Line array camera and line laser plane coplanar evaluation method and device

Abstract

The application discloses a kind of line array camera and line laser plane coplanar evaluation method and device, wherein the method comprises: obtaining the line laser light strip projected on different targets collected by observation camera, extracting light strip center point, using fitting algorithm to the light strip center point is fitted, determine the spatial position relationship of line laser plane;Obtain the image of different target collected by line array camera, determine the intersection line of each target image and imaging plane;Extract the line segment feature of intersection line, determine the imaging plane feature point based on line segment feature and the geometric feature of each target known, using fitting algorithm to the imaging plane feature point is fitted, determine the spatial position relationship of imaging plane;According to the spatial position relationship of line laser plane and the spatial position relationship of imaging plane, the included angle between the normal lines of two planes and the distance between two planes are calculated, and the coplanar degree is evaluated based on the normal line included angle and the plane distance.The present application can realize high-precision, quantitative evaluation of coplanar degree.

Description

Technical Field

[0001] This invention relates to the field of railway engineering inspection technology, and in particular to a method and apparatus for evaluating the coplanarity of a linear array camera and a line laser plane. Background Technology

[0002] Railway track inspection relies on a line laser and line scan camera vision system to detect abnormal conditions in the appearance of track infrastructure. The laser source imaging component of the track inspection system consists of a line laser and a line scan camera. Ideally, the line laser plane and the imaging plane of the line scan camera should be coplanar. However, due to factors such as installation errors and vibrations, there are cases where the line laser plane and the imaging plane of the line scan camera are not coplanar.

[0003] In existing technologies, the calibration and evaluation of the coplanarity of these two planes generally rely on human experience and subjective visual judgment. A typical approach involves mechanically adjusting the orientation of the line laser while simultaneously observing the image captured by the line scan camera, using whether the laser beam appears as a complete, uniform "bright stripe" in the image as the coplanarity criterion. This makes it difficult to achieve high-precision, quantitative evaluation of the coplanarity of the line scan camera and the line laser plane, thus failing to provide reliable technical support for the on-site calibration and performance evaluation of track inspection equipment. Summary of the Invention

[0004] This invention provides a method for evaluating the coplanarity of a line array camera and a line laser plane, enabling high-precision and quantitative evaluation of the coplanarity of the two planes. This provides reliable technical support for the on-site calibration and performance evaluation of track inspection equipment. The method includes: The observation camera captures linear laser beams projected onto different targets. The center point of the beam on each target is extracted, and the center points of each beam are transformed to a unified coordinate system. A fitting algorithm is used to fit the center points of the beams in the unified coordinate system to determine the spatial positional relationship of the linear laser plane. The system acquires images of different targets captured by a line scan camera and determines the intersection lines between each target image and the imaging plane. It extracts the line segment features of the intersection lines, and based on the line segment features and the known geometric features of each target, determines the feature points of the imaging plane. The feature points of the imaging plane are then transformed to a unified coordinate system, and a fitting algorithm is used to fit the feature points of the imaging plane to determine the spatial positional relationship of the imaging plane of the line scan camera. Based on the spatial relationship between the line laser plane and the imaging plane, the angle between the normal of the line laser plane and the normal of the imaging plane, as well as the distance between the two planes, are calculated. The degree of coplanarity is then evaluated based on the angle between the normals and the distance between the planes.

[0005] This invention also provides a device for evaluating the coplanarity of a line array camera and a line laser plane, used to achieve high-precision, quantitative evaluation of the coplanarity of the line array camera and the line laser plane, providing reliable technical support for the on-site calibration and performance evaluation of track inspection equipment. The device includes: The module for determining the spatial position relationship of the line laser plane is used to acquire the line laser light stripes projected onto different targets by the observation camera, extract the center point of the light stripe on each target, transform the center points of each light stripe to a unified coordinate system, and use a fitting algorithm to fit the center points of the light stripe in the unified coordinate system to determine the spatial position relationship of the line laser plane. The module for determining the spatial position relationship of the imaging plane is used to acquire images of different targets collected by the line scan camera, determine the intersection line between each target image and the imaging plane, extract the line segment features of the intersection line, determine the feature points of the imaging plane based on the line segment features and the known geometric features of each target, transform the feature points of the imaging plane to a unified coordinate system, and use a fitting algorithm to fit the feature points of the imaging plane to determine the spatial position relationship of the imaging plane of the line scan camera. The coplanarity assessment module is used to calculate the angle between the normal of the line laser plane and the normal of the imaging plane, as well as the distance between the two planes, based on the spatial positional relationship between the line laser plane and the imaging plane. The coplanarity is then assessed based on the angle between the normals and the distance between the planes.

