Train speed measurement positioning method and system, storage medium and electronic equipment

Abstract

The invention belongs to the technical field of rail transit, and provides a train speed measurement positioning method and system, a storage medium and electronic equipment, and the method comprises the steps: receiving original data which comprises a scanning picture generated by scanning the surrounding environment of a train through a two-dimensional laser sensor; performing linear fitting on each scanning point of the scanned picture, and determining feature points in the scanned picture; matching the feature points in the two frames of scanned pictures to obtain a feature point group of the two frames of scanned pictures, and determining a displacement distance corresponding to the two frames of scanned pictures through the feature point group; according to the multiple continuous displacement distances, the accumulated state of train displacement is calculated, and according to the accumulated state, the positioning and speed of the train are determined. Off-line map drawing in advance is not needed, the two-dimensional laser sensor is used for train positioning and speed measurement, the structure is simple, installation is convenient, cost is low, and the application scene is wide; the algorithm for realizing positioning and speed measurement is simple, the occupied memory is small, the calculation speed is high, and the real-time performance of positioning and speed measurement is improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of rail transit, and particularly relates to a train speed measurement and positioning method, system, storage medium and electronic device. Background Art

[0002] In the aspect of rail transit train positioning technology, for wheel-rail vehicles, speed sensors plus radar accelerators and other methods have been mostly used for a long time. Affected by the change of wheel diameter value, equipment such as speed transmitters need to be maintained manually regularly, otherwise there will be safety risks. For non-wheel-rail vehicles, there is no mature positioning solution yet.

[0003] Currently, taking advantage of the accurate distance measurement of the ground positioning points by lasers, through the change of the distances of the main obstacle feature points in a similar environment within different periods, the relative position change of the train in space can be accurately judged, and then information such as the speed and acceleration of the train can be calculated; moreover, the laser can also synchronously scan and map the surrounding environment for subsequent use.

[0004] Currently, the main method of two-dimensional laser speed measurement and positioning is to first establish a map through a mapping algorithm, and then compare it with the map to deduce the current position; it is necessary to perform offline mapping in advance, and it is necessary to deploy the maps of all possible running lines of the train in on-vehicle equipment, which cannot meet the operation requirements in some rail transits. Summary of the Invention

[0005] To solve the above problems, the present disclosure provides a train speed measurement and positioning method, system, storage medium and electronic device. A two-dimensional laser sensor is installed on the train. The two-dimensional laser sensor is used to scan the environment around the train, generate raw data, and obtain the scanned pictures in the raw data. The scanned pictures include multiple scan points, and feature points are determined among the multiple scan points; according to the feature points in two frames of scanned pictures, a feature point group is determined, and the displacement distance is determined using the feature point group. Multiple consecutive displacement distances generate the cumulative state of the train displacement, and then the positioning and vehicle speed of the train are determined.

[0006] The present invention is realized through the following technical solutions: In a first aspect, an embodiment of the present disclosure provides a train speed measurement and positioning method, and the method includes: Receiving raw data, where the raw data includes scanned pictures of the environment around the train; wherein, the raw data is generated by scanning the environment around the train with a two-dimensional laser sensor; Extracting multiple scan points in the scanned pictures, performing linear fitting on each scan point, and determining the feature points in the scanned pictures according to the linear fitting results of each scan point; Match the feature points in the two frames of the scanned pictures, obtain the feature point groups of the two frames of the scanned pictures, and determine the displacement distance corresponding to the two frames of the scanned pictures through the feature point groups; According to a plurality of consecutive displacement distances, calculate the cumulative state of the train displacement, and determine the train positioning and speed according to the cumulative state.

[0007] Furthermore, Generate a train travel map according to the cumulative state; wherein, the train travel map includes the surrounding environment of the track represented by feature points.

[0008] Furthermore, Plot a plurality of the scanned points in the scanned picture in a two-dimensional rectangular coordinate system; For a set composed of a target scanned point and N adjacent scanned points before and after it, use the least squares method for linear fitting. The fitting formula for linear fitting of the target scanned point includes: ; ; Wherein, is the average coordinate of N scanned points and the target scanned point on the x-axis, is the average coordinate of N scanned points and the target scanned point on the y-axis, where N is a natural number; is the abscissa of the scanned point on the x-axis, is the ordinate of the scanned point on the y-axis, i is a natural number; k is the slope of the straight line fitted by the scanned point in the two-dimensional coordinate system, and m is the intercept of the fitted straight line on the y-axis.

