Automobile shape reconstruction system and method based on quadratic curves dual to imaginary points

Abstract

The present invention discloses a system and method for reconstructing automobile morphology based on a quadratic curve dual to an imaginary circle, aiming to solve the problem of active visual detection of automobile morphology based on a quadratic curve dual to an imaginary circle. The system for active visual reconstruction of automobile morphology based on a quadratic curve dual to an imaginary circle mainly comprises a camera bracket (1), a camera (2), a connecting piece (3), a laser (4) and a two-dimensional reference plate (5). The method for active visual reconstruction of automobile morphology based on a quadratic curve dual to an imaginary circle consists of three steps: image acquisition, solving a transformation matrix from a projection space to a similarity space, and vehicle body point reconstruction. A system and method for reconstructing automobile morphology based on a quadratic curve dual to an imaginary circle with a simple structure and reliable performance are provided.

Description

Technical Field

[0001] The invention relates to a measuring device and a measuring method in the field of automobile shape detection, and more specifically, to an automobile shape reconstruction system and method based on a quadratic curve dual to a virtual circle point. Background Art

[0002] In recent decades, visual three-dimensional shape measurement has been widely used in many fields such as industrial automatic detection, reverse engineering, medical treatment, biometrics and cultural relics replication. With the development of social needs and science and technology, existing detection methods such as three-coordinate machines have low measurement efficiency due to point-by-point scanning and contact detection methods, and it is difficult to meet the requirements of automobile shape detection. Therefore, in view of the problem of automobile shape detection, it is very important to design a non-contact, fast-measuring, and non-strictly constrained detection method suitable for measuring large objects to restore the automobile shape. The present invention proposes a system and method for automobile shape reconstruction based on a quadratic curve dual to an imaginary circle. The two-dimensional reference plate in the system and the laser line projected by the laser are in the same plane. Multiple pairs of orthogonal straight lines are set on the two-dimensional reference plate to solve the quadratic curve dual to the imaginary circle and obtain the transformation matrix of the similarity space, and the coordinates of the body points are reconstructed in the similarity space using scale invariance. Summary of the invention

[0003] The present invention aims to solve the problems that in the process of obtaining the automobile morphology, fixed detection cannot flexibly detect the morphology of various parts of the automobile, the equipment is expensive, and the measurement speed is slow. A method and system with reliable performance, simple structure, easy operation and simple algorithm is proposed. The method mainly consists of a camera bracket, a camera, a connector, a laser and a two-dimensional reference plate. Reconstruction is performed using two similarity invariants: the first invariant is a quadratic curve dual to the virtual circle point, which is derived from the orthogonal lines on the reference pattern. The similarity invariant can calculate the transformation matrix from the projection space to the similarity space. The second invariant is the ratio of the line segment composed of the laser projection point and the reference point, and the laser projection point is generated on the object to be measured using a two-dimensional reference plate and a coplanar laser plane, and the laser projection point in the similarity space is converted into Euclidean space, thereby realizing the reconstruction of the automobile morphology.

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

[0005] The automobile shape reconstruction system based on the quadratic curve dual to the virtual circle point includes a camera bracket, a camera, a connecting part, a laser and a two-dimensional reference 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 reference 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 reference plate and are fixedly connected with the nut thread, the laser is inserted into the inner hole of the steel pipe of the laser connecting piece, the set screw is screwed into the threaded hole on the side of the steel pipe of the connecting piece, the end of the set screw is in contact with the cylindrical surface of the laser and is tightly fitted, and the laser line emitted by the laser is coplanar with the plane where the two-dimensional reference 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 laser described in the technical solution is a cylindrical part that can emit linear laser, and the wavelength of the laser emitted by the laser is consistent with the bandpass wavelength of the narrow-band filter of the camera.

[0011] The two-dimensional reference plate described in the technical solution is a part made of a rectangular steel plate. Regular geometric figures of alternating black and white triangles that generate quadratic curves dual to imaginary circles are pasted on the surface of the two-dimensional reference plate, and the two-dimensional reference plate is processed with through holes.

