A mobile vision-based non-contact measurement method and device for beam track alignment

Abstract

The present application relates to a kind of beam rail linear non-contact measurement method and device based on mobile vision, applied to the measurement system carried on mobile trolley.The system includes front and rear two groups of binocular industrial cameras, inertial navigation system, odometer and track gauge measuring instrument, and the known elevation of fixed control point is set at the head and tail of the bridge to be detected, and observation target is set along the line catenary column.The method triggers camera to synchronously shoot adjacent target image and record attitude information by mileage, and the relative height difference of target is obtained by image point extraction, three-dimensional coordinate solution, combined with attitude information and mileage, constructs elevation traverse and calculates the absolute elevation of target by traverse adjustment, determines the bridge linear and rail linear according to absolute elevation, and finally completes beam rail linear synchronous detection.The method of the present application realizes the automation, high-precision non-contact measurement of beam rail linear, greatly improves the detection efficiency, and provides reliable data support for bridge and rail daily operation and maintenance.

Description

Technical Field

[0001] The embodiments in this specification relate to the field of railway bridge engineering surveying and track geometry measurement technology, and in particular to a non-contact measurement method and device for beam-track alignment based on mobile vision. Background Technology

[0002] As a key structure in railway transportation systems, the alignment of bridges directly affects track smoothness and the safety and stability of train operation. Due to long-term train dynamic loads, foundation settlement, material creep, and changes in ambient temperature, bridge beams inevitably experience varying degrees of vertical settlement and lateral deformation. On the other hand, track geometry parameters are crucial for evaluating track condition, smoothness, and the service performance of the track structure, directly impacting train safety and passenger comfort. Therefore, regularly acquiring high-precision bridge and track alignment data is of great significance for timely detection of structural defects and for guiding track maintenance.

[0003] Traditional leveling is currently the most commonly used method for bridge settlement monitoring. This method relies on precision levels and leveling rods, with surveyors acquiring elevation data station by station. While leveling can achieve millimeter-level or even sub-millimeter-level accuracy, its operational efficiency is extremely low, requiring a large number of surveyors to frequently move stations, resulting in high labor intensity and making it difficult to cover long sections of bridges within the limited "maintenance windows" of railways. Furthermore, leveling only acquires elevation data from discrete sections, failing to comprehensively reflect the continuous alignment changes of the entire bridge, and is susceptible to human reading errors and on-site lighting conditions. Meanwhile, existing machine vision-based bridge alignment measurement methods mostly employ in-situ measurements, resulting in static fitting rather than real-time mobile measurement, leading to a large workload for deployment and maintenance.

[0004] On the other hand, current track alignment detection mainly relies on track control network (CP III) resurveys. However, CP III resurveys require extensive station measurements using total stations, which is time-consuming and costly. Furthermore, this operation is usually carried out independently and at different times from bridge settlement monitoring, making it impossible to measure track and bridge alignments simultaneously. This results in a mismatch in data scales between the two, making it difficult to establish a direct correlation analysis.

[0005] Global Navigation Satellite Systems (GNSS) are increasingly being applied to the monitoring of large bridges and the acquisition of track spatial coordinates. While GNSS technology can provide absolute coordinates, it faces significant challenges in the complex environment of railways: overhead contact lines, surrounding mountains, tall buildings, or tunnel entrances can obstruct satellite signals or create multipath effects, leading to signal loss or a significant decrease in positioning accuracy. This is particularly true in GNSS-denied environments such as bridge-tunnel junctions or deep mountain valleys, where satellite positioning becomes virtually ineffective. Furthermore, GNSS technology suffers from cumulative drift and its elevation calculation accuracy is often lower than its planar accuracy, making it difficult to meet the accuracy requirements of high-speed railways for bridge settlement, absolute track position and orientation, elevation, and other geometric parameters. Summary of the Invention

[0006] To address the problems existing in the prior art, this specification provides a non-contact measurement method and device for beam-track alignment based on mobile vision.

[0007] The specific technical solutions of the embodiments in this specification are as follows: On one hand, this specification provides a non-contact measurement method for beam-track alignment based on mobile vision. The method is applied to a measurement system mounted on a mobile trolley located on a track laid on the bridge to be inspected. The measurement system includes two sets of industrial cameras, an inertial navigation system, an odometer, and a track gauge. The two sets of industrial cameras are fixed at the front and rear ends of the mobile trolley in the direction of travel, respectively. Each set of industrial cameras includes two calibrated industrial cameras, forming a binocular vision system. Fixed control points with known elevations are set at both ends of the bridge to be inspected. Observation targets are provided on each contact wire post along the bridge to be inspected. The method includes: During the movement of the mobile trolley along the direction of travel, the mileage data recorded by the odometer is monitored. When the mileage data meets the predetermined requirements, a trigger signal is sent to the two sets of industrial cameras and the inertial navigation system. The trigger signal is used to control the two sets of industrial cameras to simultaneously expose and obtain images of the observation targets on two adjacent contact wire columns along the bridge to be inspected, and simultaneously control the inertial navigation system to record the attitude information of the mobile trolley at the exposure time. For each pair of adjacent catenary columns, extract the image point coordinates of the previous observation target in the image of the previous observation target in the adjacent catenary column, and extract the image point coordinates of the subsequent observation target in the image of the subsequent observation target in the adjacent catenary column. Based on the camera parameters of the two sets of industrial cameras, the image point coordinates of the front observation target and the image point coordinates of the rear observation target are transformed into the camera coordinate system to obtain the three-dimensional spatial coordinates of the front observation target and the three-dimensional spatial coordinates of the rear observation target within the camera. Using the attitude information, a rotation matrix is ​​constructed. Combined with the mileage, the camera-in-the-camera three-dimensional spatial coordinates of the front observation target and the rear observation target are transformed to the ground coordinate system. The relative height difference between the front observation target and the rear observation target is calculated in the ground coordinate system. Based on the relative elevation difference between all adjacent contact wire columns, an elevation traverse is formed, and the traverse adjustment model is constructed with the fixed control points as constraints to calculate the absolute elevation of the observation target on each contact wire column. The alignment of the bridge under test is obtained based on the absolute elevation of the observation target on each contact wire post. The three-dimensional coordinates of the observation target in the ground coordinate system are determined based on the absolute elevation of the observation target, and the three-dimensional coordinates of the camera optical center in the ground coordinate system are calculated based on the three-dimensional coordinates of the target. The continuous spatial trajectory of the mobile vehicle is obtained based on the three-dimensional coordinates of the camera optical center, the attitude and mileage data of the inertial navigation system. Based on the continuous spatial trajectory of the mobile trolley and the geometric relationship between the optical center of the camera and the top surfaces of the left and right rails in the track, the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system is calculated, and the track gauge between the left and right rails is calculated based on the output of the track gauge measuring instrument. The alignment of the track is calculated based on the three-dimensional coordinate sequence of the left and right tracks in the ground coordinate system, the track gauge, and the design alignment parameters of the track.

