A spatial pose recognition system and method for structural components

Abstract

This invention belongs to the field of welding automation technology, specifically relating to a spatial pose recognition system and method for structural components. The system includes a robotic arm, a structured light trajectory scanner, and a controller. The structured light trajectory scanner is used to capture images of the workpiece's weld joint and send these images to the controller. The controller controls the robotic arm to move the structured light trajectory scanner along the workpiece's weld joint, maintaining a preset distance and angle between the scanner and the joint. It identifies the coordinates of the centerline of the weld joint based on the image and controls the robotic arm to move the welding torch along the centerline for welding. This invention obtains a precise pre-weld joint welding trajectory through scanning and automatically controls the welding torch's trajectory movement based on the fitted weld center point coordinate curve, reducing manual teaching and improving efficiency.

Description

Technical Field

[0001] This invention belongs to the field of welding automation technology, specifically relating to a spatial pose recognition system and method for structural components. Background Technology

[0002] In fields such as engineering machinery manufacturing and aerospace, welding technology, as a key process, occupies an indispensable and important position in the equipment manufacturing industry.

[0003] Currently, the trajectory recognition of the welding head of the boom in large engineering structures typically relies on manual teaching. However, manual teaching-based programming welding has the following main drawbacks: 1. The tediousness of manual teaching significantly reduces welding efficiency, especially for long and curved welds, severely increasing pre-weld preparation time. 2. It is difficult to effectively control the position of the welding torch relative to the weld center during the welding process. Teaching-and-reproducibility welding operations are increasingly unable to meet the demands of intelligent production; intelligent and autonomous welding is the inevitable trend in the development of various welding methods.

[0004] Therefore, intelligent welding trajectory control of structural component joints urgently needs to be realized. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a spatial pose recognition system and method for structural components. By scanning, a precise welding trajectory of the pre-weld joint is obtained, and the trajectory movement of the welding torch is automatically controlled based on the fitted coordinate curve of the weld center point, reducing manual teaching and improving efficiency.

[0006] To address the shortcomings of existing technologies, the technical solution provided by this invention is as follows:

[0007] A spatial pose recognition system for structural components includes a robotic arm, a structured light trajectory scanner, and a controller;

[0008] The structured light trajectory scanner is used to capture images of the workpiece's weld joint and send these images to the controller.

[0009] The controller is used to control the robot arm to move the structured light trajectory scanner along the head of the workpiece to be welded and to maintain a preset distance and preset angle between the structured light trajectory scanner and the head of the workpiece to be welded; to identify the coordinates of the center line of the head of the workpiece to be welded based on the image of the head of the workpiece to be welded; and to control the robot arm to move the welding torch along the center line of the head of the workpiece to be welded for welding.

[0010] Preferably, it also includes a movable slide table and a movable slide table suspension beam, the movable slide table being located on one side of the workpiece, the movable slide table suspension beam and the movable slide table being slidably connected, and the base of the robot being fixedly connected to the movable slide table suspension beam.

[0011] Preferably, it also includes a workpiece support device; the workpiece support device includes a workpiece positioner base plate, a workpiece positioner column fixed on the workpiece positioner base plate, and a workpiece positioner fixed on the workpiece positioner column.

[0012] The displacement chuck of the workpiece positioner is connected to the workpiece.

[0013] Preferably, the controller identifies the coordinates of the centerline of the workpiece's joint to be welded by following these steps:

[0014] An RNN neural network is used to extract the core region of the weld joint in each frame of the workpiece image. The center line of the laser stripes within the core region is extracted using a line detection method. The intersection of the center lines of the laser stripes is used to obtain the pixel coordinates (u) of the first feature point (u) of the weld bevel edge in the i-th frame of the workpiece image. i1 ,v i1 ) and the pixel coordinates of the second feature point (u i2 ,v i2 ); i = 1, 2, ..., n, where n is the total number of images of the workpiece to be welded;

[0015] The pixel coordinates (u) of the first feature point at the edge of the weld bevel are... i1 ,v i1 ) and the pixel coordinates of the second feature point (u i2 ,v i2 ) is converted into three-dimensional coordinates (x, y) under the structured light trajectory scanner. i1 ,y i1 ,z i1 ), (x i2 ,y i2 ,z i2 );

[0016] The three-dimensional coordinates (x) of the first feature point at the edge of the weld groove i1 ,y i1 ,z i1 The coordinates of spline curve B1 are obtained by curve fitting of the set of ); the three-dimensional coordinates (x, y, z) of the second feature point at the weld groove edge are obtained. i2 ,y i2 ,z i2 The coordinates of spline curve B2 are obtained by curve fitting of the set of ) .

[0017]

[0018]

[0019] in, Let B be the coordinates of spline curve B1. i1,k (u) represents the i-th k-th order fitting parameter when obtaining spline curve B1; Let B be the coordinates of spline curve B2. i2,k (u) represents the i-th k-th order fitting parameter when obtaining spline curve B2;

[0020] The coordinates of the centerline of the workpiece to be welded are obtained by using the coordinates of spline curve B1 and spline trajectory curve B2.