[0012] The specific steps of the vehicle shape reconstruction method based on the dual quadratic curve with the imaginary circle point are as follows:

[0013] Step 1: Image acquisition based on the vehicle shape reconstruction method of the quadratic curve dual to the imaginary circle point:

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

[0015] Step 2: Solve the transformation matrix from the projection space to the similarity space based on the quadratic curve image coordinates dual to the imaginary circle point:

[0016] The Hough transform is used to extract the i-th pair (i=1, 2, ..., n, n≥5) of orthogonal lines on the two-dimensional reference plate from the image captured by the camera. The image coordinates l i 、m i, and the coordinates of the quadratic curve image of the imaginary circle can be decomposed by SVD to obtain the following formula

[0017]

[0018] in is the coordinate of the quadratic curve image dual to the imaginary circle point;

[0019] By the similarity invariance of the dual quadratic curve with the imaginary circle point, we can get

[0020]

[0021] in is the affine transformation matrix, where K is a 2×2 upper triangular matrix, is the projection transformation matrix, where is the coordinate of the quadratic curve dual to the imaginary circle in Euclidean space; let the transformation matrix from the projective space to the similarity space V = H P H A ,Right now Then the transformation relationship between the image coordinates of the quadratic curve dual to the imaginary circle and the Euclidean coordinates is

[0022]

[0023] From the above formula, we get

[0024]

[0025]

[0026] Using Cholesky decomposition to obtain the upper triangular matrix

[0027]

[0028] From the obtained upper triangular matrix K, we can get

[0029]

[0030] According to the obtained upper triangular matrix K and vector w, the transformation matrix V from the projection space to the similarity space is obtained

[0031]

[0032] Step 3: The laser projection points where the laser plane intersects the vehicle surface are reconstructed in the Euclidean coordinate system:

[0033] Arbitrarily select a pair of feature points A on the two-dimensional reference plate q , B q (q=1,2,...,m,m≥2), the feature point A can be directly obtained from the two-dimensional reference plate q , Bq The Euclidean coordinates of And extract its image coordinates from the image obtained in the first step And the image coordinates x of the laser projection point on the vehicle surface j =(x j y j 1) T , the Euclidean coordinates of the laser projection point on the vehicle surface to be determined are

[0034] According to the transformation matrix V from the projection space to the similarity space obtained in the second step, the feature points are transformed from the projection space to the similarity space

[0035]

[0036]

[0037]

[0038] According to the similarity invariance of length ratio, we can get

[0039]

[0040] Take B on the Y axis of the Euclidean coordinates of the two-dimensional reference plate q Point, and order have to

[0041]

[0042] Select another pair of feature points on the 2D reference plate The equation

[0043]

[0044] The above two equations can be used to obtain the ordinate of the Euclidean coordinate of the feature point on the body surface:

[0045]

[0046] Continue to select (m-1) groups of feature points on the 2D reference plate and find (m-1) vertical coordinates Values ​​and find their mean The mean Substituting equation In Then the horizontal coordinate of the Euclidean coordinate of the feature point on the body surface is

[0047]

[0048] The beneficial effects of the present invention are:

[0049] (1) The present invention uses two similarity invariants for reconstruction: the first invariant is the quadratic curve dual to the imaginary circle, which is derived from the orthogonal lines on the reference pattern. The similarity invariant can be used to calculate the transformation matrix from the projection space to the similarity space. The second invariant is the ratio of the line segment composed of the laser projection point and the reference point, and the laser projection point is generated on the object to be measured using a two-dimensional reference plate and a coplanar laser plane, and the laser projection point in the similarity space is converted into the Euclidean space, thereby realizing the reconstruction of the vehicle shape.

[0050] (2) During reconstruction, the feature points are taken on the Y axis of the two-dimensional reference plate 5 to avoid solving nonlinear equations, which greatly simplifies the calculation process.

[0051] (3) The present invention only requires the camera to obtain an image including the two-dimensional reference plate 5 and the projected laser point where the laser 4 intersects with the vehicle surface, so as to solve the real coordinates of the vehicle body feature points.