[0008] Furthermore, after extracting the image point coordinates of the previously observed target and the image point coordinates of the subsequently observed target, the method further includes: The distortion parameters obtained from the calibration of the industrial camera are used to correct the image point coordinates of the front observation target and the image point coordinates of the rear observation target. Based on the camera parameters of the two sets of industrial cameras, the image point coordinates of the front-observed target and the image point coordinates of the rear-observed target are transformed to the camera coordinate system, including: Based on the camera parameters of the two sets of industrial cameras, the corrected image point coordinates of the front observation target and the corrected image point coordinates of the rear observation target are transformed into the camera coordinate system.

[0009] Further, the three-dimensional coordinates of the observation target in the ground coordinate system are determined based on the absolute elevation of the observation target, and the three-dimensional coordinates of the camera optical center in the ground coordinate system are calculated based on the three-dimensional coordinates of the target. Based on the three-dimensional coordinates of the camera optical center, the attitude and odometer data of the inertial navigation system, the continuous spatial trajectory of the mobile vehicle is obtained, including: The coordinates of the i-th observation target in the ground coordinate system are: ,H i X represents the absolute elevation of the observed target. i and Y i The value is determined based on the location of the contact wire column to which the observed target belongs; As the trolley travels along the track, the three-dimensional coordinates of the camera's rigidity in the ground coordinate system are calculated according to a fixed travel distance. The location of each fixed travel distance is called a control section. The three-dimensional coordinates of the camera's optical center in the ground coordinate system at the control section are calculated using the multi-camera joint spatial resection method. ; Based on the three-dimensional coordinates of the camera's optical center and the attitude and odometer data of the inertial navigation system, the continuous spatial trajectory of the mobile vehicle is obtained. Traj The formula is:

[0010] g: Ground coordinate system; b: Vehicle inertial navigation coordinate system; c: Camera coordinate system; t: Time t; : Camera optical center ground three-dimensional coordinates; The camera is fixedly offset relative to the inertial navigation center of the vehicle; : Inertial navigation system output attitude matrix; The odometer outputs the incremental displacement of the trolley. Furthermore, based on the continuous spatial trajectory of the moving trolley and the geometric relationship between the camera's optical center and the top surfaces of the left and right rails in the track, the formula for calculating the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system is as follows:

[0011] d l The fixed deviation between the camera's optical center and the left rail in the track; d r The fixed deviation between the camera's optical center and the right rail in the track; The three-dimensional coordinates of the top of the right rail at time t; The three-dimensional coordinates of the top of the left rail at time t; The three-dimensional coordinate sequence of the top of the left rail; The three-dimensional coordinate sequence of the top of the right rail.

[0012] Furthermore, the traverse adjustment model is as follows:

[0013] in, Let be the corrected height difference between the observation target of the i-th contact wire column and the observation target of the (i-1)-th contact wire column. Let L be the relative height difference between the observation target of the i-th contact wire column and the observation target of the (i-1)-th contact wire column, and L be the distance between the fixed control points at both ends of the bridge to be inspected. Let be the distance between the i-th contact wire post and the (i-1)-th contact wire post. , H represents the relative elevation difference between the fixed control points at both ends of the bridge to be tested, where... The relative height difference between the observation target of the first contact wire post and the fixed control point at the beginning of the bridge to be inspected. This is the horizontal distance between the first contact wire post and the fixed control point at the beginning of the bridge to be inspected.

[0014] Furthermore, based on the absolute elevation of the observation target on each contact wire post, the alignment of the bridge under inspection is obtained, including: The absolute elevation of the observation target on each contact wire column is compared with the elevation of the same observation target on that contact wire column in the initial archive data to obtain the settlement of the observation target on each contact wire column. The alignment of the bridge to be inspected is determined based on the settlement of the observation targets on each contact wire column.

[0015] Furthermore, using the attitude information to construct a rotation matrix, and combining it with the odometer reading, the camera-internal 3D spatial coordinates of the forward-observed target and the camera-internal 3D spatial coordinates of the subsequent-observed target are transformed to a ground coordinate system, including: The attitude information is used to construct a rotation matrix from the camera coordinate system to the ground coordinate system; Calculate the translation vector of the camera coordinate system origin in the ground coordinate system based on the mileage; Based on the rotation matrix and translation vector, the camera-internal 3D spatial coordinates of the front observation target and the camera-internal 3D spatial coordinates of the rear observation target are respectively transformed to the ground coordinate system.

[0016] Furthermore, during the movement of the mobile trolley along the direction of travel, the mileage data recorded by the odometer is monitored. When the mileage data meets predetermined requirements, a trigger signal is sent to the two sets of industrial cameras and the inertial navigation system. The trigger signal is used to control the two sets of industrial cameras to simultaneously expose images of the observation targets on two adjacent contact wire pillars along the bridge to be inspected, and simultaneously control the inertial navigation system to record the attitude information of the mobile trolley at the exposure time, including: The mileage data is collected synchronously along with the images taken by the two sets of industrial cameras and the attitude information of the mobile trolley at the exposure time is recorded by the inertial navigation system. The mileage data is required to be set at equal intervals of not less than 20cm, or at the 1 / 4, 1 / 2 or 3 / 4 position of the bridge.

[0017] Based on the same inventive concept, this specification also provides a non-contact measurement device for beam-track alignment based on mobile vision. The device is embedded in a measurement system mounted on a mobile trolley located on a track laid on the bridge to be inspected. The measurement system includes two sets of industrial cameras, an inertial navigation system, an odometer, and a track gauge. The two sets of industrial cameras are respectively fixed at the front and rear ends of the mobile trolley in the direction of travel. Each set of industrial cameras includes two calibrated industrial cameras, forming a binocular vision system. Fixed control points with known elevations are set at both ends of the bridge to be inspected. Observation targets are provided on each contact wire post along the bridge to be inspected. The device includes: The data detection unit is used to monitor the mileage data recorded by the odometer during the movement of the mobile trolley along the direction of travel. When the mileage data meets the predetermined requirements, the unit sends a trigger signal to the two sets of industrial cameras and the inertial navigation system. The trigger signal is used to control the two sets of industrial cameras to simultaneously expose the images of the observation targets on two adjacent contact wire columns along the bridge to be inspected, and simultaneously control the inertial navigation system to record the attitude information of the mobile trolley at the exposure time. The image point coordinate extraction unit is used to extract the image point coordinates of the front observation target in the image of the front observation target in each pair of adjacent contact network columns, and to extract the image point coordinates of the rear observation target in the image of the rear observation target in each pair of adjacent contact network columns. The camera coordinate transformation unit is used to transform the image point coordinates of the front observation target and the image point coordinates of the rear observation target to the camera coordinate system according to the camera parameters of the two sets of industrial cameras, so as to obtain the camera-in-camera three-dimensional spatial coordinates of the front observation target and the camera-in-camera three-dimensional spatial coordinates of the rear observation target. The elevation difference calculation unit is used to construct a rotation matrix using the attitude information, and combined with the mileage, to transform the camera-in-the-camera three-dimensional spatial coordinates of the front observation target and the camera-in-the-camera three-dimensional spatial coordinates of the rear observation target to the ground coordinate system, and to calculate the relative elevation difference between the front observation target and the rear observation target in the ground coordinate system. The absolute elevation calculation unit is used to form an elevation traverse based on the relative elevation difference between all two adjacent contact wire columns, and to construct a traverse adjustment model with the fixed control points as constraints, so as to calculate the absolute elevation of the observation target on each contact wire column. The bridge alignment detection unit is used to obtain the alignment of the bridge to be detected based on the absolute elevation of the observation target on each contact wire post. The track alignment detection unit is used to determine the three-dimensional coordinates of the observation target in the ground coordinate system based on the absolute elevation of the observation target, and to calculate the three-dimensional coordinates of the camera optical center in the ground coordinate system based on the three-dimensional coordinates of the target. Based on the three-dimensional coordinates of the camera optical center, the attitude and odometer data of the inertial navigation system, it acquires the continuous spatial trajectory of the moving trolley. Based on the continuous spatial trajectory of the moving trolley and the geometric relationship between the camera optical center and the top surfaces of the left and right rails in the track, it calculates the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system, and calculates the track gauge between the left and right rails based on the output of the track gauge measuring instrument. Based on the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system, the track gauge, and the design alignment parameters of the track, it calculates the alignment of the track.

