Track geometric parameter measuring equipment, processing method and device

Abstract

The invention relates to track geometric parameter measuring equipment, a processing method and a device, and relates to the field of optical measurement. The track geometric parameter measuring equipment comprises three lasers, three image collectors, an inertial measurement unit and a controller which are mounted on a mounting beam, wherein the mounting beam is fixed at the bottom of a train; the two laser devices and the two image acquisition devices are mounted at the first end of the mounting beam, emit laser to the right track and acquire images of the right track; the third laser and the third image collector are mounted at the second end of the mounting beam, emit laser to the left track and collect images of the left track; the speedometer is used for counting the travelled distance of the train; and the controller is used for determining a sampling point according to the mileage, controlling each laser to emit laser at the sampling point at the same time, controlling each image collector to carry out image collection, and controlling the inertial measurement unit to collect attitude information. According to the invention, accurate measurement of related parameters of the steel rail can be realized through a small amount of hardware.

Description

Technical Field

[0001] This application relates to the field of optical measurement, and more particularly to a device, processing method and apparatus for measuring orbital geometry parameters. Background Technology

[0002] Track geometry measurement technology is one of the core technologies for ensuring the safe and stable operation of railways (especially high-speed railways). Its technological background integrates the development of multiple disciplines and the urgent needs of the railway industry. Existing track geometry measurement technologies mostly use the inertial reference method to measure track geometric parameters. The main sensors include inertial measurement sensors and two laser profilers. This type of system cannot accurately measure under low-speed conditions due to the low signal-to-noise ratio of the accelerometer. Summary of the Invention

[0003] Embodiments of this disclosure provide an orbital geometry parameter measurement device, processing method, and apparatus.

[0004] In a first aspect, embodiments of this disclosure provide a track geometry parameter measuring device, comprising: a first laser, a second laser, a third laser, a first image acquisition unit, a second image acquisition unit, a third image acquisition unit, an inertial measurement unit, an odometer, a controller, and a mounting beam; the first laser, the second laser, the third laser, the first image acquisition unit, the second image acquisition unit, the third image acquisition unit, the inertial measurement unit, and the controller are mounted on the mounting beam, and the mounting beam is fixed to the bottom of the train; the first laser, the second laser, the first image acquisition unit, and the second image acquisition unit are mounted at the first end of the mounting beam, the first laser and the second laser emit lasers toward the right side of the track in the direction of train travel, and the first image acquisition unit and the second image acquisition unit are used to acquire images of the right side of the track to obtain the first laser. The system includes a first image and a second image; a third laser and a third image acquisition unit are installed at the second end of the mounting beam. The third laser emits a laser beam towards the left side of the track in the direction of train travel, and the third image acquisition unit acquires an image of the left side of the track in the direction of train travel to obtain the third image; an odometer is used to count the train's mileage; a controller is connected to the first laser, the second laser, the third laser, the first image acquisition unit, the second image acquisition unit, the third image acquisition unit, the odometer, and the inertial measurement unit. It is used to determine the sampling point based on the mileage, and at the sampling point, control the first laser, the second laser, and the third laser to emit laser beams simultaneously, control the first image acquisition unit, the second image acquisition unit, and the third image acquisition unit to acquire images simultaneously, and control the inertial measurement unit to acquire attitude information simultaneously.

[0005] Secondly, embodiments of this disclosure provide an image processing method, comprising: acquiring a first image sequence, a second image sequence, a third image sequence, and a set of attitude information collected at various sampling points by a track geometry parameter measuring device installed on the train during the train's travel on the rail; determining the displacement parameters of the rail at each sampling point based on the first image sequence, the second image sequence, and the third image sequence; determining the angle parameters of the rail based on the set of attitude information; and determining relevant parameters of the rail based on the displacement parameters and the angle parameters.