[0021] Preferably, the structured light trajectory scanner is also used to capture images of the welded seams of the workpiece and send the images of the welded seams of the workpiece to the controller;

[0022] The controller is also used for,

[0023] The robot arm is controlled to move the structured light trajectory scanner along the welded seam of the workpiece, maintaining a preset distance and angle between the scanner and the welded seam. Then, following these steps, the coordinates of the weld quality inspection center line and the coordinates of the straight line containing the highest point of the weld are identified from the image of the welded seam:

[0024] An RNN neural network is used to extract the core region of the weld seam in each frame of the workpiece's weld seam image. The center line of the laser stripes within the core region is extracted using a line detection method. The intersection of these center lines yields the pixel coordinates (u) of the first feature point (u) at the weld toe edge in the m-th frame of the workpiece's weld seam image. m1 ,v m1 ) and the pixel coordinates of the second feature point (u m2 ,v m2 The pixel coordinates (u) of the highest point of the weld are obtained by finding the point on the center line of the laser stripe where the second derivative is zero. m3 ,v m3 ), m=1,2,…,o, where o is the total number of images of welded seams on the workpiece;

[0025] The pixel coordinates (u) of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. m1 ,v m1 ) and the pixel coordinates of the second feature point (u m2 ,v m2 ) and the pixel coordinates (u) of the highest point of the weld on the workpiece. m3 ,v m3 Transform into 3D coordinates (x, y) in the CCD camera coordinate system m1 ,y m1 ,z m1 ), (x m2 ,y m2 ,z m2 ), (x m3 ,y m3 ,z m3 );

[0026] The pixel coordinates (x, y) of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. m1 ,y m1 ,z m1 The coordinates of spline curve B4 are obtained by curve fitting of the set of ); the pixel coordinates (x, y, z) of the second feature point of the weld toe edge in the welded seam image of the workpiece are obtained. m2 ,y m2 ,z m2 The coordinates of spline curve B5 are obtained by curve fitting of the set of data; the pixel coordinates (x, y) of the highest point of the weld on the workpiece are obtained. m3 ,y m3 ,z m3 The coordinates of spline curve B6 are obtained by curve fitting of the set of ) .

[0027]

[0028]

[0029]

[0030] in, Let B be the coordinates of spline curve B4. m4,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B4; Let B5 be the coordinate of the spline curve. m5,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B5; Let B be the coordinates of spline curve B6. m6,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B6;

[0031] The coordinates of spline curve B6 are the coordinates of the straight line where the highest point of the weld is located; the coordinates of the weld quality inspection center line are obtained by using the coordinates of spline curve B4 and spline trajectory B5.

[0032] Preferably, it also includes quality inspection probes;

[0033] The controller is also used to control the robotic arm to move the inspection probe according to the weld inspection center line to perform quality inspection on the weld.

[0034] Preferably, it also includes a grinding head;

[0035] The controller is also used to control the robotic arm to drive the grinding head to move along a straight line where the highest point of the weld is located to grind the weld.

[0036] Preferably, the structured light trajectory scanner includes a fixed bracket, a CCD camera, and a laser generator;

[0037] The fixed bracket is connected to the outermost end of the robotic arm;

[0038] The CCD camera is fixed on a fixed bracket, and the central axis of the CCD camera is perpendicular to the plane of the workpiece to be welded or the welded seam.

[0039] The laser generator is fixed on a fixed bracket. The emitted laser is located on the same plane as the central axis of the CCD camera, and this plane is perpendicular to the workpiece to be welded or the welded seam. The emitted laser forms an angle of 20-40° with the central axis of the CCD camera.

[0040] Preferably, the preset distance between the structured light trajectory scanner and the workpiece to be welded or the welded joint is 100mm to 200mm, and the moving speed of the structured light trajectory scanner along the workpiece to be welded or the welded joint is 15mm / s to 30mm / s.

[0041] A method for spatial pose recognition of structural components, comprising,

[0042] The controller controls the robot arm to move the structured light trajectory scanner along the workpiece to be welded from the starting point and keep the structured light trajectory scanner at a preset distance and preset angle with the workpiece to be welded. While moving along the workpiece to be welded, the structured light trajectory scanner continuously takes pictures of the workpiece to be welded and uploads the pictures of the workpiece to be welded to the controller.

[0043] The controller identifies the coordinates of the centerline of the workpiece's weld joint based on an image of the joint to be welded.

[0044] The controller controls the robotic arm to move the welding torch along the center line of the head to be welded for welding.

[0045] Preferably, the controller identifies the coordinates of the centerline of the workpiece's weld joint based on an image of the joint to be welded, including:

[0046] An RNN neural network is used to extract the core region of the weld joint in each frame of the workpiece image. The center line of the laser stripes within the core region is extracted using a line detection method. The intersection of the center lines of the laser stripes is used to obtain the pixel coordinates (u) of the first feature point (u) of the weld bevel edge in the i-th frame of the workpiece image. i1 ,v i1 ) and the pixel coordinates of the second feature point (u i2 ,v i2 ); i = 1, 2, ..., n, where n is the total number of images of the workpiece to be welded;

[0047] The pixel coordinates (u) of the first feature point at the edge of the weld bevel are... i1 ,v i1 ) and the pixel coordinates of the second feature point (ui2 ,v i2 ) is converted into three-dimensional coordinates (x, y) under the structured light trajectory scanner. i1 ,y i1 ,z i1 ), (x i2 ,y i2 ,z i2 );

[0048] The three-dimensional coordinates (x) of the first feature point at the edge of the weld groove i1 ,y i1 ,z i1 The coordinates of spline curve B1 are obtained by curve fitting of the set of ); the three-dimensional coordinates (x, y, z) of the second feature point at the weld groove edge are obtained. i2 ,y i2 ,z i2 The coordinates of spline curve B2 are obtained by curve fitting of the set of ) .

[0049]

[0050]

[0051] in, Let B be the coordinates of spline curve B1. i1,k (u) represents the i-th k-th order fitting parameter when obtaining spline curve B1; Let B be the coordinates of spline curve B2. i2,k (u) represents the i-th k-th order fitting parameter when obtaining spline curve B2;

[0052] The coordinates of the centerline of the workpiece to be welded are obtained by using the coordinates of spline curve B1 and spline trajectory curve B2.

[0053] Preferred options also include,

[0054] After welding is completed, the controller controls the robot arm to move the optical trajectory scanner along the welded seam of the workpiece from the starting point and keep the structured optical trajectory scanner at a preset distance and preset angle with the welded seam of the workpiece. While moving along the welded seam of the workpiece, the structured optical trajectory scanner continuously takes pictures of the welded seam of the workpiece and uploads the pictures of the welded seam of the workpiece to the controller.