[0018] On the other hand, embodiments of this specification also provide a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-described method.

[0019] On the other hand, embodiments of this specification also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0020] On the other hand, embodiments of this specification also provide a computer program product, which includes a computer program that, when executed by a processor, implements the above-described method.

[0021] The beneficial effects of the embodiments in this specification are as follows: They achieve truly non-contact mobile measurement, eliminating the need for expensive prisms and long-term sensor maintenance on bridges; only simple passive targets need to be deployed, significantly reducing construction and maintenance costs. The integration of visual and inertial positioning technologies significantly improves operational efficiency. Utilizing odometer triggering and simultaneous multi-camera shooting, the vehicle does not need frequent stops or leveling processes similar to a leveling instrument's bubble leveling; it can perform continuous observation and automatic leveling while in motion, similar to a "mobile leveling instrument." Furthermore, it exhibits strong environmental adaptability, using an inertial navigation system to provide attitude references and assist in dead reckoning, thus eliminating dependence on GNSS satellite signals. Even in environments where satellite signals are blocked, such as inside tunnels, at bridge-tunnel junctions, or in deep mountain valleys, the continuity of measurement data and the accuracy of attitude correction can be guaranteed. High measurement accuracy is achieved by eliminating the trolley's own positional errors through a two-way observation structure of "forward sight + backward sight," and by combining it with the full-line traverse adjustment algorithm to effectively control error accumulation. The theoretically calculated midpoint settlement monitoring accuracy can reach millimeter level, meeting the requirements of railway engineering inspection. A technological breakthrough has been achieved in simultaneously detecting bridge alignment and track geometry, improving the efficiency and accuracy of deformation detection, quality acceptance, and periodic re-measurement analysis in engineering applications, facilitating deformation identification, quality acceptance, and periodic re-measurement analysis in engineering applications. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this specification 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 embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 The diagram shown is a flowchart illustrating a non-contact measurement method for beam-rail alignment based on mobile vision, as described in an embodiment of this specification. Figure 2 The diagram shown is a structural schematic of the mobile cart in an embodiment of this specification; Figure 3 The diagram shown is a partial structural schematic of the camera mounting bracket in an embodiment of this specification. Figure 4 The diagram shown is a schematic representation of the principle and optical path of the mobile measurement operation in an embodiment of this specification. Figure 5 The diagram shown is a coordinate system diagram for binocular visual forward intersection measurement in an embodiment of this specification; Figure 6 The diagram shown is a flowchart illustrating how the alignment of the bridge under test is obtained based on the absolute elevation of the observation target on each contact wire post in an embodiment of this specification. Figure 7 The diagram shown is a structural schematic of a non-contact beam-rail alignment measurement device based on mobile vision, as described in an embodiment of this specification. Figure 8 The diagram shown is a structural schematic of the computer device in an embodiment of this specification.

[0024] [Explanation of Figure Markers]: 701. Data Detection Unit; 702. Image point coordinate extraction unit; 703. Camera coordinate transformation unit; 704. Elevation Difference Calculation Unit; 705. Absolute Elevation Calculation Unit; 706. Bridge alignment detection unit; 707. Track alignment detection unit; 802. Computer equipment; 804. Processing equipment; 806. Storage resources; 808. Drive mechanism; 810. Input / Output Module; 812. Input devices; 814. Output devices; 816. Presentation equipment; 818. Graphical User Interface; 820. Network interface; 822. Communication link; 824. Communication bus. Detailed Implementation

[0025] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the embodiments of this specification.

[0026] It should be noted that the terms "first," "second," etc., in the description, claims, and accompanying drawings of the embodiments in this specification are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data can be used interchangeably where appropriate so that the embodiments described herein can be implemented in an order different from that illustrated or described in the specification. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0027] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of the embodiments of this specification all comply with the relevant provisions of national laws and regulations.

[0028] It should be noted that in the embodiments of this specification, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary, and their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but does not mean that the applicant has already used or necessarily used such a solution. Similarly, the descriptions of prediction algorithms, table organization forms, and hardware structures are also exemplary.

[0029] To address the problems existing in the prior art, this specification provides a non-contact measurement method for beam-track alignment based on mobile vision, which solves the problems of low operation efficiency, high equipment maintenance costs, and inability to operate accurately in weak GNSS signal environments.

[0030] The method described in this specification addresses the problems of high labor intensity, high cost, and susceptibility to interference in existing leveling techniques, as well as the insufficient accuracy of GNSS technology in environments with bridges and tunnels or obstructions. This specification's embodiments achieve rapid, continuous, and high-precision measurement of beam-track alignment by constructing a mobile measurement platform integrating inertial navigation, odometer, and multi-view vision, combined with the principle of traverse adjustment.