[0052] (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, so that the combination of the two-dimensional reference plate 5 and the laser 4 can scan a wider range and be more flexible. The wavelength of the laser emitted by the 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.

[0053] (5) The steel pipe of the connecting piece 3 is processed with two threaded holes at the top, bottom, left and right sides, and eight screws are screwed into the threaded holes to adjust and fix the position of the laser 4 so that the laser line projected by the laser 4 can be coplanar with the two-dimensional reference plate 5. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is an axonometric diagram of the reconstruction process of the automobile shape reconstruction system based on the quadratic curve dual to the imaginary circle point;

[0055] Figure 2 is an axonometric view of a camera bracket 1 in a vehicle shape reconstruction system based on a quadratic curve dual to an imaginary circle point;

[0056] Figure 3 is an axonometric view of camera 2 in a car shape reconstruction system based on a quadratic curve dual to an imaginary circle point;

[0057] Figure 4 It is an axonometric view of the connector 3 in the automobile shape reconstruction system based on the quadratic curve dual to the imaginary circle point;

[0058] Figure 5 is an axonometric view of a two-dimensional reference plate 5 in a vehicle shape reconstruction system based on a quadratic curve dual to an imaginary circle point;

[0059] Figure 6It is an axonometric view of an assembly of a connector 3, a laser 4, and a two-dimensional reference plate 5 in a vehicle shape reconstruction system based on a quadratic curve dual to an imaginary circle point;

[0060] Figure 7 It is a flowchart for solving the transformation matrix V from the projection space to the similarity space in the automobile shape reconstruction method based on the quadratic curve dual to the imaginary circle point;

[0061] Figure 8 It is a flow chart of reconstructing the characteristic points of the vehicle body by using the line segment ratio invariant in the method of reconstructing the vehicle shape based on the quadratic curve dual to the imaginary circle point;

[0062] Fig. 9 It is a schematic diagram of the automobile shape reconstruction method based on the quadratic curve dual to the imaginary circle point;

[0063] In the figure: 1. Camera bracket, 2. Camera, 3. Connector, 4. Line laser, 5. Two-dimensional reference plate. DETAILED DESCRIPTION

[0064] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0065] See also Figures 1 to 6 The automobile shape reconstruction system based on the quadratic curve dual to the imaginary circle includes a camera bracket 1, a camera 2, a connecting part 3, a laser 4 and a two-dimensional reference plate 5.

[0066] 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 top of the camera bracket 1 through the threaded hole at the bottom. The two-dimensional reference plate 5 is a part made of a rectangular steel plate. The surface of the two-dimensional reference plate 5 is pasted with a regular geometric figure of alternating black and white triangles that generates a quadratic curve dual to the virtual circle point. The two-dimensional reference plate 5 is processed with a through hole. 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 a through hole, and the side of the steel pipe is reinforced with a through hole. The two-dimensional reference plate 5 is inserted into 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 reference plate 5 and are fixedly connected with the nut threads, the 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, and the end of the set screw is in contact with the cylindrical surface of the laser 4 and is tightly matched. The laser 4 is a cylindrical part that can emit linear lasers. The laser wavelength emitted by the laser 4 is consistent with the bandpass wavelength of the narrowband filter of the camera 2, and the laser line emitted by the laser 4 is coplanar with the plane where the two-dimensional reference plate 5 pattern is located;

[0067] See also Figures 7 to 9 , the vehicle shape reconstruction method based on the quadratic curve dual to the imaginary circle point can be divided into the following three steps:

[0068] Step 1: Image acquisition based on the vehicle shape reconstruction method of the quadratic curve dual to the imaginary circle point:

[0069] The camera 2 is fixed on the camera bracket 1, and the camera bracket 1 is placed on the ground. The laser 4 is inserted into the inner hole of the steel pipe of the connecting piece 3, and the laser 4 is turned on. The laser line projected by the laser 4 is made coplanar with the two-dimensional reference plate 5 by adjusting the screws on the steel pipe of the connecting piece 3 and rotating the laser 4, and the laser 4 is fixed. The camera 2 collects an image, and the image includes the two-dimensional reference plate 5 and the projected laser point where the laser 4 intersects with the vehicle surface;

