Wear detection method, device, medium and equipment for rail section in turnout area

Abstract

The present specification discloses a wear detection method, device, medium and equipment for a rail section in a turnout area, and relates to the field of rail detection technology. A rail section template and a plurality of section point cloud data corresponding to a preset rail position can be obtained, and then at least two overlapping point cloud segments belonging to different section point cloud data and corresponding to overlapping areas are intercepted from the plurality of section point cloud data. For each overlapping area, at least two overlapping point cloud segments corresponding to the overlapping area are fused into a fused point cloud segment. The determined fused point cloud segment is spliced ​​with the plurality of section point cloud data after intercepting at least two overlapping point cloud segments to determine the section fusion data. According to the section fusion data and the rail section template, the wear data of the rail at the preset rail position is determined. It can be seen that by processing the data by intercepting overlapping point cloud segments, fusing and splicing, the fused point cloud segment after fusion is closer to the actual situation, thereby improving the accuracy of wear measurement.

Description

Technical Field

[0001] The present specification relates to the technical field of rail detection, and in particular to a method, device, medium and equipment for detecting wear of a rail section in a turnout area. Background Art

[0002] The rails laid on the road surface in the railway system can constrain the forward direction of the train wheels, but they often wear out during long-term use. In particular, the rails located in the switch area need to bear the friction caused by the train track change, which aggravates the wear. When the wear accumulates to a certain extent, it may affect the operation of the train and pose a safety hazard. Therefore, it is necessary to measure the wear of the rails.

[0003] In the prior art, when measuring the wear of a rail, a plurality of acquisition devices are usually required to acquire the cross-sectional profile data of the rail, and the data acquired by the plurality of acquisition devices are spliced.

[0004] However, the splicing method in the prior art is relatively rough, which often leads to low accuracy in wear measurement. Summary of the invention

[0005] The present specification provides a method, device, medium and equipment for detecting wear of a rail section in a turnout area, so as to at least partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This specification provides a method for detecting wear of a rail section in a turnout area, including:

[0008] Acquire a rail section template and a plurality of section point cloud data corresponding to a preset rail position; the plurality of section point cloud data are respectively acquired by a plurality of acquisition devices with different positions, and the areas corresponding to adjacent section point cloud data are at least partially overlapped;

[0009] From the plurality of cross-sectional point cloud data, at least two overlapping point cloud segments that belong to different cross-sectional point cloud data and whose corresponding areas overlap are intercepted; the at least two overlapping point cloud segments correspond to at least one overlapping area, and each overlapping area corresponds to at least two overlapping point cloud segments;

[0010] For each overlapping area, merging at least two overlapping point cloud segments corresponding to the overlapping area into a fused point cloud segment;

[0011] splicing the fused point cloud segment with a plurality of cross-section point cloud data obtained after intercepting the at least two overlapping point cloud segments to determine cross-section fused data;

[0012] The wear data of the rail at the preset rail position is determined according to the section fusion data and the rail section template.

[0013] Preferably, before intercepting at least two overlapping point cloud segments respectively belonging to different cross-section point cloud data and having overlapping corresponding areas, the method further comprises:

[0014] Based on the coordinate conversion parameters of different acquisition devices, the plurality of cross-sectional point cloud data are converted into a preset coordinate system;

[0015] According to the coordinates of multiple target points included in each cross-section point cloud data, the overlapping point cloud segments where the cross-section point cloud data overlaps with the areas corresponding to other cross-section point cloud data are determined from each cross-section point cloud data.

[0016] Preferably, the step of fusing at least two overlapping point cloud segments corresponding to the overlapping area into a fused point cloud segment includes:

[0017] The multiple target points contained in any one of the overlapping point cloud segments are determined as search points, and the multiple target points contained in other overlapping point cloud segments are determined as free points;

[0018] For any search point, determine the free point closest to it according to the coordinates of the search point and the coordinates of the plurality of free points;

[0019] When it is determined that the distance between the free point and the search point is less than a preset distance threshold, both the free point and the search point are determined as points to be fused;

[0020] According to the determined coordinates of the multiple points to be fused, the fusion point coordinates of at least one fusion point are determined, and the point cloud area composed of the at least one fusion point is determined as a fusion point cloud segment.

[0021] Preferably, the step of determining the fusion point coordinates of at least one fusion point according to the determined coordinates of the plurality of points to be fused comprises:

[0022] According to the determined coordinates of the multiple points to be fused, determine the target distance between any two points to be fused, and the target angle between the vector formed by the any two points to be fused and the preset direction;

[0023] Based on the target distance and the target angle, the multiple points to be fused are divided into multiple fusion groups, where the fusion group includes at least two points to be fused;

[0024] For each fusion group, based on the coordinates of at least two points to be fused in the fusion group, a fusion point coordinate of a fusion point is determined.

[0025] Preferably, the step of determining the fusion point coordinates of at least one fusion point according to the determined coordinates of the plurality of points to be fused comprises:

[0026] Based on preset regional parameters, the point cloud area to be fused, which is composed of the determined multiple points to be fused, is divided into multiple downsampling areas; the regional parameters include the side length of the area and / or the radius of the area;

[0027] Determine the coordinates of the centroid of each downsampling area according to the coordinates of the multiple points to be fused respectively included in the multiple downsampling areas;

[0028] The centroid of each downsampled area is determined as the fusion point.

[0029] Preferably, the step of obtaining the rail section template includes:

[0030] Obtain standard rail section and rail layout data;

[0031] Determining the working side and the non-working side of the rail corresponding to the standard rail section according to the rail layout data;

[0032] From the standard rail section, a portion corresponding to the non-working edge is cut off as a rail section template; the rail section template corresponds to the rail head side, rail waist, at least part of the rail head tread and at least part of the rail bottom surface.