[0031] Figure 1The diagram shows a flowchart of a non-contact measurement method for beam-track alignment based on mobile vision, according to an embodiment of this specification. The method of this embodiment is applied to a measurement system mounted on a mobile trolley located on a track laid on the bridge to be inspected. The measurement system includes two sets of industrial cameras, an inertial navigation system, an odometer, and a track gauge. The two sets of industrial cameras are fixed at the front and rear ends of the mobile trolley in the direction of travel, respectively. Each set of industrial cameras includes two calibrated industrial cameras, forming a binocular vision system. Fixed control points with known elevations are set at both ends of the bridge to be inspected. Observation targets are set on each contact wire post along the bridge to be inspected. The order of steps listed in the embodiment is only one possible execution order among many and does not represent the only execution order. In actual system or device products, the method can be executed sequentially or in parallel according to the embodiment or the accompanying drawings. Specifically, as shown in the figures... Figure 1 As shown, the method may include: Step 101: During the movement of the mobile trolley along the direction of travel, the mileage data recorded by the odometer is monitored. When the mileage data meets the predetermined requirements, a trigger signal is sent to the two sets of industrial cameras and the inertial navigation system. The trigger signal is used to control the two sets of industrial cameras to simultaneously expose and obtain images of the observation targets on two adjacent contact wire columns along the bridge to be inspected, and simultaneously control the inertial navigation system to record the attitude information of the mobile trolley at the exposure time. Step 102: For each pair of adjacent catenary columns, extract the image point coordinates of the front observation target in the image of the front observation target in the adjacent catenary column, and extract the image point coordinates of the rear observation target in the image of the rear observation target in the adjacent catenary column. Step 103: Based on the camera parameters of the two sets of industrial cameras, transform the image point coordinates of the front observation target and the image point coordinates of the rear observation target into the camera coordinate system to obtain the three-dimensional spatial coordinates of the front observation target and the three-dimensional spatial coordinates of the rear observation target within the camera. Step 104: Construct a rotation matrix using the attitude information, and combine it with the mileage to transform the camera-in-the-camera three-dimensional spatial coordinates of the front observation target and the camera-in-the-camera three-dimensional spatial coordinates of the rear observation target to the ground coordinate system. Calculate the relative height difference between the front observation target and the rear observation target in the ground coordinate system. Step 105: Based on the relative height difference between all two adjacent contact wire columns, form an elevation traverse, and construct a traverse adjustment model with the fixed control points as constraints to calculate the absolute elevation of the observation target on each contact wire column. Step 106: Obtain the alignment of the bridge to be inspected based on the absolute elevation of the observation target on each contact wire post; Step 107: Determine the three-dimensional coordinates of the observation target in the ground coordinate system based on the absolute elevation of the observation target, calculate the three-dimensional coordinates of the camera optical center in the ground coordinate system based on the three-dimensional coordinates of the target, and obtain the continuous spatial trajectory of the mobile vehicle based on the three-dimensional coordinates of the camera optical center, the attitude and mileage data of the inertial navigation system. Step 108: Based on the continuous spatial trajectory of the moving trolley and the geometric relationship between the camera optical center and the top surfaces of the left and right rails in the track, calculate the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system, and calculate the track gauge between the left and right rails based on the results output by the track gauge measuring instrument. Step 109: Calculate the alignment of the track based on the three-dimensional coordinate sequence of the left and right tracks in the ground coordinate system, the track gauge, and the design alignment parameters of the track.

[0032] like Figure 2 The diagram shown illustrates the structure of the mobile trolley in this embodiment, primarily consisting of a hardware platform and a measurement sensor array. The hardware platform utilizes a standard track geometry measuring instrument (mobile trolley) as its carrier, with the measuring equipment mounted on its chassis via a specially designed aluminum profile bracket. The bracket is connected to the mobile trolley using a "four screws in the middle, clamped on both sides" method, and is equipped with seven fixed columns to ensure repeatable installation accuracy. The measurement sensor array includes four high-resolution industrial cameras, a high-precision inertial navigation system, a high-precision odometer, a track gauge measuring instrument, and an industrial control computer.

[0033] like Figure 3 The diagram shown is a partial structural schematic of the camera mounting bracket in an embodiment of this specification. Four cameras are divided into two groups, fixed at the front and rear ends of the moving trolley in the direction of travel, respectively. Each group contains two cameras forming a binocular vision system. The cameras are mounted via adjustable brackets, supporting vertical adjustment to accommodate targets at different heights. The brackets are designed with clearance structures to facilitate battery replacement. An inertial navigation system is rigidly connected to the camera brackets for real-time camera attitude sensing. An odometer is installed at the axle of the moving trolley to accurately measure travel distance and provide a synchronization trigger signal.

[0034] Before the formal measurement, the four cameras were first rigorously calibrated in the laboratory. In the calibration field at a distance of about 20 meters, the camera's interior orientation elements (including focal length f, principal point coordinates (x0, y0), and distortion parameters such as radial distortion coefficients k1, k2, and tangential distortion coefficients p1, p2) were calculated using a single-film back intersection algorithm.

[0035] like Figure 4The diagram shown illustrates the principle and optical path of the mobile measurement operation in this specification. During on-site operation, fixed points A and B with known and stable elevations are set up at both ends of the bridge, and observation targets, such as target 1 and target 2, are set up on each contact wire post along the line (with a spacing of about 50 meters). (Note: The shape of the target can be arbitrarily selected according to the automatic machine recognition.)

[0036] The operator pushes or drives the mobile trolley smoothly along the track. The system uses an odometer for spatial positioning, and when it travels a certain distance, the odometer sends a hard trigger signal. At this time, four cameras at the front and rear simultaneously expose images of the observation targets on two adjacent catenary pillars along the bridge to be inspected. Specifically, the binocular vision system at the front captures an image of the observation target on the catenary pillar ahead of the travel direction, obtaining the image of the Nth observation target; the binocular vision system at the rear captures an image of the observation target on the catenary pillar behind the travel direction, obtaining the image of the (N-1)th observation target. Simultaneously, the inertial navigation system records the attitude angle of the mobile trolley at this exposure moment and transmits all data to the industrial control computer for storage.

[0037] During data processing, for each pair of adjacent catenary columns, the image point coordinates of the forward observation target in the image of the forward observation target in the adjacent catenary column are extracted, and the image point coordinates of the backward observation target in the image of the backward observation target in the adjacent catenary column are extracted.

[0038] Then, the distortion parameters obtained from the calibration of the industrial camera are used to correct the image point coordinates of the front observation target and the rear observation target, thereby eliminating the error caused by lens distortion.

[0039] In the embodiments of this specification, the distortion parameters obtained from the calibration of the industrial camera are used to correct the image point coordinates of the front-observed target and the image point coordinates of the rear-observed target, including: The distances between the image point coordinates of the previously observed target in the image-square coordinate system and the image point coordinates of the subsequently observed target in the image-square coordinate system, and the principal image point, are calculated using the following formulas: Where (x, y) are the image point coordinates, and (x0, y0) are the principal image point coordinates; Calculate the image point correction values ​​Δx and Δy in the x and y directions respectively, where (Δx, Δy) are the corrected image point coordinates:

[0040] Where k1 and k2 are the radial distortion parameters of the industrial camera lens; p1 and p2 are the tangential distortion parameters of the industrial camera lens; and a and b are the non-square correction coefficients of the pixels.

[0041] Then, based on the camera parameters of the two sets of industrial cameras, the corrected image point coordinates of the front observation target and the corrected image point coordinates of the rear observation target are transformed into the camera coordinate system.

[0042] Then, using the principle of forward intersection in binocular stereo vision, combined with the calibrated baseline length and camera parameters, the three-dimensional spatial coordinates of the front and rear targets relative to the current moving car camera coordinate system are calculated, such as... Figure 5 The diagram shows a coordinate system for binocular vision forward intersection measurement in an embodiment of this specification. A rotation matrix is ​​constructed using attitude information provided by the inertial navigation system. Simultaneously, combined with odometer data, the measurements in the camera coordinate system are transformed to the ground coordinate system. This eliminates the vibration and tilting effects caused by uneven tracks during the movement of the mobile trolley, thereby accurately calculating the relative height difference between the front and rear targets observed by the current station.