[0006] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for evaluating the coplanarity of a line scan camera and a line laser plane.

[0007] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for evaluating the coplanarity of a line scan camera and a line laser plane.

[0008] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for evaluating the coplanarity of a line scan camera and a line laser plane.

[0009] In this embodiment of the invention, by acquiring linear laser beams projected onto different targets using an observation camera, the center point of each beam on each target is extracted, and the center points of each beam are transformed to a unified coordinate system. A fitting algorithm is used to fit the center points of the beams in the unified coordinate system to determine the spatial positional relationship of the linear laser plane. Images of different targets acquired by a line scan camera are acquired, and the intersection lines between each target image and the imaging plane are determined. The line segment features of the intersection lines are extracted, and based on the line segment features and the known geometric features of each target, the feature points of the imaging plane are determined. The feature points of the imaging plane are transformed to a unified coordinate system, and a fitting algorithm is used to fit the feature points of the imaging plane to determine the spatial positional relationship of the imaging plane of the line scan camera. Based on the spatial positional relationship of the linear laser plane and the spatial positional relationship of the imaging plane, the angle between the normal of the linear laser plane and the normal of the imaging plane and the distance between the two planes are calculated. The degree of coplanarity is evaluated based on the angle between the normals and the distance between the planes. In the above process, the embodiments of the present invention calculate the normal angle and spatial distance between the two planes by fitting the spatial positional relationship between the line laser plane and the imaging plane of the line array camera, thereby achieving a high-precision and quantitative assessment of the degree of coplanarity. This overcomes the shortcomings of traditional methods that rely on human experience and subjective visual judgment, and provides reliable technical support for the on-site calibration and performance evaluation of track inspection equipment. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 This is a flowchart of the evaluation method for the coplanarity of the linear array camera and the line laser plane in an embodiment of the present invention; Figure 2 This is a structural diagram of the coplanar evaluation device in an embodiment of the present invention; Figure 3 This is a schematic diagram of the coordinate system in an embodiment of the present invention; Figure 4 This is a schematic diagram of the target coordinate system in an embodiment of the present invention; Figure 5 This is a schematic diagram illustrating the intersection of the imaging plane and the target plane in an embodiment of the present invention; Figure 6 This is a schematic diagram showing the positions of the imaging plane of the linear array camera and the laser plane on the target plane in an embodiment of the present invention; Figure 7 This is a schematic diagram of the evaluation device for coplanar evaluation of a line scan camera and a line laser plane in an embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0012] Figure 1 This is a flowchart of a method for evaluating the coplanarity of a linear array camera and a line laser plane in an embodiment of the present invention. The method includes: Step 101: Obtain the line laser light stripes projected onto different targets by the observation camera, extract the center point of the light stripe on each target, transform the center point of each light stripe to a unified coordinate system, and use a fitting algorithm to fit the center point of the light stripe in the unified coordinate system to determine the spatial position relationship of the line laser plane. Step 102: Acquire images of different targets captured by the line scan camera, determine the intersection line between each target image and the imaging plane; extract the line segment features of the intersection line, and based on the line segment features and the known geometric features of each target, determine the feature points of the imaging plane, transform the feature points of the imaging plane to a unified coordinate system, and use a fitting algorithm to fit the feature points of the imaging plane to determine the spatial position relationship of the imaging plane of the line scan camera. Step 103: Based on the spatial positional relationship between the line laser plane and the imaging plane, calculate the angle between the normal of the line laser plane and the normal of the imaging plane, as well as the distance between the two planes, and evaluate the degree of coplanarity based on the angle between the normals and the distance between the planes.

[0013] Each step is explained in detail below.