[0070] Step 2: Solve the transformation matrix from the projection space to the similarity space based on the quadratic curve image coordinates dual to the imaginary circle point:

[0071] The i-th pair (i=1, 2, ..., n, n≥5) of orthogonal straight lines on the two-dimensional reference plate 5 are extracted using Hough transform from the image captured by the camera 2. The image coordinates l i 、m i , and the coordinates of the quadratic curve image of the imaginary circle can be decomposed by SVD to obtain the following formula

[0072]

[0073] in is the coordinate of the quadratic curve image dual to the imaginary circle point;

[0074] By the similarity invariance of the dual quadratic curve with the imaginary circle point, we can get

[0075]

[0076] in is the affine transformation matrix, where K is a 2×2 upper triangular matrix, is the projection transformation matrix, where is the coordinate of the quadratic curve dual to the imaginary circle in Euclidean space; let the transformation matrix from the projective space to the similarity space V = H P H A ,Right now Then the transformation relationship between the image coordinates of the quadratic curve dual to the imaginary circle and the Euclidean coordinates is

[0077]

[0078] From the above formula, we get

[0079]

[0080]

[0081] Using Cholesky decomposition to obtain the upper triangular matrix

[0082]

[0083] From the obtained upper triangular matrix K, we can get

[0084]

[0085] According to the obtained upper triangular matrix K and vector w, the transformation matrix V from the projection space to the similarity space is obtained

[0086]

[0087] Step 3: The laser projection points where the laser plane intersects the vehicle surface are reconstructed in the Euclidean coordinate system:

[0088] Arbitrarily select a pair of feature points A on the two-dimensional reference plate 5 q , B q (q=1,2,...,m,m≥2), the feature point A can be directly obtained from the two-dimensional reference plate 5 q , B q The Euclidean coordinates of And extract its image coordinates from the image obtained in the first step And the image coordinates x of the laser projection point on the vehicle surface j =(x j y j 1) T , the Euclidean coordinates of the laser projection point on the vehicle surface to be determined are

[0089] According to the transformation matrix V from the projection space to the similarity space obtained in the second step, the feature points are transformed from the projection space to the similarity space

[0090]

[0091]

[0092]

[0093] According to the similarity invariance of length ratio, we can get

[0094]

[0095] Take B on the Y axis of the Euclidean coordinate of the two-dimensional reference plate 5 q Point, and order have to

[0096]

[0097] Select another pair of feature points on the two-dimensional reference plate 5 The equation

[0098]

[0099] The above two equations can be used to obtain the ordinate of the Euclidean coordinate of the feature point on the body surface:

[0100]

[0101] Continue to select (m-1) groups of feature points on the two-dimensional reference plate 5 and find (m-1) vertical coordinates Values ​​and find their mean The mean Substituting equation In Then the horizontal coordinate of the Euclidean coordinate of the feature point on the body surface is

[0102]

