CN115320669A - Method, device, equipment and medium for detecting railway coming car based on radar map - Google Patents

Abstract

The embodiment of the application discloses a method, a device, equipment and a medium for detecting a railway coming car based on a radar map. Wherein, the method comprises the following steps: determining a radar map according to an echo signal obtained by detecting a radar arranged at a target position point on a railway, and determining track data of a target to be detected according to the radar map; determining a co-orbit target in the target to be detected according to the flight path data of the target to be detected; wherein the common-rail target is a target located on a railway where the target location point is located; and if the distance between the co-orbit target and the target position point is less than the preset distance, carrying out safety early warning. According to the technical scheme, the radar is used for detecting, a large detection range is guaranteed, the same-rail target is determined from the target to be detected, the railway coming car can be accurately detected, and safety early warning is carried out.

Description

Method, device, equipment and medium for railway vehicle detection based on radar chart

technical field

The invention relates to the technical field of data processing, in particular to a method, device, equipment and medium for detecting incoming railway vehicles based on radar images.

Background technique

In order to keep the railway in a good state in line with the railway technical standards, it is necessary to carry out maintenance and repair operations on the railway subgrade and tracks. The other trains in the train will carry out safety warnings to prevent safety accidents.

Contents of the invention

The invention provides a method, device, equipment and medium for detecting incoming railway vehicles based on radar charts, which can accurately detect incoming railway vehicles and perform safety early warning.

According to one aspect of the present invention, there is provided a method for detecting railway vehicles based on radar images, the method comprising:

Determining the radar map according to the echo signal obtained by detecting the radar at the target position point on the railway, and determining the track data of the target to be measured according to the radar map;

According to the track data of the target to be measured, determine the target on the same track in the target to be measured; wherein, the target on the same track is a target located on the railway where the target position point is located;

If the distance between the target on the same track and the target location point is less than the preset distance, a safety warning is issued.

According to another aspect of the present invention, a kind of radar image-based railway vehicle detection device is provided, comprising:

The track data determination module is used to determine the radar map according to the echo signal obtained by detecting the radar set at the target position point on the railway, and determine the track data of the target to be measured according to the radar map;

The same-track target determination module is used to determine the same-track target in the target to be measured according to the track data of the target to be measured; wherein, the same-track target is a target located on the railway where the target position point is located ;

A safety warning module, configured to issue a safety warning if the distance between the target on the same track and the target location point is less than a preset distance.

According to another aspect of the present invention, an electronic device is provided, and the electronic device includes:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the method described in any embodiment of the present invention. A method of railway vehicle detection based on radar map.

According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement any of the embodiments of the present invention when executed. Radar map-based railway vehicle detection method.

According to the technical solution of the embodiment of the present application, the echo signal obtained by detecting the radar at the target position point on the railway is used to determine the radar map, and determine the track data of the target to be measured according to the radar map; The track data of the target determines the target on the same track in the target to be measured; wherein, the target on the same track is a target located on the railway where the target position point is located; if the distance between the target on the same track and the target position point If the distance is less than the preset distance, a safety warning will be issued. The technical solution uses radar for detection, which ensures a large detection range, and determines the same-track target from the target to be measured, and can accurately detect incoming railway vehicles and perform safety warnings.

It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will be easily understood from the following description.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.

FIG. 1 is a flow chart of a method for detecting incoming railway vehicles based on a radar map according to Embodiment 1 of the present application;

FIG. 2 is a flow chart of a method for detecting incoming railway vehicles based on a radar map according to Embodiment 2 of the present application;

Fig. 3a is a schematic diagram of a preset area of a radar map-based railway vehicle detection method provided according to an embodiment of the present application;

Fig. 3b is a schematic diagram of another preset area of a radar map-based railway vehicle detection method provided according to an embodiment of the present application;

Fig. 4 is a flow chart of a radar map-based railway vehicle detection method provided according to Embodiment 3 of the present application;