[0009] Furthermore, Determine the linear fitting characteristics of each scanned point according to the linear fitting results of each scanned point; Select the feature points from the scanned points in the scanned picture according to the linear fitting characteristics; wherein, The linear fitting characteristics include a first characteristic and a second characteristic; taking a scanned point as a selection point, the included angle formed by the linear fittings of the scanned points on both sides of the selection point is determined as the first characteristic; the distance from the scanned point to its linear fitting is determined as the second characteristic.

[0010] Furthermore, Among the selected feature points, determine the edge feature points, and the edge feature points correspond to the edge positions of the train surrounding environment or obstacles.

[0011] Furthermore, Match the feature points in two frames of the scanned pictures by combining the first features of the feature points in the two frames of the scanned pictures and the positions of the feature points in the two frames of the scanned pictures; Obtain the feature point groups of two frames of the scanned pictures; the feature point groups include the overlapping feature points corresponding to the two frames of the scanned pictures and the edge feature points corresponding to the two frames of the scanned pictures; Calculate the displacement distance corresponding to the two frames of the scanned pictures by using the coordinate transformation matrix through the feature point groups.

[0012] Further, Connect the edge feature points corresponding to the two frames of the scanned pictures in the feature point groups with the overlapping feature points in the feature point groups respectively to generate two reference lines, and the included angle formed by the two reference lines is the rotation angle corresponding to the two frames of the scanned pictures; Determine the coordinates of the edge feature points corresponding to the two frames of the scanned pictures, and use the coordinate transformation matrix to determine the displacement distance of the two frames of the scanned pictures. The coordinate transformation matrix is as follows: ; Wherein, Corresponding to , is the coordinate of the edge feature point of the previous frame in the two frames of the scanned pictures; Corresponding to , is the coordinate of the edge feature point of the corresponding latter frame in the two frames of the scanned pictures; Is , b is , c is , d is , Is the rotation angle of the two frames of the scanned pictures; Is the displacement distance of the two frames of the scanned pictures in the x-axis direction, Is the displacement distance of the two frames of the scanned pictures in the y-axis direction.

[0013] Further, Match the feature points in the scanned pictures with the typical feature points in the reference map to calibrate the train positioning.

[0014] Further, Pre-generate the reference map; wherein, the reference map includes the track surrounding environment characterized by the typical feature points and non-typical feature points, and each typical feature point includes a corresponding life parameter value, and the life parameter value is used to characterize the usage frequency of the typical feature points in the train running map; Match the feature points of the scanned image with the typical feature points in the train's surrounding environment. For the typical feature points that are successfully matched, increase their life parameter values; for those that are not successfully matched, decrease their life parameter values.

[0015] Second aspect, based on the same inventive concept, embodiments of the present disclosure further provide a train speed measurement and positioning system, which includes: a data acquisition module, a feature point determination module, a displacement calculation module, and a positioning and speed measurement module; The data acquisition module is used to receive raw data, where the raw data includes scanned images of the train's surrounding environment; among them, the raw data is generated by scanning the train's surrounding environment with a two-dimensional laser sensor. The feature point determination module is used to extract multiple scan points in the scanned image, perform linear fitting on each scan point, and determine the feature points in the scanned image according to the linear fitting results of each scan point. The displacement calculation module is used to match the feature points in two frames of the scanned images, obtain the feature point groups of the two frames of scanned images, and determine the displacement distance corresponding to the two frames of scanned images through the feature point groups. The positioning and speed measurement module is used to calculate the cumulative state of the train's displacement according to a continuous plurality of the displacement distances, and determine the position and speed of the train according to the cumulative state.

[0016] Third aspect, based on the same inventive concept, embodiments of the present disclosure further provide a computer-readable storage medium, storing one or more programs, which can implement the aforementioned train speed measurement and positioning method when the one or more programs are executed.

[0017] Fourth aspect, based on the same inventive concept, embodiments of the present disclosure further provide an electronic device, including a processor, a communication interface, the aforementioned computer-readable storage medium, and a communication bus. Among them, the processor, the communication interface, and the computer-readable storage medium communicate with each other through the communication bus. Among them, the processor is used to execute the program stored in the aforementioned computer-readable storage medium.

