Vehicle body positioning system and method based on multi-view stereoscopic vision

Abstract

The invention discloses a vehicle body positioning system and method based on multi-view stereoscopic vision, and the system comprises a first scanning robot system, a second scanning robot system, a first installation robot system, a second installation robot system, and a vehicle body. The first scanning robot system, the second scanning robot system, the first installation robot system and the second installation robot system are all arranged on the side of the vehicle body, and a first glue tower is installed on the side of the first installation robot system. According to the vehicle body positioning system and method based on the multi-view stereoscopic vision, the sampling speed is up to 64K / s and is dozens to hundreds of times that of other similar products, multiple profiles can be measured, the influence of accidental factors such as small-range welding slag sinking on the measurement result is avoided, the measurement result is not influenced by the color of a vehicle body, nearly thousands of bottom layer image processing operators are arranged, and the measurement accuracy is greatly improved. A plurality of 3D vision algorithms and calibration methods are supported, and a bottom layer algorithm automatically supports multiple threads.

Description

Technical Field

[0001] The present invention relates to the field of vehicle body positioning systems, and in particular to a vehicle body positioning system and method based on multi-eye stereo vision. Background Art

[0002] The body positioning system is a visual product used for non-contact positioning of the body and guiding the robot to achieve process adjustment. It uses multiple sets of sensors to process the images of multiple feature points on the body to solve the 6-DOF position change of the body in space, thereby guiding the machine to correct the trajectory. With the continuous development of science and technology, people's requirements for the body positioning system are getting higher and higher.

[0003] The existing body positioning system has certain drawbacks when in use. First of all, the accuracy of the existing body positioning system cannot meet the requirements well when in use, the measurement stability performance is poor, and it cannot identify the bodies of different colors well, which is not conducive to people's use. In addition, the operation reliability of the visual system is poor, and the positioning camera has poor stability in capturing the bodies of different colors, which brings certain adverse effects to people's use process. For this reason, we propose a body positioning system and method based on multi-eye stereo vision. Summary of the invention

[0004] Technical problems solved: In view of the shortcomings of the prior art, the present invention provides a vehicle body positioning system and method based on multi-eye stereo vision, with a sampling speed of up to 64K / s, which is dozens to hundreds of times that of other similar products. It can measure multiple contours and avoid the influence of accidental factors such as small-scale welding slag depressions on the measurement results. The measurement results are not affected by the color of the vehicle body. There are nearly a thousand underlying image processing operators, supporting a variety of 3D vision algorithms and calibration methods. The underlying algorithm automatically supports multi-threading, which can effectively solve the problems in the background technology.

[0005] Technical solution: To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a car body positioning system based on multi-eye stereo vision, comprising a first scanning robot system, a second scanning robot system, a first installation robot system, a second installation robot system and a car body, the first scanning robot system, the second scanning robot system, the first installation robot system and the second installation robot system are all arranged on the side of the car body, a first glue tower is installed on the side of the first installation robot system, a first glue type detector is arranged on the first glue tower, a first installation support is arranged at the bottom of the first installation robot system, a second glue tower is installed on the side of the second installation robot system, a second glue type detector is arranged on the second glue tower, a second installation robot system is arranged at the bottom of the second installation robot system, a first laser profiler is arranged at the end of the first scanning robot system, a second laser profiler is arranged at the end of the second scanning robot system, and a car body positioning vision cabinet and a glue type detection vision cabinet are arranged on the sides of the first scanning robot system and the second scanning robot system.

[0006] As a preferred technical solution of the present application, the first scanning robot system includes a vision cabinet main body, a vision display mechanism, an industrial computer, a laser head controller, communication cables, laser head cables, IO cables, a control cabinet, a robot body, a robot arm, a laser connector, a laser probe and a robot control system. The vision display mechanism, the industrial computer and the laser head controller are all arranged inside the vision cabinet main body, the laser connector is connected to the laser probe, the laser head cable is connected between the laser head controller and the laser connector, and the IO cable and the communication cable are both connected between the vision cabinet main body and the control cabinet.

[0007] As a preferred technical solution of the present application, the first scanning robot system monitors the vehicle body through a first laser profiler, the second scanning robot system monitors the vehicle body through a second laser profiler, and the first scanning robot system and the second scanning robot system are controlled to work through a vehicle body positioning vision cabinet.

