Monitoring method and device for measuring track line shape based on laser and image fusion

Abstract

The invention relates to the technical field of railway monitoring, and particularly discloses a monitoring method and device for measuring a track line shape based on laser and image fusion, and the method comprises the steps: S1, controlling an array distance measuring sensor to emit a laser beam to a target according to a preset time period, and receiving a returned laser beam; s2, calculating the transverse displacement variation of the monitoring point according to the transmitting time and the receiving time of the laser beam; s3, controlling the camera to collect a reference surface image of the target according to a preset time period; s4, determining a target image in the reference surface image according to a template matching method, and taking the vertical displacement of the target image in a preset time period as the vertical displacement variation of the monitoring point; s5, curve fitting is carried out according to the transverse displacement variable quantity and the vertical displacement variable quantity of the multiple monitoring points in the monitoring section, and the track line shape in the monitoring section is obtained.

Description

Technical Field

[0001] The invention relates to the technical field of railway monitoring, and in particular to a monitoring method and device for measuring track linearity based on laser and image fusion. Background Art

[0002] The differences in railway lines are determined by many factors, such as long railway lines, diverse geological conditions, and complex climates. In particular, large-span bridges, earthquake fault zones, and rock burst sections are prone to uneven settlement, which leads to changes in track alignment and uneven track structures, posing a major risk to train operation safety.

[0003] At present, in response to changes in track alignment, the railway operation and maintenance department mainly uses methods such as manual inspection of track inspection vehicles at skylight points, running inspection of track inspection vehicles, and measurement of prisms using theodolites. These methods are all fixed-cycle inspections and cannot be monitored online in real time, and the track alignment status during daytime train operation time cannot be grasped.

[0004] With the development of technology, in recent years, some research institutions have also developed online monitoring devices for track alignment based on optical fiber, GPS, inclinometers and other equipment. However, these technologies have disadvantages such as difficult installation and construction, single monitoring content, and long monitoring cycle. At the same time, affected by factors such as complex track structure and multi-dimensional linear changes, a single technology cannot fully and accurately monitor sudden changes in track alignment, and multiple technical means are required for joint monitoring. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide a monitoring method and device for measuring track alignment based on laser and image fusion, which can monitor the vertical and lateral displacements of the track online, and issue warning information in time when the displacement change exceeds the set warning threshold, so as to guide the railway operation and maintenance department to make quick decisions and ensure the safety of vehicle operation.

[0006] The present invention provides a monitoring method for measuring track line shape based on laser and image fusion, comprising:

[0007] Step S1, controlling the array ranging sensor to emit a laser beam to a target according to a preset time period, and receiving a returned laser beam;

[0008] Step S2, calculating the lateral displacement change of the monitoring point according to the emission time and the reception time of the laser beam;

[0009] Step S3, controlling the camera to collect the reference surface image of the target according to the preset time period;

[0010] Step S4, determining a target image in the reference plane image according to a template matching method, and taking the vertical displacement of the target image in a preset time period as the vertical displacement variation of the monitoring point;

[0011] Step S5, performing curve fitting according to the lateral displacement changes and vertical displacement changes of multiple monitoring points in the monitoring section to obtain the track line shape in the monitoring section.

[0012] In a possible implementation, the S4 includes:

[0013] Step S41, obtaining a template image;

[0014] Step S42, searching the reference plane image for a target image having the highest similarity to the template image according to the template image; the target image has an acquisition time;

[0015] Step S43, calculating the vertical displacement change of the monitoring point according to the position of the target image at the current moment and the position of the previous target image at a preset time period from the current moment.

[0016] In a possible implementation, the S42 includes:

[0017] Step S421, obtaining the image size of the template image, and traversing images of the same size in the reference surface image according to the image size of the template image;

[0018] Step S422, comparing the similarities between the template image and the image one by one, and taking the image with the highest similarity as the target image.

[0019] In a possible implementation, the S422 includes:

[0020] The similarity between the template image and the image is compared according to a square difference matching method, a correlation matching method, a correlation coefficient method, a normalized square difference, a normalized correlation, or a normalized correlation coefficient.