[0043] Specifically, a rotation matrix is ​​constructed using the attitude information, and combined with the odometer reading, the camera-internal 3D spatial coordinates of the forward-observed target and the camera-internal 3D spatial coordinates of the subsequent-observed target are transformed to a ground coordinate system, including: Step 1: Construct a rotation matrix from the camera coordinate system to the ground coordinate system using the attitude information; Step 2: Calculate the translation vector of the camera coordinate system origin in the ground coordinate system based on the mileage; Step 3: Based on the rotation matrix and translation vector, transform the camera-in-the-camera 3D spatial coordinates of the front observation target and the camera-in-the-camera 3D spatial coordinates of the rear observation target to the ground coordinate system.

[0044] In the embodiments of this specification, three coordinate systems following the right-hand rule are first defined. The origin of the camera coordinate system is located at the optical center of the binocular camera, the X-axis is forward along the camera's optical axis, the Y-axis is horizontal to the right along the camera's imaging plane, and the Z-axis is vertically downward along the camera's imaging plane. The origin of the trolley coordinate system is located at the centroid of the moving trolley, the X-axis is forward along the trolley's direction of travel, the Y-axis is horizontal to the right along the trolley, and the Z-axis is vertically downward along the trolley. The camera and the trolley are fixedly connected, and the installation error between them has been calibrated and compensated in the laboratory.

[0045] Attitude information includes pitch angle θ and roll angle And the heading angle ψ, where the pitch angle θ is the angle between the X-axis of the vehicle coordinate system and the XY plane of the ground coordinate system, with pitch being positive and a value range of [-90°, 90°]; roll angle The y-axis is the angle between the Y-axis of the vehicle coordinate system and the XY plane of the ground coordinate system, with rightward tilt being positive, and the value range is [-180°, 180°]; the heading angle ψ is the angle between the projection of the X-axis of the vehicle coordinate system onto the XY plane of the ground coordinate system and the X-axis of the ground coordinate system, with clockwise tilt being positive, and the value range is [0°, 360°].

[0046] Based on the above attitude angles, three single-axis rotation matrices are constructed sequentially. The roll rotation matrix around the X-axis is:

[0047] The pitch and rotation matrix about the Y-axis is:

[0048] The heading rotation matrix about the Z-axis is:

[0049] Multiply the three rotation matrices in the order of heading, pitch, and roll to obtain the rotation matrix from the camera coordinate system to the ground coordinate system:

[0050] Using the starting mileage of the bridge to be inspected as a benchmark, the distance traveled by the trolley along the track is calculated based on the mileage recorded by the odometer at the current exposure time. The horizontal coordinate components of the camera coordinate system origin in the ground coordinate system are determined by combining the track design parameters of the bridge to be inspected. Then, the vertical coordinate components are determined by combining the initial elevation of the trolley at the starting point, thus obtaining the translation vector of the camera coordinate system origin in the ground coordinate system. Based on the rotation matrix and translation vector, the coordinate transformation formula is used. The three-dimensional spatial coordinates of the target within the camera are respectively... and the three-dimensional spatial coordinates of the target observed by the camera Transform to the ground coordinate system to obtain the ground coordinates of the previously observed target. and the ground coordinate system coordinates of the observed target .

[0051] Then, the vertical coordinates of the previously observed target in the ground coordinate system were extracted. And the vertical coordinates of the target in the ground coordinate system after observation Calculate the difference between two vertical coordinates. This yields the relative elevation difference between the previously observed target and the later observed target. For example, continuing as follows... Figure 4 As shown, the height of target 1 is calculated as h1 and the height of target 2 is h2. Then, h2-h1 is the relative height difference between target 2 and target 1.

[0052] As the mobile trolley moves forward, the system continuously acquires the relative elevation differences between the 1st and 2nd, 2nd and 3rd, and so on, up to the (N-1)th and Nth observation targets, thus forming an elevation traverse similar to leveling. Due to measurement errors, the elevation values ​​obtained by direct accumulation usually have a closure error with the known elevation at the end point. Therefore, in this embodiment, the fixed control points A and B at both ends of the bridge to be inspected are used as constraints to construct a traverse adjustment model.

[0053] Specifically, the traverse adjustment model in the embodiments of this specification is as follows:

[0054] in, Let be the corrected height difference between the observation target of the i-th contact wire column and the observation target of the (i-1)-th contact wire column. Let L be the relative height difference between the observation target of the i-th contact wire column and the observation target of the (i-1)-th contact wire column, and let L be the distance between the fixed control points A and B at both ends of the bridge to be inspected. Let be the distance between the i-th contact wire post and the (i-1)-th contact wire post. , H represents the relative elevation difference between fixed control points A and B at both ends of the bridge to be tested, where... The relative height difference between the observation target of the first contact wire post and the fixed control point at the beginning of the bridge to be inspected. This is the horizontal distance between the first contact wire post and the fixed control point at the beginning of the bridge to be inspected.

[0055] Furthermore, the formula for calculating the absolute elevation of the observation target on each contact wire post is as follows:

[0056] in, Let be the absolute elevation of the observation target of the i-th contact wire column, where for The sum of the predetermined elevations of the fixed control points at the beginning of the bridge to be inspected and the elevations of the bridge itself.

[0057] In the embodiments of this specification, after obtaining the absolute elevation of the observation target on each contact wire post, the alignment of the bridge to be inspected can be detected based on the absolute elevation of the observation target on each contact wire post. Specifically, as shown... Figure 6 The diagram shown is a flowchart illustrating the process of obtaining the alignment of the bridge under test based on the absolute elevation of the observation targets on each contact wire post, as described in this embodiment of the specification. The process includes the following steps: Step 601: Compare the absolute elevation of the observation target on each contact wire column with the elevation of the observation target on that contact wire column in the initial archive data to obtain the settlement of the observation target on each contact wire column. Step 602: Determine the alignment of the bridge to be inspected based on the settlement of the observation targets of each contact wire column.

[0058] In the embodiments of this specification, the absolute elevations of the observation targets on all catenary columns of the current bridge, obtained through adjustment calculations, are acquired. The initial archive data or measurement data from the previous period corresponding to the bridge under test are retrieved. The current absolute elevation of the observation target on each catenary column is compared point-by-point with the reference elevation of the corresponding observation target in the initial archive data. The elevation difference of the observation target on each catenary column is calculated, and this difference represents the settlement at the corresponding point. Based on the settlement data of all catenary column observation targets, the settlement distribution pattern along the longitudinal direction of the bridge under test is analyzed. The linear smoothness and structural settlement status of the bridge under test can be comprehensively evaluated by considering the settlement trend at continuous points, the settlement difference between adjacent catenary column observation targets, and the overall settlement of the entire bridge.

[0059] Theoretical calculations show that, at an observation distance of 25 meters, the accuracy of monitoring the elevation of the intermediate point after traverse adjustment can be better than ±2.025 mm, which can meet the accuracy requirements for daily inspection of railway bridge alignment.