[0006] Thirdly, embodiments of this disclosure provide an image processing apparatus, comprising: an information acquisition unit configured to acquire a first image sequence, a second image sequence, a third image sequence, and a set of attitude information collected at various sampling points by a track geometry parameter measuring device installed on the train during the train's travel on the rail; a displacement parameter determination unit configured to determine the displacement parameters of the rail at each sampling point based on the first image sequence, the second image sequence, and the third image sequence; an angle parameter determination unit configured to determine the angle parameters of the rail based on the set of attitude information; and a related parameter determination unit configured to determine related parameters of the rail based on each displacement parameter and each angle parameter.

[0007] By applying the technical solution of this disclosure, images of the rails along which the train is traveling can be acquired using three lasers and three corresponding image acquisition units. Combined with attitude information measured by the inertial measurement unit on the train, the relevant parameters of the rails can be measured. The technical solution of this disclosure achieves accurate measurement of rail-related parameters with a small amount of hardware.

[0008] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is an exemplary system architecture diagram in which the track geometry parameter measurement device and image processing method disclosed herein can be applied; Figure 2 This is a schematic diagram of the structure of one embodiment of the track geometry parameter measuring device disclosed herein; Figure 2a This is a schematic diagram of the structure of the image acquisition unit, which consists of a first laser, a second laser, a first image acquisition unit, and a second image acquisition unit, in the track geometry parameter measurement device disclosed herein. Figure 2bThis is a three-dimensional structural schematic diagram of the track geometry parameter measuring device disclosed herein; Figure 3 This is a schematic flowchart of an embodiment of the image processing method disclosed herein. Figure 4 This is a flowchart illustrating yet another embodiment of the image processing method disclosed herein; Figure 4a This is a schematic diagram showing the positions of the rail apex and gauge point of the rail. Figure 5 This is a schematic diagram illustrating the principle of gauge and alignment measurement in the image processing method of this disclosure; Figure 6 This is a schematic diagram illustrating the principle of measuring the horizontal elevation of the rail in the image processing method of this disclosure; Figure 7 This is a schematic diagram of the structure of one embodiment of the image processing apparatus of this disclosure. Detailed Implementation

[0010] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of this disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0011] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this disclosure. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms “comprising” and / or “including” are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0012] Where there is no conflict, the embodiments and features described herein can be combined with each other.

[0013] To make the technical solutions and advantages of this disclosure clearer, the following description, in conjunction with the accompanying drawings and specific embodiments, will provide a more detailed account of this disclosure.

[0014] Figure 1 An exemplary system architecture 100 is shown, in which embodiments of the orbital geometry parameter measurement device, image processing method, or image processing apparatus of this disclosure can be applied.

[0015] like Figure 1As shown, the track geometry parameter measuring device in this embodiment is installed at the bottom of the train to acquire images of the left and right rails during train operation, as well as the train's attitude information. By processing the images and attitude information, relevant rail parameters can be determined. These parameters may include changes in the rail's orientation and height.

[0016] After acquiring images and attitude information, the track geometry parameter measuring device can process the data using a chip within the device, or it can send the images and attitude information to other terminal devices for processing. That is, the image processing method provided in this embodiment can be executed by either the track geometry parameter measuring device or a terminal device. Correspondingly, the image processing device can be located within the track geometry parameter measuring device or within the terminal device.

[0017] Figure 2 A schematic diagram of one embodiment of the track geometry parameter measuring device of this disclosure is shown. Figure 2 As shown, the track geometry parameter measuring device in this embodiment includes: a first laser 201, a second laser 202, a third laser 203, a first image acquisition unit 204, a second image acquisition unit 205, a third image acquisition unit 206, an inertial measurement unit 207, an odometer (not shown in the figure), a controller (not shown in the figure), and a mounting beam 208.

[0018] The first laser 201, the second laser 202, the third laser 203, the first image acquisition unit 204, the second image acquisition unit 205, the third image acquisition unit 206, the inertial measurement unit 207, and the controller are mounted on the mounting beam 208, which is fixed to the bottom of the train.