[0021] The present invention also provides a monitoring device for measuring track line shape based on laser and image fusion, which is used to implement any of the above-mentioned monitoring methods, and the monitoring device includes: an array ranging sensor, a host, a target, a mounting seat and a card block;

[0022] Wherein, the target is fixed on the monitored object through the clamping block;

[0023] The array distance measuring sensor is arranged on the top plane of the mounting seat, and the detection direction of the array distance measuring sensor is perpendicular to the reference plane of the target;

[0024] The array ranging sensor is used to detect the vertical displacement and the lateral displacement between the target and the array ranging sensor;

[0025] The host is used to calculate the vertical displacement change and the lateral displacement change of the monitored object according to the vertical displacement and the lateral displacement.

[0026] In a possible implementation, the array ranging sensor includes: a laser detection module and an image detection module, which respectively correspond to different areas of the plane of the target.

[0027] In a possible implementation, the array ranging sensor has an angle adjustment bracket for adjusting the pitch angle and the plane angle during monitoring.

[0028] In a possible implementation, a magnetic steel is arranged in front of the monitoring section in the direction of the oncoming vehicle, so as to filter out the lateral displacement change and the vertical displacement change when the vehicle passes.

[0029] In a possible implementation, the monitoring objects include rails, sleepers, and track plates.

[0030] In a possible implementation, the flatness of the target is less than 0.1 mm, and a marking pattern is provided on the plane of the target.

[0031] The monitoring method and device for measuring track linearity based on laser and image fusion provided by the present invention install one or more sets of ranging array devices on a relatively stable basic structure as needed, and install targets on the track accordingly, measure the relative displacement between the basic structure and the track in real time, calculate and analyze whether a sudden displacement of the track occurs, and issue a warning message in time when the displacement change exceeds a set warning threshold, so as to guide the railway operation and maintenance department to make quick decisions and ensure the safety of vehicle operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a monitoring method according to an embodiment of the present invention;

[0033] Figure 2 A schematic diagram of the layout of a monitoring device provided in an embodiment of the present invention;

[0034] Figure 3 A schematic top view of the layout of a monitoring device provided in an embodiment of the present invention;

[0035] Figure 4 A schematic diagram of the installation of an array ranging sensor provided in an embodiment of the present invention;

[0036] Figure 5 A schematic diagram of the installation of a target provided by an embodiment of the present invention;

[0037] Figure 6 A schematic diagram of the planar distribution of targets provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following detailed description of the embodiments of the present invention is further described in detail in conjunction with the accompanying drawings and examples. The detailed description of the following embodiments and the accompanying drawings are used to exemplarily illustrate the principles of the present invention, but cannot be used to limit the scope of the present invention, that is, the present invention is not limited to the preferred embodiments described, and the scope of the present invention is defined by the claims.

[0039] In the description of the present invention, it should be noted that, unless otherwise specified, “plurality” means two or more than two; the terms “first”, “second”, etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance; for ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0040] The present invention provides a monitoring device for measuring track line shape based on laser and image fusion, which is applied to any monitoring method, and one or more sets of monitoring devices are arranged along the track line direction; Figure 2 A schematic diagram of the front view of the monitoring device provided in an embodiment of the present invention, Figure 3 A schematic top view of the layout of a monitoring device provided in an embodiment of the present invention.

[0041] The monitoring device comprises: an array ranging sensor 1, a host, a target 2, a mounting seat 3 and a card block 4;

[0042] Figure 4 The schematic diagram of the installation of the array ranging sensor 1 provided in the embodiment of the present invention is as follows: Figure 4 As shown, the array ranging sensor 1 has an angle adjustment bracket 5 for adjusting the pitch angle and plane angle during monitoring;

[0043] Figure 5 The installation diagram of the target provided by the embodiment of the present invention is as follows: Figure 5 As shown, the target 2 is fixed on the monitored object through the clamp 4; the monitored object includes: rails, sleepers, and track plates; the array ranging sensor 1 is arranged on the top plane of the mounting seat 3, and the detection direction of the array ranging sensor 1 is perpendicular to the reference plane of the target 2. The array ranging sensor 1 is installed on a relatively stable reference body through a fixing seat, and the reference body can be a relatively stable structure such as a ballast retaining wall, a tunnel lining groove retaining wall, etc.

