Method, device and medium for measuring the distance of a catenary cable based on machine vision

Abstract

The application discloses a kind of method, equipment and medium based on machine vision of catenary bearing cable spacing measurement, the method comprises:1 utilizes image acquisition unit to obtain catenary bearing cable image, obtains the pixel coordinate set of bearing cable by image processing method, selects the pixel point on the bearing cable to be measured, obtains corresponding pixel coordinate;2 according to pixel coordinate control pose adjustment mechanism, and the laser point is hit to the space point corresponding to pixel point, obtains pose adjustment mechanism pose data and laser ranging unit distance data, and according to coordinate transformation, obtains the space point coordinate under the pose adjustment mechanism base coordinate system;3 according to space point coordinate, establish the straight line equation of bearing cable, and solve the vertical height distance of two bearing cables under the condition of spatial distance constraint.The application can accurately and quickly measure the vertical height distance between two bearing cables, so as to meet the demand of catenary bearing cable spacing measurement.

Description

Technical Field

[0001] This invention relates to the field of visual measurement technology, specifically to a method, device, and medium for measuring the spacing of catenary cables in overhead contact lines based on machine vision. Background Technology

[0002] In the design of electrified railway catenary systems, to ensure smooth train operation between two tracks, the pantograph must be transferred from one contact wire to another using the assistance of switch points. During the adjustment and installation of switch points, the catenary cables supporting the contact wires may become loose and experience friction, affecting the stable operation of the contact wires. Therefore, during normal operation of the catenary system, the vertical height difference between the two catenary cables must be maintained within a reasonable working range, generally not less than 60mm. If the height difference between the two catenary cables is too small, mutual friction can easily occur, leading to continuous friction between the two cables. With the increase in the number of friction cycles, the surface of the catenary cables will continuously wear down, not only reducing the electrical performance of the catenary system but also causing corrosion of the internal structure of the catenary cables, significantly reducing their service life.

[0003] Currently, measurements at the intersections of catenary cables are mostly performed manually. Manual measurement is not only labor-intensive but also lacks accuracy. Another approach combines image processing with a fan-shaped laser to search for laser points in a camera, then uses the camera to calculate parameters based on the laser spot's position. This method is more efficient than manual measurement, but the quality of the laser spot can affect the calculation results, compromising measurement accuracy. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides a machine vision-based method, device, and medium for measuring the spacing between catenary cables in overhead contact lines. This method aims to accurately and quickly measure the vertical distance between two catenary cables, improve detection efficiency and accuracy, and thus meet the requirements for measuring the spacing between catenary cables in overhead contact lines.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] The present invention provides a machine vision-based method for measuring the spacing of catenary cables. The method involves moving a mobile trolley to the measurement position of the catenary cable. A pose adjustment mechanism is installed on the trolley platform. An image acquisition unit and a laser ranging unit are fixed to the end of the pose adjustment mechanism and connected to a control unit. A pose adjustment mechanism end coordinate system E and a pose adjustment mechanism base coordinate system B are established on the pose adjustment mechanism. An image acquisition unit coordinate system C is established in the image acquisition unit. A laser ranging unit coordinate system L is established in the laser ranging unit. The spacing measurement method includes the following steps:

[0007] S1. The image acquisition unit acquires an image I of the catenary cable, processes the image I to obtain a set of pixel coordinates Q of several catenary cables, selects two pixels from the pixel coordinate sets of two catenary cables respectively to obtain two pixels q1 and q2 on the first catenary cable, and two pixels q3 and q4 on the second catenary cable; any i-th pixel among q1, q2, q3, and q4 is denoted as q. i And q i The coordinates and spatial points are denoted as (μ) i v i ) and P i i = 1, 2, 3, 4;

[0008] S2. The control unit, based on the i-th pixel q i coordinates (μ) i v i ), calculate the pose matrix of the end effector coordinate system E relative to the base coordinate system B of the pose adjustment mechanism. Then, the pose adjustment mechanism is controlled to direct the laser point to the i-th pixel q. i The corresponding spatial point P i superior;