[0018] Compared with the prior art, the present disclosure has the following advantages: 1. Effectively avoid the influence of train electromagnetic interference on the speed measurement and positioning functions, and can achieve positioning without the need to pre-draw a map offline; 2. Select a two-dimensional laser sensor for train positioning and speed measurement, with a simple structure, convenient installation, low cost, and can be applied to train positioning and speed measurement in a rail transit operation environment where there are no obvious features in the sleeper deployment, and can also be used for positioning and speed measurement of trains with different wheel diameters or non-wheel-rail vehicles; 3. The algorithms for realizing positioning and speed measurement are simple, occupy little memory, and have a fast calculation speed, improving the real-time performance of positioning and speed measurement.

[0019] Other features and advantages of the present disclosure will be described in the following specification, and part of them will become obvious from the specification or be understood by implementing the present disclosure. The objectives and other advantages of the present disclosure can be achieved and obtained through the structures pointed out in the specification, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a flowchart of a train speed measurement and positioning method provided by an embodiment of the present disclosure; Figure 2 It is a schematic diagram of a scanned picture provided by an embodiment of the present disclosure; Figure 3 It is a schematic diagram of feature points provided by an embodiment of the present disclosure; Figure 4 It is a schematic diagram of a feature point group provided by an embodiment of the present disclosure; Figure 5 It is a block diagram of a train speed measurement and positioning system provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts fall within the scope of protection of the present disclosure.

[0023] In the first aspect, Figure 1 It is a flowchart of a train speed measurement and positioning method provided by an embodiment of the present disclosure. As Figure 1 shown, an embodiment of the present disclosure provides a train speed measurement and positioning method, including: S1: Receive original data, where the original data includes scanned pictures of the train's surrounding environment.

[0024] Specifically, the original data is generated by scanning the train's surrounding environment with a two-dimensional laser sensor, and the two-dimensional laser sensor is installed on the train.

[0025] S2: Extract multiple scanning points from the scanned image, perform linear fitting on each scanning point, and determine the feature points in the scanned image according to the linear fitting results of each scanning point.

[0026] S3: Match the feature points in two frames of scanned images, obtain the feature point groups of the two frames of scanned images, and determine the displacement distance corresponding to the two frames of scanned images through the feature point groups.

[0027] S4: Calculate the cumulative state of the train displacement according to multiple consecutive displacement distances, and determine the train's position and speed according to the cumulative state.

[0028] Specifically, according to the cumulative state of the train, combined with the starting position corresponding to the train's cumulative state, the position of the train is determined, thereby realizing train positioning; at the same time, the speed of the train is determined through the cumulative state and the time used for the train's cumulative driving state.

[0029] In the embodiment of the present disclosure, a two-dimensional laser sensor is installed on the train. The two-dimensional laser sensor is used to scan the environment around the train, generate raw data, and obtain the scanned images in the raw data. The scanned images include multiple scanning points, and feature points are determined among the multiple scanning points; according to the feature points in two frames of scanned images, a feature point group is determined, and the displacement distance is determined using the feature point group. Multiple consecutive displacement distances generate the cumulative state of the train displacement, and then the train's position and speed are determined.

[0030] The train speed measurement and positioning method in the embodiment of the present disclosure effectively avoids the influence of train electromagnetic interference on the speed measurement and positioning functions, and can realize positioning without pre-drawing a map offline; a two-dimensional laser sensor is selected for train positioning and speed measurement, with a simple structure, convenient installation, low cost, and can be applied to train positioning and speed measurement in a rail transit operation environment where there are no obvious features in the sleeper deployment, and can also be used for the positioning and speed measurement of trains with different wheel diameters or non-wheel-rail vehicles.

[0031] The train speed measurement and positioning method in the embodiment of the present disclosure has a simple algorithm, small memory occupancy, and fast calculation speed, improving the real-time performance of positioning and speed measurement; for example, the train speed measurement and positioning method can be transplanted into an embedded mainboard, and the matching processing time for each frame of data is about 5ms, meeting the real-time requirements of rail transit for positioning and speed measurement.

[0032] In some examples, the train speed measurement and positioning method further includes: S5: Generate a train driving map according to the cumulative state; wherein, the train driving map includes the environment around the track represented by feature points.

[0033] Specifically, the cumulative state is the accumulation of multiple displacement distances that are continuous in time. The train speed measurement and positioning method in the embodiments of the present disclosure can generate a train travel map while the train is running, without the need for pre-offline map drawing; of course, it can also generate a train travel map before the train line is opened. In the actual process of generating a train travel map, handheld mapping can be achieved through a two-dimensional laser sensor, and then the surrounding environment of the track can be mapped to generate a train travel map.