FIG. 5 is a schematic diagram of radar detection of a method for detecting incoming railway vehicles based on radar images according to an embodiment of the present application;

Fig. 6 is a schematic diagram of adjacent position points of a radar map-based railway vehicle detection method provided according to an embodiment of the present application;

Fig. 7 is a schematic diagram of the interpolation position points of a radar map-based railway vehicle detection method provided according to an embodiment of the present application;

FIG. 8 is a flow chart of a radar map-based railway vehicle detection method provided according to Embodiment 4 of the present application;

9 is a schematic structural diagram of a radar map-based railway vehicle detection device provided according to Embodiment 5 of the present application;

FIG. 10 is a schematic structural diagram of an electronic device implementing a method for detecting incoming railway vehicles based on a radar map according to an embodiment of the present application.

Detailed ways

In order to enable those skilled in the art to better understand the solution of the present invention, the technical solution in the embodiment of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the application. Obviously, the described embodiment is only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first", "second", and "object" in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and not necessarily used to describe a specific order or priority. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

Embodiment one

Fig. 1 provides a kind of flow chart of the railway car detection method based on the radar map for the first embodiment of the present application, the embodiment of the present application can be applicable to the situation of carrying out safety warning to the railway car coming, this method can be based on the radar map The railway vehicle detection device based on the radar chart can be implemented in the form of hardware and/or software, and the radar chart-based railway vehicle detection device can be configured in an electronic device with data processing capabilities . As shown in Figure 1, the method includes:

S110. Determine a radar map according to the echo signal detected by the radar installed at the target position on the railway, and determine the track data of the target to be measured according to the radar map.

Wherein, the target location point may be a location for railway maintenance or maintenance, for example, the target location point may be on a railway maintenance vehicle. The radar can be a microwave radar, such as a mechanical scanning millimeter-wave radar with single transmission and single reception. The radar map is an image used to reflect the reflected echo intensity data of each position in the radar detection area. In the embodiment of the present application, the radar map actually reflects a circle with the target position as the center and the radar detection distance as the radius. The location information of the target to be measured in the area. The target to be tested can be various targets around the railway such as trains and signs. The track data can reflect the position, moving speed and moving direction of the target to be measured.

Specifically, if there is a target to be measured in the radar detection area, the radar reflected wave intensity data at the position of the target to be measured is different from the radar reflected wave intensity data at other positions, which is then reflected in the pixel at the corresponding position of the target to be measured on the radar map The value of the point is different from that of other positions, based on which the position of the target to be measured can be determined according to the radar map. Further, at least two radar images are acquired to determine multiple positions passed by the target to be measured, and the moving speed and direction of the target to be measured are determined according to the multiple positions passed by the target to be measured.

Exemplarily, the coordinate system is constructed with the radar as the coordinate origin, and the track data can be expressed as (id _n , x _n , y _n , vx _n , vy _n ), where id _n represents the nth target to be measured, and x _n Represents the abscissa of the target to be measured, y _n represents the ordinate of the target to be measured, vx _n represents the sailing speed of the target to be measured in the x direction, and vy _n represents the sailing speed of the target to be measured in the y direction.

S120. Determine a target on the same track among the targets to be measured according to the track data of the target to be measured; wherein the target on the same track is an object located on the railway where the target position point is located.

Wherein, the target on the same track may be a target to be measured located on the railway track where the target position point is located, such as a train on the same railway. In the embodiment of the present application, the target to be measured may be located at any position in the radar detection area. Since the target to be measured on the railway where the target position point is located has potential safety hazards to the railway staff and/or related tools, it is necessary to select the target from each target to be measured. Identify the same track target.

S130, if the distance between the target on the same track and the target location point is less than a preset distance, perform a safety warning.

Wherein, the preset distance may be determined according to actual conditions, which is not limited in this embodiment of the present application. Ways of safety warning include but are not limited to: sound warning, warning light warning, etc.