[0019] The first laser 201, the second laser 202, the first image acquisition device 204, and the second image acquisition device 205 are installed at the first end of the mounting beam 208. The first laser 201 and the second laser 202 emit lasers toward the right track in the direction of train travel. The first image acquisition device 204 and the second image acquisition device 205 are used to acquire images of the right track to obtain the first image and the second image.

[0020] The third laser 203 and the third image acquisition device 206 are installed at the second end of the mounting beam 208. The third laser 203 emits a laser towards the left track in the direction of train travel, and the third image acquisition device 206 is used to acquire an image of the left track in the direction of train travel to obtain a third image.

[0021] The odometer is used to count the train's mileage. The controller is connected to the first laser 201, second laser 202, third laser 203, first image acquisition unit 204, second image acquisition unit 205, third image acquisition unit 206, inertial measurement unit 207, and odometer. It is used to determine sampling points based on the mileage. At the sampling points, it controls the first laser 201, second laser 202, third laser 203, first image acquisition unit 204, second image acquisition unit 205, and third image acquisition unit 206 to simultaneously acquire images, and controls the inertial measurement unit 207 to simultaneously acquire attitude information.

[0022] Figure 2a A schematic diagram of an image acquisition unit consisting of a first laser 201, a second laser 202, a first image acquisition unit 204, and a second image acquisition unit 205 is shown. In this embodiment, the first laser 201 and the second laser 202 are arranged in parallel and emit laser light in the same direction. The first laser 201 is matched with the first image acquisition unit 204, which is used to acquire a first image of the first laser 201 illuminating the surface of the rail. The second laser 202 is matched with the second image acquisition unit 205, which is used to acquire a second image of the second laser 202 illuminating the surface of the rail. The fields of view of the first image acquisition unit 204 and the second image acquisition unit 205 intersect. Furthermore, the first angle between the optical axes of the first laser 201 and the first image acquisition unit 204, and the second angle between the optical axes of the second laser 202 and the second image acquisition unit 205, both fall within a preset angle range. In some specific practices, the above-mentioned preset included angle range can be 30°-60°.

[0023] In some optional implementations of this embodiment, the positions of the first laser 201, the second laser 202, and the third laser 203 can be in a T-shape, see [reference]. Figure 2b Similarly, the laser cross-sections produced by the three lasers are also arranged in a T-shape. Each image acquisition unit and inertial measurement unit acquires images or information using equal spatial intervals.

[0024] In some optional implementations of this embodiment, the spatial sampling interval is L, and the distance between the first laser 201 and the second laser 202 is also L.

[0025] In some optional implementations of this embodiment, the inertial measurement unit 207 can be disposed on the centerline of the mounting beam 208, which can coincide with the centerline between the first laser 201 and the second laser 202. Simultaneously, the inertial measurement unit 207 can be disposed at the center of the mounting beam 208.

[0026] In some optional implementations of this embodiment, the controller can determine multiple sampling points based on the train's travel distance measured by the odometer. Specifically, sampling points can be determined when a preset distance is detected that the train has traveled. That is, the distance between two adjacent sampling points is a preset distance, achieving equal spatial interval collection of information.

[0027] The track geometry parameter measuring device provided in the above embodiments of this disclosure can use three lasers and three image acquisition devices arranged in a T-shape to acquire images of the rail, while simultaneously using an inertial measurement unit to acquire attitude information. Sampling at equal spatial intervals ensures the uniformity of information acquisition. Accurate measurement of rail-related parameters is achieved with a smaller number of hardware components.

[0028] See also Figure 3 This illustrates a flow 300 of an embodiment of the image processing method according to the present disclosure. Figure 3 As shown, the method in this embodiment may include the following steps: Step 301: Obtain the first image sequence, the second image sequence, the third image sequence, and the attitude information set collected at each sampling point by the track geometry parameter measuring device installed on the train during the train's travel on the rails.