[0009] The laser ranging unit acquires spatial point P. i Distance data L i And obtain the i-th spatial point P i Coordinates in the laser ranging unit coordinate system L T represents transpose;

[0010] S3. The control unit obtains the i-th spatial point P according to equation (1). i Coordinates in coordinate system B of the pose adjustment mechanism base

[0011]

[0012] In equation (1), Let L and C represent the rotation matrix and translation vector of the laser ranging unit coordinate system L relative to the image acquisition unit coordinate system C, respectively. Let C and E represent the rotation matrix and translation vector of the image acquisition unit coordinate system C relative to the pose adjustment mechanism end coordinate system E, respectively. These represent the laser point being hit at the i-th spatial point P. i The rotation matrix and translation vector of the end coordinate system E of the pose adjustment mechanism relative to the base coordinate system B of the pose adjustment mechanism;

[0013] S4. The control unit calculates the vertical height distance H between the two catenary cables:

[0014] S4.1. Based on the coordinates of two spatial points on the first catenary. The parametric equation of the first line L1 is obtained as shown in equation (2):

[0015]

[0016] In equation (2), (k x1 k y1 kz1) represents the direction vector of the first line L1, and k x1 =(x p2 -x p1 ), k y1 =(y p2 -y p1 ), k z1 =(z p2 -z p1 ), λ1 is the parameter of the first line L1, (x L1 y L1 , z L1 ) is the coordinate point determined by parameter λ1;

[0017] Based on the coordinates of two spatial points on the second catenary The parametric equation of the second line L2 is obtained as shown in equation (3):

[0018]

[0019] In equation (3), (k x2 k y2 k z2 ) represents the direction vector of the second line L2, and k x2 =(x p4 -x p3 ), k y2 =(y p4 -yp3), k z2 =(z p4 -z p3 ), λ2 is the parameter of the second line L2, (x L2 y L2 , z L2 The coordinate point is determined by the parameter λ2.

[0020] S4.2. Let x L1 =x L2 And y L1 =y L2 Using equation (4), the parameter λ1 of the first line L1 and the parameter λ2 of the second line L2 are obtained:

[0021]

[0022] The Z-axis coordinate value z of the first straight line L1 is obtained using equation (5). L1 The Z-axis coordinate value of the second straight line L2 L2 :

[0023]

[0024] S4.3. Calculate the vertical height distance H between the two catenary cables using equation (6):

[0025] H = |z L1 -z L2 | (6)

[0026] The method for measuring the spacing of catenary cables based on machine vision described in this invention is also characterized in that the i-th pixel q in step S1 i The selection is performed according to the following process:

[0027] In image I, a pixel W is selected for the i-th time, with coordinates (μ). w v w );

[0028] Calculate the coordinates (μ, v) of any pixel on a catenary in the pixel coordinate set Q to the coordinates (μ, v) of the i-th selected pixel W. w v w Distance d(μ, v);

[0029] Select the pixel point from the set of pixel coordinates Q that minimizes the distance function d(μ, v) on the catenary as the i-th pixel point q. i .

[0030] In step S2, the pose matrix is ​​obtained using equation (7).

[0031]

[0032] In equation (7), To acquire image I, the pose matrix of the end-effector coordinate system E relative to the base coordinate system B of the pose adjustment mechanism; Let C be the pose matrix of the image acquisition unit coordinate system relative to the pose adjustment mechanism end coordinate system E; To hit the i-th spatial point P with a laser beam i When rotated, the pose matrix of the image acquisition unit coordinate system C1 after rotation relative to the image acquisition unit coordinate system C0 before rotation; express The inverse matrix, Let L be the pose matrix of the laser ranging unit coordinate system relative to the pose adjustment mechanism end coordinate system E; and we have:

[0033]

[0034] In equation (8), Representing the pose matrix respectively The rotation matrix and translation vector; Representing the pose matrix respectively The rotation matrix and translation vector; Represents the pose matrix rotation matrix; Representing the pose matrix respectively The rotation matrix and translation vector.