[0055] The controller identifies the coordinates of the weld quality inspection center line and the coordinates of the straight line containing the highest point of the weld based on the image of the welded seam of the workpiece.

[0056] The controller controls the robotic arm to move the quality inspection probe according to the weld quality inspection center line to perform quality inspection on the weld.

[0057] The controller controls the robotic arm to move the grinding head along a straight line where the highest point of the weld is located to grind the weld.

[0058] Preferably, the controller identifies the coordinates of the weld quality inspection center line and the coordinates of the straight line containing the highest point of the weld based on the image of the welded seam of the workpiece, including:

[0059] An RNN neural network is used to extract the core region of the weld seam in each frame of the workpiece's weld seam image. The center line of the laser stripes within the core region is extracted using a line detection method. The intersection of these center lines yields the pixel coordinates (u) of the first feature point (u) at the weld toe edge in the m-th frame of the workpiece's weld seam image. m1 ,v m1 ) and the pixel coordinates of the second feature point (u m2 ,v m2 The pixel coordinates (u) of the highest point of the weld are obtained by finding the point on the center line of the laser stripe where the second derivative is zero. m3 ,v m3 ), m=1,2,…,o, where o is the total number of images of welded seams on the workpiece;

[0060] The pixel coordinates (u) of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. m1 ,v m1 ) and the pixel coordinates of the second feature point (u m2 ,v m2 ) and the pixel coordinates (u) of the highest point of the weld on the workpiece. m3 ,v m3 Transform into 3D coordinates (x, y) in the CCD camera coordinate system m1 ,y m1 ,z m1 ), (x m2 ,y m2 ,z m2 ), (x m3 ,y m3 ,z m3 );

[0061] The pixel coordinates (x, y) of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. m1 ,y m1 ,z m1 The coordinates of spline curve B4 are obtained by curve fitting of the set of ); the pixel coordinates (x, y, z) of the second feature point of the weld toe edge in the welded seam image of the workpiece are obtained. m2 ,y m2 ,z m2 The coordinates of spline curve B5 are obtained by curve fitting of the set of data; the pixel coordinates (x, y) of the highest point of the weld on the workpiece are obtained. m3 ,y m3 ,z m3The coordinates of spline curve B6 are obtained by curve fitting of the set of ) .

[0062]

[0063]

[0064]

[0065] in, Let B be the coordinates of spline curve B4. m4,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B4; Let B5 be the coordinate of the spline curve. m5,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B5; Let B be the coordinates of spline curve B6. m6,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B6;

[0066] The coordinates of spline curve B6 are the coordinates of the straight line where the highest point of the weld is located; the coordinates of the weld quality inspection center line are obtained by using the coordinates of spline curve B4 and spline trajectory B5.

[0067] Preferably, the preset distance between the structured light trajectory scanner and the workpiece to be welded or the welded joint is 100mm to 200mm, the moving speed of the structured light trajectory scanner along the workpiece to be welded or the welded joint is 15mm / s to 30mm / s, and the frame rate of the structured light trajectory scanner is 30 frames / s.

[0068] The beneficial effects of this invention are:

[0069] This invention uses a structured light trajectory scanner to obtain a precise welding trajectory with an accuracy of 0.1mm. Based on the fitted coordinate curve of the joint center point, the trajectory movement of the welding torch is automatically controlled, reducing manual teaching and improving efficiency.

[0070] This invention automatically controls the scanning trajectory of the quality inspection probe based on the fitted coordinate curve of the welded seam, and automatically controls the grinding trajectory of the grinding head based on the fitted coordinate curve of the highest point of the welded seam. This realizes the integrated trajectory recognition function of welding, internal quality inspection and weld grinding, which greatly reduces the production cycle of structural component welding and improves welding quality.

[0071] The welding trajectory, probe scanning trajectory, and grinding head trajectory fitted by this invention have smoother continuity, making the robot arm operate more stably. This is very important for welding, phased array quality inspection, and weld grinding.

[0072] This invention can greatly reduce the impact of workpiece clamping and positioning errors, the positional deviation between the welding torch and the joint center caused by workpiece thermal deformation, the positional deviation between the quality inspection probe and the weld center, and the positional deviation between the grinding head and the center of the highest point of the weld. Attached Figure Description

[0073] Figure 1 A schematic diagram of a spatial pose recognition system for structural components;

[0074] Figure 2 This is a schematic diagram of a structured light trajectory scanner;

[0075] Figure 3 This is a schematic diagram of the scanning process for the joint to be welded.

[0076] Figure 4 This is a schematic diagram of the inspection of the welded seam;

[0077] Figure 5 The scan results for the welded joint are shown in the image.

[0078] Figure 6 This is a scanned image showing the results of an inspection of a welded seam.

[0079] Figure 7 Image of the joint to be welded;

[0080] Figure 8 This is a schematic diagram of the first feature point of the weld groove edge obtained from the image of the joint to be welded;

[0081] Figure 9 Images of welded seams;

[0082] Figure 10 This is a schematic diagram of the weld toe edge feature points and the highest point of the weld obtained from an image of a welded seam;

[0083] Among them, 1. movable slide table cantilever beam; 2. robot arm; 3. workpiece positioner; 4. workpiece positioner column; 5. workpiece positioner base plate; 6. base; 7. workpiece; 8. movable slide table column; 9. movable slide table; 10. structured light trajectory scanner; 11. laser generator; 12. CCD camera; A is the scanning direction; B is the transverse direction of the weld. Detailed Implementation

[0084] The present invention will be further described below with reference to the embodiments. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0085] This invention provides a spatial pose recognition system for structural components. See [link to relevant documentation]. Figure 1 and Figure 2The system includes a robotic arm 2, a workpiece support device, a structured light trajectory scanner 10, a welding torch, and a controller. Specifically, the workpiece support device is used to clamp the workpiece; the structured light trajectory scanner 10 is connected to the robotic arm 2 and is used to capture an image of the workpiece's weld joint and send the image to the controller; the welding torch is connected to the robotic arm; the controller is used to control the robotic arm to move the structured light trajectory scanner along the workpiece's weld joint and maintain a preset distance and preset angle between the structured light trajectory scanner and the workpiece's weld joint, identify the coordinates of the centerline of the workpiece's weld joint based on the image of the weld joint, and control the robotic arm to move the welding torch along the centerline of the weld joint for welding.