[0029] In this embodiment, the entity executing the image processing method can acquire a first image sequence, a second image sequence, a third image sequence, and a set of attitude information collected at various sampling points by a track geometry parameter measuring device installed on the train during its movement on the rails. The first image sequence may include multiple first images, which are acquired by a first image acquisition device at the sampling points along the right rail. Similarly, the second image sequence may include multiple second images, which are acquired by a second image acquisition device at the sampling points along the right rail. The third image sequence may include multiple third images, which are acquired by a third image acquisition device at the sampling points along the left rail. The set of attitude information may include multiple attitude information sets, each acquired by an inertial measurement unit. Here, a sampling point refers to the location where image or information needs to be acquired, and the distance between two adjacent sampling points can be the same. In some specific practices, the distance between two adjacent sampling points can be the same as the distance between the first laser and the second laser in the image acquisition device.

[0030] Step 302: Determine the displacement parameters of the rail at each sampling point based on the first image sequence, the second image sequence, and the third image sequence.

[0031] In this embodiment, after obtaining the first image sequence, the second image sequence, and the third image sequence, each image in the three image sequences can be processed to obtain the displacement parameters of the rail at each sampling point. Here, the displacement parameters can include lateral displacement and vertical displacement. Specifically, Gaussian fitting and other processing can be performed on each image in the three image sequences to accurately determine the feature points of the rail. Further, based on the positions of the feature points, the displacement parameters of the rail are determined.

[0032] Step 303: Determine the angle parameters of the rail based on the attitude information set.

[0033] After obtaining the attitude information set, the attitude information in the set can be analyzed to determine the angle parameters of the rail. Here, the angle parameters can include the heading angle, roll angle, pitch angle, etc.

[0034] Step 304: Determine the relevant parameters of the rail based on the displacement parameters and angle parameters.

[0035] After obtaining the displacement and angle parameters at each sampling point, these parameters can be further processed to obtain the relevant parameters of the rail. Specifically, the spatial position of the rail's feature points can be determined based on the displacement and angle parameters corresponding to two adjacent sampling points. The relevant parameters of the rail can then be determined based on the spatial position of these feature points. These relevant parameters may include the rail's direction and height. In some practical applications, the position of the sampling points can be used as the abscissa, and the displacement parameters corresponding to each sampling point as the ordinate, to obtain the correlation curve between the two rails. Based on this correlation curve, the values ​​of the relevant parameters can be derived.

[0036] The image processing method provided in the above embodiments of this disclosure can obtain accurate orbital geometry parameters through accurately acquired images and attitude information.

[0037] See also Figure 4 This illustrates a flow 400 of another embodiment of the image processing method of this disclosure. (See diagram 400.) Figure 4 As shown, the method in this embodiment may include the following steps: Step 401: Obtain the first image sequence, the second image sequence, the third image sequence, and the attitude information set collected at each sampling point by the track geometry parameter measuring device installed on the train during the train's travel on the rails.

[0038] Step 402: Based on the first image sequence and / or the second image sequence, determine the first lateral displacement and the second lateral displacement of the first feature point on the right track, as well as the first vertical displacement and the second vertical displacement of the second feature point at each sampling point.

[0039] In this embodiment, the first image sequence and the second image sequence can be processed separately, or they can be processed simultaneously. For example, feature point recognition can be performed on each image in the first and second image sequences to determine the positions of the first and second feature points. Furthermore, the first and second lateral displacements of the first feature point, and the first and second vertical displacements of the second feature point are determined.

[0040] Alternatively, the first and second images acquired at the same sampling point can be processed as a single combination. Specifically, image processing can be achieved through the following sub-steps: Step 4021: Process the first image and the second image respectively to determine the first light spot stripe corresponding to the first image and the second light spot stripe corresponding to the second image.

[0041] After obtaining the first and second images, they can be processed separately to determine the first light spot fringes corresponding to the first image and the second light spot fringes corresponding to the second image. Specifically, when the line laser emitted by the first laser illuminates the surface of the right track, diffraction fringes are generated due to diffraction. The first light spot fringes can be obtained by processing the first image. This processing can include, but is not limited to, fitting, deblurring, etc. The processing of the second image can be the same as or different from that of the first image. Specifically, the first and second images can be compared first to determine their differences, and different processing can be applied to these differences.