In the embodiment of the present application, after the target on the same track is determined, the distance between the target on the same track and the target position point can be determined according to the track data. The distance to the target location point.

In one embodiment, the coordinate system is constructed with the radar as the coordinate origin, and the track data can be expressed as (id _n , x _n , y _n , vx _n , vy _n ), and the distance between the target on the same track and the target position point is L ,

If the distance L between the target on the same track and the target location point is less than a preset distance, a safety warning is issued.

According to the technical solution of the embodiment of the present application, the echo signal obtained by detecting the radar at the target position point on the railway is used to determine the radar map, and determine the track data of the target to be measured according to the radar map; The track data of the target determines the target on the same track in the target to be measured; wherein, the target on the same track is a target located on the railway where the target position point is located; if the distance between the target on the same track and the target position point If the distance is less than the preset distance, a safety warning will be issued. The technical solution uses radar for detection, which ensures a large detection range, and determines the same-track target from the target to be measured, and can accurately detect incoming railway vehicles and perform safety warnings.

Embodiment two

FIG. 2 is a flow chart of a method for detecting incoming railway vehicles based on a radar map provided in Embodiment 2 of the present application. The embodiment of the present application is optimized based on the foregoing embodiments.

As shown in Figure 2, the method of the embodiment of the present application specifically includes the following steps:

S210. Determine the radar map according to the echo signal detected by the radar installed at the target position on the railway, and determine the track data of the target to be measured according to the radar map.

S220. Determine whether the position point of the target to be measured is within a preset area according to the track data of the target to be measured.

Wherein, as shown in FIG. 3 a , the preset area may reflect the area of the railway where the target position point is located within the radar detection range.

Specifically, because the railway where the target location point is located is fixed, and the target to be measured located on the railway where the target location point is located may endanger railway maintenance personnel and/or maintenance equipment, so the preset area to determine whether the target to be tested is a target on the same track.

In this embodiment of the present application, optionally, the process of determining the preset area includes: determining a range of a railway section within a radar detection area; and using a polygonal range including the range of the railway section as the preset area.

In this solution, since the railway may have a turning part, the railway may be a straight line, or it may be approximated to a straight line in a small area. Furthermore, the shape of the preset area may be a polygon, as shown in Figure 3a. Specifically, the preset area may be determined according to the range of the railway section where the target position point within the radar detection range is located, and the embodiment of the present application does not limit the specific shape of the preset area.

In the embodiment of the present application, optionally, the polygonal range including the range of the railway section is used as the preset area, including: the range of the railway segment, or the range after expanding the range of the railway segment along the width direction of the railway, as the preset area .

Wherein, the preset area may be as shown in Fig. 3b. Exemplarily, taking the target to be measured as a train as an example, since the width of the train is wider than the width of the railway, the scope of the railway section expanded along the width direction of the railway is used as the preset area, so that the width of the preset area can be larger than that of the train width to ensure that the target to be measured can be located within the preset area.

S230, if the position point of the area to be measured is within the preset area, determine that the object to be measured is a target on the same track.

S240, if the distance between the target on the same track and the target location point is less than a preset distance, perform a safety warning.

In the technical solution of the embodiment of the present application, by delimiting the preset area, the target to be measured located in the preset area is used as the same-track target, and if the distance between the same-track target and the target position point is less than the preset distance, the safety early warning. The technical solution accurately determines the target on the same track through the preset area, and achieves the effect of high alarm accuracy.

Embodiment three

FIG. 4 is a flow chart of a method for detecting incoming railway vehicles based on a radar map provided in Embodiment 3 of the present application. The embodiment of the present application is optimized based on the foregoing embodiments.

As shown in Figure 4, the method of the embodiment of the present application specifically includes the following steps:

S310, according to the intensity data of the echo signal at the adjacent position point which is equal to the radar distance in the adjacent detection direction of the radar, perform intensity interpolation between the adjacent position points, and determine the intensity data at the interpolated position point which is equal to the radar distance .