[0035] Rotate the coordinate system C of the image acquisition unit around its own coordinate axis so that the optical axis of the image acquisition unit passes through the coordinates (μ) of pixel qi. i v i ), thus based on the pixel points q before and after rotation i The coordinates in the image acquisition unit coordinate system C are used to obtain the rotation matrix of the rotated image acquisition unit coordinate system C1 relative to the original image acquisition unit coordinate system C0 through coordinate transformation.

[0036] The present invention provides an electronic device, including a memory and a processor, wherein the memory is used to store a program that supports the processor in executing the spacing measurement method, and the processor is configured to execute the program stored in the memory.

[0037] The present invention discloses a computer-readable storage medium on which a computer program is stored, wherein the computer program is executed by a processor to perform the steps of the spacing measurement method.

[0038] Compared with the prior art, the present invention has the following advantages:

[0039] 1. This invention utilizes an image acquisition unit to obtain the position information of the catenary and a laser ranging unit to obtain the distance information. The image acquisition unit and the laser ranging unit work together to obtain measurement data, and no complex data processing is required. The calculation speed is fast, which improves the measurement efficiency.

[0040] 2. Based on the coordinate transformation relationship, this invention derives the pose matrix of the end coordinate system of the pose adjustment mechanism relative to the base coordinate system of the pose adjustment mechanism when the laser point is hit on the catenary cable, thereby controlling the pose adjustment mechanism to accurately hit the laser point on the catenary cable, improving the measurement accuracy and precision.

[0041] 3. This invention utilizes a flexible pose adjustment mechanism to drive the image acquisition unit and the laser ranging unit, enabling multi-angle and multi-directional measurement of the load-bearing cable, thus improving measurement flexibility. At the same time, the entire measurement process does not require excessive manual intervention, thereby saving manpower and greatly improving measurement efficiency. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the overall structure of the catenary cable spacing measuring device of the present invention;

[0043] Figure 2 This is a schematic diagram of the method for measuring the spacing of catenary cables in the present invention.

[0044] The diagram is labeled as follows: 1. Pose adjustment mechanism; 2. End of pose adjustment mechanism; 3. Base of pose adjustment mechanism; 4. Image acquisition unit; 5. Laser ranging unit; 6. Human-computer interaction unit; 7. Control unit; 8. Mobile trolley. Detailed Implementation

[0045] In this embodiment, as Figure 1 As shown, a machine vision-based catenary cable spacing measurement device includes: a posture adjustment mechanism 1, an image acquisition unit 4, a laser ranging unit 5, a control unit 7, a human-machine interaction unit 6, and a mobile trolley 8. The mobile trolley 8 is a motor-driven trolley that can travel on trackless or tracked surfaces, used to move the entire device to the measurement position. The posture adjustment mechanism 1 is a robotic arm, fixedly mounted on the platform of the mobile trolley 8, which drives the image acquisition unit 4 and the laser ranging unit 5 through translation and rotation. The image acquisition unit 4 and the laser ranging unit 5 are mounted at the end 2 of the posture adjustment mechanism; the image acquisition unit 4 is an industrial camera, and the laser ranging unit 5 is a laser rangefinder. They work together to complete the catenary cable data acquisition task. The control unit 7 is an industrial computer used for data processing and command transmission. The human-machine interaction unit 6 is used for video monitoring, displaying measurement data and system operating status, and issuing commands to the control unit 7 to complete corresponding operations.