[0033] Preferably, the step of obtaining a plurality of cross-section point cloud data corresponding to preset rail positions includes:

[0034] Obtain continuously collected continuous cross-section data and rail layout data;

[0035] According to the preset rail position, determining the instantaneous section data corresponding to the preset rail position from the continuous section data; the instantaneous section data corresponds to at least two rails;

[0036] According to the rail layout data, a plurality of cross-section point cloud data matching the rail cross-section template are determined from the instantaneous cross-section data.

[0037] Preferably, the determining the wear data of the rail at the preset rail position according to the cross-section fusion data and the rail cross-section template includes:

[0038] By using a preset algorithm, the cross-section fusion data is matched with the rail cross-section template, and a matching mapping matrix is ​​determined; wherein the cross-section fusion data corresponds to a preset coordinate system, and the rail cross-section template corresponds to a template coordinate system;

[0039] Determine the coordinates of the vertical wear measurement point and the horizontal wear measurement point in the template coordinate system according to the width of the rail head of the rail section template and the coordinates of the highest point of the rail head tread;

[0040] According to the matching mapping matrix, mapping the vertical wear measurement points and the horizontal wear measurement points to the preset coordinate system;

[0041] Determine the vertical wear value and the horizontal wear value respectively according to the coordinates of each target point in the cross-section fusion data, and the coordinates of the vertical wear measurement point and the horizontal wear measurement point;

[0042] The vertical wear value and the horizontal wear value are determined as the wear data of the rail section.

[0043] Preferably, matching the cross-section fusion data with the rail cross-section template by a preset algorithm includes:

[0044] Based on a paired point feature algorithm, matching the cross-section fusion data with the rail cross-section template;

[0045] Based on the iterative closest point algorithm, the initial mapping matrix between the section fusion data and the rail section template is fine-tuned to determine the matching mapping matrix, and the section fusion data is made to fit the rail section template.

[0046] On the other hand, the present specification provides a wear detection device for a rail section in a turnout area, comprising:

[0047] An acquisition unit is used to acquire a rail section template and a plurality of section point cloud data corresponding to a preset rail position; the plurality of section point cloud data are respectively acquired by a plurality of acquisition devices with different positions, and the areas corresponding to adjacent section point cloud data are at least partially overlapped;

[0048] A cutting unit is used to cut at least two overlapping point cloud segments which belong to different cross-sectional point cloud data and whose corresponding areas overlap from the multiple cross-sectional point cloud data; the at least two overlapping point cloud segments correspond to at least one overlapping area, and each overlapping area corresponds to at least two overlapping point cloud segments;

[0049] a fusion unit, for fusing, for each overlapping area, at least two overlapping point cloud segments corresponding to the overlapping area into a fused point cloud segment;

[0050] A splicing unit, used for splicing the fused point cloud segment with a plurality of cross-section point cloud data obtained after intercepting the at least two overlapping point cloud segments, to determine cross-section fused data;

[0051] The calculation unit is used to determine the wear data of the rail at the preset rail position according to the section fusion data and the rail section template.

[0052] On the other hand, the computer-readable storage medium provided in this specification stores a computer program, and when the computer program is executed by a processor, the wear detection method for the rail section in the switch area provided in the above aspect is implemented.

[0053] On the other hand, the present specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for detecting wear of a rail section in a switch area provided in the above aspect is implemented.

[0054] On the other hand, the present specification provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device implements the wear detection method for the rail section in the switch area provided in the above aspect.

[0055] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0056] based on Figure 1 The wear detection method of the rail section in the turnout area shown in the figure, the electronic device can obtain the rail section template and multiple section point cloud data corresponding to the preset rail position, and then intercept at least two overlapping point cloud segments that belong to different section point cloud data and overlap in the corresponding areas from the multiple section point cloud data. For each overlapping area, the at least two overlapping point cloud segments corresponding to the overlapping area are fused into a fused point cloud segment, and then the determined fused point cloud segment is spliced ​​with the multiple section point cloud data after intercepting the at least two overlapping point cloud segments to determine the section fused data. Finally, the wear data of the rail at the preset rail position is determined based on the section fused data and the rail section template.

[0057] It can be seen from the above method that in order to solve the problem that the areas corresponding to the multiple cross-sectional point cloud data collected partially overlap and there are deviations in the multiple cross-sectional point cloud data corresponding to the overlapping areas, the electronic device can process the overlapping point cloud segments by intercepting, fusing and splicing them, so that the fused point cloud segments after fusion are closer to the actual situation, thereby improving the accuracy of wear measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0059] Figure 1 A schematic flow chart of a method for detecting wear of a rail section in a turnout area provided as an embodiment of the present specification;

[0060] Figure 2 A schematic diagram of cross-sectional point cloud data provided for one embodiment of this specification;

[0061] Figure 3 A schematic diagram of a process for intercepting overlapping point cloud segments provided in one embodiment of the present specification;

[0062] Figure 4 A schematic diagram of cross-section splicing provided for one embodiment of this specification;

[0063] Figure 5 A schematic diagram of cross-sectional wear of a rail provided in one embodiment of this specification;

[0064] Figure 6 A schematic diagram of a rail section template provided for one embodiment of this specification;

[0065] Figure 7 A schematic diagram of wear measurement provided for one embodiment of this specification;

[0066] Figure 8 A schematic flow chart of a method for detecting wear of a rail section in a turnout area provided as an embodiment of the present specification;

[0067] Fig. 9 A schematic diagram of the structure of a wear detection device for a rail section in a turnout area provided in one embodiment of the present specification;

[0068] Fig.10 A schematic diagram of the structure of an electronic device provided for one embodiment of the present specification. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0070] In the description of the present invention, it should be noted that the term "or" is generally used in a meaning including "and / or", unless the content clearly indicates otherwise.