The technical solution of the embodiment of the present application detects the target through the radar. The position of the radar is shown in FIG. 5 , which may be a mechanical scanning millimeter-wave radar with single transmission and single reception. The radar rotates around the center, continuously transmitting and receiving FM radio waves. Among them, the divergent dotted line emitted from the radar is the detection signal of the radar, the direction corresponding to two adjacent detection signals is the adjacent detection direction, and the adjacent position point is the point at the same distance from the radar in the adjacent detection direction, as shown in Points A and B in Figure 6. The reflected echo is the echo received by the radar after the detection signal emitted by the radar is reflected, and the intensity data of the reflected echo can be detected by the radar. The intensity data of the reflected echo corresponding to a certain position in the environment can reflect whether there is a target at the position, and the position, size, shape and other information of the target can be determined according to the intensity data of the reflected echo. The detection direction of each detection signal emitted by the radar can be characterized by the azimuth angle, and the azimuth angle of a detection direction can be the horizontal angle between the north pointing direction line of the radar and the detection direction in a clockwise direction. When the radar detects each azimuth angle, at each position point with a different distance from the radar in the azimuth angle, the intensity data of a reflected echo is correspondingly obtained, and each azimuth angle corresponds to multiple intensity data to obtain one-dimensional intensity data , the radar rotates and scans for a circle, and a two-dimensional intensity data corresponding to each position point represented by polar coordinates can be formed.

In the embodiment of the present application, different weights can be selected according to the intensity data of adjacent position points to determine the intensity data at the interpolation position points. For example, the intensity of adjacent position points is S _A and S _B , and their weights are respectively ω ₁ and ω ₂ , the intensity data at the interpolation position point is S _C , then S _C = _SA ×ω ₁ +S _B ×ω ₂ .

In the embodiment of the present application, S310 is optimized, and according to the intensity data of reflected echoes at adjacent positions equal to the distance from the radar in the adjacent detection direction of the radar, intensity interpolation is performed between adjacent position points to determine the The intensity data at the interpolation position points with equal distances includes: performing intensity interpolation on a concentric arc with the adjacent position point as the endpoint to obtain the interpolation position point; the concentric arc is centered on the radar, with The radar arrives at the arc of the radius of the adjacent position point; the concentric arc length from the first position point to the interpolation position point in the adjacent position point, and the ratio of the concentric arc length between the adjacent position points, as The first weight value of the intensity data of the second position point in the adjacent position points; the concentric arc length from the second position point to the interpolation position point in the adjacent position points, and the concentric arc length between the adjacent position points The ratio of is used as the second weight value of the intensity data of the first position point in the adjacent position points; according to the first weight value and the second weight value, the weighted sum of the intensity data of the adjacent position points is used as the interpolation value Intensity data for the location point.

上进行插值得到的。插值位置点的间隔可以相等，也可以不相等。如图7所示，A、B两点为相邻位置点，C、D两点为插值位置点且位于A、B两点之间，A、B、C和D到雷达的距离相同，则C点的强度数据

D点的强度数据

Specifically, the present application provides an interpolation method: performing intensity interpolation between adjacent location points may be to perform interpolation on a circular arc with the radar as the center and the adjacent location points as endpoints to obtain interpolated location points. As shown in Figure 7. The interpolation position point C and the interpolation position point D are in the circle centered on the radar

obtained by interpolation. Interpolation position points can be equally or unequally spaced. As shown in Figure 7, two points A and B are adjacent position points, two points C and D are interpolated position points and are located between A and B, and the distances from A, B, C and D to the radar are the same, then Intensity data at point C

Intensity data at point D

Exemplarily, the intensity data of reflected echoes at positions at different distances from the radar in the same detection direction of the radar are used as row elements of the matrix, and the intensity data of reflected echoes at positions at the same distance from the radar in different detection directions of the radar are used as a matrix The column elements of , construct the initial matrix.