[0086] In an optional embodiment of the present invention, see Figure 1 and Figure 2 The spatial pose recognition system for structural components also includes a movable slide 9, a movable slide beam 1, and a base 6. The movable slide 9 is located on one side of the workpiece and is fixed to the base via a movable slide column 8. The movable slide beam 1 and the movable slide 9 are slidably connected. The base of the robot 2 is fixedly connected to the bottom surface of the movable slide beam 1 and placed upside down, allowing the robot 2 to move along the movable slide 9. In use, the speed at which the movable slide beam 1 translates along the movable slide 9 is controlled by a controller, which in turn controls the speed at which the robot translates along the workpiece. The workpiece support device includes a workpiece positioner base plate 5 fixed to the base 6, a workpiece positioner column 4 fixed to the workpiece positioner base plate 5, and a workpiece positioner 3 fixed to the workpiece positioner column 4. The positioner chuck of the workpiece positioner 3 is connected to the workpiece 7, and the spatial pose transformation of the workpiece 7 is achieved through the pose transformation of the positioner chuck, thereby enabling trajectory scanning of the workpiece 7 at different spatial positions. The base can be the ground or a separate installation. The movable slide can be set horizontally or tilted, and can be designed in a curved shape, allowing it to rotate flexibly according to the shape of the workpiece. A 6-axis robot arm is optional.

[0087] In an optional embodiment of the present invention, see Figure 2 The structured light trajectory scanner 10 is a non-contact visual inspection device, including a fixed bracket, a CCD camera 12, and a laser generator 11. The fixed bracket is connected to the outermost end of the robot arm 2. The CCD camera 12 is fixed on the fixed bracket, and the central axis of the CCD camera 12 is perpendicular to the plane of the workpiece to be welded. The laser generator is fixed on the fixed bracket. (See attached image) Figure 3 and Figure 4 A represents the scanning direction, and B represents the transverse direction of the weld. When scanning the butt weld to be welded, the laser emitted by the laser generator 11 is on the same plane as the central axis of the CCD camera 12, and this plane is perpendicular to the weld joint of the workpiece. The central axis of the CCD camera 12 is perpendicular to the scanning surface, and the laser emitted by the laser generator 11 forms an angle of 20-40° with the central axis of the CCD camera 12.

[0088] In an optional embodiment of the present invention, the preset distance between the structured light trajectory scanner and the workpiece to be welded is 100mm to 200mm, and the moving speed of the structured light trajectory scanner along the workpiece to be welded, i.e., along the scanning direction A, is 15mm / s to 30mm / s.

[0089] Specifically, the controller identifies the coordinates of the centerline of the workpiece's weld joint using the following steps:

[0090] An RNN neural network is used to extract the core region of the weldable area from each frame of the workpiece's image. Figure 7 (The area enclosed by the Chinese frame) See Figure 8 The center line of the laser stripes in the core area is extracted by the straight line detection method, and the intersection of the center lines of the laser stripes is obtained to obtain the pixel coordinates (u) of the first feature point (u) of the weld groove edge in the image of the workpiece to be welded in the i-th frame. i1 ,v i1 ) and the pixel coordinates of the second feature point (u i2 ,v i2 ) and the pixel coordinates of the feature points at the bottom of the weld groove (u i3 v i3 ), i = 1, 2, ..., n, where n is the total number of images of the workpiece to be welded;

[0091] The pixel coordinates (u) of the first feature point at the edge of the weld bevel are... i1 ,v i1 ) and the pixel coordinates of the second feature point (u i2 ,v i2 ) is converted into three-dimensional coordinates (x, y) under the structured light trajectory scanner. i1 ,y i1 ,z i1 ), (x i2 ,y i2 ,z i2 );

[0092] The three-dimensional coordinates (x) of the first feature point at the edge of the weld groove i1 ,y i1 ,z i1 The coordinates of spline curve B1 are obtained by curve fitting of the set of ); the three-dimensional coordinates (x, y, z) of the second feature point at the weld groove edge are obtained. i2 ,y i2 ,z i2 The coordinates of spline curve B2 are obtained by curve fitting of the set of ) .

[0093]

[0094]

[0095] in, Let B be the coordinates of spline curve B1. i1,k (u) represents the i-th k-th order fitting parameter when obtaining spline curve B1, derived from the three-dimensional coordinates (x, y) of the first feature point at the weld bevel edge. i1 ,y i1 ,z i1 It is calculated using the B-spline curve interpolation algorithm; Let B be the coordinates of spline curve B2. i2,k (u) represents the i-th k-th order fitting parameter when obtaining spline curve B2, derived from the three-dimensional coordinates (x, y) of the second feature point at the weld bevel edge. i2 ,y i2 ,z i2 It is calculated using the B-spline curve interpolation algorithm;

[0096] The coordinates of the centerline of the workpiece to be welded are obtained using the coordinates of spline curve B1 and spline trajectory curve B2. The center of the workpiece to be welded is the midpoint between the first and second characteristic points of the weld groove edge, that is, the centerline of the workpiece to be welded is the curve containing the midpoint between the first and second characteristic points of the weld groove edge.

[0097] Figure 5 This is a schematic diagram of the workpiece surface formed by arranging the laser curves in all the photos according to the shooting order and position.

[0098] Specifically, the structured light trajectory scanner is also used to capture images of the welded seams of a workpiece and send these images to the controller.