[0014] In step 101, the observation camera acquires line laser beams projected onto different targets, extracts the center point of the beam on each target, transforms the center points of each beam to a unified coordinate system, and uses a fitting algorithm to fit the center points of the beams in the unified coordinate system to determine the spatial positional relationship of the line laser plane.

[0015] In a specific embodiment, two targets are taken as an example. Figure 2 This is a structural diagram of the coplanar evaluation device in an embodiment of the present invention. A line laser and a line scan camera are encapsulated within a laser source imaging assembly, forming the laser source imaging assembly of the track inspection system. Two targets are located directly below the line scan camera, with the optical axis of the line scan camera lens perpendicular to the target plane. An observation camera is mounted at a 45° angle to the upper right of the targets, covering both targets in its field of view, and is used to acquire laser light stripe images. The two targets are placed parallel to each other on the track plane, staggered vertically and horizontally, ensuring that the observation camera can simultaneously capture images of both targets.

[0016] In one embodiment, transforming the center points of each light stripe to a unified coordinate system includes: Based on the intrinsic and extrinsic parameter matrices of the observation camera, the center points of each light stripe are transformed to the camera coordinate system.

[0017] In a specific embodiment, intrinsic parameter calibration of the line scan camera is required. Only the intrinsic parameter matrix of the line scan camera needs to be calibrated. Establish a mapping relationship between pixel coordinates and the camera coordinate system to eliminate the effects of lens distortion. The intrinsic parameter calibration process for a line scan camera is as follows: Calibration image acquisition: A fixed linear array camera was used to move the target to 15 different positions, and one image was captured at each position, for a total of 20 calibration images.

[0018] Corner extraction and subpixel localization: The Harris corner detection algorithm is used to extract checkerboard corners, and subpixel localization is achieved through quadratic surface fitting.

[0019] Intrinsic parameter matrix calculation: Based on Zhang Zhengyou's calibration method, pixel coordinates are established. With physical coordinates Mapping relationship:

[0020] in Focal length (unit: pixels). The coordinates of the principal point are used to solve the problem using least squares.

[0021] In addition, the intrinsic and extrinsic parameters of the observation camera need to be calibrated. The intrinsic parameter matrix of the observation camera needs to be calibrated simultaneously. and extrinsic parameter matrix This establishes the transformation relationship between the observation camera coordinate system (CCS) and the dual target coordinate systems (TCS1, TCS2), providing a benchmark for the unification of the light plane point set coordinates. For example... Figure 3 This is a schematic diagram of the coordinate system in an embodiment of the present invention. Figure 4 This is a schematic diagram of the target coordinate system in an embodiment of the present invention, as shown below. Figure 4 As shown, ten equilateral triangles with a side length of 30mm are arranged horizontally on the upper surface of the target, with the endpoints of the base sides of adjacent triangles coinciding. The origin of the TCS1 coordinate system is located at the lower left corner of the target, the X-axis extends to the right along the long side of the target, the Y-axis extends upwards along the short side of the target, and the Z-axis is perpendicular to the target plane (Z=0). The TCS2 coordinate system is similar to the TCS1 coordinate system. The calibration procedure for the camera's intrinsic and extrinsic parameters is as follows: Multi-view image acquisition: Rotate the handheld calibration board around the observation camera to capture 20 images from different viewpoints (covering 0°-30° pitch angle and 0°-360° azimuth angle), ensuring that the calibration board is completely within the field of view.

[0022] Intrinsic parameter calculation: The intrinsic parameter matrix is ​​calculated using Zhang Zhengyou's calibration method.

[0023] Including focal length Principal point coordinates .

[0024] The camera extrinsic parameter calibration procedure is as follows: For the TCS1 target, obtain the pixel coordinates and physical coordinates of at least 6 feature points on the target (feature points refer to the vertices of the triangular target, obtained by edge extraction and intersection point calculation), and use the PNP algorithm to solve for the extrinsic parameter matrix: ; in It is a 3×3 rotation matrix. It is a 3×1 translation vector.

[0025] Similarly, for the TCS2 target, extract the pixel coordinates and physical coordinates of at least 6 feature points on the target, and repeat the above operation.