In the embodiment of the present application, because the intensity data of the interpolation position point is calculated from the intensity data of the adjacent position points, the intensity data of the reflected echoes at the position points at different distances from the radar in the same detection direction of the radar are used as the row elements of the matrix, According to the change order of the radar detection direction, the second row, the third row, the fourth row, etc. of the initial matrix are sequentially formed. The intensity data of each detection direction is recorded as a sequence {a _n′ |n′∈[1,N]}, a _n′ represents the intensity data at a distance of n′×δ meters from the radar, where N is the number of samples, and δ is the range resolution of the radar. Each row represents the intensity data of the position points in the same detection direction of the radar and the distance from the radar increases sequentially, and each column represents the intensity data of the position points with the same distance from the radar in different detection directions, and the detection direction corresponding to the adjacent elements in each column is Adjacent detection direction, the detection direction corresponding to the first column element and the last column element is the adjacent detection direction, where the initial matrix A is as follows:

Among them, M represents the number of radar detection directions, and N represents the number of samples, that is, the number of intensity data obtained by the radar in the same detection direction. a ₁₁ indicates the intensity data of the point closest to the radar in the initial detection direction of the radar, a ₁₂ indicates the intensity data of the second position point in the initial detection direction of the radar and the distance from the radar is greater than a ₁₁ , and a ₂₁ indicates the second position of the radar in the initial detection direction of the radar In the first detection direction, the intensity data of the position point closest to the radar, a ₃₁ represents the intensity data of the position point closest to the radar in the third detection direction of the radar, and so on.

Further, the intensity interpolation is performed according to the column elements of the same column in the initial matrix to obtain an interpolation matrix, and the intensity data at the interpolation position point at the same distance as the radar is determined according to the interpolation matrix.

Exemplarily, the size of the initial matrix is M×N. If an interpolation position point is inserted between adjacent position points, the size of the interpolation matrix is 2M×N. If two interpolation position points are inserted between adjacent position points , the size of the interpolation matrix is 3M×N, and the embodiment of the present application does not limit the number of interpolation. In the embodiment of the present application, the intensity data of the interpolation position point is calculated based on the intensity data of the adjacent position points. In the initial matrix, the two adjacent matrix elements in each column are the intensity data of the adjacent position points, such as a ₃₁ and a ₄₁ is an adjacent matrix point. It should be noted that, in the same column of the initial matrix, the first element and the last element are adjacent position points.

In the embodiment of the present application, the distance between the position points equal to the radar is equal; the intensity interpolation is performed according to the column elements of the same column in the initial matrix, and the interpolation matrix is obtained, including:

Based on the following formula, the value of each element in the interpolation matrix can be determined by performing equal interval intensity interpolation according to the column elements of the same column in the initial matrix:

表示初始矩阵，

表示向下取整，％表示求余运算，T表示在相邻位置点之间插值位置点的数量加一，M表示雷达扫描一周时探测方向的数量。需要说明的是，通过上述公式确定的b_ij可能不是整数，因此为了使插值矩阵中的各元素为整数，可以对b_ij进行四舍五入取整，也可以向上取整或者向下取整，具体取整方式不做限定。另外，如果在之前的执行过程中未对强度数据进行归一化，也可以将此数据进行归一化到[0,255]之后再进行取整。Among them, b _ij represents the value of the element in row i, column j of the interpolation matrix,

represents the initial matrix,

Indicates rounding down, % indicates the remainder operation, T indicates the number of interpolated position points between adjacent position points plus one, M indicates the number of detection directions when the radar scans one cycle. It should be noted that b _ij determined by the above formula may not be an integer, so in order to make each element in the interpolation matrix an integer, b _ij can be rounded up or rounded up or down. The adjustment method is not limited. In addition, if the intensity data has not been normalized in the previous execution process, the data can also be normalized to [0,255] and then rounded.