[0046] In this embodiment, a machine vision-based method for measuring the spacing of catenary cables involves moving a mobile trolley to the measurement position of the catenary cable. The mobile trolley platform is equipped with a pose adjustment mechanism. An image acquisition unit and a laser ranging unit are fixed to the end of the pose adjustment mechanism and connected to a control unit, respectively. A pose adjustment mechanism end coordinate system E and a pose adjustment mechanism base coordinate system B are established on the pose adjustment mechanism; an image acquisition unit coordinate system C is established in the image acquisition unit; and a laser ranging unit coordinate system L is established in the laser ranging unit. This spacing measurement method is as follows: Figure 2 As shown, it includes the following steps:

[0047] S1. The image acquisition unit acquires image I of the catenary cable, and after filtering, binarizing, and thinning image I, obtains a set of pixel coordinates Q of several catenary cables. Two pixels are selected from the pixel coordinate sets of any two catenary cables to obtain two pixels q1 and q2 on the first catenary cable, and two pixels q3 and q4 on the second catenary cable. Any i-th pixel among q1, q2, q3, and q4 is denoted as q... i And q i The coordinates and spatial points are denoted as (μ) i v i ) and P i i = 1, 2, 3, 4;

[0048] S2. The control unit determines the i-th pixel q. i coordinates (μ) i υ i Using equation (1), the pixel q before rotation transformation is obtained. i Coordinates in the image acquisition unit coordinate system

[0049]

[0050] In equation (1), (μ i υ i ) represents pixel q i The pixel coordinates are (μ0, v0), where (μ0, v0) are the pixel coordinates of the principal point of the image acquisition unit, and d x d y These are the physical dimensions of a single pixel of the image acquisition unit on the horizontal and vertical axes of the image physical coordinate system, respectively, and f is the focal length of the image acquisition unit.

[0051] After rotation, pixel q i On the optical axis, that is, after rotation, pixel q i The coordinates of the image acquisition unit in the coordinate system are (0, 0, Si), where,

[0052] Solve for the rotation angle γ using coordinate transformation formula (2). i β i :

[0053]

[0054] In equation (2), γ i β i The angles by which the image acquisition unit rotates around its own coordinate system's X and Y axes.

[0055] The rotation moment of the image acquisition unit coordinate system C1 after rotation relative to the image acquisition unit coordinate system C0 before rotation is obtained using equation (3).

[0056]

[0057] The pose matrix of the end effector coordinate system E relative to the base coordinate system B of the pose adjustment mechanism is calculated using equation (4).

[0058]

[0059] In equation (4), To acquire image I, the pose matrix of the end-effector coordinate system E relative to the base coordinate system B of the pose adjustment mechanism; Let C be the pose matrix of the image acquisition unit coordinate system relative to the pose adjustment mechanism end coordinate system E; To hit the i-th spatial point P with a laser beam i When rotated, the pose matrix of the image acquisition unit coordinate system C1 after rotation relative to the image acquisition unit coordinate system C0 before rotation; express The inverse matrix, Let L be the pose matrix of the laser ranging unit coordinate system relative to the pose adjustment mechanism end coordinate system E; and we have:

[0060]

[0061] In equation (5), Representing the pose matrix respectively The rotation matrix and translation vector; Representing the pose matrix respectively The rotation matrix and translation vector; Represents the pose matrix rotation matrix; Representing the pose matrix respectively The rotation matrix and translation vector.

[0062] Then, the pose adjustment mechanism is controlled to direct the laser point to the i-th pixel q. i The corresponding spatial point P i superior;

[0063] The laser ranging unit acquires spatial point P. i Distance data L i And obtain the i-th spatial point P i Coordinates in the laser ranging unit coordinate system L T represents transpose;

[0064] S3. The control unit obtains the i-th spatial point P according to equation (6). i Coordinates in coordinate system B of the pose adjustment mechanism base

[0065]

[0066] In equation (6), Let L and C represent the rotation matrix and translation vector of the laser ranging unit coordinate system L relative to the image acquisition unit coordinate system C, respectively. Let C and E represent the rotation matrix and translation vector of the image acquisition unit coordinate system C relative to the pose adjustment mechanism end coordinate system E, respectively. These represent the laser point being hit at the i-th spatial point P. i The rotation matrix and translation vector of the end coordinate system E of the pose adjustment mechanism relative to the base coordinate system B of the pose adjustment mechanism.

