Active visual reconstruction system and method of automobile shape based on point and line invariants

Abstract

The present invention discloses an active visual reconstruction system and method for automobile morphology based on point and line invariants, aiming to solve the problem of active visual detection of automobile morphology based on point and line invariants. The active visual reconstruction system for automobile morphology based on point and line invariants mainly comprises a camera bracket (1), a camera (2), a connecting piece (3), a line laser (4) and a two-dimensional calibration plate (5). The active visual reconstruction method for automobile morphology based on point and line invariants comprises three steps: image acquisition, coordinate solution of vehicle body feature points in the coordinate system of the two-dimensional calibration plate (5) based on point and line invariants, and vehicle body point reconstruction. A system and method for active visual reconstruction of automobile morphology based on point and line invariants with simple structure and reliable performance is provided.

Description

Technical Field

[0001] The present invention relates to a measuring device and a measuring method in the field of active visual reconstruction of automobile appearance, and more specifically, it is a system and a method for active visual reconstruction of automobile appearance based on point and line invariants. Background Art

[0002] Automobile shape detection based on machine vision can realize automatic identification of whether the vehicle is overloaded or over-limited, and provide an important basis for the classification of vehicle models, the acquisition of vehicle size parameters, and vehicle information. Researching active visual detection methods for automobile shape without motion constraints has important research significance for enriching automobile performance detection methods, protecting people's lives and property safety, and realizing automobile automatic detection through non-contact measurement methods. The present invention proposes an active visual reconstruction system and method for automobile shape based on point and line invariants. The laser line projected by the linear laser in the system is within the plane of the two-dimensional calibration plate, and a projection invariant consisting of the straight line on the two-dimensional calibration plate and the points not on it, including the laser line and the projection point of the laser line on the car body, is constructed. A solution model for the characteristic points of automobile shape is established, and non-contact detection of the characteristic points of automobile shape is realized. Summary of the invention

[0003] The present invention aims to solve the problems that fixed detection cannot flexibly detect various parts of the automobile shape in the process of obtaining the automobile shape, and the equipment is expensive and the measurement speed is slow. A detection system and method with reliable performance, simple structure, easy operation and simple algorithm is proposed. The system is mainly composed of a camera bracket, a camera, a connector, a line laser and a two-dimensional calibration plate. By solving the invariant values ​​obtained by solving the two straight lines and two points not on the straight line in the image captured by the camera, and then obtaining the intersection point of the laser line and the body surface, the reconstruction of the characteristic points of the automobile shape is realized by using the point and line invariants.

[0004] In conjunction with the accompanying drawings of the specification, the present invention is implemented by the following technical solutions:

[0005] The active visual reconstruction system of automobile shape based on point and line invariants includes a camera bracket, a camera, a connecting piece, a line laser and a two-dimensional calibration plate;

[0006] The camera bracket is placed on the ground, the camera is fixedly connected to the bolt thread on the top of the camera bracket through the threaded hole at the bottom, the two-dimensional calibration plate is placed in the slender groove of the U-shaped steel plate of the connecting piece, the bolts are inserted into the through holes of the connecting piece and the two-dimensional calibration plate and fixedly connected with the nut threads, the line laser is inserted into the inner hole of the steel pipe of the laser connecting piece, the fixing screw is screwed into the threaded hole on the side of the steel pipe of the connecting piece, the end of the fixing screw is in contact with the cylindrical surface of the line laser, and the laser line emitted by the line laser is coplanar with the plane where the two-dimensional calibration plate figure is located.

[0007] The camera bracket described in the technical solution is a tripod bracket with adjustable height.

[0008] The camera described in the technical solution is a wide-angle industrial camera equipped with a narrow-band filter.

[0009] The connecting piece described in the technical solution is a part welded by a U-shaped steel plate and a steel pipe, a through hole is processed on the side of the U-shaped steel plate, and a threaded hole is processed on the side of the steel pipe.

[0010] The line laser described in the technical solution is a cylindrical part that can emit line laser, and the wavelength of the laser emitted by the line laser is consistent with the bandpass wavelength of the narrow-band filter of the camera.

[0011] The two-dimensional calibration plate described in the technical solution is a part made of a rectangular steel plate. Regular geometric figures of black and white rectangular marks that can generate point and straight line features are pasted on the surface of the two-dimensional calibration plate, and the two-dimensional calibration plate is processed with through holes.