[0008] As a preferred technical solution of the present application, the first installation robot system monitors the glue type through a first glue type detector, the second installation robot system monitors the glue type through a second glue type detector, and the operation of the first installation robot system and the second installation robot system are controlled by a glue type detection vision cabinet.

[0009] As a preferred technical solution of the present application, the industrial computer is electrically connected to the laser head controller, the laser head controller is connected to the laser probe via a laser head cable and a laser connector, and the visual cabinet body and the control cabinet are connected via a communication cable and an IO cable.

[0010] As a preferred technical solution of the present application, the robot body controls and adjusts the angle between the robot arm and the laser probe through a robot control system.

[0011] A vehicle body positioning method based on multi-eye stereo vision includes the following steps: S1: The visual system mainly includes 1 control cabinet, 2 industrial computers, and 2 laser profilers; S2: A laser profiler is installed on each of the front and rear windshield robot fixtures. The robot uses the profiler to scan and measure the frame of the windshield frame of the vehicle body, thereby accurately locating the position of the window frame; S3: Scan the four positions marked on the front and rear windshields of the vehicle body; S4: During the gluing process of the gluing robot, the scanning machine performs scanning and positioning, and it can be directly installed after the gluing is completed, which can meet the 70JPH production requirements; S5: The visual software has an alignment display function. After the current car is offset, that is, the position of the visual positioning is offset, if the visual positioning accuracy is OK, the model car is completely consistent with the current car, otherwise there is a deviation in positioning or body size, which is convenient for subsequent analysis and processing; S6: When creating a model, the modeling area can be set by dragging in 3D visualization, and the area to be modeled is more intuitively displayed; S7: The vision software has added a new function to measure the spatial distance between the model vehicle and the current vehicle. It can measure the distance at any position, which is convenient for analyzing positioning deviation and vehicle body size deviation.

[0012] As a preferred technical solution of the present application, an ultra-high-speed laser profiler is used in the S1 step, with a sampling speed of up to 64K / s, which can measure multiple profiles and avoid the influence of small-scale welding slag depressions on the measurement results.

[0013] Beneficial effects: Compared with the prior art, the present invention provides a vehicle body positioning system and method based on multi-eye stereo vision, which has the following beneficial effects: the vehicle body positioning system and method based on multi-eye stereo vision has a sampling speed of up to 64K / s, which is dozens to hundreds of times that of other similar products. It can measure multiple contours to avoid the influence of accidental factors such as small-scale welding slag depressions on the measurement results. The measurement results are not affected by the color of the vehicle body. There are nearly a thousand underlying image processing operators, which support a variety of 3D vision algorithms and calibration methods. The underlying algorithm automatically supports multi-threading. The visual system mainly includes 1 control cabinet, 2 industrial computers, and 2 laser profilers; 1 laser profiler is installed on the fixtures of the front and rear windshield robots respectively. The robot carries the profiler to scan and measure the frame of the windshield frame of the vehicle body, so as to accurately locate the position of the window frame. ; Scan the 4 positions marked on the front and rear windshields on the vehicle body; During the gluing process of the gluing robot, the scanning machine performs scanning and positioning, and it can be directly installed after gluing is completed, which can meet the 70JPH production requirements; The visual software has an alignment display function, which offsets the current vehicle, that is, after the visual positioning position is offset, if the visual positioning accuracy is OK, the model vehicle is completely consistent with the current vehicle, otherwise there is a deviation in positioning or body size, which is convenient for subsequent analysis and processing; When creating a model, 3D visualization drags to set the modeling area, and the area to be modeled is more intuitively displayed; The visual software has a new function of measuring the spatial distance between the model vehicle and the current vehicle, which can measure the distance at any position, which is convenient for analyzing positioning deviations and body size deviations. The entire body positioning system has a simple structure, easy operation, and better effect than traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The figure is a schematic diagram of the overall structure of a vehicle body positioning system and method based on multi-eye stereo vision of the present invention.

[0015] Figure 2 The present invention is a schematic structural diagram of a scanning robot system in a vehicle body positioning system and method based on multi-eye stereo vision.

[0016] Figure 3 The present invention is a schematic structural diagram of a robot system installed in a vehicle body positioning system and method based on multi-eye stereo vision.

[0017] Figure 4 The present invention is a structural schematic diagram of a visual cabinet main body in a vehicle body positioning system and method based on multi-eye stereo vision.