[0042] Step 4022: Determine the first sub-pixel in the first image and the second sub-pixel in the second image based on the first light spot stripe and the second light spot stripe.

[0043] After determining the first and second light spot fringes, further processing can be performed to determine the first sub-pixel in the first image and the second sub-pixel in the second image. Here, a pixel is the smallest discrete unit in a digital image, representing the brightness or color value at a specific location on the image, and its position is usually represented by integer coordinates. A sub-pixel is not a physically existing independent unit, but refers to a value in which position and coordinates are allowed to take non-integer values ​​(such as 12.3 pixels) in calculations. Continuous changes between pixel grids are estimated using mathematical methods, thereby achieving precision higher than the integer pixel level. For the first light spot fringe, its central fringe can be determined first, and then the pixel corresponding to the central fringe can be used as the first sub-pixel. The processing of the second light spot fringe can be the same as that of the first light spot fringe.

[0044] Step 4023: Perform coordinate transformation on the first sub-pixel and the second sub-pixel respectively, and fuse the first sub-pixel and the second sub-pixel after coordinate transformation to obtain the point cloud data of the right track surface contour.

[0045] After determining the first and second sub-pixels, their coordinates can be transformed to the world coordinate system to obtain their 3D coordinates. Then, based on these 3D coordinates, the first and second sub-pixels are fused to obtain the point cloud data of the right-side track surface contour. Specifically, the coordinates of the first and second sub-pixels can be transformed from the image coordinate system to the laser plane coordinate system, and then to the world coordinate system. After transformation to the world coordinate system, the intersection of the first and second sub-pixels can be taken as the fusion result.

[0046] Step 4024: Based on the point cloud data, determine the first lateral displacement and second lateral displacement of the first feature point on the right track, as well as the first vertical displacement and second vertical displacement of the second feature point.

[0047] After obtaining the point cloud data of the right track, the spatial positions of the feature points can be further determined, and the lateral and vertical displacements can be determined from each spatial position.

[0048] Here, the first feature point can be the gauge point of the rail, and the second feature point can be the rail vertex. The positional relationship between the gauge point and the rail vertex can be as follows: Figure 4a As shown. The rail vertex is defined as the highest point on the top surface of the rail, and the gauge point is defined as the point below the rail vertex on the gauge edge. γ Location, γ 16mm is usually used.

[0049] Step 403: Based on the third image sequence, determine the third lateral displacement of the first feature point on the left track and the third vertical displacement of the second feature point at each sampling point.

[0050] In this embodiment, the processing method for the third image sequence can be the same as that for the first image sequence. Further details will not be provided here.

[0051] Step 404: Based on the attitude information set, determine the heading angle and roll angle of the installation beam at each sampling point.

[0052] In this embodiment, the attitude information in the attitude information set can be parsed to determine the heading angle and roll angle of the mounting beam at each sampling point.

[0053] Step 405: Determine the rail orientation based on each first lateral displacement, each second lateral displacement, each third lateral displacement, and each heading angle.

[0054] For the first lateral displacement, second lateral displacement, third lateral displacement and heading angle corresponding to the same sampling point, substitute them into the pre-established formula to determine the rail orientation.

[0055] In some optional implementations of this embodiment, the spatial coordinates of the center gauge points of the left and right rails can be determined based on the first lateral displacement, second lateral displacement, third lateral displacement, and heading angle corresponding to two adjacent sampling points. Then, by filtering these spatial coordinates, the rail orientation can be obtained.