[0034] In some examples, multiple scan points in the scanned image are extracted, linear fitting is performed on each scan point, and according to the linear fitting results of each scan point, the feature points in the scanned image are determined, specifically including: S21: Plot multiple scan points in the scanned image in a two-dimensional rectangular coordinate system.

[0035] S22: For the set composed of the target scan point and its N adjacent scan points before and after, use the least squares method to perform linear fitting. The fitting formula for performing linear fitting on the target scan point includes: (1) (2) Wherein, is the average coordinate of the N scan points and the target scan point on the x-axis, is the average coordinate of the N scan points and the target scan point on the y-axis, where N is a natural number; is the abscissa of the scan point on the x-axis, is the ordinate of the scan point on the y-axis, and i is a natural number; k is the slope of the line fitted by the scan point in the two-dimensional coordinate system, and m is the intercept of the fitted line on the y-axis.

[0036] It should be understood that the target scan point refers to the scan point for which linear fitting is performed using formula (1) and formula (2), and is mainly used for description here, rather than generating or determining a single scan point separately.

[0037] Furthermore, extracting multiple scan points in the scanned image, performing linear fitting on each scan point, and determining the feature points in the scanned image according to the linear fitting results of each scan point further includes: S23: Determine the fitting line feature of each scan point according to the linear fitting result of each scan point.

[0038] S24: Select feature points from the scan points in the scanned image according to the fitting line feature.

[0039] Specifically, the fitting straight line feature includes a first feature and a second feature; taking a scanned point as a selection point, the included angle formed by the fitting straight lines of the scanned points on both sides of the selection point is determined as the first feature; the distance from the scanned point to its fitting straight line is determined as the second feature. The way to determine the first feature can be to determine the included angle between the two fitting straight lines through the slopes of the two fitting straight lines of the scanned points on both sides of the selection point.

[0040] Furthermore, among the selected feature points, edge feature points are determined, and the edge feature points correspond to the edge positions of the train's surrounding environment or obstacles. The edge feature points correspond to the edge positions of the train's surrounding environment or obstacles; for example: the corners of the building walls around the train, the edge positions of the columns in the station, etc. Among the feature points in a frame of scanned image, the feature points with a significantly larger distance between adjacent two feature points can be used as edge feature points.

[0041] In some examples, the feature points in two frames of scanned images are matched to obtain the feature point groups of the two frames of scanned images, and the displacement distance corresponding to the two frames of scanned images is determined through the feature point groups, including: S31: Match the feature points in the two frames of scanned images by combining the first feature of the feature points in the two frames of scanned images with the positions of the feature points in the two frames of scanned images.

[0042] S32: Obtain the feature point groups of the two frames of scanned images.

[0043] Specifically, the feature point group includes the coincident feature points corresponding to the two frames of scanned images and the corresponding edge feature points in the two frames of scanned images.

[0044] S33: Calculate the displacement distance corresponding to the two frames of scanned images through the feature point group using the coordinate transformation matrix.

[0045] Furthermore, calculating the displacement distance corresponding to the two frames of scanned images through the feature point group using the coordinate transformation matrix includes: S331: Connect the corresponding edge feature points in the two frames of scanned images in the feature point group with the coincident feature points in the feature point group respectively to generate two reference straight lines, and the included angle formed by the two reference straight lines is the rotation angle corresponding to the two frames of scanned images.

[0046] S332: Determine the coordinates of the corresponding edge feature points in the two frames of scanned images, and use the coordinate transformation matrix to determine the displacement distance between the two frames of scanned images. The coordinate transformation matrix is as follows: (3) Among them, Corresponding to , is the coordinate of the edge feature point of the previous frame among the two frames of scanned images; Corresponding to , are the coordinates of the corresponding edge feature points in the latter frame among two frames of scanned pictures; is , b is , c is , d is , is the rotation angle of two frames of scanned pictures; is the displacement distance of two frames of scanned pictures in the x-axis direction, is the displacement distance of two frames of scanned pictures in the y-axis direction.

[0047] In some examples, according to multiple consecutive displacement distances, calculate the cumulative state of the train displacement, and according to the cumulative state, determine the train's positioning and speed, specifically including: S41: According to the cumulative state of the train, combined with the starting position corresponding to the train's cumulative state, determine the position of the train, thereby realizing train positioning.

[0048] S42: Determine the speed of the train through the cumulative state and the time used for the train's cumulative driving state.