[0071] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. In addition, in the description of the present application, the terms "first", "second" and the like are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0072] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0074] Figure 1 A schematic flow chart of a method for detecting wear of a rail section in a turnout area provided as an embodiment of the present specification is shown in FIG. Figure 1 As shown, the method specifically comprises the following steps:

[0075] S100: Acquire a rail section template and a plurality of section point cloud data corresponding to preset rail positions.

[0076] In one or more embodiments of this specification, the method may be executed by an electronic device. The electronic device may be a computer, a server, a control center, etc. This specification does not limit the specific model or type of the electronic device.

[0077] Preferably, the electronic device can obtain a rail section template.

[0078] It is understood by those skilled in the art that when performing rail wear detection, it is usually necessary to download a standard template from a relevant database. Therefore, the rail section template can also be downloaded from a relevant database.

[0079] Preferably, the electronic device can obtain a plurality of cross-sectional point cloud data corresponding to preset rail positions.

[0080] Preferably, the multiple cross-section point cloud data all correspond to a rail, and the rail may be a base rail, a center rail, a point rail, etc., or may be a combination of at least two of the base rail, the center rail, the point rail, etc.

[0081] Preferably, the plurality of cross-section point cloud data are spliced.

[0082] Preferably, the preset rail position is a preset setting, for example, a position 500 mm away from the tip of the point rail, a position 1000 mm away from the heel of the guard rail, etc.

[0083] Preferably, the cross-sectional point cloud data is collected by a collection device. Furthermore, those skilled in the art will appreciate that, due to the irregular shape of the rail, at least two collection devices are usually required to face different angles to complete the collection of the cross-sectional point cloud data. Furthermore, in order to collect data on the rail as completely as possible, when adjusting the angle of the collection device, the areas collected by the two collection devices will often overlap partially, thereby improving the integrity of the collected cross-sectional point cloud data.

[0084] Figure 2 A schematic diagram of cross-sectional point cloud data provided by an embodiment of this specification. Figure 2 As shown, there is an overlapping area 23 between the first point cloud 21 and the second point cloud 22 .

[0085] Therefore, in this specification, the multiple cross-sectional point cloud data acquired by the electronic device are respectively acquired by multiple acquisition devices with different postures, and the areas corresponding to adjacent cross-sectional point cloud data are at least partially overlapped.

[0086] It is understood by those skilled in the art that when multiple acquisition devices are collecting cross-sectional point cloud data of rails, due to the differences in objective factors such as the positions, orientations, and mapping matrices of different acquisition devices, there will often be deviations between the point cloud data collected by different acquisition devices. In other words, when different acquisition devices collect data from the same area, there will be deviations in the collected point cloud data. Figure 2 As shown, in the overlapping area, there is a deviation between the first point cloud and the second point cloud.

[0087] S102: From the plurality of cross-sectional point cloud data, at least two overlapping point cloud segments that belong to different cross-sectional point cloud data and whose corresponding areas overlap are intercepted.

[0088] In one or more embodiments of the present application, the electronic device can solve the problem of deviation in point cloud data obtained by different acquisition devices when acquiring the same area by splicing and fusion.

[0089] Preferably, in one or more preferred embodiments of the present specification, overlapping areas corresponding to different cross-sectional point cloud data are determined as overlapping areas.

[0090] Preferably, each overlapping area corresponds to at least two overlapping point cloud segments.

[0091] Preferably, the electronic device can extract at least two overlapping point cloud segments which belong to different cross-sectional point cloud data and whose corresponding areas overlap from the multiple cross-sectional point cloud data.

[0092] Those skilled in the art can understand that there may be multiple cross-sectional point cloud data, and the areas corresponding to any two adjacent cross-sectional point cloud data may partially overlap, so there may also be multiple overlapping areas.

[0093] Preferably, at least two overlapping point cloud segments intercepted by the electronic device correspond to at least one overlapping area.

[0094] Figure 3 A schematic diagram of a process for intercepting overlapping point cloud segments provided in one embodiment of this specification, such as Figure 3 The first overlapping point cloud segment 24 and the second overlapping point cloud segment 25 both correspond to the overlapping area 26 .

[0095] S104: For each overlapping area, merging at least two overlapping point cloud segments corresponding to the overlapping area into a fused point cloud segment.

[0096] Preferably, after determining at least one overlapping area, the electronic device may fuse at least two overlapping point cloud segments corresponding to each overlapping area.

[0097] Preferably, during the fusion process, the electronic device can perform splicing and fusion through algorithms such as iterative closest point (ICP) and Gaussian mixture model (GMM) to determine the fused point cloud segment and the coordinates of each fused point contained in the fused point cloud segment.

[0098] S106: splicing the fused point cloud segment with a plurality of cross-sectional point cloud data obtained after intercepting the at least two overlapping point cloud segments to determine cross-sectional fused data.

[0099] Preferably, after determining the coordinates of multiple fusion points contained in the fused point cloud segment, the electronic device can splice at least one determined fused point cloud segment with multiple section point cloud data obtained by intercepting at least two overlapping point cloud segments to determine the section fusion data.

[0100] It should be noted that the cross-section fusion data actually also includes point cloud data of multiple target points and fusion points.

[0101] Figure 4 A schematic diagram of cross-section splicing provided for one embodiment of this specification, such as Figure 4 The fused point cloud segment 27 is spliced ​​with a plurality of cross-sectional point cloud data 28 obtained by intercepting at least two overlapping point cloud segments to form cross-sectional fused data 29.

[0102] S108: Determine the wear data of the rail at the preset rail position according to the cross-section fusion data and the rail cross-section template.

[0103] Preferably, after the electronic device completes processing of multiple cross-section point cloud data and determines the cross-section fusion data, it can match and compare the cross-section fusion data with the rail cross-section data, thereby determining the wear data of the rail at the preset rail position.

[0104] Preferably, the electronic device can match the rail section template with the section fusion data so that the rail section template fits at least a partial area of ​​the section fusion data.