[0056] In some specific practices, see [reference needed]. Figure 5 Use the diagram shown to understand. Figure 5 The symbols in the text are explained below: --No. i Mileage of each sampling point; --No. i +1 sampling point mileage; --No. i The heading angle of the beam installed at each sampling point; --No. i The heading angle of the beam installed at +1 sampling point; --No. i The first lateral displacement of the track gauge point at each sampling point; --No. i The second lateral displacement of the track gauge point at each sampling point; --No. i +1 sampling point at the first lateral displacement of the gauge point; --No. i The second lateral displacement of the track gauge point at +1 sampling point; --No. i The third lateral displacement of the track gauge point at each sampling point; --No. i +1 sampling point at the third lateral displacement of the track gauge point; --No. i The lateral spatial coordinates of the left track gauge point at each sampling point; --No. i The lateral spatial coordinates of the track gauge point on the right side of each sampling point; --No. i -1 sampling point and the first i The lateral spatial coordinates of the track gauge point on the right side of the middle position of each sampling point; --No.i The sampling point and the first i+ The lateral spatial coordinates of the track gauge point on the right side of the middle position of a sampling point; --No. i+ 1 sampling point and the first i+ The lateral spatial coordinates of the track gauge point on the right side at the midpoint between the two sampling points; --The distance from point P2 to line P1P3, i.e., the distance of the first line. i The measurement system error of the track gauge at each sampling point.

[0057] The spatial sampling interval L of the detection system is generally no greater than 0.25m. Within 0.25m, the rail is almost a straight line. The accuracy is far below the system's effective measurement accuracy, therefore the first value is not considered. i System error at each sampling point , No. i Track gauge at each sampling point Calculate according to formula (1).

[0058] The calculation process for the orbital orientation of the reference track (right track) is relatively complex. Since the distance between the first and second lasers remains consistent with the system sampling interval L, when the system samples at equal intervals, it is assumed that the first laser... i +1 sampling point rear profiler and the first i The front profiler at each sampling point is on the same measurement section. i The sampling point and the first i The horizontal coordinate of the reference rail (right track) gauge point at the middle position of +1 sampling point It can be calculated recursively from equation (2). For the first i The heading angle of the mounting beam at each sampling point is measured by an inertial measurement unit installed inside the mounting beam.

[0059] No. i The lateral spatial coordinates of the left and right track gauge points at each sampling point location are calculated according to formula (3):

[0060] After obtaining the lateral spatial coordinates of the track gauge points on the left and right sides of each sampling point by recursion calculation using equation (3), the track direction within a certain wavelength range is obtained by filtering the samples with a filter. The detailed process will not be elaborated here.

[0061] Step 406: Determine the height of the rail based on each first vertical displacement, each second vertical displacement, each third vertical displacement, and each roll angle.

[0062] In this embodiment, for the first vertical displacement, the second vertical displacement, the third vertical displacement, and the roll angle corresponding to the same sampling point, they are substituted into a pre-established formula to determine the height of the rail.

[0063] In some optional implementations of this embodiment, the spatial coordinates of the second feature points of the left and right rails can be determined based on the first vertical displacement, the second vertical displacement, the third vertical displacement, and the roll angle. The spatial coordinates of the second feature points of the left and right rails are then filtered to determine the rail elevation.

[0064] In some specific practices, see [reference needed]. Figure 6 Use the diagram shown to understand. Figure 6 The symbols in the text are explained below: --No. i The side roll angle of the beam is installed at each sampling point; --No. i The first vertical displacement of the track apex at each sampling point; --No. i The second vertical displacement of the track apex at each sampling point; --No. i The third vertical displacement of the track apex at each sampling point; --No. i Track gauge at each sampling point; --The distance from point P2 to line P1P3; --No. i The elevation of the top of the track on the left side at each sampling point; --No. i The elevation of the top edge of the track on the right side at each sampling point; --No. i Elevation of the top edge of the reference rail (right rail) at position L / 2 before each sampling point; --No. i Elevation of the top edge of the reference rail (right rail) at position L / 2 after each sampling point; Similarly, when the sampling interval is very small, the change in the rail is considered to be almost a straight line, and the first... i System error at each sampling point , No. i Horizontal at each sampling point location Calculate according to formula (4), For the first i The roll angle of the mounting beam at each sampling point is measured by an inertial measurement unit installed inside the mounting beam.

[0065] The calculation process for elevation is similar to that for track orientation. First, the elevation of the top of the reference track (right track) at the midpoint between the i-th and (i+1)-th sampling points is calculated recursively using formula (5). , Let be the pitch angle of the beam installed at the i-th sampling point.