[0012] The specific steps of the active visual reconstruction method of automobile shape based on point and line invariants are as follows:

[0013] Step 1: Image acquisition for active visual reconstruction of vehicle shape based on point and line invariants:

[0014] The camera is fixed on the camera bracket, and the camera bracket is placed on the ground. The line laser is inserted into the inner hole of the steel pipe of the connector, and the line laser is turned on. By adjusting the screws on the steel pipe of the connector, the laser line projected by the line laser is in the plane of the two-dimensional calibration plate and the line laser is fixed. The camera collects an image, which includes the two-dimensional calibration plate and the projected laser point where the line laser intersects with the vehicle body surface;

[0015] Step 2: Solve the coordinates of the body feature points in the 2D calibration plate coordinate system based on the point and line invariants:

[0016] An image coordinate system is established on the image captured by the camera, and a two-dimensional calibration plate coordinate system is established on the two-dimensional calibration plate. H is the transformation matrix from the two-dimensional calibration plate coordinate system to the image coordinate system obtained by Zhang Zhengyou's method. The transformation relationship of the straight line on the two-dimensional calibration plate from the image coordinate l to the coordinate L of the two-dimensional calibration plate coordinate system is:

[0017] L=H -T l

[0018] The transformation relationship of the feature point on the two-dimensional calibration plate from the image coordinate x to the coordinate X of the two-dimensional calibration plate coordinate system is:

[0019] X=H -T x

[0020] Then the invariant formed by the two straight lines on the plane and the two points X1 and X2 not on the straight line is

[0021]

[0022] Where L I is a straight line on the two-dimensional calibration plate, L II It is the laser line emitted by the line laser;

[0023] The corresponding invariant on the image can be expressed as follows

[0024]

[0025] Among them l I , l II L I , L II The coordinates in the image coordinate system, l I It can be extracted by Hough transform, II SVD decomposition can be used, through the formula To obtain, The image coordinates of the intersections between the laser light emitted by the fixed state line laser and the vehicle body at different positions during calibration of the two-dimensional calibration plate;

[0026] Let the origin of the two-dimensional calibration plate coordinate system be X1 = (0, 0, 1) T , the point on the Y axis is X 2，1 =(0, Y 2，1 , 1) T , by the straight line on the two-dimensional calibration plate And the straight line emitted by the line laser 4 have to

[0027]

[0028] The corresponding invariant on the image is

[0029]

[0030] Among them, x 2，1 is the feature point X on the 2D calibration plate 2，1 , x1 is the image coordinate of the feature point X1 on the two-dimensional calibration plate;

[0031] Let the origin on the two-dimensional calibration plate be X1 = (0, 0, 1) T , the point on the X axis is X 2，2 =(X 2，1 , 0, 1) T , by the straight line on the two-dimensional calibration plate And the straight line emitted by the line laser have to

[0032]

[0033] The corresponding invariant on the image is

[0034]

[0035] Among them, x 2，2 is the feature point X on the 2D calibration plate 2，2 The image coordinates of

[0036] According to I 1，1 =I 2，1 , I 1，2 =I 2，2 The second and first coordinate elements of the laser line of the line laser in the two-dimensional calibration plate coordinate system are obtained as follows:

[0037]

[0038]

[0039] Finally, the coordinates of the laser line in the two-dimensional calibration plate coordinate system are obtained.

[0040] Step 3: Reconstruction of body surface feature points in the camera coordinate system based on point and line invariants:

[0041] The camera coordinate system is selected as the fixed global coordinate system, and then the two-dimensional calibration plate is placed at the qth position. The camera collects the image at the qth position, q = 1, 2, ..., n. Using the collected n images, according to Zhang Zhengyou's two-dimensional calibration algorithm, the rotation matrix R = (r1 r2 r3) from the two-dimensional calibration plate coordinate system to the camera coordinate system, the translation vector t and the camera intrinsic parameter A can be obtained. Then the projection matrix from the two-dimensional calibration plate coordinate system to the image coordinate system is

[0042] P=A(r1 r2 t)

[0043] The homography matrix from the 2D calibration plate coordinate system to the camera coordinate system is

[0044]

[0045] The L in the two-dimensional calibration plate coordinate system obtained in the second step II The coordinates of the two-dimensional calibration plate coordinate system and the projection matrix P from the two-dimensional calibration plate coordinate system to the image coordinate system. According to the transformation relationship between the point on the straight line and the two-dimensional calibration plate coordinate system to the image coordinate system, we have

[0046] (L II ) T X II =0

[0047] PX II =x II

[0048] where x II The feature point X projected by the laser line onto the vehicle body surface II The image coordinates of the body surface feature points in the two-dimensional calibration plate coordinate system can be obtained.