[0105] Preferably, the electronic device can also determine the wear data according to the coordinates of the preset wear measurement points and the coordinates of the multiple target points and the multiple fusion points included in the cross-section fusion data.

[0106] based on Figure 1 The wear detection method of the rail section in the turnout area shown in the figure, the electronic device can obtain the rail section template and multiple section point cloud data corresponding to the preset rail position, and then intercept at least two overlapping point cloud segments that belong to different section point cloud data and overlap in the corresponding areas from the multiple section point cloud data. For each overlapping area, the at least two overlapping point cloud segments corresponding to the overlapping area are fused into a fused point cloud segment, and then the determined fused point cloud segment is spliced ​​with the multiple section point cloud data after intercepting the at least two overlapping point cloud segments to determine the section fused data. Finally, the wear data of the rail at the preset rail position is determined based on the section fused data and the rail section template.

[0107] It can be seen from the above method that in order to solve the problem that the areas corresponding to the multiple cross-sectional point cloud data collected partially overlap and there are deviations in the multiple cross-sectional point cloud data corresponding to the overlapping areas, the electronic device can process the overlapping point cloud segments by intercepting, fusing and splicing them, so that the fused point cloud segments after fusion are closer to the actual situation, thereby improving the accuracy of wear measurement.

[0108] Preferably, when executing step S102, the electronic device may further process a plurality of cross-sectional point cloud data before intercepting at least two overlapping point cloud segments that belong to different cross-sectional point cloud data and whose corresponding areas overlap.

[0109] Specifically, the electronic device can convert the multiple cross-sectional point cloud data into a preset coordinate system based on the coordinate conversion parameters of different acquisition devices, wherein the preset coordinate system is a pre-set two-dimensional coordinate system.

[0110] The electronic device can also determine, from each cross-sectional point cloud data, overlapping point cloud segments where the cross-sectional point cloud data overlaps with areas corresponding to other cross-sectional point cloud data, based on the coordinates of multiple target points included in each cross-sectional point cloud data.

[0111] Those skilled in the art will appreciate that the technology for determining overlapping point cloud segments has been developed to a relatively mature level, and this description does not limit how to determine the overlapping point cloud segments.

[0112] For example, the electronic device may determine the overlapping point cloud segment in response to the user's operation. Alternatively, the electronic device may determine the distance between the target points belonging to different cross-sectional point cloud data based on the coordinates of the target points belonging to different cross-sectional point cloud data, and determine the two target points whose distance is less than a preset overlapping distance threshold as target points belonging to the overlapping point cloud segment, and then determine the partial point cloud data composed of the target points belonging to the overlapping point cloud segment as the overlapping point cloud segment.

[0113] Preferably, when executing step S104, the electronic device may also fuse at least two overlapping point cloud segments in the following manner.

[0114] Specifically, the electronic device can determine multiple target points included in any one of the overlapping point cloud segments as search points, and determine multiple target points included in other overlapping point cloud segments as free points.

[0115] For any search point, the free point closest to it is determined according to the coordinates of the search point and the coordinates of the multiple free points.

[0116] It is determined whether the distance between the free point and the search point is less than a preset distance threshold.

[0117] If so, both the free point and the search point are determined as points to be fused.

[0118] If not, no action is performed.

[0119] Finally, according to the determined coordinates of the multiple points to be fused, the fusion point coordinates of at least one fusion point are determined, and the point cloud area formed by the at least one fusion point is determined as a fusion point cloud segment.

[0120] When determining the fusion point based on multiple points to be fused, the electronic device may determine the fusion point in multiple ways.

[0121] For example, the electronic device may divide the point cloud area to be fused, which is composed of the determined multiple points to be fused, into multiple down-sampling areas based on preset area parameters. Then, according to the coordinates of the multiple points to be fused respectively included in the multiple down-sampling areas, the coordinates of the centroid of each down-sampling area are respectively determined. Finally, the centroid of each down-sampling area is determined as the fusion point. Among them, the area parameters include the area side length and / or area radius, etc.

[0122] For another example, the electronic device may determine the target distance between any two points to be fused, and the target angle between a vector formed by any two points to be fused and a preset direction according to the determined coordinates of the multiple points to be fused. And according to the target distance and the target angle, the multiple points to be fused are divided into multiple fusion groups, and any fusion group includes at least two points to be fused. Finally, for each fusion group, based on the coordinates of at least two points to be fused in the fusion group, the fusion point coordinates of a fusion point are determined.

[0123] When determining the coordinates of the fusion point, the average value or centroid of at least two to-be-fused points may be directly used as the coordinates of the fusion point. When grouping multiple to-be-fused points according to target distance and target angle, multiple to-be-fused points whose target angles are within a preset angle range and whose distances are within a preset distance range may be grouped into one fusion group. The preset direction is predetermined, or the preset direction is perpendicular to a plane formed by the to-be-fused point and multiple to-be-fused points adjacent to the to-be-fused point.

[0124] Preferably, any point to be fused belongs to at most one fusion group.

[0125] Preferably, there are at least two groups to be fused in any fusion group.

[0126] Preferably, if there is a point to be fused that is not classified into any fusion group, the point to be fused is discarded.

[0127] Preferably, all sites to be fused are grouped into fusion groups.

[0128] Preferably, when executing step S100, the electronic device can obtain the rail section template in the following manner.

[0129] Specifically, the electronic device can obtain standard rail sections and rail layout data, wherein the rail layout data includes acquisition position parameters, working edge setting parameters, and the position of the rail to be measured.

