Feature point calibration method, device, medium and equipment for railway turnout

Abstract

This specification discloses a method, device, medium and equipment for calibrating characteristic points applied to railway turnouts, and relates to the field of data processing technology. It can determine the first characteristic point identification area from three-dimensional point cloud data composed of multiple point cloud sections, and then determine the first rail head width of the basic rail. The first rail head coordinate range is determined according to the first rail head width and the extension direction of the first target track. When the first point cloud section in which a target point that is not within the first rail head coordinate range is determined from multiple point cloud sections according to the extension direction of the first target track, and there are target points that are not within the first rail head coordinate range in the subsequent point cloud sections, and the distance between the target point and the first rail head coordinate range gradually increases, the first target point that is not within the first rail head coordinate range is calibrated as the tip of the pointed rail. It can be seen that the electronic device can identify and calibrate the tip of the pointed rail based on the three-dimensional point cloud data, saving costs, improving efficiency and improving accuracy.

Description

Technical Field

[0001] This specification relates to the field of data processing technology, and in particular to a method, device, medium, and equipment for calibrating characteristic points of railway turnouts. Background Art

[0002] A turnout is a specific structure in a railway track system, including components such as the center rail, guard rail, point rail, and wing rail. Typically, a turnout is installed at the intersection of a Y-shaped railway track. By operating the turnout, a train can travel to any of the turnouts.

[0003] The structure of the turnout is relatively complex, and when a railway train changes tracks, the wheels of the train often rub against the turnout violently, which in turn causes wear on the various components that make up the turnout.

[0004] In the existing technology, the wear of turnouts is usually detected by combining manual and mechanical methods. For example, three-dimensional data of the turnout area is collected through a mechanical structure, and the positions of components such as the heart rail, guard rail, and point rail are calibrated manually to measure the wear.

[0005] However, this calibration method is costly and manual operation may lead to large errors. Summary of the Invention

[0006] This specification provides a method and device for calibrating characteristic points of railway turnouts to at least partially solve the above-mentioned problems existing in the prior art.

[0007] This manual adopts the following technical solutions:

[0008] This specification provides a method for calibrating characteristic points of railway turnouts, including:

[0009] Acquire three-dimensional point cloud data composed of a plurality of point cloud sections; the point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track;

[0010] Based on a preset first target range, determining a first feature point recognition area corresponding thereto from the three-dimensional point cloud data;

[0011] determining a first rail head width of the stock rail based on a plurality of point cloud sections within the first feature point recognition area;

[0012] Determining a first rail head coordinate range according to the first rail head width and a preset first target rail extension direction;

[0013] When the first point cloud section having a target point that is not within the first rail head coordinate range is determined from the multiple point cloud sections according to the extension direction of the first target rail, and target points that are not within the first rail head coordinate range are present in subsequent point cloud sections, and the distances between the target points and the first rail head coordinate range gradually increase, the first target point that is not within the first rail head coordinate range is calibrated as the tip of the pointed rail.

[0014] Preferably, determining the first rail head width of the stock rail based on a plurality of point cloud sections within the first feature point recognition area includes:

[0015] determining, according to a preset first target track extension direction, first rail head widths of the base rails of a plurality of point cloud sections within the first feature point recognition area;

[0016] Determining the distribution parameters of the first n rail head widths; the distribution parameters are standard deviation, variance, mean absolute deviation or coefficient of variation;

[0017] According to the order of n values from small to large, the first time the value of n of the distribution parameter is greater than or equal to the preset first parameter, is determined as the out-of-limit parameter;

[0018] Determine the value of m as the difference between the over-limit parameter and a preset second parameter;

[0019] The first rail head width of the basic rail is determined according to the first m first rail head widths.

[0020] Preferably, determining the value of m as the difference between the over-limit parameter and a preset second parameter includes:

[0021] Determining whether the difference between the over-limit parameter and the preset second parameter is greater than or equal to a preset third parameter;

[0022] If so, no other action is performed;

[0023] If not, the value of m is determined to be the third parameter.

[0024] Preferably, after the point rail tip is calibrated, the method further comprises:

[0025] Determine a position along the extension direction of the first target track and at a first mileage distance from the tip of the switch rail as an initial guardrail detection position;

[0026] Arranging the plurality of point cloud sections according to the extension direction of the first target track;

[0027] When the first point cloud section in which a target point that is not within the first rail head coordinate range is determined from the multiple point cloud sections, and there are target points in subsequent point cloud sections whose distance from the first rail head coordinate range is greater than a preset second distance, the first target point that is not within the first rail head coordinate range is calibrated as the guardrail toe.

[0028] Preferably, after the mark is determined as the guard rail toe, the method further comprises:

[0029] Starting from the point cloud section corresponding to the target point calibrated as the guard rail toe, along the extension direction of the first target track, the point cloud section of the target point where all the first target points are within the coordinate range of the first rail head is determined as the initial position of the center rail detection;

[0030] When the first point cloud section in which a target point is not within the first rail head coordinate range is determined from the multiple point cloud sections, and target points that are not within the first rail head coordinate range are present in subsequent point cloud sections, and the distance between the target points and the first rail head coordinate range gradually increases, the first target point that is not within the first rail head coordinate range is calibrated as the center rail tip.

[0031] Preferably, before determining the first feature point recognition area corresponding to the preset first target range, the method further includes:

[0032] Obtaining straight and curved track information and track direction information corresponding to the three-dimensional point cloud data; the straight and curved track information includes straight track or curved track, and the track direction information includes left track or right track;

[0033] A first target range is determined based on the coordinates of multiple target points constituting different basic tracks in the three-dimensional point cloud data, the straight and curved track information, and the track direction information.