[0018] Figure 5 The present invention is a schematic structural diagram of a robot body in a vehicle body positioning system and method based on multi-eye stereo vision.

[0019] In the figure: 1. first scanning robot system; 2. body positioning vision cabinet; 3. glue type detection vision cabinet; 4. second scanning robot system; 5. second laser profiler; 6. first laser profiler; 7. first glue type detector; 8. first glue tower; 9. first mounting support; 10. first mounting robot system; 11. second mounting robot system; 12. second mounting support; 13. second glue tower; 14. second glue type detector; 15. vehicle body; 16. vision cabinet body; 17. visual display mechanism; 18. industrial computer; 19. laser head controller; 20. communication cable; 21. laser head cable; 22. IO cable; 23. control cabinet; 24. robot body; 25. robot arm; 26. laser connector; 27. laser probe; 28. robot control system. DETAILED DESCRIPTION

[0020] The technical scheme of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and specific embodiments, but it will be appreciated by those skilled in the art that the following described embodiments are part of embodiments of the present invention, rather than all embodiments, and are only used to illustrate the present invention, and should not be considered as limiting the scope of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative work, all belong to the scope of protection of the present invention. If the specific conditions are not indicated in the embodiments, they are carried out according to the normal conditions or the conditions recommended by the manufacturer. If the manufacturer is not indicated in the reagents or instruments used, they are all conventional products that can be purchased commercially.

[0021] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0022] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0023] like Figure 1-5As shown, a vehicle body positioning system based on multi-eye stereo vision includes a first scanning robot system 1, a second scanning robot system 4, a first installation robot system 10, a second installation robot system 11 and a vehicle body 15. The first scanning robot system 1, the second scanning robot system 4, the first installation robot system 10 and the second installation robot system 11 are all arranged on the side of the vehicle body 15. A first glue tower 8 is installed on the side of the first installation robot system 10, and a first glue pattern detector 7 is arranged on the first glue tower 8. A first installation support 9 is arranged at the bottom of the first installation robot system 10. A second glue tower 13 is installed on the side of the second installation robot system 11, and a second glue pattern detector 7 is arranged on the second glue tower 13. A second mounting robot system 12 is arranged at the bottom of the second mounting robot system 11, a first laser profiler 6 is arranged at the end of the first scanning robot system 1, and a second laser profiler 5 is arranged at the end of the second scanning robot system 4. Body positioning vision cabinet 2 and glue type detection vision cabinet 3 are arranged on the sides of the first scanning robot system 1 and the second scanning robot system 4. The sampling speed is as high as 64K / s, which is dozens to hundreds of times that of other similar products. Multiple contours can be measured to avoid the influence of accidental factors such as small-scale welding slag depressions on the measurement results. The measurement results are not affected by the color of the body. There are nearly a thousand underlying image processing operators, which support a variety of 3D vision algorithms and calibration methods, and the underlying algorithm automatically supports multi-threading.

[0024] Furthermore, the first scanning robot system 1 includes a visual cabinet body 16, a visual display mechanism 17, an industrial computer 18, a laser head controller 19, a communication cable 20, a laser head cable 21, an IO cable 22, a control cabinet 23, a robot body 24, a robot arm 25, a laser connector 26, a laser probe 27 and a robot control system 28. The visual display mechanism 17, the industrial computer 18 and the laser head controller 19 are all arranged inside the visual cabinet body 16, the laser connector 26 is connected to the laser probe 27, the laser head cable 21 is connected between the laser head controller 19 and the laser connector 26, and the IO cable 22 and the communication cable 20 are both connected between the visual cabinet body 16 and the control cabinet 23.

[0025] Furthermore, the first scanning robot system 1 monitors the vehicle body through the first laser profiler 6 , the second scanning robot system 4 monitors the vehicle body through the second laser profiler 5 , and the vehicle body positioning vision cabinet 2 controls the operation of the first scanning robot system 1 and the second scanning robot system 4 .

[0026] Furthermore, the first installation robot system 10 monitors the glue type through the first glue type detector 7, and the second installation robot system 11 monitors the glue type through the second glue type detector 14, and the first installation robot system 10 and the second installation robot system 11 are controlled to work through the glue type detection visual cabinet 3.

