking end of the three-axis manipulator, and the suction cup is used to absorb the magazine from the vibration plate.

5. The binocular vision-based magazine positioning system according to claim 4, characterized in that: The second visual camera is located on the right side of the first visual camera, and the material picking end of the three-axis manipulator is located on the left side of the first visual camera.

6. A method for locating a magazine based on binocular vision, characterized in that: The following steps are involved: Step S1: The vibration plate vibrates to turn the magazine over, and performs matching calculation based on the magazine contour template to form a matching array [d 1, d2,d3........], each matching array contains the angle θ 1i , coordinates (x 1i o 1i y 1i z 1i ), coordinates (x 2i o 2i y 2i z 2i ), matching success rate k1, where: matching array d1 contains {θ 1i , coordinates (x 1i o 1i y 1i z 1i ),, coordinates (x 2i o 2i y 2i z 2i ), k1} three parameters; Step S2: sorting the matching array according to the success rate k1, removing the magazines with k1 values ​​less than 0.8, and determining the grabbing priority of the flipped magazines according to the sorting of the matching array; Step S3: Extract the captured clip in the coordinate system (x 1i o 1i y 1i z 1i ) and the coordinate system (x 2i o 2i y 2i z 2i ) in the coordinate system (x 4i o 4i y 4i z 4i ) in the value; Step S4: Determine the coordinate value of the captured clip at x 4i The positive and negative values ​​of the direction, if it is a positive value, the clip position is in the vibration plate B area, if it is a negative value, the clip position is in the vibration plate A area; Step S5: According to the depth of field principle, if the clip is in area A, the first visual camera obtains point A and point B in the coordinate system (x 4i o 4i y 4i z 4i ) is the calibration value, and the coordinate values ​​of point A and point B obtained by the second vision camera are the calibration values; if the clip is in area B, the coordinate system (x 4i o 4i y 4i z 4i ) are the calibration values, and the coordinate values ​​of point A and point B obtained by the first visual camera are the calibration values; Step S6: Calculate the calibration error of the magazine. If it is in area A, the difference between the absolute value of the coordinates of point A and point B of the magazine obtained by the second visual camera and the absolute value of the coordinates of point A and point B of the magazine obtained by the first visual camera is the error correction value; if it is in area B, the difference between the absolute value of the coordinates of point A and point B of the magazine obtained by the first visual camera and the absolute value of the coordinates of point A and point B of the magazine obtained by the second visual camera is the error correction value; Step S7: by using the coordinate transformation matrix, the coordinate values ​​of the calibrated coordinates of the three-axis manipulator coordinate system (x3o3y3z3) in the vibration plate coordinate system (x4o4y4z4) are solved, and the grasping path planning from the three-axis manipulator to the clip point A and point B is performed; Step S8: Repeat the above steps until the clips in the matching array are captured.

Images