[0034] On the other hand, this specification provides a method for calibrating characteristic points applied to railway turnouts, comprising:

[0035] Acquire three-dimensional point cloud data composed of a plurality of point cloud sections; the point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track;

[0036] determining, from the three-dimensional point cloud data, a second feature point recognition area corresponding to a preset second target range according to the coordinates of the plurality of target points;

[0037] determining a second rail head width of the stock rail based on a plurality of point cloud sections within the second feature point recognition area;

[0038] determining a second rail head coordinate range according to the second rail head width and a preset second target rail extension direction;

[0039] When the first point cloud section in which a target point is not within the second rail head coordinate range is determined from the multiple point cloud sections according to the extension direction of the second target track, and target points that are not within the second rail head coordinate range are present in subsequent point cloud sections, and the distance between the target points and the second rail head coordinate range gradually increases, the first target point that is not within the second rail head coordinate range is calibrated as the second target point.

[0040] On the other hand, this specification provides a method for calibrating characteristic points applied to railway turnouts, comprising:

[0041] Acquire three-dimensional point cloud data composed of a plurality of point cloud sections; the point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track;

[0042] determining, from the three-dimensional point cloud data, a third feature point recognition area corresponding to a preset third target range according to the coordinates of the plurality of target points;

[0043] determining a third rail head width of the base rail based on a plurality of point cloud sections within the third feature point recognition area;

[0044] Determining a coordinate range of the third rail head according to the third rail head width and a preset third target rail extension direction;

[0045] When the first point cloud section in which a target point that is not within the third rail head coordinate range is determined from the multiple point cloud sections according to the extension direction of the third target rail, and when there are target points in subsequent point cloud sections whose distance from the third rail head coordinate range is greater than a preset third distance, the first target point that is not within the third rail head coordinate range is calibrated as the third target point.

[0046] On the other hand, this specification provides a feature point calibration device for railway turnouts, comprising:

[0047] An acquisition unit is used to acquire three-dimensional point cloud data composed of a plurality of point cloud sections; the point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track;

[0048] a matching unit, configured to determine, from the three-dimensional point cloud data, a first feature point recognition area corresponding to a preset first target range based on the coordinates of the plurality of target points;

[0049] a determining unit, configured to determine a first rail head width of the stock rail based on a plurality of point cloud sections within the first feature point recognition area;

[0050] a dividing unit, configured to determine a first rail head coordinate range according to the first rail head width and a preset first target rail extension direction;

[0051] The calibration unit is configured to, when, according to the extension direction of the first target rail, determine from the multiple point cloud sections a first point cloud section in which a target point is not within the first rail head coordinate range, and when subsequent point cloud sections all contain target points that are not within the first rail head coordinate range, and when the distance between the target points and the first rail head coordinate range gradually increases, calibrate the first target point that is not within the first rail head coordinate range as the tip of the pointed rail.

[0052] On the other hand, this specification provides a feature point calibration device for railway turnouts, comprising:

[0053] An acquisition unit is used to acquire three-dimensional point cloud data composed of a plurality of point cloud sections; the point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track;

[0054] a matching unit, configured to determine, from the three-dimensional point cloud data, a second feature point recognition area corresponding to a preset second target range based on the coordinates of the plurality of target points;

[0055] a determining unit, configured to determine a second rail head width of the stock rail based on a plurality of point cloud sections within the second feature point recognition area;

[0056] a dividing unit, configured to determine a second rail head coordinate range according to the second rail head width and a preset second target rail extension direction;

[0057] The calibration unit is configured to, when, according to the extension direction of the second target track, a first point cloud section having a target point that is not within the second rail head coordinate range is determined from the multiple point cloud sections, and when target points that are not within the second rail head coordinate range are present in subsequent point cloud sections, and when the distance between the target points and the second rail head coordinate range gradually increases, calibrate the first target point that is not within the second rail head coordinate range as the second target point.

[0058] On the other hand, this specification provides a feature point calibration device for railway turnouts, comprising:

[0059] An acquisition unit is used to acquire three-dimensional point cloud data composed of a plurality of point cloud sections; the point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track;

[0060] a matching unit, configured to determine, from the three-dimensional point cloud data, a third feature point recognition area corresponding to a preset third target range based on the coordinates of the plurality of target points;

[0061] a determining unit, configured to determine a third rail head width of the base rail based on a plurality of point cloud sections within the third feature point recognition area;

[0062] a dividing unit, configured to determine a coordinate range of the third rail head according to the third rail head width and a preset third target rail extension direction;

[0063] The calibration unit is configured to, when determining, from the multiple point cloud sections according to the extension direction of the third target track, a first point cloud section in which a target point that is not within the third rail head coordinate range is present, and when subsequent point cloud sections all have target points whose distance from the third rail head coordinate range is greater than a preset third distance, calibrate the first target point that is not within the third rail head coordinate range as a third target point.

[0064] On the other hand, the present specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for calibrating characteristic points applied to railway switches provided in the above aspect is implemented.

[0065] On the other hand, this specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, the feature point calibration method for railway turnouts provided in the above aspect is implemented.

[0066] 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 feature point calibration method for railway turnouts provided in the above aspect.