[0060] According to one embodiment of this specification, the track alignment is also obtained based on the absolute elevation of the observation target on the contact wire post. Specifically, determining the track alignment includes the following steps: Step 11: Determine the three-dimensional coordinates of the observation target in the ground coordinate system based on the absolute elevation of the observation target, calculate the three-dimensional coordinates of the camera optical center in the ground coordinate system based on the three-dimensional coordinates of the target, and obtain the continuous spatial trajectory of the mobile vehicle based on the three-dimensional coordinates of the camera optical center, the attitude and mileage data of the inertial navigation system. In the embodiments described in this specification, the coordinates of the i-th observation target in the ground coordinate system are... , H i X represents the absolute elevation of the observed target. i and Y i The value can be determined based on the location of the contact wire column to which the observed target belongs.

[0061] As the trolley travels along the track, the three-dimensional coordinates of the camera's rigidity in the ground coordinate system are calculated according to a fixed travel distance. For ease of explanation, the location of each fixed travel distance is referred to as the control section. The three-dimensional coordinates of the camera's optical center in the ground coordinate system at the control section are calculated using the multi-camera joint spatial resection method. .

[0062] In the embodiments described in this specification, the continuous spatial trajectory of the mobile vehicle is obtained based on the three-dimensional coordinates of the camera's optical center and the attitude and odometer data of the inertial navigation system. Traj The formula is:

[0063] g: Ground coordinate system; b: Vehicle inertial navigation coordinate system; c: Camera coordinate system; t: Time t; : Camera optical center ground three-dimensional coordinates; The camera is fixedly offset relative to the inertial navigation center of the vehicle; : Inertial navigation system output attitude matrix; The odometer outputs the trolley's displacement increment.

[0064] Step 12: Based on the continuous spatial trajectory of the moving trolley and the geometric relationship between the camera optical center and the top surfaces of the left and right rails in the track, calculate the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system, and calculate the track gauge between the left and right rails based on the results output by the track gauge measuring instrument. Based on the continuous spatial trajectory of the mobile trolley and the geometric relationship between the camera optical center and the top surfaces of the left and right rails in the track, the formula for calculating the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system is as follows:

[0065] d l The fixed deviation between the camera's optical center and the left rail in the track; d r The fixed deviation between the camera's optical center and the right rail in the track; The three-dimensional coordinates of the top of the right rail at time t; The three-dimensional coordinates of the top of the left rail at time t; The three-dimensional coordinate sequence of the top of the left rail; The three-dimensional coordinate sequence of the top of the right rail.

[0066] Step 13: Calculate the alignment of the track based on the three-dimensional coordinate sequence of the left and right tracks in the ground coordinate system, the track gauge, and the design alignment parameters of the track.

[0067] In the embodiments of this specification, the track alignment includes track geometric parameters such as measured track gauge, track gauge deviation, measured superelevation (or horizontal), superelevation deviation, 10-meter chord of elevation difference, 10-meter chord of track alignment, versine, versine deviation, triangular pit (twist), and track gauge change rate.

[0068] In some other embodiments of this specification, a track geometry parameter report can also be generated. The track geometry parameter results for each detection location are output in mileage order, and a track geometry parameter analysis report is generated for track condition assessment, re-measurement comparison, and maintenance decision-making.

[0069] Preferably, the superelevation (or horizontal) parameter can be calculated by combining the measured track gauge and the inertial navigation roll angle.

[0070] Preferably, the high and low 10-meter chords and the track direction 10-meter chords are both calculated from the left and right track spatial trajectories after resampling at equal mileage.

[0071] Preferably, the versine is calculated using a chord length of 20 meters. The design versine is obtained from the design linear parameters, and the measured versine is calculated from the measured planar trajectory.

[0072] Based on the same inventive concept, this specification also provides a non-contact measurement device for beam-track alignment based on mobile vision. The device is embedded in a measurement system mounted on a mobile trolley located on a track laid on the bridge to be inspected. The measurement system includes two sets of industrial cameras, an inertial navigation system, an odometer, and a track gauge. The two sets of industrial cameras are respectively fixed at the front and rear ends of the mobile trolley in the direction of travel. Each set of industrial cameras includes two calibrated industrial cameras, forming a binocular vision system. Fixed control points with known elevations are set at both ends of the bridge to be inspected. Observation targets are set on each contact wire post along the bridge to be inspected, such as... Figure 7 As shown, the device includes: The data detection unit 701 is used to monitor the mileage data recorded by the odometer during the movement of the mobile trolley along the direction of travel. When the mileage data meets the predetermined requirements, the unit sends a trigger signal to the two sets of industrial cameras and the inertial navigation system. The trigger signal is used to control the two sets of industrial cameras to simultaneously expose and obtain images of the observation targets on two adjacent contact wire columns along the bridge to be inspected, and simultaneously control the inertial navigation system to record the attitude information of the mobile trolley at the exposure time. Image point coordinate extraction unit 702 is used to extract the image point coordinates of the front observation target in the image of the front observation target in each of the two adjacent contact network columns, and to extract the image point coordinates of the rear observation target in the image of the rear observation target in the adjacent contact network columns. The camera coordinate transformation unit 703 is used to transform the image point coordinates of the front observation target and the image point coordinates of the rear observation target to the camera coordinate system according to the camera parameters of the two sets of industrial cameras, so as to obtain the camera-in-camera three-dimensional spatial coordinates of the front observation target and the camera-in-camera three-dimensional spatial coordinates of the rear observation target. The elevation difference calculation unit 704 is used to construct a rotation matrix using the attitude information, and combined with the mileage, to transform the camera-in-the-camera three-dimensional spatial coordinates of the front observation target and the camera-in-the-camera three-dimensional spatial coordinates of the rear observation target to the ground coordinate system, and to calculate the relative elevation difference between the front observation target and the rear observation target in the ground coordinate system. The absolute elevation calculation unit 705 is used to form an elevation traverse based on the relative elevation difference between all two adjacent contact wire columns, and to construct a traverse adjustment model with the fixed control points as constraints, so as to calculate the absolute elevation of the observation target on each contact wire column. The bridge alignment detection unit 706 is used to obtain the alignment of the bridge to be detected based on the absolute elevation of the observation target on each contact wire post. The track alignment detection unit 707 is used to determine the three-dimensional coordinates of the observation target in the ground coordinate system based on the absolute elevation of the observation target, and to calculate the three-dimensional coordinates of the camera optical center in the ground coordinate system based on the three-dimensional coordinates of the target. Based on the three-dimensional coordinates of the camera optical center, the attitude and odometer data of the inertial navigation system, it acquires the continuous spatial trajectory of the moving trolley. Based on the continuous spatial trajectory of the moving trolley and the geometric relationship between the camera optical center and the top surfaces of the left and right rails in the track, it calculates the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system, and calculates the track gauge between the left and right rails based on the output of the track gauge measuring instrument. Based on the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system, the track gauge, and the design alignment parameters of the track, it calculates the alignment of the track.