[0049]

[0050] From the homography matrix H C Obtain the coordinates of the feature points on the body surface in the camera coordinate system

[0051]

[0052] The beneficial effects of the present invention are:

[0053] (1) A projective invariant consisting of straight lines and points not on the two-dimensional calibration plate, including the laser line and the projection point of the laser line on the car body, is constructed. Feature points with relatively simple coordinates are selected, and a solution model for the vehicle morphology feature points is established, thereby realizing non-contact detection of the vehicle morphology feature points.

[0054] (2) The calibration test and reconstruction test of the method of the present invention can be combined into one, which greatly simplifies the test process. During reconstruction, one picture can be used to reconstruct the vehicle body feature points.

[0055] (3) The system of the present invention has a wide measurement range, reliable performance, simple device structure, easy operation and low cost. The method of the present invention has simple calculation and small error, and realizes non-contact and rapid measurement of automobile morphology, solving the problems of expensive fixed contact measurement system, low measurement efficiency and poor convenience.

[0056] (4) The camera 2 used in the system of the present invention is a wide-angle industrial camera equipped with a narrow-band filter, which can obtain a wider field of view. The laser wavelength emitted by the line laser 4 used is consistent with the bandpass wavelength of the narrow-band filter of the camera 2, which can effectively reduce the interference of the ambient light source on the measurement process and greatly improve the measurement accuracy.

[0057] (5) The combination of the two-dimensional calibration plate 5 and the line laser 4 in the system of the present invention can be scanned freely within the field of view of the camera 2, with a wider field of view for reconstruction and a wider range of positions for scanning, which has a significant reconstruction effect for areas that are not easily observed directly, such as the interior of a car body. The steel pipe of the connector 3 is processed with threaded holes for adjusting and fixing the position of the line laser 4, so that the laser line projected by the line laser 4 is within the plane to which the two-dimensional calibration plate 5 belongs. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is an axonometric diagram of the active visual reconstruction system of the car shape based on point and line invariants;

[0059] Figure 2 is an axonometric diagram of a camera bracket 1 in an active visual reconstruction system of automobile shape based on point and line invariants;

[0060] Figure 3 It is the axonometric view of camera 2 in the active visual reconstruction system of automobile shape based on point and line invariants;

[0061] Figure 4 It is an axonometric view of the connector 3 in the active visual reconstruction system of the automobile shape based on point and line invariants;

[0062] Figure 5 It is an axonometric view of a two-dimensional calibration plate 5 in an active visual reconstruction system of automobile shape based on point and line invariants;

[0063] Figure 6 It is an axonometric diagram of a connector 3, a line laser 4, and a two-dimensional calibration plate 5 in an active visual reconstruction system of an automobile shape based on point and line invariants;

[0064] Figure 7 This is a schematic diagram of the active visual reconstruction method of automobile shape based on point and line invariants;

[0065] Figure 8 It is a flow chart of the laser line solution in the 5-coordinate system of the two-dimensional calibration plate in the active visual reconstruction method of the automobile shape based on point and line invariants;

[0066] Fig. 9 This is a flowchart of the reconstruction of the vehicle body surface feature points in the camera 2 coordinate system using the active visual reconstruction method of the vehicle shape based on point and line invariants;

[0067] In the figure: 1. Camera bracket, 2. Camera, 3. Connector, 4. Line laser, 5. Two-dimensional calibration plate. DETAILED DESCRIPTION

[0068] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0069] See also Figures 1 to 6 The active visual reconstruction system of automobile shape based on point and line invariants includes a camera bracket 1, a camera 2, a connecting part 3, a line laser 4 and a two-dimensional calibration plate 5;