[0026] Among them, the dual targets can provide a reference coordinate system for the external parameter calibration of the observation camera: the observation camera needs to establish the transformation relationship between its coordinate system (ccs) and the target coordinate system (tcs1, tcs2) through external parameter calibration, while the dual targets construct two independent physical references with known spatial positions by pre-setting clear spatial parameters (tcs2 is translated 100mm along the Z axis and 300mm along the X axis relative to tcs1).

[0027] Dual targets can also provide a large spatial baseline for the light stripe point set for line laser plane fitting. Solving the line laser plane equation requires fitting the light stripe point set in the camera coordinate system, while the spatial misalignment design of dual targets (vertical spacing of 100mm and horizontal offset of 300mm) can significantly expand the spatial distribution range of the light stripe point set, forming a large spatial baseline.

[0028] The dual targets (tcs1 and tcs2) are the core auxiliary components for realizing the coplanar evaluation of the linear array camera and the line structured light. Their role is involved in the entire process of camera parameter calibration, subsequent solution of plane equations and final coplanar evaluation.

[0029] In one embodiment, a fitting algorithm is used to fit the center point of the light stripe in a unified coordinate system to determine the spatial positional relationship of the line laser plane, including: The RANSAC algorithm was used to remove outliers from the center point of the light stripe, resulting in the processed center point of the light stripe. The least squares method is used to fit the center point of the processed light stripe, and the coefficients of the line laser plane equation are calculated to determine the spatial positional relationship of the line laser plane.

[0030] In a specific embodiment, the line laser is turned on, and the line laser is projected onto target 1 and target 2 to form light stripes; the light stripe image is acquired by the observation camera, and the center pixel coordinates of the light stripe are extracted; based on the intrinsic and extrinsic parameter matrices of the observation camera, the center pixel coordinates of the light stripe are transformed to the camera coordinate system to obtain the light stripe point set of the two targets.

[0031] The center points of the light stripes on targets 1 and 2 are merged in the camera coordinate system (CCS) to form a dual-target light stripe point set. Outliers are removed using the RANSAC algorithm, retaining ≥20 valid points.

[0032] The least squares method is used to fit the processed set of light stripe center points. The equation of the plane to be fitted is: Az+ By+Cz+ D=0 ; The parameters are solved by constructing an objective function based on minimizing the sum of squared residuals of the point-to-plane distances. The coefficients of the line laser plane equation, i.e., the normal vector, are (A, B, C).

[0033] In step 102, images of different targets acquired by the line scan camera are obtained, and the intersection lines of each target image and the imaging plane are determined. The line segment features of the intersection lines are extracted, and based on the line segment features and the known geometric features of each target, the imaging plane feature points are determined. The imaging plane feature points are transformed to a unified coordinate system, and a fitting algorithm is used to fit the imaging plane feature points to determine the spatial positional relationship of the imaging plane of the line scan camera.

[0034] In one embodiment, acquiring images of different targets captured by a linear scan camera and determining the intersection line between each target image and the imaging plane includes: Extract the contour lines of the corresponding preset geometric patterns on the target from different target images; Based on the proportional relationship between the pixel length of the contour line segment in the target image and the known geometric features of the target, a mathematical model is established to solve the intersection line parameters. By solving the mathematical model, the equation of the intersection line between the imaging plane and the corresponding target plane is determined.

[0035] In one embodiment, determining imaging plane feature points based on line segment features and known geometric features of each target includes: Based on the equation of the intersection of the imaging plane and the corresponding target plane, and the equation of the boundary line segment of the preset geometric pattern on the target, the intersection point is calculated and used as the feature point of the imaging plane.

[0036] In one embodiment, transforming feature points on the imaging plane to a unified coordinate system includes: Based on the intrinsic and extrinsic parameter matrices of a linear scan camera, feature points on the imaging plane are transformed into the camera coordinate system.

[0037] In a specific embodiment, the line laser is first turned off to avoid interference with target features, ensuring that the line scan camera captures a clean image containing only the target's geometric features. The line scan camera captures images of target 1 (tcs1) and target 2 respectively. The two targets have a clear spatial offset, providing spatial constraints for subsequent intersection line calculation. Based on the intrinsic parameter matrix of the line scan camera, radial distortion correction is performed on the captured images of target 1 and target 2 to eliminate the influence of lens distortion on geometric features, ensuring the consistency of line segment lengths and angles in the image with the physical world.