[0099] The controller is also used for,

[0100] The robot arm is controlled to move the structured light trajectory scanner along the welded seam of the workpiece, maintaining a preset distance and angle between the scanner and the welded seam. Then, following these steps, the coordinates of the weld quality inspection center line and the coordinates of the straight line containing the highest point of the weld are identified from the image of the welded seam:

[0101] The core region of the weld seam in each frame of the workpiece's weld seam image is extracted using an RNN neural network. Figure 9 (The area enclosed by the Chinese frame), see [link / reference]. Figure 10 The center line of the laser stripes in the core area is extracted by the straight line detection method, and the intersection of the center lines of the laser stripes is obtained to obtain the pixel coordinates (u) of the first feature point of the weld toe edge in the welded seam image of the m-th frame of the workpiece. m1 ,v m1 ) and the pixel coordinates of the second feature point (u m2 ,v m2The pixel coordinates (u) of the highest point of the weld are obtained by finding the point on the center line of the laser stripe where the second derivative is zero. m3 ,v m3 ), m=1,2,…,o, where o is the total number of images of welded seams on the workpiece;

[0102] The pixel coordinates (u) of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. m1 ,v m1 ) and the pixel coordinates of the second feature point (u m2 ,v m2 ) and the pixel coordinates (u) of the highest point of the weld on the workpiece. m3 ,v m3 Transform into 3D coordinates (x, y) in the CCD camera coordinate system m1 ,y m1 ,z m1 ), (x m2 ,y m2 ,z m2 ), (x m3 ,y m3 ,z m3 );

[0103] The pixel coordinates (x, y) of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. m1 ,y m1 ,z m1 The coordinates of spline curve B4 are obtained by curve fitting of the set of ); the pixel coordinates (x, y, z) of the second feature point of the weld toe edge in the welded seam image of the workpiece are obtained. m2 ,y m2 ,z m2 The coordinates of spline curve B5 are obtained by curve fitting of the set of data; the pixel coordinates (x, y) of the highest point of the weld on the workpiece are obtained. m3 ,y m3 ,z m3 The coordinates of spline curve B6 are obtained by curve fitting of the set of ) .

[0104]

[0105]

[0106]

[0107] in, Let B be the coordinates of spline curve B4. m4,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B4, derived from the three-dimensional coordinates (x, y) of the first feature point of the weld toe. m1 ,y m1 ,z m1 It is calculated using the B-spline curve interpolation algorithm; Let B5 be the coordinate of the spline curve. m5,k (u) represents the m-th k-th order fitting parameter for obtaining spline curve B5, derived from the three-dimensional coordinates (x, y) of the second feature point of the weld toe. m2 ,y m2 ,z m2 It is calculated using the B-spline curve interpolation algorithm; Let B be the coordinates of spline curve B6. m6,k (u) represents the m-th k-th order fitting parameter for obtaining spline curve B6, derived from the three-dimensional coordinates (x, y) of the highest point of the weld on the workpiece. m3 ,y m3 ,z m3 It is calculated using the B-spline curve interpolation algorithm;

[0108] The coordinates of spline curve B6 are the coordinates of the straight line containing the highest point of the weld. The coordinates of the weld quality inspection centerline are obtained through the coordinates of spline curve B4 and spline trajectory B5. The weld quality inspection center point is the midpoint between the first and second characteristic points of the weld toe; that is, the weld quality inspection centerline is the curve containing the midpoint between the first and second characteristic points of the weld toe.

[0109] Figure 6 This is a schematic diagram of the welded seam on the workpiece surface, formed by arranging the laser curves from all the photographs according to the shooting order and position.

[0110] In an optional embodiment of the present invention, the spatial pose recognition system for structural components further includes a quality inspection probe. The controller is also used to control the robotic arm to move the quality inspection probe according to the weld quality inspection center line to perform quality inspection on the weld. After obtaining the weld quality inspection center line, it is used as the movement trajectory to keep the quality inspection probe at a certain distance from the weld center line to perform quality inspection on the weld, thereby realizing real-time control of the quality inspection trajectory of the phased array probe after welding.

[0111] In an optional embodiment of the present invention, the spatial pose recognition system for the structural component further includes a grinding head; the controller is also used to control the robot arm to drive the grinding head to move along the straight line where the highest point of the weld is located to grind the weld.

[0112] In this invention, the welding torch, structured light trajectory scanner, grinding head, and quality inspection probe are all driven by a robotic arm and are connected to the robotic arm. Where space permits, the components can be assembled with the robotic arm simultaneously. Alternatively, the welding torch, structured light trajectory scanner, grinding head, and quality inspection probe can be assembled with the robotic arm in a detachable manner, and can be replaced and installed before the corresponding process.

[0113] This invention also provides a method for spatial pose recognition of structural components, taking an excavator boom stick tooling as an example, including:

[0114] S1.1: Installation of excavator boom stick tooling: The excavator boom stick workpiece is installed on the workpiece positioner. Before welding, the bevel surface is cleaned, rusted, and ground.

[0115] S1.2: Number the welds to be inspected: 1......n; inspect the welds in sequence, and rotate the welds to be inspected to the horizontal plane by moving the workpiece positioner;

[0116] S1.3: See Figure 3 In preparation for scanning the weld joint, the robotic arm holds the structured light trajectory scanner and adjusts its spatial pose so that the bottom of the scanner, controlled by the robotic arm, is 100mm to 200mm away from the weld to be inspected. The laser generator and the CCD camera are at a 20-40° angle, with the central axis of the CCD camera perpendicular to the scanning surface and the surface formed by the laser generator and the CCD camera perpendicular to the weld joint. The structured light trajectory scanner is then moved so that the laser line reaches the arc starting point.

[0117] S1.4: Start the CCD camera, and control the robot arm via the controller to drive the structured light trajectory scanner to scan along the workpiece. Configure the sensor to acquire frames at 30 frames / s, and set the scanning speed to V. s (15mm / s~30mm / s) Start moving towards the arc extinguishing point; during the movement, the line laser generated by the line laser generator continuously sweeps the unwelded weld, and the CCD camera continuously takes pictures of the joint to be welded with the laser line and uploads the pictures of the joint to be welded to the controller.