[0067] S4. The control unit calculates the vertical height distance H between the two catenary wires:

[0068] S4.1. Based on the coordinates of two spatial points on the first catenary. The parametric equation of the first line L1 is obtained as shown in equation (7):

[0069]

[0070] In equation (7), (k x1 k y1 k z1 ) represents the direction vector of the first line L1, and k x1 =(x p2 -x p1 ), k y1 =(y p2 -y p1 ), k z1 =(z p2 -z p1 ), λ1 is the parameter of the first line L1, (x L1 y L1 , z L1 ) is the coordinate point determined by parameter λ1;

[0071] Based on the coordinates of two spatial points on the second catenary The parametric equation of the second line L2 is obtained as shown in equation (8):

[0072]

[0073] In equation (8), (k x2 k y2 k z2 ) represents the direction vector of the second line L2, and k x2 =(xp4 -x p3 ), k y2 =(y p4 -y p3 ), k z2 =(z p4 -z p3 ), λ2 is the parameter of the second line L2, (x L2 y L2 , z L2 The coordinate point is determined by the parameter λ2.

[0074] S4.2. Let x L1 =x L2 And y L1 =y L2 Using equation (9), the parameter λ1 of the first line L1 and the parameter λ2 of the second line L2 are obtained:

[0075]

[0076] The Z-axis coordinate value z of the first straight line L1 is obtained using equation (10). L1 The Z-axis coordinate value of the second straight line L2 L2 :

[0077]

[0078] S4.3. Calculate the vertical height distance H between the two catenary cables using equation (11):

[0079] H = |z L1 -z L2 | (11).

[0080] In this embodiment, an electronic device includes a memory and a processor. The memory stores a program that supports the processor in executing the above-described method, and the processor is configured to execute the program stored in the memory.

[0081] In this embodiment, a computer-readable storage medium stores a computer program, which is executed by a processor to perform the steps of the above method.

Claims

1. A method for measuring the spacing of catenary cables in a contact network based on machine vision, characterized in that, The mobile trolley is moved to the measurement position of the catenary cable. A pose adjustment mechanism is installed on the mobile trolley platform. An image acquisition unit and a laser ranging unit are fixed to the end of the pose adjustment mechanism and connected to the control unit respectively. A pose adjustment mechanism end coordinate system E and a pose adjustment mechanism base coordinate system B are established on the pose adjustment mechanism; an image acquisition unit coordinate system C is established in the image acquisition unit; and a laser ranging unit coordinate system L is established in the laser ranging unit. The spacing measurement method includes the following steps: S1. The image acquisition unit acquires an image I of the catenary cable, processes the image I to obtain a set of pixel coordinates Q of several catenary cables, selects two pixels from the pixel coordinate sets of two catenary cables respectively to obtain two pixels q1 and q2 on the first catenary cable, and two pixels q3 and q4 on the second catenary cable; any i-th pixel among q1, q2, q3, and q4 is denoted as q. i And q i The coordinates and spatial points are denoted as (μ) i υ i ) and P i i = 1, 2, 3, 4; S2. The control unit, based on the i-th pixel q i coordinates (μ) i υ i ), calculate the pose matrix of the end effector coordinate system E relative to the base coordinate system B of the pose adjustment mechanism. Then, the pose adjustment mechanism is controlled to direct the laser point to the i-th pixel q. i The corresponding spatial point P i superior; The laser ranging unit acquires spatial point P. i Distance data L i And obtain the i-th spatial point P i Coordinates in the laser ranging unit coordinate system L T represents transpose; S3. The control unit obtains the i-th spatial point P according to equation (1). i Coordinates in coordinate system B of the pose adjustment mechanism base In equation (1), Let L and C represent the rotation matrix and translation vector of the laser ranging unit coordinate system L relative to the image acquisition unit coordinate system C, respectively. Let C and E represent the rotation matrix and translation vector of the image acquisition unit coordinate system C relative to the pose adjustment mechanism end coordinate system E, respectively. These represent the laser point being hit at the i-th spatial point P. i The rotation matrix and translation vector of the end coordinate system E of the pose adjustment mechanism relative to the base coordinate system B of the pose adjustment mechanism; S4. The control unit calculates the vertical height distance H between the two catenary cables: S4.