[0038] Figure 5 This is a schematic diagram illustrating the intersection of the imaging plane and the target plane in an embodiment of the present invention, as shown below. Figure 5 As shown, the imaging plane intersects the target plane to form an intersection line, which intersects the left and right sides of each triangle on the target, with the intersection points forming line segments. , k =1,2,…10. Figure 6 This diagram illustrates the positions of the imaging plane and laser plane of the line scan camera on the target plane in an embodiment of the present invention. The solid red line represents the intersection of the laser plane and the target plane, and the dashed blue line represents the intersection of the imaging plane and the target plane. Ideally, the imaging plane of the line scan camera and the laser plane should be coplanar. However, in practical applications, due to installation errors, vehicle vibrations, etc., they may not be coplanar. Where the overlapping area between the imaging plane and the laser plane is large, the light intake of the line scan camera is sufficient, resulting in high image quality. Where the overlapping area is small, the light intake of the line scan camera is insufficient, resulting in low image quality.

[0039] In a specific embodiment, the imaging plane intersects the target plane at a straight line L1. This line of intersection passes through 10 regularly arranged equilateral triangles on the target, intersecting the left and right sides of each triangle at point A. k and B k Thus, a line segment A is intercepted within each triangle. k B k .

[0040] line segment A k B k The pixel length l in the image k Its actual physical length L in the target coordinate system k There exists a definite mathematical relationship between them. This relationship is uniquely determined by the spatial pose of the imaging plane relative to the target plane. This is achieved by establishing the pixel length l of all 10 triangles. k With physical length L k By using the joint constraint model between them, the parameters defining the intersection line L1 can be solved inversely.

[0041] The specific steps for solving the intersection line are as follows: Threshold segmentation was performed on the distortion-corrected target image to accurately identify the contours of 10 equilateral triangles, and the line segment A intercepted by the intersection line L1 within each triangle was extracted. k B k pixel length l k (k=1, 2, ..., 10).

[0042] Establish the physical length L of the line segment k With pixel length l k The proportional model between: L k = m × l k Here, m is a key intermediate scaling factor, the value of which comprehensively reflects the intrinsic parameters of the line scan camera and the spatial attitude of the imaging plane.

[0043] The pixel length l of the 10 triangles k Substituting the known physical geometric parameters (such as the waistline equation) into the above scaling model, an overdetermined system of equations is constructed regarding the intersection parameters (slope a and intercept b) and the scaling factor m. A weighted least squares method is used for initial estimation, combined with Newton's iteration method for precise solution, ultimately yielding the equation Y = aX + b for the intersection line L1 of the imaging plane and the current target plane.

[0044] Within the target coordinate system (tcs1, Z=0), based on the solved intersection line equation L1 and the equations of the left and right waistlines of each triangle, calculate all intersection points A simultaneously. k and B k The two-dimensional coordinates are used. These intersection points are assigned a depth value of Z=0 to form a three-dimensional point set P1. Similarly, the same operation is performed in the target coordinate system to obtain a three-dimensional point set P2.

[0045] Using the pre-calibrated extrinsic parameter matrix, the point sets P1 and P2 are transformed from their respective target coordinate systems (tcs1, tcs2) to the observation camera coordinate system (ccs), resulting in point sets P1' and P2' in a unified coordinate system.

[0046] Merge point sets P1' and P2' to form the final feature point set of the imaging plane. Use weighted least squares to fit this composite point set to the plane, assigning weights based on the residuals from each point to the initial fitted plane (smaller residuals result in larger weights) to suppress the influence of noise points. Finally, solve for the equation of the linear array camera's imaging plane in the observation camera coordinate system and normalize its normal vector.

[0047] In step 103, based on the spatial positional relationship between the line laser plane and the imaging plane, the angle between the normal of the line laser plane and the normal of the imaging plane and the distance between the two planes are calculated, and the degree of coplanarity is evaluated based on the angle between the normals and the distance between the planes.