[0073] The beneficial effects obtained by the above-described device are the same as those obtained by the above-described method, and will not be described in detail in the embodiments of this specification.

[0074] like Figure 8The diagram shown is a structural schematic of a computer device according to an embodiment of this specification. The system in this embodiment can be the computer device described in this embodiment, executing the method of the present invention described above. The computer device 802 may include one or more processing devices 804, such as one or more central processing units (CPUs), each processing unit may implement one or more hardware threads.

[0075] The computer device 802 may also include any storage resource 806 for storing any kind of information such as code, settings, data, etc.

[0076] Non-limiting, for example, storage resource 806 may include any one or more of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc.

[0077] More generally, any storage resource can use any technology to store information.

[0078] Furthermore, any storage resource can provide volatile or non-volatile retention of information.

[0079] Furthermore, any storage resource can represent a fixed or removable component of the computer device 802.

[0080] In one scenario, when processing device 804 executes associated instructions stored in any storage resource or combination of storage resources, computer device 802 can perform any operation of the associated instructions. Computer device 802 also includes one or more drive mechanisms 808 for interacting with any storage resource, such as hard disk drive mechanisms, optical disk drive mechanisms, etc.

[0081] Computer device 802 may also include an input / output module 810 (I / O) for receiving various inputs (via input device 812) and providing various outputs (via output device 814). A specific output mechanism may include a presentation device 816 and an associated graphical user interface (GUI) 818. In other embodiments, the input / output module 810 (I / O), input device 812, and output device 814 may be omitted, and the device may function solely as a computer device within a network. Computer device 802 may also include one or more network interfaces 820 for exchanging data with other devices via one or more communication links 822. One or more communication buses 824 couple the components described above together.

[0082] Communication link 822 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0083] This specification also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0084] This specification also provides computer-readable instructions, wherein when a processor executes the instructions, the program therein causes the processor to perform the above-described method.

[0085] It should be understood that in the various embodiments of this specification, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0086] It should also be understood that, in the embodiments of this specification, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the embodiments of this specification, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0087] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the embodiments in this specification.

[0088] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0089] In the embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0090] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described in this specification, depending on actual needs.

[0091] Furthermore, the functional units in the various embodiments of this specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this specification, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this specification. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0093] This specification describes the principles and implementation methods of the embodiments using specific examples. The above descriptions of the embodiments are only for the purpose of helping to understand the methods and core ideas of the embodiments in this specification. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the embodiments in this specification. Therefore, the content of this specification should not be construed as a limitation on the embodiments in this specification.

Claims

1. A non-contact measurement method for beam-track alignment based on mobile vision, characterized in that, The method is applied to a measurement system mounted on a mobile trolley, which is located on the track of the bridge to be inspected. The measurement system includes two sets of industrial cameras, an inertial navigation system, an odometer, and a track gauge. The two sets of industrial cameras are respectively fixed at the front and rear ends of the mobile trolley in the direction of travel. Each set of industrial cameras includes two calibrated industrial cameras, forming a binocular vision system. Fixed control points with known elevations are set at both ends of the bridge to be inspected. Observation targets are set on each contact wire post along the bridge to be inspected. The method includes: During the movement of the mobile trolley along the direction of travel, the mileage data recorded by the odometer is monitored. When the mileage data meets the predetermined requirements, a trigger signal is sent to the two sets of industrial cameras and the inertial navigation system. The trigger signal is used to control the two sets of industrial cameras to simultaneously expose and obtain images of the observation targets on two adjacent contact wire columns along the bridge to be inspected, and simultaneously control the inertial navigation system to record the attitude information of the mobile trolley at the exposure time. For each pair of adjacent catenary columns, extract the image point coordinates of the previous observation target in the image of the previous observation target in the adjacent catenary column, and extract the image point coordinates of the subsequent observation target in the image of the subsequent observation target in the adjacent catenary column. Based on the camera parameters of the two sets of industrial cameras, the image point coordinates of the front observation target and the image point coordinates of the rear observation target are transformed into the camera coordinate system to obtain the three-dimensional spatial coordinates of the front observation target and the three-dimensional spatial coordinates of the rear observation target within the camera. Using the attitude information, a rotation matrix is ​​constructed. Combined with the mileage, the camera-in-the-camera three-dimensional spatial coordinates of the front observation target and the rear observation target are transformed to the ground coordinate system. The relative height difference between the front observation target and the rear observation target is calculated in the ground coordinate system. Based on the relative elevation difference between all adjacent contact wire columns, an elevation traverse is formed, and the traverse adjustment model is constructed with the fixed control points as constraints to calculate the absolute elevation of the observation target on each contact wire column. The alignment of the bridge under test is obtained based on the absolute elevation of the observation target on each contact wire post. The three-dimensional coordinates of the observation target in the ground coordinate system are determined based on the absolute elevation of the observation target, and the three-dimensional coordinates of the camera optical center in the ground coordinate system are calculated based on the three-dimensional coordinates of the target. The continuous spatial trajectory of the mobile vehicle is obtained based on the three-dimensional coordinates of the camera optical center, the attitude and mileage data of the inertial navigation system. Based on the continuous spatial trajectory of the mobile trolley and the geometric relationship between the optical center of the camera and the top surfaces of the left and right rails in the track, the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system is calculated, and the track gauge between the left and right rails is calculated based on the output of the track gauge measuring instrument. The alignment of the track is calculated based on the three-dimensional coordinate sequence of the left and right tracks in the ground coordinate system, the track gauge, and the design alignment parameters of the track.

2. The method according to claim 1, characterized in that, After extracting the image point coordinates of the previously observed target and the image point coordinates of the subsequently observed target, the method further includes: The distortion parameters obtained from the calibration of the industrial camera are used to correct the image point coordinates of the front observation target and the image point coordinates of the rear observation target. Based on the camera parameters of the two sets of industrial cameras, the image point coordinates of the front-observed target and the image point coordinates of the rear-observed target are transformed to the camera coordinate system, including: Based on the camera parameters of the two sets of industrial cameras, the corrected image point coordinates of the front observation target and the corrected image point coordinates of the rear observation target are transformed into the camera coordinate system.

3. The method according to claim 1, characterized in that, The three-dimensional coordinates of the observation target in the ground coordinate system are determined based on the absolute elevation of the observation target, and the three-dimensional coordinates of the camera optical center in the ground coordinate system are calculated based on the three-dimensional coordinates of the target. Based on the three-dimensional coordinates of the camera optical center, the attitude and odometer data of the inertial navigation system, the continuous spatial trajectory of the mobile vehicle is obtained, including: The coordinates of the i-th observation target in the ground coordinate system are: , H i X represents the absolute elevation of the observed target. i and Y i The value is determined based on the location of the contact wire column to which the observed target belongs; As the trolley travels along the track, the three-dimensional coordinates of the camera's rigidity in the ground coordinate system are calculated according to a fixed travel distance. The location of each fixed travel distance is called a control section. The three-dimensional coordinates of the camera's optical center in the ground coordinate system at the control section are calculated using the multi-camera joint spatial resection method. ; Based on the three-dimensional coordinates of the camera's optical center and the attitude and odometer data of the inertial navigation system, the continuous spatial trajectory of the mobile vehicle is obtained. Traj The formula is: g: Ground coordinate system; b: Vehicle inertial navigation coordinate system; c: Camera coordinate system; t: Time t; : Camera optical center ground three-dimensional coordinates; The camera is fixedly offset relative to the inertial navigation center of the vehicle; : Inertial navigation system output attitude matrix; The odometer outputs the trolley's displacement increment.