[0049] In the embodiments of the present disclosure, in order to improve the positioning accuracy and positioning efficiency, a reference map of the train's driving route is pre-generated. The reference map can be a more accurate map determined by the train driving along a line multiple times, or a pre-drawn map, and no further limitation is made here.

[0050] The reference map includes the track surrounding environment characterized by typical feature points and atypical feature points. Each typical feature point includes a corresponding life parameter value, and the life parameter value is used to characterize the usage frequency of the typical feature points in the train driving map. Match the feature points in the scanned picture with the typical feature points in the reference map to calibrate the train positioning.

[0051] The life parameter value of the successfully matched typical feature points is increased, and the life parameter value of the unsuccessfully matched typical feature points is decreased. During the process of matching the scanned picture and the reference map, give priority to matching with the typical feature points, thereby improving the positioning accuracy while improving the positioning efficiency.

[0052] Embodiment 1: S101: Receive the original data and determine the scanned picture.

[0053] Use a two-dimensional laser sensor to scan the track surrounding environment and collect the original data at a certain moment. The original data can be a frame of data or multiple frames of data within a time range, and each frame of data corresponds to a scanned picture.

[0054] S102: Determine the feature points in the scanned picture.

[0055] Such asFigure 2 As shown in Figure 2 , the scanned image includes multiple scanning points. The multiple scanning points are plotted in a two-dimensional rectangular coordinate system. All adjacent scanning points are connected to generate line segments. The multiple scanning points and line segments form a scanned image of the train's surrounding environment. Linear fitting is performed on all scanning points. The following takes the linear fitting of one scanning point as an example for illustration.

[0056] A set composed of the target scanning point and the N scanning points adjacent to it before and after. Using the least squares method, linear fitting is performed. The fitting formula for performing linear fitting on the target scanning point includes: (1) (2) Where, is the average value of the coordinates of the N scanning points and the target scanning point on the x-axis, is the average value of the coordinates of the N scanning points and the target scanning point on the y-axis, where N is a natural number; is the abscissa of the scanning point on the x-axis, is the ordinate of the scanning point on the y-axis, i is a natural number; k is the slope of the line fitted by the scanning point in the two-dimensional coordinate system, and m is the intercept of the fitted line on the y-axis.

[0057] Using formula (1) and formula (2), linear fitting is performed on all scanning points in a scanned image. According to the characteristics of the fitted lines of each scanning point, characteristic points are determined from the scanning points. The characteristics of the fitted lines include the first characteristic and the second characteristic. The first characteristic is the angle formed by the fitted lines of the scanning points on both sides adjacent to the scanning point. Specifically, taking one scanning point as the selected point, the angle formed by the fitted lines of the scanning points on both sides of the selected point is the first characteristic; the second characteristic is the distance from the scanning point to its fitted line. The first characteristic of the fitted line of the scanning point reflects the change in the physical characteristics corresponding to the scanning point. For example, a large angle formed by the fitted lines of the scanning points on both sides of the selected point indicates that the selected point corresponds to the corner of a building, the edge of a column, etc. in the train's surrounding environment; the second characteristic can screen out high-quality characteristic points with good fitting quality. The shorter the distance from the scanning point to the corresponding fitted line, the better the fitting quality. Usually, scanning points with a large angle corresponding to the first characteristic of the fitted line of the scanning point and a short distance corresponding to the second characteristic are used as characteristic points.

[0058] After determining the characteristic points among several scanning points, edge characteristic points are determined among the characteristic points. The edge characteristic points correspond to the edge positions of the train's surrounding environment or obstacles; for example: the corner of the building wall around the train, the edge position of the column in the station, etc. In a scanned image, characteristic points with a significantly longer distance between two adjacent characteristic points can be used as edge characteristic points. As Figure 3As shown in the figure, the blue solid marked points in the figure are the edge feature points, and the green hollow marked points are the non-edge feature points.

[0059] S103: Determine the displacement distance corresponding to two frames of scanned pictures through the feature point group.

[0060] Through the first feature of the feature points of two frames of scanned pictures, combined with the positions of the feature points in the two frames of scanned pictures, match the feature points in the two frames of scanned pictures to determine the corresponding relationship of each feature point in the two frames of scanned pictures. For example, among the feature points in the same area of two frames of scanned pictures, select one feature point respectively, so that the first features of the two selected feature points are the closest, so as to determine the corresponding relationship of the feature points. It can be understood that determining the corresponding feature points in the front and back two frames of scanned pictures is used to judge the displacement corresponding to the two frames of scanned pictures.