[0130] Among them, the collection position parameter is the cross-section collection position corresponding to each track type. For example, taking the position of the point rail tip, the guard rail toe end, the heart rail tip or the guard rail heel end as the starting point, 500mm, 1000mm, 3000mm, and 5000mm in the direction of the rail extension are all cross-section collection positions. The working edge setting parameter is which side of the rail is the working edge. It can be understood by those skilled in the art that, under normal circumstances, when a train is traveling on a track, only one side of the wheel with a flange will contact and rub against the rail, causing wear of the rail. In addition, since only one side of the wheel is provided with a flange, the rail often only has one side that is worn, and the side that is worn is the working side of the rail. Those skilled in the art can also understand that, rails are usually laid in pairs, but when measuring wear, only one of the rails may be measured. Therefore, the position of the rail to be measured is the relative position of the rail whose wear needs to be measured. For example, taking the tip of the center rail as the starting point, the rail relatively to the left in the direction in which the rails extend is the position of the rail to be measured.

[0131] It should be noted that both the working edge and the non-working edge refer to the boundaries of the outer surface of the rail section.

[0132] Figure 5 The cross-sectional wear diagram of a rail provided in one embodiment of this specification is shown in FIG. Figure 5 As shown, the outer surface of the rail section consists of a working edge 31 and a non-working edge 32. The working edge 31 is severely worn, while the non-working edge 32 is almost not worn.

[0133] Then, the electronic device can determine the working side and the non-working side of the rail corresponding to the standard rail section according to the rail layout data.

[0134] Finally, the electronic device can cut out a portion corresponding to the non-working edge from the standard rail section as a rail section template.

[0135] Preferably, the rail section template corresponds to the side surface of the rail head, the rail waist, at least a portion of the rail head tread and at least a portion of the rail bottom surface.

[0136] Figure 6 A schematic diagram of a rail section template provided for one embodiment of this specification. Figure 6 As shown, the rail section template 33 is not a complete rail section.

[0137] It can be seen that the rail section template not only includes the profile of the rail side, but also includes part of the rail head tread and part of the rail bottom surface. When fitting with the actual rail section data, it can constrain the actual rail section data in the vertical and horizontal directions to improve the accuracy of fitting. Among them, the horizontal direction is the extension direction of the rail bottom surface of the rail section data, and the vertical direction is the direction perpendicular to the rail bottom surface.

[0138] Preferably, when executing step S100, the electronic device may also obtain a plurality of cross-section point cloud data corresponding to the preset rail positions in the following manner.

[0139] Specifically, firstly, the electronic device can obtain continuously collected continuous cross-section data and rail layout data.

[0140] Secondly, the electronic device can determine the instantaneous cross-sectional data corresponding to the preset rail position from the continuous cross-sectional data according to the preset rail position. The preset rail position can be determined in response to the user's operation, or can be determined based on the cross-sectional acquisition position in the aforementioned rail layout data. In addition, rails usually appear in pairs, so the instantaneous cross-sectional data corresponds to at least two rails.

[0141] Finally, according to the position of the rail to be measured in the rail layout data, a plurality of cross-section point cloud data matching the rail cross-section template are determined from the instantaneous cross-section data.

[0142] Preferably, when executing step S108, the electronic device may determine the wear data in the following manner.

[0143] Specifically, first, the electronic device can match the cross-section fusion data with the rail cross-section template through a preset algorithm and determine a matching mapping matrix. The cross-section fusion data corresponds to a preset coordinate system, and the rail cross-section template corresponds to a template coordinate system. The template coordinate system is the coordinate system where the rail template is located, which can be a two-dimensional or three-dimensional coordinate system, and this specification does not limit this.

[0144] Secondly, the electronic device can determine the coordinates of the vertical wear measurement point and the horizontal wear measurement point in the template coordinate system according to the width of the rail head of the rail section template and the coordinates of the highest point of the rail head tread.

[0145] Thirdly, the electronic device may map the vertical wear measurement point and the horizontal wear measurement point to the preset coordinate system according to the matching mapping matrix.

[0146] Then, the electronic device can determine the vertical wear value and the horizontal wear value according to the coordinates of each target point in the cross-sectional fusion data, and the coordinates of the vertical wear measurement point and the horizontal wear measurement point, respectively. All points in the cross-sectional fusion data are target points.

[0147] Finally, the electronic device can determine the vertical wear value and the horizontal wear value as the wear data of the rail section.

[0148] For example, when determining the horizontal wear value, the electronic device can determine the highest point of the rail tread in the cross-section fusion data based on the coordinates of each target point in the cross-section fusion data. The highest point is the highest point in the vertical direction. An auxiliary line segment is created at a position 16 mm vertically downward from the highest point, and the direction of the line segment is parallel to the vertical direction. The intersection of the line segment and the working edge is the horizontal wear measurement point.

[0149] Then, through the matching mapping matrix, the horizontal wear measurement point is transformed into a preset coordinate system, and according to the coordinates of the transformed horizontal wear measurement point and the target point in the cross-section fusion data, the target point closest to the horizontal wear measurement point is determined as the measured side wear point, and the distance between the horizontal wear measurement point and the measured side wear point in the horizontal direction is determined as the horizontal wear value.

[0150] Alternatively, when determining the measured side wear point, the electronic device can also use the horizontal wear measurement point as the starting point and any target point in the cross-section fusion data as the end point to determine multiple vectors, and determine the measured side wear point based on the distance between each target point and the horizontal wear measurement point, and the angle between the vector corresponding to the target point and the horizontal direction.

[0151] Those skilled in the art will appreciate that the technology for determining the horizontal wear value has been relatively mature, and this specification does not limit the specific method for determining the horizontal wear value, and the above content is only for illustration.

[0152] For another example, when determining the vertical wear value, the electronic device may determine the vertical wear measurement point in different ways based on different rail head widths.

[0153] Firstly, the electronic device can determine the rail head width according to the coordinates of each target point in the cross-section fusion data.