[0044] The array distance sensor 1 is used to detect the vertical displacement and lateral displacement between the target 2 and the array distance sensor 1;

[0045] The host can be installed on or near the array ranging sensor 1, or can be a cloud. The host is used to calculate the vertical displacement change and the lateral displacement change of the monitored object according to the vertical displacement and the lateral displacement.

[0046] Figure 6A schematic diagram of the planar distribution of targets provided in an embodiment of the present invention is shown in FIG. Figure 6 As shown, the array ranging sensor 1 includes: a laser detection module and an image detection module, which correspond to different areas of the target 2 plane respectively to reduce the influence of the laser on image recognition.

[0047] In a possible implementation, a magnetic steel is arranged in front of the monitoring section in the direction of the oncoming vehicle, so as to filter out the lateral displacement change and the vertical displacement change when the vehicle passes.

[0048] In a possible implementation, the flatness of the target 2 is less than 0.1 mm to improve the ranging accuracy.

[0049] In a possible implementation, a marking pattern is provided on the plane of the target 2. The marking pattern is a two-dimensional code or a cross.

[0050] In a possible implementation, a protective cover 6 is provided at the front end of the array ranging sensor 1 and the target 2 to prevent rain, snow, etc. from changing the shape of the reference surface of the target 2 and causing inaccurate monitoring results.

[0051] Figure 1 A flow chart of a monitoring method provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the present invention provides a monitoring method for measuring track line shape based on laser and image fusion, comprising:

[0052] Step S1, controlling the array ranging sensor to emit a laser beam to a target according to a preset time period, and receiving a returned laser beam;

[0053] In one possible implementation, the preset time period is calculated based on parameters of a device for emitting a laser beam and collecting an image.

[0054] Step S2, calculating the lateral displacement change of the monitoring point according to the emission time and the reception time of the laser beam;

[0055] In one possible approach, based on the principle that the speed of light propagating in the air is constant, the distance the light propagates in the air is calculated through the time difference between the emission time and the reception time of the laser beam, and the lateral displacement change of the monitoring point is obtained.

[0056] Step S3, controlling the camera to collect a reference surface image of the target according to a preset time period;

[0057] After acquisition, in order to provide a reference surface image for recognition accuracy, the reference surface image is first preprocessed.

[0058] Step S4, determining the target image in the reference plane image according to the template matching method, and taking the vertical displacement of the target image in a preset time period as the vertical displacement change of the monitoring point;

[0059] In a possible implementation, S4 includes:

[0060] Step S41, obtaining a template image;

[0061] In a possible implementation, the template image can be set according to user requirements.

[0062] In one example, the template image is a cross or a two-dimensional code, which is consistent with the pattern of the target plane, so as to improve the recognition accuracy of the medium array ranging sensor.

[0063] Step S42, searching the reference plane image for a target image having the highest similarity to the template image according to the template image; the target image has an acquisition time;

[0064] In a possible implementation, S42 includes:

[0065] Step S421, obtaining the image size of the template image, and traversing the images of the same size in the reference surface image according to the image size of the template image;

[0066] Step S422, comparing the similarities between the template image and the image one by one, and taking the image with the highest similarity as the target image.

[0067] In a possible implementation, the similarity between the template image and the image is compared according to a square difference matching method, a correlation matching method, a correlation coefficient method, a normalized square difference, a normalized correlation, or a normalized correlation coefficient.

[0068] In one example, the template image is an image of a pair of eyes, and the reference plane image is an image of a person's frontal face. Through traversal and comparison, the image of the eye part in the reference plane image is finally found as the target image.

[0069] Step S43, calculating the vertical displacement change of the monitoring point according to the position of the target image at the current moment and the position of the previous target image at a preset time period from the current moment.

[0070] If the size of the input reference image is W*H and the size of the template image is w*h, the size of the return value is (W-w+1)*(H-h+1). When performing template matching, the template is traversed in the original image.

[0071] In the horizontal direction, the starting coordinate of the traversal is the first pixel value from the left of the reference plane image (the serial number starts from 1). The last comparison is when the template image is located at the rightmost side of the reference plane image, and the position of its upper left corner pixel is W-w+1. Therefore, the size of the return value in the horizontal direction is W-w+1, that is, the number of comparisons in the horizontal direction is W-w+1.

[0072] In the vertical direction, the starting coordinate of the traversal starts from the first pixel at the top of the reference image. When the template image is at the bottom of the original image during the last comparison, the position of its upper left corner pixel is H-h+1.