[0061] After determining the corresponding relationship of each feature point in the two frames of scanned pictures, determine the feature point group according to the corresponding relationship of each feature point in the two frames of scanned pictures; the feature point group includes the overlapping feature points corresponding to the two frames of scanned pictures and the corresponding edge feature points in the two frames of scanned pictures.

[0062] As Figure 4 shown in the figure, there are three obvious marked points in the figure. The largest marked point (green marked point) below is the overlapping feature point corresponding to the two frames of scanned pictures. There are two relatively smaller marked points (red marked point and yellow marked point) above, which are the corresponding edge feature points in the two frames of scanned pictures respectively. Connect the two edge feature points (red marked point and yellow marked point) with the largest marked point (green marked point) below to generate two reference lines. The included angle formed by these two reference lines is the rotation angle corresponding to the two frames of scanned pictures. After determining the coordinates of the corresponding edge feature points in the two frames of scanned pictures, use the coordinate transformation matrix to determine the displacement distance of the two frames of scanned pictures. The coordinate transformation matrix is as follows: (3) Among them, Corresponding to , it is the coordinate of the edge feature point of the previous frame in the two frames of scanned pictures; Corresponding to , it is the coordinate of the corresponding edge feature point of the latter frame in the two frames of scanned pictures; Is , b is , c is , d is , Is the rotation angle of the two frames of scanned pictures; Is the displacement distance of the two frames of scanned pictures in the x-axis direction, Is the displacement distance of the two frames of scanned pictures in the y-axis direction.

[0063] It should be understood that, as Figure 4 shown, there are three obvious marked points, which actually correspond to 4 feature points. The overlapping feature points are usually the feature points with unchanged relative positions or the smallest relative position changes in two consecutive frame scanning pictures.

[0064] S104: Determine the cumulative state of the train displacement, and determine the train's position and speed.

[0065] Determine the displacement distance between two consecutive frame scanning pictures through formula (3) 、 , and accumulate multiple consecutive displacement distances e and f in time to generate the cumulative state of the train displacement; according to the cumulative state of the train, combined with the starting position corresponding to the cumulative state of the train, determine the position of the train, thereby realizing train positioning; at the same time, determine the train speed through the cumulative state and the time used for the cumulative state of the train's travel.

[0066] S105: Generate a train travel map.

[0067] While positioning the train, generate a train travel map according to the cumulative state of the train displacement. The train travel map includes the surrounding environment of the track represented by feature points.

[0068] Furthermore, a train travel map can be generated while the train is traveling for the first time, or a train travel map can be generated before the train line is opened. The method for generating a train travel map includes steps 101 to 104.

[0069] Furthermore, through the methods of steps 101 to 104, handheld mapping can be realized through a two-dimensional laser sensor, and then the surrounding environment of the track can be mapped.

[0070] Embodiment 2: The two-dimensional laser sensor on the train scans the surrounding environment of the train to generate scanning pictures. Extract multiple scanning points in the scanning pictures, perform linear fitting on each scanning point, and determine the feature points in the scanning pictures according to the linear fitting results of each scanning point. Match the feature points in two consecutive frame scanning pictures to obtain the feature point groups of the two consecutive frame scanning pictures, and determine the displacement distance corresponding to the two consecutive frame scanning pictures through the feature point groups. Generate the cumulative state of the train displacement according to multiple consecutive displacement distances, and determine the train's position and speed. Positioning and speed measurement are performed through the cumulative state determined by accumulating the displacement distances of two consecutive frame scanning pictures. There may be a certain error in the displacement distance of each two consecutive frame scanning pictures, and when determining the cumulative state of the train displacement, the errors existing in the displacement distances of each two consecutive frame scanning pictures will also be accumulated, ultimately resulting in an error in train positioning.

[0071] Therefore, it is necessary to match the feature points in the scanned image with the typical feature points in the reference map to improve the positioning accuracy. The reference map can be a more accurate map determined by the train traveling along a line multiple times, or a pre-drawn map, which is not further limited here.

[0072] The reference map includes the environment around the track characterized by typical feature points and atypical feature points. Each typical feature point includes a corresponding life parameter value, and the life parameter value is used to characterize the usage frequency of the typical feature points in the train traveling map.