[0070] The camera bracket 1 is a tripod bracket with adjustable height, which is placed on the ground. The camera 2 is a wide-angle industrial camera equipped with a narrow-band filter. The camera 2 is fixedly connected to the bolt thread on the top of the camera bracket 1 through the threaded hole at the bottom. The two-dimensional calibration plate 5 is a part made of a rectangular steel plate. The surface of the two-dimensional calibration plate 5 is pasted with regular geometric figures of black and white rectangular logos that can generate point and straight line features. The two-dimensional calibration plate 5 is processed with through holes. The connecting piece 3 is a part welded by a U-shaped steel plate and a steel pipe. The side of the U-shaped steel plate is processed with through holes, and the side of the steel pipe is processed with threaded holes. The two-dimensional calibration plate 5 is placed in the slender groove of the U-shaped steel plate of the connecting part 3, the bolts are inserted into the through holes of the connecting part 3 and the two-dimensional calibration plate 5 and are fixedly connected with the nut threads, the line laser 4 is inserted into the inner hole of the steel pipe of the laser connecting part 3, the set screw is screwed into the threaded hole on the side of the steel pipe of the connecting part 3, and the end of the set screw is tightly fitted with the cylindrical surface of the line laser 4. The line laser 4 is a cylindrical part that can emit a line laser. The laser wavelength emitted by the line laser 4 is consistent with the bandpass wavelength of the narrowband filter of the camera 2, and the laser line emitted by the line laser 4 is coplanar with the plane where the two-dimensional calibration plate 5 pattern is located.

[0071] See also Figures 7 to 9 , the active visual reconstruction method of automobile shape based on point and line invariants can be divided into the following three steps:

[0072] Step 1: Image acquisition for active visual reconstruction of vehicle shape based on point and line invariants:

[0073] The camera 2 is fixed on the camera bracket 1, and the camera bracket 1 is placed on the ground. The line laser 4 is inserted into the inner hole of the steel pipe of the connecting piece 3, and the line laser 4 is turned on. By adjusting the screws on the steel pipe of the connecting piece 3, the laser line projected by the line laser 4 is in the plane to which the two-dimensional calibration plate 5 belongs, and the line laser 4 is fixed. The camera 2 collects an image, and the image includes the two-dimensional calibration plate 5 and the projected laser point where the line laser 4 intersects with the vehicle body surface;

[0074] Step 2: Solve the coordinates of the body feature points in the 2D calibration plate 5 coordinate system based on the point and line invariants:

[0075] An image coordinate system is established on the image captured by camera 2, and a two-dimensional calibration plate 5 coordinate system is established on the two-dimensional calibration plate 5. H is the transformation matrix from the two-dimensional calibration plate 5 coordinate system to the image coordinate system obtained by Zhang Zhengyou's method. The transformation relationship of the straight line on the two-dimensional calibration plate 5 from the image coordinate l to the coordinate L of the two-dimensional calibration plate 5 coordinate system is:

[0076] L=H -T l

[0077] The conversion relationship of the feature point on the two-dimensional calibration plate 5 from the image coordinate x to the coordinate X of the two-dimensional calibration plate 5 coordinate system is:

[0078] X=H -T x

[0079] Then the invariant formed by the two straight lines on the plane and the two points X1 and X2 not on the straight line is

[0080]

[0081] Where L I is a straight line on the two-dimensional calibration plate 5, L II is the laser line emitted by the line laser 4;

[0082] The corresponding invariant on the image can be expressed as follows

[0083]

[0084] Among them l I , l II L I , L II The coordinates in the image coordinate system, l I It can be extracted by Hough transform, II SVD decomposition can be used, through the formula To obtain, The image coordinates of the intersections between the laser light emitted by the two-dimensional calibration plate 5 and the vehicle body at different positions are fixed during calibration;

[0085] Let the origin of the coordinate system of the two-dimensional calibration plate 5 be X1 = (0, 0, 1) T , the point on the Y axis is X 2，1 =(0, Y 2，1 , 1) T , by the straight line on the two-dimensional calibration plate 5 And the straight line emitted by the line laser 4 have to

[0086]

[0087] The corresponding invariant on the image is

[0088]

[0089] Among them, x 2，1 is the feature point X on the two-dimensional calibration plate 5 2，1 , x1 is the image coordinate of the feature point X1 on the two-dimensional calibration plate 5;

[0090] Let the origin on the two-dimensional calibration plate 5 be X1 = (0, 0, 1) T , the point on the X axis is X 2，2 =(X 2，1 , 0, 1)T , by the straight line on the two-dimensional calibration plate 5 And the straight line emitted by the line laser 4 have to

[0091]

[0092] The corresponding invariant on the image is

[0093]

[0094] Among them, x 2，2 is the feature point X on the two-dimensional calibration plate 5 2，2 The image coordinates of

[0095] According to I 1，1 =I 2，1 , I 1，2 =I 2，2 The second and first coordinate elements of the laser line of the line laser in the coordinate system of the two-dimensional calibration plate 5 are obtained as follows:

[0096]

[0097]

[0098] Finally, the coordinates of the laser line in the 5-coordinate system of the two-dimensional calibration plate are obtained.