[0066] No. i The elevations of the top points of the left and right tracks at each sampling point are calculated according to formula (6):

[0067] After obtaining the elevation coordinates of the left and right track vertices at each sampling point by recursion calculation using equation (6), the track elevation within a certain wavelength range is obtained by filtering the samples. The detailed process will not be elaborated here.

[0068] The image processing method provided in the above embodiments of this disclosure can minimize the size of the equipment while ensuring the accuracy of profile measurement. The two image sensors are controlled by the same integrated circuit, ensuring highly synchronized profile data acquisition. The T-shaped compact three-laser profiler designed for dynamic detection of track geometric parameters, utilizing a cross-optical-path dual-laser profiler, can save hardware costs, reduce equipment size, and improve system stability. The study investigates a measurement model for track geometric parameters (gauge, alignment, elevation, and level) suitable for the aforementioned T-shaped compact three-laser profile track detection system structure, ignoring system errors below the system's measurement accuracy. Since laser profilers are susceptible to environmental interference, this invention, compared to existing solutions, reduces the number of sensors, improves the stability of the measurement model, and enables accurate measurement of track geometric parameters under low-speed conditions.

[0069] Further reference Figure 7 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of an image processing apparatus, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0070] like Figure 7 As shown, the image processing device 700 of this embodiment includes: an information acquisition unit 701, a displacement parameter determination unit 702, an angle parameter determination unit 703, and a related parameter determination unit 704.

[0071] The information acquisition unit 701 is configured to acquire a first image sequence, a second image sequence, a third image sequence, and a set of attitude information collected at each sampling point by a track geometry parameter measuring device installed on the train during the train's travel on the rails.

[0072] The displacement parameter determination unit 702 is configured to determine the displacement parameters of the rail at each sampling point based on the first image sequence, the second image sequence, and the third image sequence.

[0073] The angle parameter determination unit 703 is configured to determine the angle parameters of the rail based on the set of attitude information.

[0074] The relevant parameter determination unit 704 is configured to determine the relevant parameters of the rail based on each displacement parameter and each angle parameter.

[0075] In summary, the technical solution disclosed herein utilizes three lasers and three corresponding image acquisition units to capture images of the rails on which the train is traveling. Combined with attitude information measured by the inertial measurement unit on the train, the relevant parameters of the rails can be measured. This technical solution achieves accurate measurement of rail-related parameters with a small amount of hardware.

[0076] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A device for measuring track geometry parameters, characterized in that, include: First laser, second laser, third laser, first image acquisition unit, second image acquisition unit, third image acquisition unit, inertial measurement unit, odometer, controller, and mounting beam; The first laser, the second laser, the third laser, the first image acquisition unit, the second image acquisition unit, the third image acquisition unit, the inertial measurement unit, and the controller are mounted on the mounting beam, which is fixed to the bottom of the train. The first laser, the second laser, the first image acquisition device, and the second image acquisition device are installed at the first end of the mounting beam. The first laser and the second laser emit lasers toward the right track in the direction of train travel. The first image acquisition device and the second image acquisition device are used to acquire images of the right track to obtain a first image and a second image. The third laser and the third image acquisition device are installed at the second end of the mounting beam. The third laser emits a laser beam toward the left track in the direction of train travel, and the third image acquisition device is used to acquire an image of the left track in the direction of train travel to obtain a third image. The odometer is used to count the mileage traveled by the train; The controller is connected to the first laser, the second laser, the third laser, the first image acquisition unit, the second image acquisition unit, the third image acquisition unit, the odometer, and the inertial measurement unit. It is used to determine sampling points based on the driving mileage, and control the first laser, the second laser, and the third laser to emit lasers simultaneously at the sampling points. It also controls the first image acquisition unit, the second image acquisition unit, and the third image acquisition unit to perform image acquisition simultaneously, and controls the inertial measurement unit to acquire attitude information simultaneously.