Claims

1. A reconstruction method of a vehicle shape reconstruction system based on a quadratic curve dual to an imaginary circle, wherein the vehicle shape reconstruction system based on a quadratic curve dual to an imaginary circle comprises a camera bracket (1), a camera (2), a connecting piece (3), a laser (4) and a two-dimensional reference 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 reference 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 reference plate (5) and are threadedly fixedly connected with the nuts, the 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 laser (4) and is tightly matched, the laser line emitted by the laser (4) is coplanar with the plane where the two-dimensional reference plate (5) pattern is located, and it is characterized in that The specific steps are as follows: Step 1: Image acquisition based on the vehicle shape reconstruction method of the quadratic curve dual to the imaginary circle point: The camera (2) is fixed on the camera bracket (1), and the camera bracket (1) is placed on the ground. The laser (4) is inserted into the inner hole of the steel pipe of the connecting piece (3), and the laser (4) is turned on. The laser line projected by the laser (4) is made coplanar with the two-dimensional reference plate (5) by adjusting the screw on the steel pipe of the connecting piece (3) and rotating the laser (4) and fixing the laser (4). The camera (2) collects an image, and the image includes the two-dimensional reference plate (5) and the projected laser point where the laser (4) intersects with the vehicle surface; Step 2: Solve the transformation matrix from the projection space to the similarity space based on the quadratic curve image coordinates dual to the imaginary circle point; The i-th pair (i=1, 2, ..., n, n≥5) of orthogonal straight lines on a two-dimensional reference plate (5) are extracted from an image captured by a camera (2) using Hough transform. The image coordinates l i 、m i , and the coordinates of the quadratic curve image of the imaginary circle can be decomposed by SVD to obtain the following formula in is the coordinate of the quadratic curve image dual to the imaginary circle point; By the similarity invariance of the dual quadratic curve with the imaginary circle point, we can get in is the affine transformation matrix, where K is a 2×2 upper triangular matrix, is the projection transformation matrix, where is the coordinate of the quadratic curve dual to the imaginary circle in Euclidean space; let the transformation matrix from the projective space to the similarity space V = H P H A ,Right now Then the transformation relationship between the image coordinates of the quadratic curve dual to the imaginary circle and the Euclidean coordinates is From the above formula, we get Using Cholesky decomposition to obtain the upper triangular matrix From the obtained upper triangular matrix K, we can get According to the obtained upper triangular matrix K and vector w, the transformation matrix V from the projection space to the similarity space is obtained Step 3: The laser projection points where the laser plane intersects the vehicle surface are reconstructed in the Euclidean coordinate system: Arbitrarily select a pair of feature points A on the two-dimensional reference plate (5) q , B q (q=1,2,…,m,m≥2), the feature point A can be directly obtained from the two-dimensional reference plate (5) q , B q The Euclidean coordinates of And extract its image coordinates from the image obtained in the first step And the image coordinates x of the laser projection point on the vehicle surface j =(x j y j 1) T , the Euclidean coordinates of the laser projection point on the vehicle surface to be determined are According to the transformation matrix V from the projection space to the similarity space obtained in the second step, the feature points are transformed from the projection space to the similarity space According to the similarity invariance of length ratio, we can get Take B on the Y axis of the Euclidean coordinates of the two-dimensional reference plate (5) q Point, and order have to Select another pair of feature points on the two-dimensional reference plate (5) The equation The above two equations can be used to obtain the ordinate of the Euclidean coordinate of the feature point on the body surface: Continue to select (m-1) groups of feature points on the two-dimensional reference plate (5) and calculate (m-1) vertical coordinates Values ​​and find their mean The mean Substituting equation In Then the horizontal coordinate of the Euclidean coordinate of the feature point on the body surface is 2. The reconstruction method of the automobile shape reconstruction system based on the quadratic curve dual to the imaginary circle point according to claim 1, characterized in that The camera bracket (1) is a tripod bracket with adjustable height.

3. The reconstruction method of the automobile shape reconstruction system based on the quadratic curve dual to the imaginary circle point according to claim 1, characterized in that The camera (2) is a wide-angle industrial camera equipped with a narrow-band filter.

4. The reconstruction method of the automobile shape reconstruction system based on the quadratic curve dual to the imaginary circle point according to claim 1, 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 reconstruction system based on the quadratic curve dual to the imaginary circle point according to claim 1, characterized in that The laser (4) is a cylindrical part capable of emitting linear laser light. The wavelength of the laser light emitted by the laser (4) is consistent with the bandpass wavelength of the narrow-band filter of the camera (2).

6. The reconstruction method of the automobile shape reconstruction system based on the quadratic curve dual to the imaginary circle point according to claim 1, characterized in that The two-dimensional reference plate (5) is a part made of a rectangular steel plate. A regular geometric figure of alternating black and white triangles that generates a quadratic curve dual to the virtual circle point is pasted on the surface of the two-dimensional reference plate (5). The two-dimensional reference plate (5) is processed with a through hole.

Images