[0067] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0068] based on Figure 1The illustrated method for calibrating characteristic points for railway turnouts involves an electronic device capable of acquiring three-dimensional point cloud data comprised of multiple point cloud sections and, based on a preset first target range, determining a corresponding first characteristic point identification region from the three-dimensional point cloud data. The method then determines the first rail head width of the base rail based on the multiple point cloud sections within the first characteristic point identification region. The method then determines the first rail head coordinate range based on the first rail head width and a preset first target rail extension direction. Finally, when the first point cloud section containing a target point outside the first rail head coordinate range is determined from the multiple point cloud sections according to the first target rail extension direction, and subsequent point cloud sections all contain target points outside the first rail head coordinate range, and the distance between the target points and the first rail head coordinate range gradually increases, the first target point outside the first rail head coordinate range is calibrated as the tip of the rail.

[0069] It can be seen from the above method that the electronic device can identify and calibrate the tip of the pointed rail based on three-dimensional point cloud data, saving costs, improving efficiency and increasing accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The exemplary embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation of this specification. In the drawings:

[0071] Figure 1 A schematic flow chart of a characteristic point calibration method for a railway turnout provided in accordance with one embodiment of this specification;

[0072] Figure 2 A schematic cross-sectional view of a point cloud cross section provided for one embodiment of this specification;

[0073] Figure 3 A schematic diagram of the structure of a point rail and a stock rail provided for one embodiment of this specification;

[0074] Figure 4 A schematic diagram of the structure of a point rail and a stock rail provided for one embodiment of this specification;

[0075] Figure 5 A schematic diagram of the structure of a point rail and a stock rail provided for one embodiment of this specification;

[0076] Figure 6 A schematic diagram of the structure of a guard rail and a base rail provided for one embodiment of this specification;

[0077] Figure 7 A schematic diagram of the structure of a guard rail and a base rail provided for one embodiment of this specification;

[0078] Figure 8 A schematic diagram of the structure of a center rail and a base rail provided for one embodiment of this specification;

[0079] Figure 9 A schematic diagram of the structure of a center rail and a base rail provided for one embodiment of this specification;

[0080] Figure 10 A schematic diagram of the structure of a center rail and a base rail provided for one embodiment of this specification;

[0081] Figure 11 A flow chart of a characteristic point calibration method for railway turnouts provided in this specification;

[0082] Figure 12 A flow chart of a characteristic point calibration method for railway turnouts provided in this specification;

[0083] Figure 13 A schematic structural diagram of a characteristic point calibration device for a railway turnout provided in accordance with one embodiment of this specification;

[0084] Figure 14 A schematic diagram of the structure of an electronic device provided in one embodiment of this specification. DETAILED DESCRIPTION

[0085] 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 conjunction with the specific embodiments of this specification and the corresponding drawings. Obviously, the embodiments described 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 making any creative efforts are within the scope of protection of this application.

[0086] In the description of the present invention, it should be noted that the term "or" is generally used in a sense including "and / or", unless the content clearly indicates otherwise.

[0087] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. In addition, in the description of this application, the terms "first," "second," etc. are used only to distinguish descriptions and should not be understood to indicate or imply relative importance.

[0088] Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0089] The technical solutions provided by the embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0090] Figure 1 A flow chart of a characteristic point calibration method for a railway turnout provided in one embodiment of this specification is shown as follows: Figure 1 As shown, the characteristic point calibration method applied to railway turnout specifically includes the following steps:

[0091] S100: Acquire three-dimensional point cloud data consisting of multiple point cloud sections.

[0092] In this specification, the feature point calibration method applied to railway turnouts can be executed by an electronic device, which can be a terminal device such as a computer, a laptop, a single-chip microcomputer, a server, etc., and this specification does not limit this.

[0093] In one or more embodiments of the present specification, the three-dimensional point cloud data is collected by a line laser collector. When the line laser collector collects the three-dimensional point cloud data, the line laser output by the line laser collector is a pulsed laser, and the direction of the line laser is perpendicular to the direction of the basic rail. Therefore, the three-dimensional point cloud data is composed of multiple point cloud sections, and each point cloud section is perpendicular to the extension direction of the basic rail. It should be noted that the extension direction of the basic rail is the direction of a section of the basic rail corresponding to the point cloud section. Those skilled in the art will understand that the basic rail will often bend during the laying process, but no matter how the basic rail bends, the point cloud section is perpendicular to the corresponding basic rail.

[0094] Preferably, the point cloud section consists of multiple target points.

[0095] S102: Determine a first feature point recognition area corresponding to a preset first target range from the three-dimensional point cloud data according to the coordinates of the plurality of target points.

[0096] Typically, a switch area has a certain range. For example, the distance between the switch rail and the guard rail is generally 20 meters. However, during the feature point calibration process, only feature points such as the switch rail tip, guard rail toe, and center rail tip need to be calibrated. Therefore, in order to determine the smaller range within which feature points such as the switch rail tip, guard rail toe, and center rail tip are located within the point cloud data of the larger switch area, the electronic device can determine a first feature point recognition area corresponding to the first target range from the three-dimensional point cloud data based on a preset first target range.

[0097] Preferably, the first feature point identification area corresponds to the tip of the pointed rail.

[0098] S104: Determine a first rail head width of the base rail according to a plurality of point cloud sections within the first feature point recognition area.

[0099] Those skilled in the art will appreciate that stock rails often wear out after a period of use, and that stock rails in turnout areas often wear out at a faster rate. Therefore, the rail head width of the stock rail is likely to be different from that of a brand new rail. Therefore, the electronic device can determine the first rail head width of the stock rail in the following manner.

[0100] Specifically, the electronic device can determine the first rail head width of the basic rail based on multiple point cloud sections within the first feature point recognition area.