4. The method according to claim 1, characterized in that, Based on the continuous spatial trajectory of the mobile trolley and the geometric relationship between the camera optical center and the top surfaces of the left and right rails in the track, the formula for calculating the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system is as follows: d l The fixed deviation between the camera's optical center and the left rail in the track; d r The fixed deviation between the camera's optical center and the right rail in the track; The three-dimensional coordinates of the top of the right rail at time t; The three-dimensional coordinates of the top of the left rail at time t; The three-dimensional coordinate sequence of the top of the left rail; The three-dimensional coordinate sequence of the top of the right rail.

5. The method according to claim 1, characterized in that, The traverse adjustment model is as follows: in, Let be the corrected height difference between the observation target of the i-th contact wire column and the observation target of the (i-1)-th contact wire column. Let L be the relative height difference between the observation target of the i-th contact wire column and the observation target of the (i-1)-th contact wire column, and L be the distance between the fixed control points at both ends of the bridge to be inspected. Let be the distance between the i-th contact wire post and the (i-1)-th contact wire post. H represents the relative elevation difference between the fixed control points at both ends of the bridge to be tested. The relative height difference between the observation target of the first contact wire post and the fixed control point at the beginning of the bridge to be inspected. This is the horizontal distance between the first contact wire post and the fixed control point at the beginning of the bridge to be inspected.

6. The method according to claim 1, characterized in that, Based on the absolute elevation of the observation targets on each contact wire post, the alignment of the bridge under inspection is obtained, including: The absolute elevation of the observation target on each contact wire column is compared with the elevation of the same observation target on that contact wire column in the initial archive data to obtain the settlement of the observation target on each contact wire column. The alignment of the bridge to be inspected is determined based on the settlement of the observation targets on each contact wire column.

7. The method according to claim 1, characterized in that, Using the attitude information to construct a rotation matrix, and combining it with the odometer reading, transform the camera-internal 3D spatial coordinates of the forward-observed target and the camera-internal 3D spatial coordinates of the subsequent-observed target to a ground coordinate system, including: The attitude information is used to construct a rotation matrix from the camera coordinate system to the ground coordinate system; Calculate the translation vector of the camera coordinate system origin in the ground coordinate system based on the mileage; Based on the rotation matrix and translation vector, the camera-internal 3D spatial coordinates of the front observation target and the camera-internal 3D spatial coordinates of the rear observation target are respectively transformed to the ground coordinate system.

8. The method according to claim 1, characterized in that, During the movement of the mobile trolley along the direction of travel, the mileage data recorded by the odometer is monitored. When the mileage data meets predetermined requirements, a trigger signal is sent to the two sets of industrial cameras and the inertial navigation system. The trigger signal is used to control the two sets of industrial cameras to simultaneously expose images of the observation targets on two adjacent contact wire pillars along the bridge to be inspected, and simultaneously control the inertial navigation system to record the attitude information of the mobile trolley at the exposure time, including: The mileage data is collected synchronously along with the images taken by the two sets of industrial cameras and the attitude information of the mobile trolley at the exposure time is recorded by the inertial navigation system. The mileage data is required to be set at equal intervals of not less than 20cm, or at the 1 / 4, 1 / 2 or 3 / 4 position of the bridge.

9. A non-contact measurement device for beam-track alignment based on mobile vision, characterized in that, The device is embedded in a measurement system mounted on a mobile trolley, which is positioned on a track laid out on the bridge to be inspected. The measurement system includes two sets of industrial cameras, an inertial navigation system, an odometer, and a track gauge. The two sets of industrial cameras are respectively fixed at the front and rear ends of the mobile trolley in the direction of travel. Each set of industrial cameras includes two calibrated industrial cameras, forming a binocular vision system. Fixed control points with known elevations are set at both ends of the bridge to be inspected. Observation targets are set on each contact wire post along the bridge to be inspected. The device includes: The data detection unit is used to monitor the mileage data recorded by the odometer during the movement of the mobile trolley along the direction of travel. When the mileage data meets the predetermined requirements, the unit sends a trigger signal to the two sets of industrial cameras and the inertial navigation system. The trigger signal is used to control the two sets of industrial cameras to simultaneously expose the images of the observation targets on two adjacent contact wire columns along the bridge to be inspected, and simultaneously control the inertial navigation system to record the attitude information of the mobile trolley at the exposure time. The image point coordinate extraction unit is used to extract the image point coordinates of the front observation target in the image of the front observation target in each pair of adjacent contact network columns, and to extract the image point coordinates of the rear observation target in the image of the rear observation target in each pair of adjacent contact network columns. The camera coordinate transformation unit is used to transform the image point coordinates of the front observation target and the image point coordinates of the rear observation target to the camera coordinate system according to the camera parameters of the two sets of industrial cameras, so as to obtain the camera-in-camera three-dimensional spatial coordinates of the front observation target and the camera-in-camera three-dimensional spatial coordinates of the rear observation target. The elevation difference calculation unit is used to construct a rotation matrix using the attitude information, and combined with the mileage, to transform the camera-in-the-camera three-dimensional spatial coordinates of the front observation target and the camera-in-the-camera three-dimensional spatial coordinates of the rear observation target to the ground coordinate system, and to calculate the relative elevation difference between the front observation target and the rear observation target in the ground coordinate system. The absolute elevation calculation unit is used to form an elevation traverse based on the relative elevation difference between all two adjacent contact wire columns, and to construct a traverse adjustment model with the fixed control points as constraints, so as to calculate the absolute elevation of the observation target on each contact wire column. The bridge alignment detection unit is used to obtain the alignment of the bridge to be detected based on the absolute elevation of the observation target on each contact wire post. The track alignment detection unit is used to determine the three-dimensional coordinates of the observation target in the ground coordinate system based on the absolute elevation of the observation target, and to calculate the three-dimensional coordinates of the camera optical center in the ground coordinate system based on the three-dimensional coordinates of the target. Based on the three-dimensional coordinates of the camera optical center, the attitude and odometer data of the inertial navigation system, it acquires the continuous spatial trajectory of the moving trolley. Based on the continuous spatial trajectory of the moving trolley and the geometric relationship between the camera optical center and the top surfaces of the left and right rails in the track, it calculates the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system, and calculates the track gauge between the left and right rails based on the output of the track gauge measuring instrument. Based on the three-dimensional coordinate sequence of the left and right rails in the ground coordinate system, the track gauge, and the design alignment parameters of the track, it calculates the alignment of the track.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 8.

11. 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 8.

12. 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 8.

Images