[0027] Furthermore, the industrial computer 18 is electrically connected to the laser head controller 19 , the laser head controller 19 is connected to the laser probe 27 via a laser head cable 21 and a laser connector 26 , and the visual cabinet body 16 and the control cabinet 23 are connected via a communication cable 20 and an IO cable 22 .

[0028] Furthermore, the robot body 24 controls and adjusts the angle between the robot arm 25 and the laser probe 27 through the robot control system 28 .

[0029] A vehicle body positioning method based on multi-eye stereo vision includes the following steps: S1: The visual system mainly includes 1 control cabinet, 2 industrial computers, and 2 laser profilers; S2: A laser profiler is installed on each of the front and rear windshield robot fixtures. The robot uses the profiler to scan and measure the frame of the windshield frame of the vehicle body, thereby accurately locating the position of the window frame; S3: Scan the four positions marked on the front and rear windshields of the vehicle body; S4: During the gluing process of the gluing robot, the scanning machine performs scanning and positioning, and it can be directly installed after the gluing is completed, which can meet the 70JPH production requirements; S5: The visual software has an alignment display function. After the current car is offset, that is, the position of the visual positioning is offset, if the visual positioning accuracy is OK, the model car is completely consistent with the current car, otherwise there is a deviation in positioning or body size, which is convenient for subsequent analysis and processing; S6: When creating a model, the modeling area can be set by dragging in 3D visualization, and the area to be modeled is more intuitively displayed; S7: The vision software has added a new function to measure the spatial distance between the model vehicle and the current vehicle. It can measure the distance at any position, which is convenient for analyzing positioning deviation and vehicle body size deviation.

[0030] Furthermore, an ultra-high-speed laser profile measuring instrument is used in step S1, with a sampling speed of up to 64K / s, which can measure multiple profiles and avoid the influence of small-scale welding slag depression on the measurement results.

[0031] Working principle: The present invention includes a first scanning robot system 1, a vehicle body positioning vision cabinet 2, a glue type detection vision cabinet 3, a second scanning robot system 4, a second laser profiler 5, a first laser profiler 6, a first glue type detector 7, a first glue tower 8, a first mounting support 9, a first mounting robot system 10, a second mounting robot system 11, a second mounting robot system 12, a second glue tower 13, a second glue type detector 14, a vehicle body 15, a vision cabinet body 16, a visual display mechanism 17, an industrial computer 18, a laser head controller 19, a communication cable 20, a laser head cable 21, an IO cable 22, a control cabinet 23, a robot body 24, a robot arm 25, a laser connector 26, a laser probe 27, and a robot control system 28. The sampling speed is as high as 64K / second, which is dozens to hundreds of times that of other similar products. It can measure multiple contours and avoid the influence of accidental factors such as small-scale welding slag depressions on the measurement results. The measurement results are not affected by the color of the vehicle body. There are nearly a thousand underlying image processing operators and support for a variety of 3D vision algorithms. and calibration methods, the underlying algorithm automatically supports multi-threading, the visual system mainly includes 1 control cabinet, 2 industrial computers, and 2 laser profilers; a laser profiler is installed on the fixtures of the front and rear windshield robots respectively, and the robot uses the profiler to scan and measure the frame of the windshield frame of the vehicle body, so as to accurately locate the position of the window frame; scan the 4 positions marked on the front windshield and the rear windshield on the vehicle body; during the gluing process of the gluing robot, the scanning machine scans and locates, and it can be directly installed after the gluing is completed, which can meet the 70JPH production requirements; the visual software has an alignment display function, which will offset the current vehicle, that is, the position of the visual positioning will be offset. If the visual positioning accuracy is OK, the model car will be completely consistent with the current vehicle, otherwise there will be deviations in positioning or body size, which is convenient for subsequent analysis and processing; when creating a model, 3D visualization drags to set the modeling area, and the area to be modeled is more intuitively displayed; the visual software has a new spatial distance measurement function between the model vehicle and the current vehicle, which can measure the distance between any position, which is convenient for analyzing positioning deviations and body size deviations.