[0118] S1.5: The controller identifies the coordinates of the centerline of the workpiece's weld joint based on the image of the joint to be welded.

[0119] An RNN neural network is used to extract the core region of the weld joint in each frame of the workpiece image. The center line of the laser stripes within the core region is extracted using a line detection method. The intersection of the center lines of the laser stripes is used to obtain the pixel coordinates (u) of the first feature point (u) of the weld bevel edge in the i-th frame of the workpiece image. i1 ,v i1 ) and the pixel coordinates of the second feature point (u i2 ,v i2 ); i = 1, 2, ..., n, where n is the total number of images of the workpiece to be welded;

[0120] The pixel coordinates (u) of the first feature point at the edge of the weld bevel are... i1 ,v i1 ) and the pixel coordinates of the second feature point (u i2 ,v i2 ) is converted into three-dimensional coordinates (x, y) under the structured light trajectory scanner. i1 ,y i1 ,zi1 ), (x i2 ,y i2 ,z i2 );

[0121] The three-dimensional coordinates (x) of the first feature point at the edge of the weld groove i1 ,y i1 ,z i1 The coordinates of spline curve B1 are obtained by curve fitting of the set of ); the three-dimensional coordinates (x, y, z) of the second feature point at the weld groove edge are obtained. i2 ,y i2 ,z i2 The coordinates of spline curve B2 are obtained by curve fitting of the set of ) .

[0122]

[0123]

[0124] in, Let B be the coordinates of spline curve B1. i1,k (u) represents the i-th k-th order fitting parameter when obtaining spline curve B1; Let B be the coordinates of spline curve B2. i2,k (u) represents the i-th k-th order fitting parameter when obtaining spline curve B2;

[0125] The coordinates of the centerline of the workpiece to be welded are obtained by using the coordinates of spline curve B1 and spline trajectory curve B2.

[0126] S1.6: The controller controls the robot arm to move the welding torch along the center line of the workpiece to be welded. While the welding torch moves along the center line of the workpiece to be welded, it applies welding to the weld seam, realizing automated welding trajectory.

[0127] S2: Intelligent control of phased array probe scanning trajectory for welded seams

[0128] S2.1: Installation of excavator boom stick tooling:

[0129] S2.2: Number the welds to be inspected: 1......n; inspect the welds in sequence, and rotate the welds to be inspected to the horizontal plane by moving the workpiece positioner;

[0130] S2.3: Preparation for scanning the welded seam. The robotic arm holds the structured light trajectory scanner, and the spatial pose of the structured light trajectory scanner is adjusted so that the distance between the bottom of the structured light trajectory scanner controlled by the robotic arm and the weld seam to be inspected is 100mm to 200mm, and the laser generator and the CCD camera form an angle of 20-40°. Figure 4The central axis of the CCD camera is perpendicular to the scanning surface, and the surface formed by the laser generator and the industrial CCD camera is perpendicular to the weld seam; the moving structured light trajectory scanner moves the laser line to the starting point.

[0131] S2.4: Start the CCD camera. The controller controls the robot arm to drive the structured light trajectory scanner to scan along the workpiece. Configure the sensor to acquire frames at 30 frames / s, with a scanning speed of V. s (15mm / s~30mm / s) Start moving towards the arc extinguishing point; during the movement, the line laser generated by the line laser generator continuously sweeps the weld seam, and the CCD camera continuously takes pictures of the welded seam with the laser line and uploads the pictures of the welded seam of the workpiece to the controller.

[0132] S2.5: The controller identifies the coordinates of the weld quality inspection center line and the coordinates of the straight line containing the highest point of the weld based on the image of the welded seam on the workpiece.

[0133] An RNN neural network is used to extract the core region of the weld seam in each frame of the workpiece's weld seam image. The center line of the laser stripes within the core region is extracted using a line detection method. The intersection of these center lines yields the pixel coordinates (u) of the first feature point (u) at the weld toe edge in the m-th frame of the workpiece's weld seam image. m1 ,v m1 ) and the pixel coordinates of the second feature point (u m2 ,v m2 The pixel coordinates (u) of the highest point of the weld are obtained by finding the point on the center line of the laser stripe where the second derivative is zero. m3 ,v m3 ), m=1,2,…,o, where o is the total number of images of welded seams on the workpiece;

[0134] The pixel coordinates (u) of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. m1 ,v m1 ) and the pixel coordinates of the second feature point (u m2 ,v m2 ) and the pixel coordinates (u) of the highest point of the weld on the workpiece. m3 ,v m3 Transform into 3D coordinates (x, y) in the CCD camera coordinate system m1 ,y m1 ,z m1 ), (x m2 ,y m2 ,z m2 ), (x m3 ,y m3 ,z m3 );

[0135] The pixel coordinates (x, y) of the first feature point on the weld toe edge in the image of the welded seam of the workpiece.m1 ,y m1 ,z m1 The coordinates of spline curve B4 are obtained by curve fitting of the set of ); the pixel coordinates (x, y, z) of the second feature point of the weld toe edge in the welded seam image of the workpiece are obtained. m2 ,y m2 ,z m2 The coordinates of spline curve B5 are obtained by curve fitting of the set of data; the pixel coordinates (x, y) of the highest point of the weld on the workpiece are obtained. m3 ,y m3 ,z m3 The coordinates of spline curve B6 are obtained by curve fitting of the set of ) .

[0136]

[0137]

[0138]

[0139] in, Let B be the coordinates of spline curve B4. m4,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B4; Let B5 be the coordinate of the spline curve. m5,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B5; Let B be the coordinates of spline curve B6. m6,k (u) represents the m-th k-th order fitting parameter when obtaining spline curve B6;

[0140] The coordinates of spline curve B6 are the coordinates of the straight line where the highest point of the weld is located; the coordinates of the weld quality inspection center line are obtained by using the coordinates of spline curve B4 and spline trajectory B5.