[0154] When the rail head width is equal to 0, the electronic device can determine the highest point of the rail tread in the cross-section fusion data based on the coordinates of each target point in the cross-section fusion data. The highest point is the highest point in the vertical direction. And create an auxiliary line segment 16 mm vertically downward from the highest point, and the direction of the line segment is parallel to the vertical direction. And the distance between the two intersection points of the line segment with the working edge and the non-working edge is determined as the top surface width. Based on the top surface width, determine the first distance. The first distance can be half, one third, etc. of the top surface width. Finally, the first distance from the intersection of the line segment and the working edge, and the position on the line segment and between the working edge and the non-working edge is determined as the vertical wear measurement point.

[0155] When the rail head width is greater than or equal to 70 mm, first, the electronic device may segment the cross-section fusion data into basic rail cross-section data and other rail cross-section data based on a preset first segmentation point. The first segmentation point may be set by a user, or the rail layout data may include the first segmentation point.

[0156] Those skilled in the art can understand that when the rail head width is greater than or equal to 70 mm, it means that the section fusion data corresponds to a combined rail, which is composed of a basic rail and other rails, and the other rails may be a point rail, a heart rail, and the like.

[0157] Then, the electronic device can determine the highest point of the rail tread in the basic rail section data based on the coordinates of each target point in the basic rail section data. The highest point is the highest point in the vertical direction. And create an auxiliary line segment at a position 16 mm vertically downward from the highest point, and the direction of the line segment is parallel to the vertical direction. And the distance between the two intersection points of the line segment with the working edge and the non-working edge is determined as the top surface width. Based on the top surface width, the second distance is determined. The second distance can be half, one third, etc. of the top surface width. Finally, the second distance from the intersection of the line segment and the working edge, and the position on the line segment and between the working edge and the non-working edge is determined as the vertical wear measurement point.

[0158] When the rail head width is between 0-70 mm, first, the electronic device may segment the cross-section fusion data into basic rail cross-section data and other rail cross-section data based on a preset second segmentation point. The second segmentation point may be set by a user, or the rail layout data may include the second segmentation point.

[0159] Then, the electronic device can determine the highest point of the rail tread in the other rail section data based on the coordinates of each target point in the other rail section data. The highest point is the highest point in the vertical direction. And create an auxiliary line segment at a position 16 mm vertically downward from the highest point, and the direction of the line segment is parallel to the vertical direction. And the distance between the two intersection points of the line segment with the working edge and the non-working edge is determined as the top surface width. Based on the top surface width, the third distance is determined. The third distance can be one half, one third, etc. of the top surface width. Finally, the position at the third distance from the intersection of the line segment and the working edge and on the line segment and between the working edge and the non-working edge is determined as the vertical wear measurement point.

[0160] Preferably, after determining the vertical wear measurement point, the electronic device can transform the vertical wear measurement point to a preset coordinate system through the matching mapping matrix, and according to the coordinates of the transformed vertical wear measurement point and each target point in the cross-sectional fusion data, determine the target point closest to the vertical wear measurement point as the measured vertical wear point, and determine the distance between the vertical wear measurement point and the measured vertical wear point in the vertical direction as the vertical wear value.

[0161] Those skilled in the art will appreciate that the technology for determining the vertical wear value has been relatively mature, and this specification does not limit the specific method for determining the vertical wear value, and the above content is only for illustration.

[0162] Preferably, the above method of determining the vertical wear value and the horizontal wear value can be used to measure the wear of all rails in the turnout area, such as the wear of stock rails, wing rails, point rails, heart rails, combination rails and other rails.

[0163] Figure 7 A schematic diagram of wear measurement provided for one embodiment of this specification is shown in FIG. Figure 7 As shown, the cross-section fusion data 29 is compared with the complete rail cross-section template 45 to determine the horizontal wear measurement point 41 and the vertical wear measurement point 42, and then measure the horizontal wear value 43 and the vertical wear value 44. The distance between the auxiliary line segment 46 and the highest point of the rail tread is 16 mm.

[0164] Preferably, when the electronic device matches the cross-section fusion data with the rail cross-section template through a preset algorithm, the matching can be performed in the following manner.

[0165] First, the electronic device can preferentially match the cross-section fusion data with the rail cross-section template based on a paired point feature algorithm to determine an initial mapping matrix. It should be noted that this matching does not require the cross-section fusion data to fit the rail cross-section template perfectly, but is only for determining an initial mapping relationship.

[0166] Secondly, the electronic device can map the rail section template to the preset coordinate system based on the initial mapping matrix, and the preset coordinate system is the coordinate system carrying the section fusion data. In other words, the electronic device maps the rail section template to the preset coordinate system based on the initial mapping matrix, so that the section fusion data and the rail section template are in the same coordinate system.

[0167] Again, the electronic device can fine-tune the initial mapping matrix of the section fusion data and the rail section template both in the preset coordinate system based on the iterative closest point algorithm, determine the matching mapping matrix, and make the section fusion data fit the rail section template.

[0168] In addition, in one or more preferred embodiments provided in this specification, the rail layout data also includes the track direction. Those skilled in the art will appreciate that in the turnout area, the track can be changed during the train travel, that is, in the turnout area, the track is changed from one group to two or more groups, that is, one or more groups of tracks are added. For example, when the train travels to the track change point on track segment A, it can choose a section from track segment B and track segment C to travel. Among them, track segment A and track segment B are directly connected, that is, the original track. Track segment C is newly added. Track direction, that is, the relative position of the newly added track and the original track.

[0169] When the electronic device determines multiple cross-sectional point cloud data matching the rail cross-sectional template from the instantaneous cross-sectional data according to the position of the rail to be measured in the rail layout data, the electronic device may preferentially determine the coordinates of the centroid of multiple target points in the instantaneous cross-sectional data based on the instantaneous cross-sectional data. Then, based on the centroid coordinates, the track direction and the position of the rail to be measured, multiple cross-sectional point cloud data are extracted from the instantaneous cross-sectional data. It can be understood by those skilled in the art that the development of relevant technologies is relatively mature, and the electronic device may also use other methods to determine multiple cross-sectional point cloud data, which is not limited in this specification.