[0032] It should be noted that, in this article, relational terms such as first and second (number one, number two), etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0033] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A vehicle body positioning system based on multi-eye stereo vision, comprising a first scanning robot system (1), a second scanning robot system (4), a first installation robot system (10), a second installation robot system (11) and a vehicle body (15), characterized in that: The first scanning robot system (1), the second scanning robot system (4), the first installation robot system (10) and the second installation robot system (11) are all arranged on the side of a vehicle body (15); a first glue tower (8) is installed on the side of the first installation robot system (10); a first glue pattern detector (7) is arranged on the first glue tower (8); a first installation support (9) is arranged at the bottom of the first installation robot system (10); a second glue tower (13) is installed on the side of the second installation robot system (11); a second glue pattern detector (14) is arranged on the second glue tower (13); a second installation robot system (12) is arranged at the bottom of the second installation robot system (11); a first laser profiler (6) is arranged at the end of the first scanning robot system (1); a second laser profiler (5) is arranged at the end of the second scanning robot system (4); and a vehicle body positioning vision cabinet (2) and a glue pattern detection vision cabinet (3) are arranged on the sides of the first scanning robot system (1) and the second scanning robot system (4).

2. The vehicle body positioning system based on multi-eye stereo vision according to claim 1, characterized in that: The first scanning robot system (1) comprises a visual cabinet body (16), a visual display mechanism (17), an industrial computer (18), a laser head controller (19), a communication cable (20), a laser head cable (21), an IO cable (22), a control cabinet (23), a robot body (24), a robot arm (25), a laser connector (26), a laser probe (27) and a robot control system (28); the visual display mechanism (17), the industrial computer (18) and the laser head controller (19) are all arranged inside the visual cabinet body (16); the laser connector (26) is connected to the laser probe (27); the laser head cable (21) is connected between the laser head controller (19) and the laser connector (26); and the IO cable (22) and the communication cable (20) are both connected between the visual cabinet body (16) and the control cabinet (23).

3. The vehicle body positioning system based on multi-eye stereo vision according to claim 1, characterized in that: The first scanning robot system (1) monitors the vehicle body through a first laser profiler (6), the second scanning robot system (4) monitors the vehicle body through a second laser profiler (5), and the first scanning robot system (1) and the second scanning robot system (4) are controlled to work through a vehicle body positioning vision cabinet (2).

4. The vehicle body positioning system based on multi-eye stereo vision according to claim 1, characterized in that: The first installation robot system (10) monitors the glue type through a first glue type detector (7), and the second installation robot system (11) monitors the glue type through a second glue type detector (14), and the operation of the first installation robot system (10) and the second installation robot system (11) is controlled by a glue type detection vision cabinet (3).

5. The vehicle body positioning system based on multi-eye stereo vision according to claim 1, characterized in that: The industrial computer (18) is electrically connected to the laser head controller (19), the laser head controller (19) is connected to the laser probe (27) via a laser head cable (21) and a laser connector (26), and the visual cabinet body (16) is connected to the control cabinet (23) via a communication cable (20) and an IO cable (22).

6. The vehicle body positioning system based on multi-eye stereo vision according to claim 1, characterized in that: The robot body (24) controls and adjusts the angle between the robot arm (25) and the laser probe (27) through a robot control system (28).

7. A vehicle body positioning method based on multi-eye stereo vision, characterized in that: The steps include: S1: The visual system mainly includes 1 control cabinet, 2 industrial computers, and 2 laser profilers; S2: A laser profiler is installed on each of the front and rear windshield robot fixtures. The robot uses the profiler to scan and measure the frame of the windshield frame of the vehicle body, thereby accurately locating the position of the window frame; S3: Scan the four positions marked on the front and rear windshields of the vehicle body; S4: During the gluing process of the gluing robot, the scanning machine performs scanning and positioning, and it can be directly installed after the gluing is completed, which can meet the 70JPH production requirements; S5: The visual software has an alignment display function. After the current car is offset, that is, the position of the visual positioning is offset, if the visual positioning accuracy is OK, the model car is completely consistent with the current car, otherwise there is a deviation in positioning or body size, which is convenient for subsequent analysis and processing; S6: When creating a model, the modeling area can be set by dragging in 3D visualization, and the area to be modeled is more intuitively displayed; S7: The vision software has added a new function to measure the spatial distance between the model vehicle and the current vehicle. It can measure the distance at any position, which is convenient for analyzing positioning deviation and vehicle body size deviation.

8. The vehicle body positioning method based on multi-eye stereo vision according to claim 7, characterized in that: In the S1 step, an ultra-high-speed laser profile measuring instrument is used, with a sampling speed of up to 64K / s, which can measure multiple profiles and avoid the influence of small-scale welding slag depression on the measurement results.

Images