[0099] Step 3: Reconstruction of body surface feature points in the camera 2 coordinate system based on point and line invariants:

[0100] The camera 2 coordinate system is selected as the fixed global coordinate system, and then the two-dimensional calibration plate 5 is placed at the qth position. The camera 2 collects the image at the qth position, q = 1, 2, ..., n. Using the collected n images, according to Zhang Zhengyou's two-dimensional calibration algorithm, the rotation matrix R = (r1 r2 r3) from the two-dimensional calibration plate 5 coordinate system to the camera 2 coordinate system, the translation vector t and the camera 2 intrinsic parameter A can be obtained. Then the projection matrix from the two-dimensional calibration plate 5 coordinate system to the image coordinate system is

[0101] P=A(r1 r2 t)

[0102] The homography matrix from the 2D calibration plate 5 coordinate system to the camera 2 coordinate system is

[0103]

[0104] The L in the coordinate system of the two-dimensional calibration plate 5 obtained in the second step II The coordinates of the two-dimensional calibration plate 5 coordinate system and the projection matrix P from the image coordinate system, according to the transformation relationship between the point on the straight line and the two-dimensional calibration plate 5 coordinate system to the image coordinate system,

[0105] (L II ) T X II =0

[0106] PX II =x II

[0107] where x II The feature point X projected by the laser line onto the vehicle body surface II The image coordinates of the vehicle body surface feature points in the 2D calibration plate 5 coordinate system can be obtained.

[0108]

[0109] From the homography matrix H C Obtain the coordinates of the feature points on the body surface in the camera 2 coordinate system

[0110]