[0101] Figure 2 A schematic cross-sectional view of a point cloud cross section provided for one embodiment of this specification is shown in FIG. Figure 2 As shown, the rail head width 41 corresponding to the point cloud section.

[0102] S106: Determine a first rail head coordinate range according to the first rail head width and a preset first target rail extension direction.

[0103] Those skilled in the art will appreciate that the tip portion of the point rail is in close contact with the base rail and gradually becomes thicker.

[0104] Figure 3 Figure 4 as well as Figure 5 These are schematic diagrams of the structure of the point rail and the base rail provided in one embodiment of this specification. Figure 3 、 Figure 4 as well as Figure 5 As shown, the point rail 42 is in close contact with the stock rail 43, and the thickness of the tip 421 of the point rail is relatively small.

[0105] Therefore, in one or more preferred embodiments of the present specification, the electronic device may determine the first rail head coordinate range according to the first rail head width and a preset first target rail extension direction.

[0106] The first target rail extension direction is the direction in which the thickness of the point rail gradually increases. The first rail head coordinate range is the coordinate range of the base rail head. Because the base rail may be curved, the first rail head coordinate range needs to be determined in conjunction with the first target rail extension direction.

[0107] Further preferably, the extension direction of the first target track may be preset or may be determined based on the direction of each point cloud section, which is not limited in this specification.

[0108] S108: Based on the extension direction of the first target track, determine from the multiple point cloud sections whether there is a first point cloud section containing a target point that is not within the first rail head coordinate range, determine whether there are target points that are not within the first rail head coordinate range in subsequent point cloud sections, and then determine whether the distance between the target point and the first rail head coordinate range gradually increases. If the judgment results are all yes, execute step S110. If any judgment result is no, repeat step S108.

[0109] Preferably, the electronic device can determine whether there is a point cloud section of a target point that is not within the coordinate range of the first rail head from the multiple point cloud sections according to the extension direction of the first target rail, and determine whether there are target points that are not within the coordinate range of the first rail head in subsequent point cloud sections, and then determine whether the distance between the target point and the coordinate range of the first rail head gradually increases.

[0110] It is understandable to those skilled in the art that there may be foreign matter on the surface of the base rail, which may cause coordinate points in certain point cloud sections to be outside the coordinate range of the first rail head. However, the characteristics of the point rail are more obvious. The tip of the point rail is closely attached to the base rail, and as the base rail extends, the point rail gradually changes from thin to thick. Therefore, the electronic device can use the above method to identify the point rail.

[0111] It should be noted that when determining whether subsequent point cloud sections contain target points that are not within the coordinate range of the first rail head, the number of point cloud sections required for determination can be set arbitrarily, and the density of the point cloud sections can be used as a reference during the setting process. Preferably, the extension length of the basic rail corresponding to the point cloud sections required for determination is 5 cm.

[0112] S100: Marking the first target point that is not within the first rail head coordinate range as the tip of the rail.

[0113] based on Figure 1 The illustrated method for calibrating characteristic points for railway turnouts involves an electronic device capable of acquiring three-dimensional point cloud data comprised of multiple point cloud sections and, based on a preset first target range, determining a corresponding first characteristic point identification region from the three-dimensional point cloud data. The method then determines the first rail head width of the base rail based on the multiple point cloud sections within the first characteristic point identification region. The method then determines the first rail head coordinate range based on the first rail head width and a preset first target rail extension direction. Finally, when the first point cloud section containing a target point outside the first rail head coordinate range is determined from the multiple point cloud sections according to the first target rail extension direction, and subsequent point cloud sections all contain target points outside the first rail head coordinate range, and the distance between the target points and the first rail head coordinate range gradually increases, the first target point outside the first rail head coordinate range is calibrated as the tip of the rail.

[0114] It can be seen from the above method that the electronic device can identify and calibrate the tip of the pointed rail based on three-dimensional point cloud data, saving costs, improving efficiency and increasing accuracy.

[0115] Preferably, the electronic device may adopt the following method when executing step S104.

[0116] Specifically, first, the electronic device can determine the first rail head widths of the basic rails of the multiple point cloud sections within the first feature point recognition area according to the preset first target rail extension direction.

[0117] Next, the electronic device may determine a distribution parameter of the first n rail head widths, wherein the distribution parameter may be a standard deviation, variance, mean absolute deviation, or coefficient of variation, etc., which is not limited in this specification.

[0118] Then, the electronic device may determine the first time that the distribution parameter is greater than or equal to the preset first parameter as an out-of-limit parameter in the order of n from smallest to largest values, and determine the value of m as the difference between the out-of-limit parameter and the preset second parameter.

[0119] Finally, the electronic device may determine the first rail head width of the basic rail according to the first m first rail head widths.

[0120] Among them, m and n are both positive integers, and m <n。

[0121] Further preferably, the value of n can be determined according to the density of the point cloud section, and the value of n is positively correlated with the density of the point cloud section.

[0122] Further preferably, when determining the distribution parameters of the first n first rail head widths, the electronic device may first determine the first p first rail head widths based on the density of the point cloud cross section, where the first p first rail head widths correspond to a basic rail having a length of a first value, p > n, and p is a positive integer. The p first rail head widths are then sampled to determine n first rail head widths. Finally, the distribution parameters of the n first rail head widths are determined.

[0123] By adopting the above-mentioned method, the electronic device can reduce the influence of the center rail when determining the first rail head width, thereby improving the accuracy of determining the first rail head width.