[0048] In a specific embodiment, the included angle of the normals is calculated as follows:

[0049] in, The unit normal vector to the plane of the line laser is represented by the following components: A 1 ，B 1 ，C 1 ); The unit normal vector to the imaging plane of the linear scan camera is represented by the following components: A 2 ，B 2 ，C 2 ).

[0050] (2) Calculation of planar distance

[0051] for If we approximate the planes as parallel, then the plane distance is... d The calculation method is as follows:

[0052] in, For the constant terms of the line laser plane equation and the imaging plane equation.

[0053] In one embodiment, the degree of coplanarity is evaluated based on the included normal angle and the plane distance, including: The included angle of the normal and the plane distance are compared with the preset included angle threshold range and the distance threshold range, respectively; Based on the comparison results, the evaluation results used to characterize the spatial alignment between the imaging plane of the line scan camera and the line laser plane are output. The evaluation results of the alignment degree are shown in Table 1: Table 1

[0054] This invention also provides a device for evaluating the coplanarity of a line scan camera and a line laser plane, as described in the following embodiments. Since the principle by which this device solves the problem is similar to the method for evaluating the coplanarity of a line scan camera and a line laser plane, the implementation of this device can refer to the implementation of the method for evaluating the coplanarity of a line scan camera and a line laser plane; repeated details will not be elaborated further.

[0055] Figure 7 This is a schematic diagram of an evaluation device for coplanarity of a line scan camera and a line laser plane, as described in an embodiment of the present invention. The device includes: The spatial position relationship determination module 701 for the line laser plane is used to acquire the line laser light stripes projected on different targets by the observation camera, extract the center point of the light stripe on each target, transform the center point of each light stripe to a unified coordinate system, and use a fitting algorithm to fit the center point of the light stripe in the unified coordinate system to determine the spatial position relationship of the line laser plane. The spatial position relationship determination module 702 of the imaging plane is used to acquire images of different targets collected by the line scan camera, determine the intersection line between each target image and the imaging plane; extract the line segment features of the intersection line, and determine the imaging plane feature points based on the line segment features and the known geometric features of each target; transform the imaging plane feature points to a unified coordinate system; and use a fitting algorithm to fit the imaging plane feature points to determine the spatial position relationship of the imaging plane of the line scan camera. The coplanarity assessment module 703 is used to calculate the angle between the normal of the line laser plane and the normal of the imaging plane and the distance between the two planes based on the spatial positional relationship between the line laser plane and the imaging plane, and to assess the coplanarity based on the angle between the normals and the distance between the planes.

[0056] In one embodiment, the spatial position relationship determination module 701 of the line laser plane is further configured to: Based on the intrinsic and extrinsic parameter matrices of the observation camera, the center points of each light stripe are transformed to the camera coordinate system.

[0057] In one embodiment, the spatial position relationship determination module 701 of the line laser plane is specifically used for: The RANSAC algorithm was used to remove outliers from the center point of the light stripe, resulting in the processed center point of the light stripe. The least squares method is used to fit the center point of the processed light stripe, and the coefficients of the line laser plane equation are calculated to determine the spatial positional relationship of the line laser plane.

[0058] In one embodiment, the spatial position relationship determination module 702 of the imaging plane is further configured to: Extract the contour lines of the corresponding preset geometric patterns on the target from different target images; Based on the proportional relationship between the pixel length of the contour line segment in the target image and the known geometric features of the target, a mathematical model is established to solve the intersection line parameters. By solving the mathematical model, the equation of the intersection line between the imaging plane and the corresponding target plane is determined.

[0059] In one embodiment, the spatial position relationship determination module 702 of the imaging plane is specifically used for: Based on the equation of the intersection of the imaging plane and the corresponding target plane, and the equation of the boundary line segment of the preset geometric pattern on the target, the intersection point is calculated and used as the feature point of the imaging plane.

[0060] In one embodiment, the spatial position relationship determination module 702 of the imaging plane is further configured to: Based on the intrinsic and extrinsic parameter matrices of a linear scan camera, feature points on the imaging plane are transformed into the camera coordinate system.