Claims

1. A reconstruction method of an active visual reconstruction system for automobile shape based on point and line invariants, the active visual reconstruction system for automobile shape based on point and line invariants comprising a camera bracket (1), a camera (2), a connecting piece (3), a line laser (4) and a two-dimensional calibration plate (5); The camera bracket (1) is placed on the ground, the camera (2) is threadedly fixedly connected to the bolt on the top of the camera bracket (1) through the threaded hole at the bottom, the two-dimensional calibration plate (5) is placed in the slender groove of the U-shaped steel plate of the connecting piece (3), the bolts are inserted into the through holes of the connecting piece (3) and the two-dimensional calibration plate (5) and are threadedly fixedly connected with the nuts, the line laser (4) is inserted into the inner hole of the steel pipe of the laser connecting piece (3), the set screw is screwed into the threaded hole on the side of the steel pipe of the connecting piece (3), the end of the set screw is in contact with the cylindrical surface of the line laser (4) and is tightly matched, the laser line emitted by the line laser (4) is coplanar with the plane where the two-dimensional calibration plate (5) pattern is located, and it is characterized in that The specific steps are as follows: Step 1: Image acquisition for active visual reconstruction of vehicle shape based on point and line invariants: The camera (2) is fixed on the camera bracket (1), and the camera bracket (1) is placed on the ground. The line laser (4) is inserted into the inner hole of the steel pipe of the connecting piece (3), and the line laser (4) is turned on. By adjusting the screws on the steel pipe of the connecting piece (3), the laser line projected by the line laser (4) is in the plane to which the two-dimensional calibration plate (5) belongs and the line laser (4) is fixed. The camera (2) collects an image, and the image includes the two-dimensional calibration plate (5) and the projected laser point where the line laser (4) intersects with the surface of the vehicle body; Step 2: Solve the coordinates of the body feature points in the two-dimensional calibration plate (5) coordinate system based on the point and line invariants: An image coordinate system is established on the image captured by the camera (2), and a two-dimensional calibration plate (5) coordinate system is established on the two-dimensional calibration plate (5). H is a transformation matrix from the two-dimensional calibration plate (5) coordinate system to the image coordinate system obtained by using the Zhang Zhengyou method. The transformation relationship of the straight line on the two-dimensional calibration plate (5) from the image coordinate l to the coordinate L of the two-dimensional calibration plate (5) coordinate system is: L=H -T l The conversion relationship of the feature point on the two-dimensional calibration plate (5) from the image coordinate x to the coordinate X of the two-dimensional calibration plate (5) coordinate system is: X=H -T x Then the invariant formed by the two straight lines on the plane and the two points X1 and X2 not on the straight line is Where L I is a straight line on the two-dimensional calibration plate (5), L II is a laser line emitted by a line laser (4); The corresponding invariant on the image can be expressed as follows Among them l I , l II L I , L II The coordinates in the image coordinate system, l I It can be extracted by Hough transform, II SVD decomposition can be used, through the formula To obtain, The image coordinates of the intersections of the laser light emitted by the fixed state line laser (4) and the vehicle body at different positions on the two-dimensional calibration plate (5) during calibration; Let the origin of the coordinate system of the two-dimensional calibration plate (5) be X1 = (0, 0, 1) T , the point on the Y axis is X 2，1 =(0, Y 2，1 , 1) T , by the straight line on the two-dimensional calibration plate (5) and the straight line emitted by the line laser (4) have to The corresponding invariant on the image is Among them, x 2，1 is the feature point X on the two-dimensional calibration plate (5) 2，1 The image coordinates of x1 are the image coordinates of the feature point X1 on the two-dimensional calibration plate (5); Let the origin on the two-dimensional calibration plate (5) be X1 = (0, 0, 1) T , the point on the X-axis is x 2，2 =(X 2，1 , 0, 1) T , by the straight line on the two-dimensional calibration plate (5) and the straight line emitted by the line laser (4) have to The corresponding invariant on the image is Among them, x 2，2 is the feature point X on the two-dimensional calibration plate (5) 2，2 The image coordinates of According to I 1，1 =I 2，1 , I 1，2 =I 2，2 The second and first coordinate elements of the laser line of the line laser in the two-dimensional calibration plate coordinate system are obtained as follows: Finally, the coordinates of the laser line in the two-dimensional calibration plate coordinate system are obtained. Step 3: Reconstruction of the body surface feature points in the camera (2) coordinate system based on point and line invariants: The coordinate system of the camera (2) is selected as the fixed global coordinate system, and then the two-dimensional calibration plate (5) is placed at the qth position. The camera (2) collects the image at the qth position, q = 1, 2, ..., n. Using the collected n images, according to Zhang Zhengyou's two-dimensional calibration algorithm, the rotation matrix R = (r1 r2 r3) from the coordinate system of the two-dimensional calibration plate (5) to the coordinate system of the camera (2), the translation vector t and the intrinsic parameter A of the camera (2) can be obtained. Then the projection matrix from the coordinate system of the two-dimensional calibration plate (5) to the image coordinate system is: P=A(r1 r2 t) The homography matrix from the coordinate system of the two-dimensional calibration plate (5) to the coordinate system of the camera (2) is The coordinate system L of the two-dimensional calibration plate (5) obtained in the second step is II The coordinates of the two-dimensional calibration plate (5) and the projection matrix P from the coordinate system of the image coordinate system are: (L II ) T X II =0 PX II =x II where x II The feature point X projected by the laser line onto the vehicle body surface II The image coordinates of the vehicle body surface feature points in the two-dimensional calibration plate (5) coordinate system can be obtained From the homography matrix H C Obtain the coordinates of the feature points on the body surface in the camera (2) coordinate system 2. The reconstruction method of the active visual reconstruction system of automobile shape based on point and line invariants according to claim 1 is characterized in that The camera bracket (1) is a tripod bracket with adjustable height.

3. The reconstruction method of the active visual reconstruction system of automobile shape based on point and line invariants according to claim 1 is characterized in that The camera (2) is a wide-angle industrial camera equipped with a narrow-band filter.

4. The reconstruction method of the active visual reconstruction system of automobile shape based on point and line invariants according to claim 1 is characterized in that The connecting piece (3) is a part formed by welding a U-shaped steel plate and a steel pipe. A through hole is processed on the side of the U-shaped steel plate, and a threaded hole is processed on the side of the steel pipe.

5. The reconstruction method of the automobile shape active visual reconstruction system based on point and line invariants according to claim 1 is characterized in that The line laser (4) is a cylindrical part capable of emitting line laser light. The wavelength of the laser light emitted by the line laser (4) is consistent with the bandpass wavelength of the narrow-band filter of the camera (2).

6. The reconstruction method of the active visual reconstruction system of automobile shape based on point and line invariants according to claim 1 is characterized in that The two-dimensional calibration plate (5) is a part made of a rectangular steel plate. Regular geometric figures of black and white rectangular marks that can generate point and straight line features are pasted on the surface of the two-dimensional calibration plate (5). The two-dimensional calibration plate (5) is processed with through holes.

Images