1. Based on the coordinates of two spatial points on the first catenary. The parametric equation of the first line L1 is obtained as shown in equation (2): In equation (2), (k x1 k y1 k z1 ) represents the direction vector of the first line L1, and k x1 =(x p2 -x p1 ), k y1 =(y p2 -y p1 ), k z1 =(z p2 -z p1 ), λ1 is the parameter of the first line L1, (x L1 y L1 , z L1 ) is the coordinate point determined by parameter λ1; Based on the coordinates of two spatial points on the second catenary The parametric equation of the second line L2 is obtained as shown in equation (3): In equation (3), (k x2 k y2 k z2 ) represents the direction vector of the second line L2, and k x2 =(x p4 -x p3 ), k y2 =(y p4 -y p3 ), k z2 =(z p4 -z p3 ), λ2 is the parameter of the second line L2, (x L2 y L2 , z L2 The coordinate point is determined by the parameter λ2. S4.

2. Let x L1 =x L2 And y L1 =y L2 Using equation (4), the parameter λ1 of the first line L1 and the parameter λ2 of the second line L2 are obtained: The Z-axis coordinate value z of the first straight line L1 is obtained using equation (5). L1 The Z-axis coordinate value of the second straight line L2 L2 : S4.

3. Calculate the vertical height distance H between the two catenary cables using equation (6): H=|z L1 -z L2 | (6)。 2. The method for measuring the spacing of catenary cables based on machine vision according to claim 1, characterized in that, The i-th pixel q in step S1 i The selection is performed according to the following process: In image I, a pixel W is selected for the i-th time, with coordinates (μ). w v w ); Calculate the coordinates (μ, v) of any pixel on a catenary in the pixel coordinate set Q to the coordinates (μ, v) of the i-th selected pixel W. w v w Distance d(μ, v); Select the pixel point from the set of pixel coordinates Q that minimizes the distance function d(μ, v) on the catenary as the i-th pixel point q. i .

3. The method for measuring the spacing of catenary cables based on machine vision according to claim 1, characterized in that, In step S2, the pose matrix is ​​obtained using equation (7). In equation (7), To acquire image I, the pose matrix of the end-effector coordinate system E relative to the base coordinate system B of the pose adjustment mechanism; Let C be the pose matrix of the image acquisition unit coordinate system relative to the pose adjustment mechanism end coordinate system E; To hit the i-th spatial point P with a laser beam i When rotated, the pose matrix of the image acquisition unit coordinate system C1 after rotation relative to the image acquisition unit coordinate system C0 before rotation; express The inverse matrix, Let L be the pose matrix of the laser ranging unit coordinate system relative to the pose adjustment mechanism end coordinate system E; and we have: In equation (8), Representing the pose matrix respectively The rotation matrix and translation vector; Representing the pose matrix respectively The rotation matrix and translation vector; Represents the pose matrix The rotation matrix; Representing the pose matrix respectively The rotation matrix and translation vector.

4. The method for measuring the spacing of catenary cables based on machine vision according to claim 3, characterized in that, Rotate the coordinate system C of the image acquisition unit around its own coordinate axis so that the optical axis of the image acquisition unit passes through pixel q. i coordinates (μ) i ,υ i ), thus based on the pixel points q before and after rotation i The coordinates in the image acquisition unit coordinate system C are used to obtain the rotation matrix of the rotated image acquisition unit coordinate system C1 relative to the original image acquisition unit coordinate system C0 through coordinate transformation.

5. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store a program that supports the processor in executing any of the spacing measurement methods of claims 1-4, the processor being configured to execute the program stored in the memory.

6. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program, when run by a processor, performs the steps of any of the spacing measurement methods described in claims 1-4.

Images