2. The track geometry parameter measuring device according to claim 1, characterized in that, The fields of view of the first image acquisition device and the second image acquisition device overlap; The first angle between the optical axis of the first laser and the optical axis of the first image acquisition device, and the second angle between the optical axis of the second laser and the optical axis of the second image acquisition device, belong to a preset angle range.

3. The track geometry parameter measuring device according to claim 1, characterized in that, The inertial measurement unit is located on the centerline between the first laser and the second laser, and at the center of the mounting beam, the center of which coincides with the centerline of the train.

4. The track geometry parameter measuring device according to claim 1, characterized in that, The controller is used to determine the location of the train at each preset mileage distance as the sampling point based on the statistical mileage, and to emit laser emission commands to the first laser, the second laser and the third laser at the sampling point, send image acquisition commands to the first image acquisition unit, the second image acquisition unit and the third image acquisition unit, and send information acquisition commands to the inertial measurement unit, wherein the preset mileage is the same as the distance between the first laser and the second laser.

5. An image processing method, applied to the track geometry parameter measuring device as described in any one of claims 1-4, characterized in that, The method includes: The train travels on the rails and acquires a set of first image sequences, second image sequences, third image sequences, and attitude information collected at various sampling points by a track geometry parameter measuring device installed on the train. Based on the first image sequence, the second image sequence, and the third image sequence, the displacement parameters of the rail at each sampling point are determined; The angle parameters of the rail are determined based on the set of attitude information. Based on the displacement parameters and angle parameters, the relevant parameters of the rail are determined.

6. The method according to claim 5, characterized in that, Determining the displacement parameters of the rail at each sampling point based on the first image sequence, the second image sequence, and the third image sequence includes: Based on the first image sequence and / or the second image sequence, determine the first lateral displacement, the second lateral displacement, and the first vertical displacement and the second vertical displacement of the second feature point of the right track at each sampling point; Based on the third image sequence, the sampling points determine the third lateral displacement of the first feature point on the left track and the third vertical displacement of the second feature point at each sampling point.

7. The method according to claim 6, characterized in that, Determining the angle parameters of the rail based on the attitude information set includes: Based on the attitude information set, the heading angle and roll angle of the mounting beam at each sampling point are determined.

8. The method according to claim 7, characterized in that, The process of determining the relevant parameters of the rail based on each displacement parameter and each angle parameter includes: The rail orientation is determined based on each first lateral displacement, each second lateral displacement, each third lateral displacement, and each heading angle. The height of the rail is determined based on each first vertical displacement, each second vertical displacement, each third vertical displacement, and each roll angle.

9. The method according to claim 7, characterized in that, The step of determining the rail orientation based on each first lateral displacement, each second lateral displacement, each third lateral displacement, and each heading angle includes: Based on each first lateral displacement, each second lateral displacement, each third lateral displacement, and each heading angle, determine the spatial coordinates of the first feature points of the left and right rails of the steel rail; The spatial coordinates of the first feature points on the left and right tracks are filtered to determine the rail orientation. The determination of the rail height based on each first vertical displacement, each second vertical displacement, each third vertical displacement, and each roll angle includes: Based on each first vertical displacement, each second vertical displacement, each third vertical displacement, and each roll angle, the spatial coordinates of the second feature points of the left and right rails of the rail are determined. The spatial coordinates of the second feature points on the left and right tracks are filtered to determine the height of the rails.

10. An image processing apparatus, comprising: The information acquisition unit is configured to acquire a first image sequence, a second image sequence, a third image sequence, and a set of attitude information collected at each sampling point by a track geometry parameter measuring device installed on the train during the train's travel on the rails. The displacement parameter determination unit is configured to determine the displacement parameters of the rail at each sampling point based on the first image sequence, the second image sequence, and the third image sequence. An angle parameter determination unit is configured to determine the angle parameters of the rail based on the set of attitude information. The relevant parameter determination unit is configured to determine the relevant parameters of the rail based on each displacement parameter and each angle parameter.

Images