[0073] Furthermore, the feature points with higher usage frequency are selected as typical feature points, and the typical feature points are updated according to the life parameter values. When the train is positioning, in order to improve the positioning accuracy of the train, the feature points in the scanned image are matched with the typical feature points in the train surrounding environment. In each matching process, the life parameter value of the typical feature point used increases, and the life parameter value of the typical feature point not used for a period of time decreases. When the feature points in the scanned image cannot match the typical feature points in the reference map, the atypical feature points in the reference map can be matched. If the atypical feature points are successfully matched multiple times, they can be used as typical feature points.

[0074] In a second aspect, Figure 5 a block diagram of a train speed measurement and positioning system provided by an embodiment of the present disclosure is shown in Figure 5 As shown, based on the same inventive concept, an embodiment of the present disclosure further provides a train speed measurement and positioning system, which includes: a data acquisition module, a feature point determination module, a displacement calculation module, and a positioning and speed measurement module. The data acquisition module is used to receive raw data, and the raw data includes scanned images of the train surrounding environment. Among them, the raw data is generated by scanning the train surrounding environment with a two-dimensional laser sensor. The feature point determination module is used to extract multiple scan points in the scanned image, perform linear fitting on each scan point, and determine the feature points in the scanned image according to the linear fitting results of each scan point. The displacement calculation module is used to match the feature points in two frames of scanned images, obtain the feature point groups of the two frames of scanned images, and determine the displacement distance corresponding to the two frames of scanned images through the feature point groups. The positioning and speed measurement module is used to calculate the cumulative state of the train displacement according to a continuous plurality of displacement distances, and determine the position and speed of the train according to the cumulative state.

[0075] In a third aspect, based on the same inventive concept, an embodiment of the present disclosure further provides a computer-readable storage medium, storing one or more programs, and when the one or more programs are executed, the foregoing train speed measurement and positioning method can be implemented.

[0076] Fourthly, based on the same inventive concept, embodiments of the present disclosure further provide an electronic device, including a processor, a communication interface, the aforementioned computer-readable storage medium, and a communication bus. Among them, the processor, the communication interface, and the computer-readable storage medium communicate with each other through the communication bus. Among them, the processor is configured to execute the program stored in the aforementioned computer-readable storage medium.

[0077] It should be noted that the electrical connections between the above-mentioned various units do not necessarily represent the connections between the lines. Indirect connection methods, as long as the purpose of the present disclosure is achieved, can be applied to the embodiments of the present disclosure.

[0078] Although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A train speed measurement and positioning method, characterized in that The method includes: Receiving original data, where the original data includes scanned pictures of the environment around the train; wherein, the original data is generated by scanning the environment around the train with a two-dimensional laser sensor; Extracting multiple scan points from the scanned pictures, performing linear fitting on each of the scan points, and determining feature points in the scanned pictures according to the linear fitting results of each scan point; Matching the feature points in two frames of the scanned pictures, obtaining a feature point group of the two frames of the scanned pictures, and determining the displacement distance corresponding to the two frames of the scanned pictures through the feature point group; Calculating the cumulative state of the train displacement according to multiple consecutive displacement distances, and determining the positioning and vehicle speed of the train according to the cumulative state.

2. The method according to claim 1, characterized in that The method further includes: Generating a train travel map according to the cumulative state; wherein, the train travel map includes the environment around the track represented by feature points.

3. The method according to claim 1, wherein Extracting multiple scan points from the scanned pictures, performing linear fitting on each scan point, and determining feature points in the scanned pictures according to the linear fitting results of each scan point, including: Plotting the multiple scan points in the scanned pictures in a two-dimensional rectangular coordinate system; For a set composed of a target scan point and its N adjacent scan points before and after, using the least squares method to perform linear fitting, and the fitting formula for performing linear fitting on the target scan point includes: ； ； Among them, is the average coordinate on the x-axis of N scanning points and the target scanning point, is the average coordinate on the y-axis of N scanning points and the target scanning point, where N is a natural number; is the abscissa on the x-axis of the scanning point, is the ordinate on the y-axis of the scanning point, i is a natural number; k is the slope of the line fitted by the scanning points in the two-dimensional coordinate system, and m is the intercept of the fitted line on the y-axis.

4. The method according to claim 3, wherein The extracting multiple scan points from the scanned pictures, performing linear fitting on each scan point, and determining feature points in the scanned pictures according to the linear fitting results of each scan point, including: Determining the fitting line feature of each scan point according to the linear fitting result of each scan point; Selecting the feature points from the scan points in the scanned pictures according to the fitting line feature; wherein, The fitting line feature includes a first feature and a second feature; taking a scan point as a selection point, the included angle formed by the fitting lines of the scan points on both sides of the selection point is determined as the first feature; the distance from the scan point to its fitting line is determined as the second feature.