[0124] Further preferably, when determining that the value of m is the difference between the excess parameter and a preset second parameter, the electronic device may preferentially determine whether the difference between the excess parameter and the preset second parameter is greater than or equal to a preset third parameter.

[0125] If so, no other action is performed;

[0126] If not, the value of m is determined to be the third parameter.

[0127] By adopting the above-mentioned method, the electronic device can ensure a minimum value of the number of point cloud sections used to determine the first rail head width, thereby ensuring that the first rail head width can be determined.

[0128] Preferably, after executing step 110 , the electronic device may further calibrate the guardrail toe.

[0129] Specifically, the electronic device may first determine a position along the extension direction of the first target rail and a first distance from the tip of the switch rail as the initial guardrail detection position. The first distance is a preset value, such as 15m or 20m, and is not limited in this specification. The first distance is the distance along the extension direction of the base rail.

[0130] Secondly, the electronic device can arrange the multiple point cloud sections according to the extension direction of the first target track.

[0131] Then, the electronic device can determine whether there is a first point cloud section of the target point that is not within the first rail head coordinate range among the multiple point cloud sections, and determine whether there are target points in the subsequent point cloud sections whose distance from the first rail head coordinate range is greater than a preset second distance.

[0132] If the judgment structure is yes, the first target point that is not in the coordinate range of the first rail head is marked as the guardrail toe.

[0133] If the judgment result of any item is negative, the judgment is repeated.

[0134] Preferably, after completing the calibration of the guard rail toe, the electronic device can also calibrate the center rail tip.

[0135] Specifically, first, the electronic device can start from the point cloud section corresponding to the target point calibrated as the toe end of the guard rail, and along the extension direction of the first target rail, determine the point cloud section of the target point whose first target point is within the coordinate range of the first rail head as the initial position of the heart rail detection.

[0136] Secondly, the electronic device can determine whether there is a first point cloud section of the target point that is not within the coordinate range of the first rail head among the multiple point cloud sections, and determine whether there are target points that are not within the coordinate range of the first rail head in the subsequent point cloud sections, and then determine whether the distance between the target point and the coordinate range of the first rail head gradually increases.

[0137] If the judgment results are all yes, the first target point that is not in the coordinate range of the first rail head is marked as the center rail tip.

[0138] If the judgment result of any item is negative, the judgment is repeated.

[0139] Using the above method, the electronic equipment completes the positioning of the guard rail and the heart rail based on the relative position relationship between the point rail, guard rail and heart rail when only the first target range is required, and realizes the calibration of the guard rail toe and the heart rail tip, thereby improving the calibration efficiency, simplifying the calibration process and saving computing power.

[0140] Figure 6 as well as Figure 7 These are schematic diagrams of the structure of the guard rail and the basic rail provided in one embodiment of this specification. Figure 6 as well as Figure 7 As shown, the guard rail 44 is adjacent to the stock rail 43 , and the guard rail toe 441 is the edge of the guard rail 44 .

[0141] Figure 8 、 Figure 9 as well as Figure 10 Each of them is a schematic structural diagram of a center rail and a basic rail provided by an embodiment of this specification.

[0142] like Figure 8 、 Figure 9 as well as Figure 10 As shown, the center rail 45 is in close contact with the base rail 43, and the thickness of the center rail tip 451 is relatively small.

[0143] Preferably, before executing step S102, the electronic device may obtain the straight and curved track information and track direction information corresponding to the three-dimensional point cloud data. The straight and curved track information may include straight or curved track, and the track direction information may include left or right track. The first target range is determined based on the coordinates of multiple target points constituting different basic tracks within the three-dimensional point cloud data, the straight and curved track information, and the track direction information.

[0144] The above is a characteristic point calibration method applied to railway turnouts provided in one or more embodiments of this specification. Based on similar ideas, this specification also provides a corresponding characteristic point calibration method applied to railway turnouts, such as Figure 11 shown.

[0145] Figure 11 This is a flow chart of the characteristic point calibration method applied to railway turnouts provided in this specification.

[0146] S200: Acquire three-dimensional point cloud data consisting of a plurality of point cloud sections. The point cloud section consists of a plurality of target points. The point cloud section is perpendicular to the extension direction of the base track.

[0147] In this specification, the feature point calibration method applied to railway turnouts can be executed by an electronic device, which can be a terminal device such as a computer, a laptop, a single-chip microcomputer, a server, etc., and this specification does not limit this.

[0148] S202: Determine a second feature point recognition area corresponding to a preset second target range from the three-dimensional point cloud data according to the coordinates of the plurality of target points.

[0149] S204: Determine a second rail head width of the base rail according to a plurality of point cloud sections within the second feature point recognition area.

[0150] S206: Determine a second rail head coordinate range according to the second rail head width and a preset second target rail extension direction.

[0151] S208: Based on the extension direction of the second target track, determine whether there is a point cloud section in the multiple point cloud sections that contains the first target point that is not within the second rail head coordinate range, determine whether there are target points in subsequent point cloud sections that are not within the second rail head coordinate range, and then determine whether the distance between the target point and the second rail head coordinate range gradually increases. If the judgment structure is yes in all cases, execute step S210. If the judgment structure is no in any case, execute step S208 again.

[0152] S210: Marking the first target point that is not within the second rail head coordinate range as a second target point, wherein the second target point can be a point rail tip, a center rail tip, etc., which is not limited in this specification.

[0153] The above is a characteristic point calibration method applied to railway turnouts provided in one or more embodiments of this specification. Based on similar ideas, this specification also provides a corresponding characteristic point calibration method applied to railway turnouts, such as Figure 12 shown.