[0170] Preferably, the acquisition device is a 3D line laser profiler camera.

[0171] Preferably, the data of any rail is collected by two collection devices, that is, the number of the cross-section point cloud data is 2.

[0172] Figure 8 The following is a flow chart of a method for detecting wear of a rail section in a turnout area provided in accordance with an embodiment of the present specification. Figure 8 As shown, the method may further include the following steps:

[0173] S800: Acquire multiple instantaneous cross-sectional data collected by multiple collection devices based on collection position parameters.

[0174] The acquisition position parameter is included in the rail layout data, and the acquisition position parameter includes the cross-section acquisition position corresponding to each track type.

[0175] S802: splicing the multiple instantaneous cross-section data into two groups of cross-section point cloud data, each group of cross-section point cloud data corresponds to one rail.

[0176] The rail may be a base rail, a center rail, a point rail, etc., or may be a combination of at least two of the base rail, the center rail, the point rail, etc.

[0177] Each set of cross-section point cloud data includes at least two cross-section point cloud data.

[0178] S804: Based on the rail layout data and the coordinates of multiple target points in each set of cross-section point cloud data, at least two cross-section point cloud data included in one set of cross-section point cloud data are selected to perform wear measurement.

[0179] S806: Fusing the at least two cross-section point cloud data to determine cross-section fusion data.

[0180] S808: Match the preset rail section template with the section fusion data to determine a matching mapping matrix.

[0181] S810: Based on the rail section template, determine the horizontal wear measurement point and the vertical wear measurement point.

[0182] S812: Determine wear data according to the cross-section fusion data, the matching mapping matrix, the horizontal wear measurement point, and the vertical wear measurement point.

[0183] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0184] The above is a method for detecting wear of a rail section in a turnout area provided by one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding device for detecting wear of a rail section in a turnout area, such as Fig. 9 shown.

[0185] Fig. 9 A schematic diagram of a wear detection device for a rail section in a turnout area provided in accordance with an embodiment of the present specification is shown in FIG. Fig. 9 As shown, the device specifically includes:

[0186] The acquisition unit 900 is used to acquire a rail section template and a plurality of section point cloud data corresponding to a preset rail position; the plurality of section point cloud data are respectively acquired by a plurality of acquisition devices with different positions, and the areas corresponding to adjacent section point cloud data are at least partially overlapped;

[0187] The interception unit 902 is used to intercept at least two overlapping point cloud segments that belong to different cross-sectional point cloud data and whose corresponding areas overlap from the multiple cross-sectional point cloud data; the at least two overlapping point cloud segments correspond to at least one overlapping area, and each overlapping area corresponds to at least two overlapping point cloud segments;

[0188] A fusion unit 904 is used to fuse at least two overlapping point cloud segments corresponding to each overlapping area into a fused point cloud segment;

[0189] A splicing unit 906 is used to splice the fused point cloud segment with a plurality of cross-section point cloud data obtained after intercepting the at least two overlapping point cloud segments to determine cross-section fused data;

[0190] The calculation unit 908 is used to determine the wear data of the rail at the preset rail position according to the section fusion data and the rail section template.

[0191] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Provided is a wear detection method for rail sections in the turnout area.

[0192] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Provided is a wear detection method for rail sections in the turnout area.

[0193] This specification also provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device implements the above Figure 1 Provided is a wear detection method for rail sections in the turnout area.

[0194] Fig.10 The structure diagram of an electronic device provided by one embodiment of this specification. Fig.10 As mentioned above, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The wear detection method of the rail section in the turnout area. Of course, in addition to the software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0195] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0196] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0197] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0198] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0199] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0200] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0201] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0202] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0203] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0204] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0205] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0206] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0207] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0208] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0209] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0210] The above description is only an embodiment of this specification and is not intended to limit this specification. For those skilled in the art, this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification should be included in the scope of the claims of this application.

Claims

1. A method for detecting wear of a rail section in a turnout area, characterized in that: include: Obtain a rail section template and a plurality of section point cloud data corresponding to preset rail positions; The plurality of cross-sectional point cloud data are respectively collected by a plurality of collection devices with different positions and postures, and the areas corresponding to adjacent cross-sectional point cloud data are at least partially overlapped; From the plurality of cross-sectional point cloud data, at least two overlapping point cloud segments that belong to different cross-sectional point cloud data and whose corresponding areas overlap are intercepted; the at least two overlapping point cloud segments correspond to at least one overlapping area, and each overlapping area corresponds to at least two overlapping point cloud segments; For each overlapping area, merging at least two overlapping point cloud segments corresponding to the overlapping area into a fused point cloud segment; splicing the fused point cloud segment with a plurality of cross-section point cloud data obtained after intercepting the at least two overlapping point cloud segments to determine cross-section fused data; Determining wear data of the rail at the preset rail position according to the cross-section fusion data and the rail cross-section template; The step of fusing at least two overlapping point cloud segments corresponding to the overlapping area into a fused point cloud segment comprises: The multiple target points contained in any one of the overlapping point cloud segments are determined as search points, and the multiple target points contained in other overlapping point cloud segments are determined as free points; For any search point, determine the free point closest to it according to the coordinates of the search point and the coordinates of the plurality of free points; When it is determined that the distance between the free point and the search point is less than a preset distance threshold, both the free point and the search point are determined as points to be fused; Determine the fusion point coordinates of at least one fusion point according to the determined coordinates of the multiple points to be fused, and determine the point cloud area composed of the at least one fusion point as a fusion point cloud segment; The step of determining the fusion point coordinates of at least one fusion point according to the determined coordinates of the plurality of points to be fused includes: According to the determined coordinates of the multiple points to be fused, determine the target distance between any two points to be fused, and the target angle between the vector formed by the any two points to be fused and the preset direction; Based on the target distance and the target angle, the multiple points to be fused are divided into multiple fusion groups, where the fusion group includes at least two points to be fused; For each fusion group, based on the coordinates of at least two points to be fused in the fusion group, a fusion point coordinate of a fusion point is determined.