[0141] S2.6: The controller controls the robotic arm to move the quality inspection probe according to the weld quality inspection center line to perform quality inspection on the weld;

[0142] S2.7: The controller controls the robot arm to drive the grinding head to move along the straight line where the highest point of the weld is located to grind the weld.

[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0145] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0147] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

[0148] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A spatial pose recognition system for structural components, characterized in that, Includes robotic arms, structured light trajectory scanners, and controllers; The structured light trajectory scanner is used to capture images of the workpiece's weld joint and send these images to the controller. The controller is used to control the robot arm to move the structured light trajectory scanner along the head of the workpiece to be welded and to keep the structured light trajectory scanner and the head of the workpiece to be welded at a preset distance and a preset angle, to identify the coordinates of the center line of the head of the workpiece to be welded based on the image of the head of the workpiece to be welded, and to control the robot arm to move the welding torch along the center line of the head to be welded for welding. The controller identifies the coordinates of the centerline of the workpiece's weld joint according to the following steps: An RNN neural network is used to extract the core region of the weldable joint in each frame of the workpiece image. The center line of the laser stripes within the core region is extracted using a line detection method. The intersection of the center lines of the laser stripes is then obtained to determine the first... The pixel coordinates of the first feature point on the weld bevel edge in the image of the workpiece to be welded. Pixel coordinates of the second feature point ; , This represents the total number of images of the workpiece's weld joints. The pixel coordinates of the first feature point at the edge of the weld bevel Pixel coordinates of the second feature point Converted into 3D coordinates under a structured light trajectory scanner , ; Three-dimensional coordinates of the first feature point at the edge of the weld groove Curve fitting is performed on the set to obtain the spline curve. The coordinates of the second feature point at the weld groove edge; the three-dimensional coordinates of the second feature point at the weld groove edge. Curve fitting is performed on the set to obtain the spline curve. Coordinates: ， ， in, spline curve coordinates To obtain spline curves The i-th k-th order fitting parameter at time; spline curve coordinates To obtain spline curves The i-th k-th order fitting parameter at time; spline curves coordinates, spline trajectory curve The coordinates of the center line of the workpiece to be welded are obtained from the coordinates of the workpiece. The structured light trajectory scanner is also used to capture images of the welded seams of the workpiece and send the images of the welded seams of the workpiece to the controller. The controller is also used to identify the coordinates of the weld quality inspection center line and the coordinates of the straight line where the highest point of the weld is located based on the image of the welded seam of the workpiece.

2. The spatial pose recognition system for structural components according to claim 1, characterized in that, The controller identifies the coordinates of the weld quality inspection center line and the coordinates of the straight line containing the highest point of the weld from an image of the welded seam of the workpiece, according to the following steps: An RNN neural network is used to extract the core region of the weld seam in each frame of the workpiece's welded seam image. The center line of the laser stripes within the core region is extracted using a straight line detection method. The intersection of the center lines of the laser stripes is then obtained to obtain the first... The pixel coordinates of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. Pixel coordinates of the second feature point The pixel coordinates of the highest point of the weld are obtained by finding the point on the center line of the laser stripe where the second derivative is zero. , , This represents the total number of images of the welded seams on the workpiece. The pixel coordinates of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. Pixel coordinates of the second feature point And the pixel coordinates of the highest point of the weld on the workpiece. Transform into 3D coordinates in CCD camera coordinate system , , ; The pixel coordinates of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. Curve fitting is performed on the set to obtain the spline curve. The coordinates; the pixel coordinates of the second feature point on the weld toe edge in the image of the welded seam of the workpiece. Curve fitting is performed on the set to obtain the spline curve. The coordinates of the highest point of the weld on the workpiece; the pixel coordinates of the highest point of the weld. Curve fitting is performed on the set to obtain the spline curve. Coordinates: ， ， ， in, spline curve coordinates To obtain spline curves The first time k-order fitting parameters; spline curve coordinates To obtain spline curves The first time k-order fitting parameters; spline curve coordinates To obtain spline curves The first time k-order fitting parameters; spline curve The coordinates of the workpiece are the coordinates of the straight line containing the highest point of the weld; through the spline curve coordinates, spline trajectory The coordinates of the weld quality inspection center line are obtained from the coordinates.

3. The spatial pose recognition system for structural components according to claim 1, characterized in that, It also includes a movable slide table and a movable slide table suspension beam. The movable slide table is located on one side of the workpiece, and the movable slide table and the movable slide table are slidably connected. The base of the robot is fixedly connected to the movable slide table suspension beam.

4. The spatial pose recognition system for structural components according to claim 1, characterized in that, It also includes a workpiece support device; the workpiece support device includes a workpiece positioner base plate, a workpiece positioner column fixed on the workpiece positioner base plate, and a workpiece positioner fixed on the workpiece positioner column. The displacement chuck of the workpiece positioner is connected to the workpiece.

5. The spatial pose recognition system for structural components according to claim 2, characterized in that, The controller is also used to control the robot arm to move the structured light trajectory scanner along the welded seam of the workpiece and to maintain a preset distance and preset angle between the structured light trajectory scanner and the welded seam of the workpiece.

6. The spatial pose recognition system for structural components according to claim 5, characterized in that, It also includes quality inspection probes; The controller is also used to control the robotic arm to move the inspection probe according to the weld inspection center line to perform quality inspection on the weld.

7. The spatial pose recognition system for structural components according to claim 5, characterized in that, This also includes grinding heads; The controller is also used to control the robotic arm to drive the grinding head to move along a straight line where the highest point of the weld is located to grind the weld.