[0154] Figure 12 This is a flow chart of the characteristic point calibration method applied to railway turnouts provided in this specification.

[0155] S300: Acquire three-dimensional point cloud data consisting of a plurality of point cloud sections. The point cloud section consists of a plurality of target points. The point cloud section is perpendicular to the extension direction of the base track.

[0156] In this specification, the feature point calibration method applied to railway turnouts can be executed by an electronic device, which can be a terminal device such as a computer, a laptop, a single-chip microcomputer, a server, etc., and this specification does not limit this.

[0157] S302: Determine a third feature point recognition area corresponding to a preset third target range from the three-dimensional point cloud data according to the coordinates of the plurality of target points.

[0158] S304: Determine a third rail head width of the base rail according to a plurality of point cloud sections within the third feature point recognition area.

[0159] S306: Determine a coordinate range of the third rail head according to the third rail head width and a preset third target rail extension direction.

[0160] S308: Based on the extension direction of the third target track, determine whether there is a point cloud section in the multiple point cloud sections that contains the first target point that is not within the coordinate range of the third rail head, and determine whether there are target points in subsequent point cloud sections that are farther away from the coordinate range of the third rail head than a preset third distance. If the judgment is yes in all cases, execute step S310. If any of the judgments is no, execute step S308 again.

[0161] S310: Marking the first target point that is not within the coordinate range of the third rail head as the third target point.

[0162] Preferably, the third target point may be the toe of a guard rail, etc., which is not limited in this specification.

[0163] It should be noted that Figure 1 The content of the characteristic point calibration method applied to railway turnouts is relatively detailed and Figure 11 as well as Figure 12 The content of the characteristic point calibration method applied to railway turnouts is similar to Figure 1 The content of the characteristic point calibration method applied to railway turnouts is similar to that shown in FIG. Figure 11 as well as Figure 12 The content will not be described in detail, the relevant content can be found in Figure 1 The feature point calibration method applied to railway turnouts is shown.

[0164] The above is a characteristic point calibration method applied to railway turnouts provided in one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding characteristic point calibration device applied to railway turnouts, such as Figure 13 shown.

[0165] Figure 13 A schematic diagram of a characteristic point calibration device for a railway turnout according to an embodiment of the present invention is provided. Figure 13 As shown, the characteristic point calibration device applied to railway turnout specifically includes:

[0166] An acquisition unit 900 is configured to acquire three-dimensional point cloud data consisting of a plurality of point cloud sections, wherein the point cloud section is composed of a plurality of target points and is perpendicular to an extension direction of the base track.

[0167] A matching unit 902 is configured to determine, from the three-dimensional point cloud data, a first feature point recognition area corresponding to a preset first target range based on the coordinates of the plurality of target points;

[0168] a determining unit 904 for determining a first rail head width of the base rail based on a plurality of point cloud sections within the first feature point recognition area;

[0169] A division unit 906 is configured to determine a first rail head coordinate range according to the first rail head width and a preset first target rail extension direction;

[0170] The calibration unit 908 is configured to, when, according to the extension direction of the first target track, determine, from the multiple point cloud sections, a first point cloud section having a target point that is not within the first rail head coordinate range, and when subsequent point cloud sections all have target points that are not within the first rail head coordinate range, and when the distance between the target points and the first rail head coordinate range gradually increases, calibrate the first target point that is not within the first rail head coordinate range as the tip of the pointed rail.

[0171] 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.

[0172] This specification also provides a computer-readable storage medium, which stores a computer program that can be used to execute the above Figure 1 、 Figure 11 as well as Figure 12 A feature point calibration method for railway turnouts is provided.

[0173] This specification also provides a computer program product, which, when the instructions in the computer program product are executed by a processor of an electronic device, enables the electronic device to implement the above-mentioned Figure 1 、 Figure 11 as well as Figure 12 A feature point calibration method for railway turnouts is provided.

[0174] Figure 14 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this specification. Figure 14As shown, 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 、 Figure 11 as well as Figure 12 The characteristic point calibration method for railway turnouts is described. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0175] In the 1990s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements can now be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using physical hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly performed using software called a "logic compiler." This is similar to the software compilers used during program development. Before compilation, the original code must be written in a specific programming language, called a Hardware Description Language (HDL). There are many types of HDL, including 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, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that simply by programming a method flow in one of these hardware description languages and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0176] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the memory control logic. Those skilled in the art will also appreciate that, in addition to implementing the controller purely in computer-readable program code, the controller can also be implemented in the form of logic gates, switches, an application-specific integrated circuit, a programmable logic controller, an embedded microcontroller, etc. by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the means for implementing the various functions included therein can also be considered as structures within the hardware component. Alternatively, the means for implementing the various functions can be considered both a software module implementing the method and a structure within the hardware component.

[0177] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having 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 smartphone, 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.

[0178] For the convenience of description, the above devices are described as being divided into 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.

[0179] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0180] 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 flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 flowcharts and / or block diagrams. 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.

[0181] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0182] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0183] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0184] 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. Memory is an example of a computer-readable medium.

[0185] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The 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 disc read-only memory (CD-ROM), digital versatile disc (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 transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0186] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0187] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like 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 communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0189] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0190] The foregoing is merely an embodiment of the present invention and is not intended to limit the present invention. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of this application.