[0061] In one embodiment, the coplanarity assessment module 703 is specifically used for: The included angle of the normal and the plane distance are compared with the preset included angle threshold range and the distance threshold range, respectively; Based on the comparison results, an evaluation result is output to characterize the spatial alignment between the imaging plane of the linear array camera and the line laser plane.

[0062] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for evaluating the coplanarity of a line scan camera and a line laser plane.

[0063] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for evaluating the coplanarity of a line scan camera and a line laser plane.

[0064] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method for evaluating the coplanarity of a line scan camera and a line laser plane.

[0065] In this embodiment of the invention, by acquiring linear laser beams projected onto different targets using an observation camera, the center point of each beam on each target is extracted, and the center points of each beam are transformed to a unified coordinate system. A fitting algorithm is used to fit the center points of the beams in the unified coordinate system to determine the spatial positional relationship of the linear laser plane. Images of different targets acquired by a line scan camera are acquired, and the intersection lines between each target image and the imaging plane are determined. The line segment features of the intersection lines are extracted, and based on the line segment features and the known geometric features of each target, the feature points of the imaging plane are determined. The feature points of the imaging plane are transformed to a unified coordinate system, and a fitting algorithm is used to fit the feature points of the imaging plane to determine the spatial positional relationship of the imaging plane of the line scan camera. Based on the spatial positional relationship of the linear laser plane and the spatial positional relationship of the imaging plane, the angle between the normal of the linear laser plane and the normal of the imaging plane and the distance between the two planes are calculated. The degree of coplanarity is evaluated based on the angle between the normals and the distance between the planes. In the above process, the embodiments of the present invention calculate the normal angle and spatial distance between the two planes by fitting the spatial positional relationship between the line laser plane and the imaging plane of the line array camera, thereby achieving a high-precision and quantitative assessment of the degree of coplanarity. This overcomes the shortcomings of traditional methods that rely on human experience and subjective visual judgment, and provides reliable technical support for the on-site calibration and performance evaluation of track inspection equipment.

[0066] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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.

[0067] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0068] 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.

[0069] 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.

[0070] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating the coplanarity of a linear scan camera and a line laser plane, characterized in that, include: The observation camera captures linear laser beams projected onto different targets. The center point of the beam on each target is extracted, and the center points of each beam are transformed to a unified coordinate system. A fitting algorithm is used to fit the center points of the beams in the unified coordinate system to determine the spatial positional relationship of the linear laser plane. The system acquires images of different targets captured by a line scan camera and determines the intersection lines between each target image and the imaging plane. It extracts the line segment features of the intersection lines, and based on the line segment features and the known geometric features of each target, determines the feature points of the imaging plane. The feature points of the imaging plane are then transformed to a unified coordinate system, and a fitting algorithm is used to fit the feature points of the imaging plane to determine the spatial positional relationship of the imaging plane of the line scan camera. Based on the spatial relationship between the line laser plane and the imaging plane, the angle between the normal of the line laser plane and the normal of the imaging plane, as well as the distance between the two planes, are calculated. The degree of coplanarity is then evaluated based on the angle between the normals and the distance between the planes.

2. The method as described in claim 1, characterized in that, Transform the center points of each light stripe to a unified coordinate system, including: Based on the intrinsic and extrinsic parameter matrices of the observation camera, the center points of each light stripe are transformed to the camera coordinate system.

3. The method as described in claim 1, characterized in that, A fitting algorithm is used to fit the center point of the light stripe in a unified coordinate system to determine the spatial positional relationship of the line laser plane, including: The RANSAC algorithm was used to remove outliers from the center point of the light stripe, resulting in the processed center point of the light stripe. The least squares method is used to fit the center point of the processed light stripe, and the coefficients of the line laser plane equation are calculated to determine the spatial positional relationship of the line laser plane.

4. The method as described in claim 1, characterized in that, Acquire images of different targets captured by a linear scan camera, and determine the intersection lines between each target image and the imaging plane, including: Extract the contour lines of the corresponding preset geometric patterns on the target from different target images; Based on the proportional relationship between the pixel length of the contour line segment in the target image and the known geometric features of the target, a mathematical model is established to solve the intersection line parameters. By solving the mathematical model, the spatial intersection relationship between the imaging plane and the corresponding target plane is determined.