[0073] Therefore, the size of the return value in the vertical direction is H-h+1, that is, the number of comparisons in the vertical direction is H-h+1.

[0074] Therefore, if the size of the reference plane image is W*H and the size of the template image is w*h, the size of the return value is (W-w+1)*(H-h+1), and the template image needs to be compared with the reference plane image (W-w+1)*(H-h+1) times.

[0075] Step S5, performing curve fitting according to the lateral displacement changes and vertical displacement changes of multiple monitoring points in the monitoring section to obtain the track line shape in the monitoring section.

[0076] Railway tracks directly carry wheels and guide trains. The geometry of the track must be closely matched with the geometry of the locomotive wheelset. Therefore, the control of track geometry is very important to ensure the safety of train operation. In addition, with the increase in train speed and the application of high-speed railway technology, in order to maintain the stability and comfort of high-speed train operation, the geometry of the track must also be strictly controlled. Track alignment refers to the geometry, relative position and basic dimensions of each part of the track.

[0077] This non-contact measurement reduces the number of devices installed on the track and does not require the laying of cables on the track. It can be used to monitor the linear changes of special sections of the track in real time and provide technical support for driving safety. The monitoring method of the present invention is of great significance to track safety.

[0078] The following are multiple application scenarios of the monitoring device for measuring track line shape based on laser and image fusion provided by the present invention.

[0079] Embodiment 1

[0080] The monitoring device of the present invention can also be used to monitor whether a bridge is deformed, mainly for monitoring the displacement of the bridge beam and the pier.

[0081] In one example, the span style of the bridge is 16×32m reinforced concrete prestressed simply supported box girder. The whole bridge has 15 piers, of which 1#, 4#-6#, 10#-15# piers are gravity piers, and 2#-3#, 7#-9# piers are hollow piers.

[0082] Assuming that the elevation of the upward line section K1951+760~K1952+390 changed little between March 15, 2020 and June 15, 2018, there was a significant change in elevation between April 15, 2021 and March 15, 2020. The largest change was at mileage K1952+080 (near Pier 8#), where the elevation decreased by 22.5mm.

[0083] The elevation of the downline section K1951+760~K1952+390 decreased slightly by about 5mm on March 15, 2020 compared with June 15, 2018. The elevation decreased significantly on April 15, 2021 compared with March 15, 2020, with the maximum peak at mileage K1952+082 (near Pier 8#), and the elevation decreased by 21.7mm.

[0084] By analyzing the elevation change data of the uplink and downlink lines,

[0085] 1) The elevation change trends of the up and down routes are basically the same;

[0086] 2) The section from Pier 3# to Pier 14# (1952+247~1951+895) has a large elevation change and is a high-risk section.

[0087] Assuming that the plane of the upline section K1951+760~K1952+381 changed little between March 15, 2020 and June 15, 2018, there was a significant change between April 15, 2021 and March 15, 2020. The largest change was at mileage K1952+068 (between piers 7# and 8#), with a plane deviation (left deviation in the mileage direction) of 35.0 mm.

[0088] The plane of the downline section K1951+760~K1952+395 changed little between March 15, 2020 and June 15, 2018. There was a significant change between April 15, 2021 and March 15, 2020. The largest change was at mileage K1952+067 (between piers 7# and 8#), with a plane deviation (left deviation in the mileage direction) of 35.8mm.

[0089] The following conclusions are drawn from the analysis of the uplink and downlink line plane change data:

[0090] 1) The change trends of the uplink and downlink planes are basically the same;

[0091] 2) The section from Pier 3# to Pier 14# (1952+247~1951+895) has large changes in plane and is a high-risk section.

[0092] The conclusions obtained through analysis can be used to provide early warning to staff, facilitate timely maintenance, and improve facility safety.

[0093] Embodiment 2

[0094] The monitoring device of the present invention can also be used to monitor the relative displacement changes between the track and the bridge beam.

[0095] Drill holes on the beam groove retaining wall, and use chemical anchors or bolts to securely fix the laser array sensor, bracket and protective cover. Use bolts to securely fix the rail fixture and target on the corresponding rails in the transverse direction.