Claims

1. A method for calibrating characteristic points of railway turnouts, characterized in that: include: Acquire three-dimensional point cloud data composed of multiple point cloud sections; The point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track; Based on a preset first target range, determining a first feature point recognition area corresponding thereto from the three-dimensional point cloud data; determining a first rail head width of the stock rail based on a plurality of point cloud sections within the first feature point recognition area; Determining a first rail head coordinate range according to the first rail head width and a preset first target rail extension direction; When a first point cloud section having a target point that is not within the first rail head coordinate range is determined from the multiple point cloud sections according to the extension direction of the first target rail, and target points that are not within the first rail head coordinate range are present in subsequent point cloud sections, and the distances between the target points and the first rail head coordinate range gradually increase, the first target point that is not within the first rail head coordinate range is marked as the tip of the rail; The determining of the first rail head width of the base rail according to a plurality of point cloud sections within the first feature point recognition area includes: determining, according to a preset first target track extension direction, first rail head widths of the base rails of a plurality of point cloud sections within the first feature point recognition area; Determining the distribution parameters of the first n rail head widths; the distribution parameters are standard deviation, variance, mean absolute deviation or coefficient of variation; In order of n values from small to large, the first time the value of n of the distribution parameter is greater than or equal to the preset first parameter, is determined as the out-of-limit parameter; Determine the value of m as the difference between the over-limit parameter and a preset second parameter; The first rail head width of the basic rail is determined according to the first m first rail head widths.

2. The characteristic point calibration method for railway turnout according to claim 1, characterized in that: Determining the value of m as the difference between the over-limit parameter and a preset second parameter includes: Determining whether the difference between the over-limit parameter and the preset second parameter is greater than or equal to a preset third parameter; If so, no other action is performed; If not, the value of m is determined to be the third parameter.

3. The characteristic point calibration method for railway turnout according to claim 1, characterized in that: After the point rail tip is determined, the method further includes: Determine a position along the extension direction of the first target track and at a first mileage distance from the tip of the switch rail as an initial guardrail detection position; Arranging the plurality of point cloud sections according to the extension direction of the first target track; When the first point cloud section in which a target point that is not within the first rail head coordinate range is determined from the multiple point cloud sections, and there are target points in subsequent point cloud sections whose distance from the first rail head coordinate range is greater than a preset second distance, the first target point that is not within the first rail head coordinate range is calibrated as the guardrail toe.

4. The characteristic point calibration method for railway turnout according to claim 3 is characterized in that: After the guard rail toe is determined, the method further includes: Starting from the point cloud section corresponding to the target point calibrated as the guard rail toe, along the extension direction of the first target track, the point cloud section of the target point where all the first target points are within the coordinate range of the first rail head is determined as the initial position of the center rail detection; When the first point cloud section in which a target point is not within the first rail head coordinate range is determined from the multiple point cloud sections, and target points that are not within the first rail head coordinate range are present in subsequent point cloud sections, and the distance between the target points and the first rail head coordinate range gradually increases, the first target point that is not within the first rail head coordinate range is calibrated as the center rail tip.

5. The characteristic point calibration method for railway turnout according to claim 1, characterized in that: Before determining the first feature point recognition area corresponding to the preset first target range, the method further includes: Obtaining straight and curved track information and track direction information corresponding to the three-dimensional point cloud data; the straight and curved track information includes straight track or curved track, and the track direction information includes left track or right track; A first target range is determined based on the coordinates of multiple target points constituting different basic tracks in the three-dimensional point cloud data, the straight and curved track information, and the track direction information.

6. A method for calibrating characteristic points of railway turnouts, characterized in that: include: Acquire three-dimensional point cloud data composed of multiple point cloud sections; The point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track; determining, from the three-dimensional point cloud data, a second feature point recognition area corresponding to a preset second target range according to the coordinates of the plurality of target points; determining a second rail head width of the stock rail based on a plurality of point cloud sections within the second feature point recognition area; determining a second rail head coordinate range according to the second rail head width and a preset second target rail extension direction; When a first point cloud section having a target point that is not within the second rail head coordinate range is determined from the multiple point cloud sections according to the extension direction of the second target rail, and target points that are not within the second rail head coordinate range are present in subsequent point cloud sections, and the distances between the target points and the second rail head coordinate range gradually increase, the first target point that is not within the second rail head coordinate range is marked as the second target point; The determining of the second rail head width of the base rail according to a plurality of point cloud sections within the second feature point recognition area includes: determining, according to a preset second target track extension direction, second rail head widths of the base rail for a plurality of point cloud sections within the second feature point recognition area; Determining the distribution parameters of the first n second rail head widths; the distribution parameters are standard deviation, variance, mean absolute deviation or coefficient of variation; In order of n values from small to large, the first time the value of n of the distribution parameter is greater than or equal to the preset first parameter, is determined as the out-of-limit parameter; Determine the value of m as the difference between the over-limit parameter and a preset second parameter; The second rail head width of the basic rail is determined according to the first m second rail head widths.