5. The method as described in claim 4, characterized in that, Based on line segment features and the known geometric features of each target, feature points on the imaging plane are determined, including: Based on the equation of the intersection of the imaging plane and the corresponding target plane, and the equation of the boundary line segment of the preset geometric pattern on the target, the intersection point is calculated and used as the feature point of the imaging plane.

6. The method as described in claim 1, characterized in that, Transforming feature points on the imaging plane to a unified coordinate system includes: Based on the intrinsic and extrinsic parameter matrices of a linear scan camera, feature points on the imaging plane are transformed into the camera coordinate system.

7. The method as described in claim 1, characterized in that, The degree of coplanarity is evaluated based on the included angle between normals and the distance between planes, including: The included angle of the normal and the plane distance are compared with the preset included angle threshold range and the distance threshold range, respectively; Based on the comparison results, an evaluation result is output to characterize the spatial alignment between the imaging plane of the linear array camera and the line laser plane.

8. A device for evaluating the coplanarity of a linear array camera and a line laser, characterized in that, include: The module for determining the spatial position relationship of the line laser plane is used to acquire the line laser light stripes projected onto different targets by the observation camera, extract the center point of the light stripe on each target, transform the center point of each light stripe to a unified coordinate system, and use a fitting algorithm to fit the center point of the light stripe in the unified coordinate system to determine the spatial position relationship of the line laser plane. The spatial position relationship determination module of the imaging plane is used to acquire images of different targets collected by the line scan camera, determine the intersection line between each target image and the imaging plane; extract the line segment features of the intersection line, and determine the imaging plane feature points based on the line segment features and the known geometric features of each target; transform the imaging plane feature points to a unified coordinate system; and use a fitting algorithm to fit the imaging plane feature points to determine the spatial position relationship of the imaging plane of the line scan camera. The coplanarity assessment module is used to calculate the angle between the normal of the line laser plane and the normal of the imaging plane, as well as the distance between the two planes, based on the spatial positional relationship between the line laser plane and the imaging plane. The coplanarity is then assessed based on the angle between the normals and the distance between the planes.

9. The apparatus as claimed in claim 8, characterized in that, The module for determining the spatial positional relationship of the line laser plane is also used for: Based on the intrinsic and extrinsic parameter matrices of the observation camera, the center points of each light stripe are transformed to the camera coordinate system.

10. The apparatus as claimed in claim 8, characterized in that, The module for determining the spatial positional relationship of a line laser plane is specifically used for: The RANSAC algorithm was used to remove outliers from the center point of the light stripe, resulting in the processed center point of the light stripe. The least squares method is used to fit the center point of the processed light stripe, and the coefficients of the line laser plane equation are calculated to determine the spatial positional relationship of the line laser plane.

11. The apparatus as claimed in claim 8, characterized in that, The imaging plane equation determination module is also used for: Extract the contour lines of the corresponding preset geometric patterns on the target from different target images; Based on the proportional relationship between the pixel length of the contour line segment in the target image and the known geometric features of the target, a mathematical model is established to solve the intersection line parameters. By solving the mathematical model, the equation of the intersection line between the imaging plane and the corresponding target plane is determined.

12. The apparatus as claimed in claim 11, characterized in that, The module for determining the spatial positional relationship of the imaging plane is specifically used for: Based on the equation of the intersection of the imaging plane and the corresponding target plane, and the equation of the boundary line segment of the preset geometric pattern on the target, the intersection point is calculated and used as the feature point of the imaging plane.

13. The apparatus as claimed in claim 8, characterized in that, The module for determining the spatial positional relationship of the imaging plane is also used for: Based on the intrinsic and extrinsic parameter matrices of a linear scan camera, feature points on the imaging plane are transformed into the camera coordinate system.

14. The apparatus as claimed in claim 8, characterized in that, The coplanarity assessment module is specifically used for: The included angle of the normal and the plane distance are compared with the preset included angle threshold range and the distance threshold range, respectively; Based on the comparison results, an evaluation result is output to characterize the spatial alignment between the imaging plane of the linear array camera and the line laser plane.

15. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

17. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

Images