[0096] The laser array sensor monitors the displacement between the sensor and the target in real time. When the track and the beam undergo relative displacement, the laser array sensor measures the change in relative displacement between the track and the bridge beam in real time.

[0097] Embodiment 3

[0098] The monitoring device of the present invention can also be used to monitor the relative displacement change between the track and the tunnel infrastructure.

[0099] Drill holes in the tunnel infrastructure and secure the laser array sensor, bracket and protective cover with chemical anchors or bolts. Secure the rail fixture and target with bolts on the corresponding rails.

[0100] The laser array sensor monitors the displacement between the sensor and the target in real time. When the track and the tunnel infrastructure undergo relative displacement, the laser array sensor measures the change in relative displacement between the track and the tunnel infrastructure in real time.

[0101] The monitoring method and device for measuring track linearity based on laser and image fusion provided by the present invention install one or more sets of ranging array devices on a relatively stable basic structure as needed, and install targets on the track accordingly, measure the relative displacement between the basic structure and the track in real time, calculate and analyze whether a sudden displacement of the track occurs, and issue a warning message in time when the displacement change exceeds a set warning threshold, so as to guide the railway operation and maintenance department to make quick decisions and ensure the safety of vehicle operation.

[0102] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A monitoring method for measuring track line shape based on laser and image fusion, characterized in that: include: Step S1, controlling the array ranging sensor to emit a laser beam to a target according to a preset time period, and receiving a returned laser beam; Step S2, calculating the lateral displacement change of the monitoring point according to the emission time and the reception time of the laser beam; Step S3, controlling the camera to collect the reference surface image of the target according to the preset time period; Step S4, determining a target image in the reference plane image according to a template matching method, and taking the vertical displacement of the target image in a preset time period as the vertical displacement variation of the monitoring point; Step S5, performing curve fitting according to the lateral displacement changes and vertical displacement changes of multiple monitoring points in the monitoring section to obtain the track line shape in the monitoring section.

2. The monitoring method according to claim 1, characterized in that: The S4 includes: Step S41, obtaining a template image; Step S42, searching the reference plane image for a target image having the highest similarity to the template image according to the template image; the target image has an acquisition time; Step S43, calculating the vertical displacement change of the monitoring point according to the position of the target image at the current moment and the position of the previous target image at a preset time period from the current moment.

3. The monitoring method according to claim 2, characterized in that: The S42 includes: Step S421, obtaining the image size of the template image, and traversing images of the same size in the reference surface image according to the image size of the template image; Step S422, comparing the similarities between the template image and the image one by one, and taking the image with the highest similarity as the target image.

4. The monitoring method according to claim 3, characterized in that: The S422 includes: The similarity between the template image and the image is compared according to a square difference matching method, a correlation matching method, a correlation coefficient method, a normalized square difference, a normalized correlation, or a normalized correlation coefficient.

5. A monitoring device for measuring track line shape based on laser and image fusion, characterized in that: Used to implement the monitoring method described in any one of claims 1 to 4, the monitoring device comprises: an array ranging sensor, a host, a target, a mounting seat and a card block; Wherein, the target is fixed on the monitored object through the clamping block; The array ranging sensor is arranged on the top plane of the mounting seat, and the detection direction of the array ranging sensor is perpendicular to the reference plane of the target; The array ranging sensor is used to detect the vertical displacement and the lateral displacement between the target and the array ranging sensor; The host is used to calculate the vertical displacement change and the lateral displacement change of the monitored object according to the vertical displacement and the lateral displacement.

6. The monitoring device according to claim 5, characterized in that: The array ranging sensor comprises: a laser detection module and an image detection module, which respectively correspond to different areas of the plane of the target.

7. The monitoring device according to claim 5, characterized in that: The array ranging sensor has an angle adjustment bracket for adjusting the pitch angle and plane angle during monitoring.

8. The monitoring device according to claim 5, characterized in that: Magnetic steel is arranged in front of the monitoring section in the direction of the oncoming vehicle, so as to filter out the lateral displacement change and the vertical displacement change when the vehicle passes.

9. The monitoring device according to claim 5, characterized in that: The monitoring objects include rails, sleepers and track plates.

10. The monitoring device according to claim 5, characterized in that: The flatness of the target is less than 0.1 mm, and a marking pattern is arranged on the plane of the target.

Images