7. A method for calibrating characteristic points of railway turnouts, characterized in that: include: Acquire three-dimensional point cloud data composed of multiple point cloud sections; The point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track; determining, from the three-dimensional point cloud data, a third feature point recognition area corresponding to a preset third target range according to the coordinates of the plurality of target points; determining a third rail head width of the base rail based on a plurality of point cloud sections within the third feature point recognition area; Determining a coordinate range of the third rail head according to the third rail head width and a preset third target rail extension direction; When a first point cloud section having a target point that is not within the third rail head coordinate range is determined from the plurality of point cloud sections according to the extension direction of the third target rail, and target points whose distance from the third rail head coordinate range is greater than a preset third distance are present in subsequent point cloud sections, the first target point that is not within the third rail head coordinate range is marked as the third target point; The determining of the third rail head width of the base rail according to a plurality of point cloud sections within the third feature point recognition area includes: determining, according to a preset third target track extension direction, third rail head widths of the base rails of a plurality of point cloud sections within the third feature point recognition area; Determining the distribution parameters of the first n third rail head widths; the distribution parameters are standard deviation, variance, mean absolute deviation or coefficient of variation; According to the order of n values from small to large, the first time the value of n of the distribution parameter is greater than or equal to the preset first parameter, the value is determined as the out-of-limit parameter; Determine the value of m as the difference between the over-limit parameter and a preset second parameter; Determine the third rail head width of the base rail based on the first m third rail head widths.

8. A characteristic point calibration device for railway turnouts, characterized in that: include: An acquisition unit, used for acquiring three-dimensional point cloud data composed of multiple point cloud sections; The point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track; a matching unit, configured to determine, from the three-dimensional point cloud data, a first feature point recognition area corresponding to a preset first target range based on the coordinates of the plurality of target points; a determining unit, configured to determine a first rail head width of the stock rail based on a plurality of point cloud sections within the first feature point recognition area; a dividing unit, configured to determine a first rail head coordinate range according to the first rail head width and a preset first target rail extension direction; a calibration unit, configured to, when determining, from the plurality of point cloud sections, in accordance with the extension direction of the first target track, a first point cloud section having a target point that is not within the first rail head coordinate range, and when subsequent point cloud sections all have target points that are not within the first rail head coordinate range, and when the distances between the target points and the first rail head coordinate range gradually increase, calibrate the first target point that is not within the first rail head coordinate range as a pointed rail tip; The determining unit is configured to respectively determine a first rail head width of a base rail of a plurality of point cloud sections within the first feature point recognition area according to a preset first target rail extension direction; Determine the distribution parameters of the first n first rail head widths; the distribution parameters may be standard deviation, variance, mean absolute deviation, or coefficient of variation; in ascending order of n values, determine the value of n for which the distribution parameter is greater than or equal to a preset first parameter for the first time as an overrun parameter; determine the value of m as the difference between the overrun parameter and a preset second parameter; and determine the first rail head width of the base rail based on the first m first rail head widths.

9. A characteristic point calibration device for railway turnouts, characterized in that: include: An acquisition unit, used for acquiring three-dimensional point cloud data composed of multiple point cloud sections; The point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track; a matching unit, configured to determine, from the three-dimensional point cloud data, a second feature point recognition area corresponding to a preset second target range based on the coordinates of the plurality of target points; a determining unit, configured to determine a second rail head width of the stock rail based on a plurality of point cloud sections within the second feature point recognition area; a dividing unit, configured to determine a second rail head coordinate range according to the second rail head width and a preset second target rail extension direction; a calibration unit, configured to, when a first point cloud section having a target point that is not within the second rail head coordinate range is determined from the plurality of point cloud sections according to the extension direction of the second target rail, and when target points that are not within the second rail head coordinate range are present in subsequent point cloud sections, and when the distances between the target points and the second rail head coordinate range gradually increase, calibrate the first target point that is not within the second rail head coordinate range as the second target point; The determination unit is configured to determine, according to a preset second target track extension direction, the second rail head widths of a plurality of point cloud sections within the second feature point recognition area; determine distribution parameters of the first n second rail head widths; the distribution parameters being standard deviation, variance, mean absolute deviation, or coefficient of variation; determine, in ascending order of n values, the value of n at which the distribution parameter is greater than or equal to the preset first parameter for the first time as an overrun parameter; determine the value of m as the difference between the overrun parameter and the preset second parameter; and determine the second rail head width of the base rail based on the first m second rail head widths.

10. A characteristic point calibration device for railway turnouts, characterized in that: include: An acquisition unit, used for acquiring three-dimensional point cloud data composed of multiple point cloud sections; The point cloud section is composed of a plurality of target points; the point cloud section is perpendicular to the extension direction of the base track; a matching unit, configured to determine, from the three-dimensional point cloud data, a third feature point recognition area corresponding to a preset third target range based on the coordinates of the plurality of target points; a determining unit, configured to determine a third rail head width of the base rail based on a plurality of point cloud sections within the third feature point recognition area; a dividing unit, configured to determine a coordinate range of the third rail head according to the third rail head width and a preset third target rail extension direction; a calibration unit, configured to, when determining, from the plurality of point cloud sections according to the extension direction of the third target track, a first point cloud section having a target point that is not within the third rail head coordinate range, and when subsequent point cloud sections all have target points whose distance from the third rail head coordinate range is greater than a preset third distance, calibrate the first target point that is not within the third rail head coordinate range as a third target point; The determination unit is configured to determine, according to a preset third target rail extension direction, the third rail head widths of the base rail of multiple point cloud sections within the third feature point recognition area; determine distribution parameters of the first n third rail head widths; the distribution parameters being standard deviation, variance, mean absolute deviation, or coefficient of variation; determine, in ascending order of n values, the value of n for which the distribution parameter is greater than or equal to a preset first parameter for the first time as an overrun parameter; determine the value of m as the difference between the overrun parameter and a preset second parameter; and determine the third rail head width of the base rail based on the first m third rail head widths.

11. 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.

12. An electronic device comprising 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 according to any one of claims 1 to 7 is implemented.

13. 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 is caused to perform the method according to any one of claims 1 to 7.

Images