8. The spatial pose recognition system for structural components according to claim 5, characterized in that, The structured light trajectory scanner includes a fixed bracket, a CCD camera, and a laser generator; The fixed bracket is connected to the outermost end of the robotic arm; The CCD camera is fixed on a fixed bracket, and the central axis of the CCD camera is perpendicular to the plane of the workpiece to be welded or the welded seam. The laser generator is fixed on a fixed bracket. The emitted laser is located on the same plane as the central axis of the CCD camera, and this plane is perpendicular to the workpiece to be welded or the welded seam. The emitted laser forms an angle of 20-40° with the central axis of the CCD camera.

9. The spatial pose recognition system for structural components according to claim 5, characterized in that, The preset distance between the structured light trajectory scanner and the workpiece to be welded or the welded seam is 100mm~200mm, and the moving speed of the structured light trajectory scanner along the workpiece to be welded or the welded seam is 15mm / s~30mm / s.

10. A method for spatial pose recognition of a structural component, characterized in that, include, The controller controls the robot arm to move the structured light trajectory scanner along the workpiece to be welded from the starting point and keep the structured light trajectory scanner at a preset distance and preset angle with the workpiece to be welded. While the structured light trajectory scanner moves along the workpiece to be welded, it continuously takes pictures of the workpiece to be welded and uploads the pictures of the workpiece to be welded to the controller. The controller identifies the coordinates of the centerline of the workpiece's weld joint based on an image of the joint to be welded. The controller controls the robotic arm to move the welding torch along the centerline of the head to be welded for welding. The controller identifies the coordinates of the centerline of the workpiece's weld joint based on an image of the joint to be welded, including: An RNN neural network is used to extract the core region of the weldable joint in each frame of the workpiece image. The center line of the laser stripes within the core region is extracted using a line detection method. The intersection of the center lines of the laser stripes is then obtained to determine the first... The pixel coordinates of the first feature point on the weld bevel edge in the image of the workpiece to be welded. Pixel coordinates of the second feature point ; , This represents the total number of images of the workpiece's weld joints. The pixel coordinates of the first feature point at the edge of the weld bevel Pixel coordinates of the second feature point Converted into 3D coordinates under a structured light trajectory scanner , ; Three-dimensional coordinates of the first feature point at the edge of the weld groove Curve fitting is performed on the set to obtain the spline curve. The coordinates of the second feature point at the weld groove edge; the three-dimensional coordinates of the second feature point at the weld groove edge. Curve fitting is performed on the set to obtain the spline curve. Coordinates: ， ， in, spline curve coordinates To obtain spline curves The i-th k-th order fitting parameter at time; spline curve coordinates To obtain spline curves The i-th k-th order fitting parameter at time; spline curves coordinates, spline trajectory curve The coordinates of the center line of the workpiece to be welded are obtained from the coordinates of the workpiece. The method further includes: after welding is completed, the controller identifies the coordinates of the weld quality inspection center line and the coordinates of the straight line where the highest point of the weld is located based on the image of the welded seam of the workpiece.

11. The spatial pose recognition method for structural components according to claim 10, characterized in that, The controller identifies the coordinates of the weld quality inspection center line and the coordinates of the straight line containing the highest point of the weld based on the image of the welded seam of the workpiece, including: An RNN neural network is used to extract the core region of the weld seam in each frame of the workpiece's welded seam image. The center line of the laser stripes within the core region is extracted using a straight line detection method. The intersection of the center lines of the laser stripes is then obtained to obtain the first... The pixel coordinates of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. Pixel coordinates of the second feature point The pixel coordinates of the highest point of the weld are obtained by finding the point on the center line of the laser stripe where the second derivative is zero. , , This represents the total number of images of the welded seams on the workpiece. The pixel coordinates of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. Pixel coordinates of the second feature point And the pixel coordinates of the highest point of the weld on the workpiece. Transform into 3D coordinates in CCD camera coordinate system , , ; The pixel coordinates of the first feature point on the weld toe edge in the image of the welded seam of the workpiece. Curve fitting is performed on the set to obtain the spline curve. The coordinates; the pixel coordinates of the second feature point on the weld toe edge in the image of the welded seam of the workpiece. Curve fitting is performed on the set to obtain the spline curve. The coordinates of the highest point of the weld on the workpiece; the pixel coordinates of the highest point of the weld. Curve fitting is performed on the set to obtain the spline curve. Coordinates: ， ， ， in, spline curve coordinates To obtain spline curves The first time k-order fitting parameters; spline curve coordinates To obtain spline curves The first time k-order fitting parameters; spline curve coordinates To obtain spline curves The first time k-order fitting parameters; spline curve The coordinates of the workpiece are the coordinates of the straight line containing the highest point of the weld; through the spline curve coordinates, spline trajectory The coordinates of the weld quality inspection center line are obtained from the coordinates.

12. The spatial pose recognition method for structural components according to claim 10, characterized in that, It also includes, After welding is completed, the controller controls the robot arm to move the optical trajectory scanner along the welded seam of the workpiece from the starting point and keep the structured optical trajectory scanner at a preset distance and preset angle with the welded seam of the workpiece. While moving along the welded seam of the workpiece, the structured optical trajectory scanner continuously takes pictures of the welded seam of the workpiece and uploads the pictures of the welded seam of the workpiece to the controller. The controller identifies the coordinates of the weld quality inspection center line and the coordinates of the straight line containing the highest point of the weld based on the image of the welded seam of the workpiece. The controller controls the robotic arm to move the quality inspection probe according to the weld quality inspection center line to perform quality inspection on the weld. The controller controls the robotic arm to move the grinding head along a straight line where the highest point of the weld is located to grind the weld.

13. The spatial pose recognition method for structural components according to claim 12, characterized in that, The preset distance between the structured light trajectory scanner and the workpiece to be welded or the welded seam is 100mm~200mm, and the moving speed of the structured light trajectory scanner along the workpiece to be welded or the welded seam is 15mm / s~30mm / s; the frame rate of the structured light trajectory scanner is 30 frames / s.

Images