5. The method according to claim 4, characterized in that, Selecting feature points from the scan points in the scanned pictures according to the fitting line feature further includes: Determining edge feature points among the selected feature points, and the edge feature points correspond to the edge positions of the environment around the train or obstacles.

6. The method according to claim 1, characterized in that, Matching the feature points in two frames of the scanned pictures, obtaining a feature point group of the two frames of the scanned pictures, and determining the displacement distance corresponding to the two frames of the scanned pictures through the feature point group, including: Matching the feature points in two frames of the scanned pictures through the first feature of the feature points in the two frames of the scanned pictures, in combination with the positions of the feature points in the two frames of the scanned pictures; Obtaining the feature point group of the two frames of the scanned pictures; the feature point group includes the coincident feature points corresponding to the two frames of the scanned pictures and the corresponding edge feature points in the two frames of the scanned pictures; Calculating the displacement distance corresponding to the two frames of the scanned pictures through the feature point group using a coordinate transformation matrix.

7. The method according to claim 6, wherein The calculating the displacement distance corresponding to the two frames of the scanned pictures through the feature point group using a coordinate transformation matrix includes: Connect the corresponding edge feature points in two frames of the scanned pictures in the feature point group to the coincident feature points in the feature point group respectively to generate two reference lines, and the included angle formed by the two reference lines is the rotation angle corresponding to the two frames of the scanned pictures; Determine the coordinates of the corresponding edge feature points in two frames of the scanned pictures, and use the coordinate transformation matrix to determine the displacement distance between the two frames of the scanned pictures. The coordinate transformation matrix is as follows: ； Among them, corresponds to , which is the coordinate of the edge feature point in the previous frame among the two frames of the scanned pictures; corresponds to , which is the coordinate of the corresponding edge feature point in the subsequent frame among the two frames of the scanned pictures; is , b is , c is , d is , is the rotation angle of the two frames of the scanned pictures; is the displacement distance of the two frames of the scanned pictures in the x-axis direction, is the displacement distance of the two frames of the scanned pictures in the y-axis direction.

8. The method according to claim 1, wherein The method further includes: Match the feature points in the scanned picture with the typical feature points in the reference map to calibrate the train positioning.

9. The method according to claim 8, wherein Matching the feature points in the scanned picture with the typical feature points in the reference map to calibrate the train positioning includes: Pre-generate the reference map; wherein, the reference map includes the track surrounding environment characterized by the typical feature points and non-typical feature points, and each typical feature point includes a corresponding life parameter value, and the life parameter value is used to characterize the usage frequency of the typical feature point in the train running map; Match the feature points of the scanned picture with the typical feature points in the train surrounding environment, and increase the life parameter value of the typical feature points that are successfully matched, and decrease the life parameter value of the typical feature points that are not successfully matched.

10. A train speed measurement and positioning system, characterized in that, The system includes: a data acquisition module, a feature point determination module, a displacement calculation module, and a positioning and speed measurement module; The data acquisition module is used to receive the original data, and the original data includes the scanned pictures of the train surrounding environment; wherein, the original data is generated by scanning the train surrounding environment with a two-dimensional laser sensor; The feature point determination module is used to extract a plurality of scan points in the scanned picture, perform linear fitting on each scan point, and determine the feature points in the scanned picture according to the linear fitting results of each scan point; The displacement calculation module is used to match the feature points in two frames of the scanned pictures, obtain the feature point group of the two frames of the scanned pictures, and determine the displacement distance corresponding to the two frames of the scanned pictures through the feature point group; The positioning and speed measurement module is used to calculate the cumulative state of the train displacement according to a plurality of consecutive displacement distances, and determine the positioning and speed of the train according to the cumulative state.

11. A computer-readable storage medium storing one or more programs, characterized in that, When the one or more programs are executed, the train speed measurement and positioning method according to any one of claims 1-9 can be implemented.

12. An electronic device, comprising a processor, a communication interface, the computer-readable storage medium according to claim 11, and a communication bus; wherein, The processor, the communication interface, and the computer-readable storage medium communicate with each other through a communication bus; Characterized in that, The processor is used to execute the program stored in the computer-readable storage medium.

Images