2. The method according to claim 1, characterized in that Before intercepting at least two overlapping point cloud segments respectively belonging to different cross-section point cloud data and having overlapping corresponding areas, the method further includes: Based on the coordinate conversion parameters of different acquisition devices, the plurality of cross-sectional point cloud data are converted into a preset coordinate system; According to the coordinates of multiple target points included in each cross-section point cloud data, the overlapping point cloud segments where the cross-section point cloud data overlaps with the areas corresponding to other cross-section point cloud data are determined from each cross-section point cloud data.

3. The method according to claim 1, characterized in that The step of determining the fusion point coordinates of at least one fusion point according to the determined coordinates of the plurality of points to be fused includes: Based on preset regional parameters, the point cloud area to be fused, which is composed of the determined multiple points to be fused, is divided into multiple downsampling areas; the regional parameters include the side length of the area and / or the radius of the area; Determine the coordinates of the centroid of each downsampling area according to the coordinates of the multiple points to be fused respectively included in the multiple downsampling areas; The centroid of each downsampled area is determined as the fusion point.

4. The method according to claim 1, characterized in that: The step of obtaining the rail section template comprises: Obtain standard rail section and rail layout data; Determining the working side and the non-working side of the rail corresponding to the standard rail section according to the rail layout data; From the standard rail section, a portion corresponding to the non-working edge is cut off as a rail section template; the rail section template corresponds to the rail head side, rail waist, at least part of the rail head tread and at least part of the rail bottom surface.

5. The method according to claim 1, characterized in that The step of obtaining a plurality of cross-section point cloud data corresponding to the preset rail positions includes: Obtain continuously collected continuous cross-section data and rail layout data; According to the preset rail position, determining the instantaneous section data corresponding to the preset rail position from the continuous section data; the instantaneous section data corresponds to at least two rails; According to the rail layout data, a plurality of cross-section point cloud data matching the rail cross-section template are determined from the instantaneous cross-section data.

6. The method according to any one of claims 1 to 5, characterized in that: The step of determining the wear data of the rail at the preset rail position according to the cross-section fusion data and the rail cross-section template includes: By using a preset algorithm, the cross-section fusion data is matched with the rail cross-section template, and a matching mapping matrix is ​​determined; wherein the cross-section fusion data corresponds to a preset coordinate system, and the rail cross-section template corresponds to a template coordinate system; Determine the coordinates of the vertical wear measurement point and the horizontal wear measurement point in the template coordinate system according to the width of the rail head of the rail section template and the coordinates of the highest point of the rail head tread; According to the matching mapping matrix, mapping the vertical wear measurement points and the horizontal wear measurement points to the preset coordinate system; Determine the vertical wear value and the horizontal wear value respectively according to the coordinates of each target point in the cross-section fusion data, and the coordinates of the vertical wear measurement point and the horizontal wear measurement point; The vertical wear value and the horizontal wear value are determined as the wear data of the rail section.

7. The method according to claim 6, characterized in that The matching of the cross-section fusion data with the rail cross-section template by a preset algorithm includes: Based on a paired point feature algorithm, matching the cross-section fusion data with the rail cross-section template; Based on the iterative closest point algorithm, the initial mapping matrix between the section fusion data and the rail section template is fine-tuned to determine the matching mapping matrix, and the section fusion data is made to fit the rail section template.

8. A wear detection device for rail section in turnout area, characterized in that: include: An acquisition unit, used for acquiring a rail section template and a plurality of section point cloud data corresponding to a preset rail position; The plurality of cross-sectional point cloud data are respectively collected by a plurality of collection devices with different positions and postures, and the areas corresponding to adjacent cross-sectional point cloud data are at least partially overlapped; A cutting unit is used to cut at least two overlapping point cloud segments which belong to different cross-sectional point cloud data and whose corresponding areas overlap from the multiple cross-sectional point cloud data; the at least two overlapping point cloud segments correspond to at least one overlapping area, and each overlapping area corresponds to at least two overlapping point cloud segments; a fusion unit, for fusing, for each overlapping area, at least two overlapping point cloud segments corresponding to the overlapping area into a fused point cloud segment; A splicing unit, used for splicing the fused point cloud segment with a plurality of cross-section point cloud data obtained after intercepting the at least two overlapping point cloud segments, to determine cross-section fused data; A calculation unit, used for determining the wear data of the rail at the preset rail position according to the cross-section fusion data and the rail cross-section template; The fusion unit is further used to determine multiple target points included in any one of the overlapping point cloud segments as search points, and to determine multiple target points included in other overlapping point cloud segments as free points; For any search point, determine the free point closest to it according to the coordinates of the search point and the coordinates of the plurality of free points; When it is determined that the distance between the free point and the search point is less than a preset distance threshold, both the free point and the search point are determined as points to be fused; Determine the fusion point coordinates of at least one fusion point according to the determined coordinates of the multiple points to be fused, and determine the point cloud area composed of the at least one fusion point as a fusion point cloud segment; The step of determining the fusion point coordinates of at least one fusion point according to the determined coordinates of the multiple points to be fused includes: According to the determined coordinates of the multiple points to be fused, determine the target distance between any two points to be fused, and the target angle between the vector formed by the any two points to be fused and the preset direction; Based on the target distance and the target angle, the multiple points to be fused are divided into multiple fusion groups, where the fusion group includes at least two points to be fused; For each fusion group, based on the coordinates of at least two points to be fused in the fusion group, a fusion point coordinate of a fusion point is determined.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method according to any one of claims 1 to 7.

Images