的长度等于

的长度等于

的长度。In this scheme, in order to facilitate the calculation of the intensity data of the interpolation position points, the distance between the position points equal to the radar distance is set to be equal, that is, as shown in Figure 7, A and B are adjacent position points, C and D are interpolation position points, and A , B, C and D are the same distance from the radar, then

has a length equal to

has a length equal to

length.

Specifically, if interpolation is performed as shown in Figure 7, it can be determined that the interpolation matrix is:

S320. Determine the position point corresponding to each pixel point in the radar image.

Wherein, the position points include position points corresponding to each intensity data after intensity interpolation.

In the embodiment of the present application, determining the position point corresponding to each pixel point in the radar map includes: setting the radar as the image center of the radar map, and setting The pixel coordinates of each pixel point in the radar map are converted to Cartesian coordinates; according to the conversion relationship between Cartesian coordinates and polar coordinates, the polar coordinates corresponding to each pixel point are determined; according to the position points corresponding to the polar coordinates, each The location point corresponding to the pixel point.

Exemplarily, if the radar map F is set to include P rows and Q columns of pixels, then

Among them, f _pq represents the gray value of the pixel at the position (p, q), and F can be mapped to a rectangular area of PΔ×QΔ, where each pixel corresponds to a square area with a side length of Δm in the actual space, such as F Including 3000 rows and 2000 columns of pixels, if F maps a radar detection area of 600×400 meters, each pixel corresponds to a square area with a side length of 0.2 meters. In the embodiment of the present application, P and Q can be taken as odd numbers to set the radar position at the center of the radar map.

Specifically, if the radar position is set at the center of the radar map, the pixel point (p, q) is transformed into a Cartesian coordinate system as:

According to the above formula, the Cartesian coordinates corresponding to each pixel point can be obtained. According to the conversion relationship between Cartesian coordinates and polar coordinates, the polar coordinates corresponding to each pixel point can be determined. The conversion relationship is as follows:

(γ, θ) are polar coordinates, and || represents the relationship of or. The corresponding polar coordinates of each pixel can be obtained through the above formula operation. According to the position points corresponding to the polar coordinates, the position points corresponding to each pixel point in the radar image can be determined. For example, if the polar coordinates are (10,0°), the position points corresponding to the polar coordinates are: in the initial detection direction of the radar, the distance from the radar 10 meters away.

S330. According to the intensity data of each location point, determine the grayscale value of the radar image pixel point corresponding to each location point, and generate the radar image according to the grayscale value.

In the embodiment of the present application, the location point includes the adjacent location point before interpolation, and the interpolation location point after interpolation, correspondingly, the intensity data includes the intensity data of the adjacent location point before interpolation, and the interpolation location point after interpolation strength data. After determining the location point corresponding to each pixel point in the radar image, the gray value of each pixel point can be determined according to the intensity data of the location point, and then the radar image is drawn according to the gray value.

Determine the gray value of the radar image pixel based on the following formula:

若在相邻位置点之间插值位置点的数量为2，则

需要说明的是，根据上述公式确定雷达图像素点的灰度值之前，需已经将b_ij归一化至[0,255]之间，以表示灰度值。Among them, f _pq represents the gray value of the pixel with pixel coordinates (p, q) in the radar image, round represents rounding, θ represents the azimuth of the current detection direction, θ ₁ represents the azimuth of the initial detection direction, σ Indicates the deflection angle between two adjacent position points equal to the distance from the radar after intensity interpolation, γ indicates the distance between the position point and the radar, and δ indicates the minimum detection distance of the radar. Exemplarily, without interpolation,

If the number of interpolated position points between adjacent position points is 2, then

It should be noted that before determining the gray value of the radar image pixel according to the above formula, bij needs to be normalized to [ _0,255 ] to represent the gray value.

S340. Determine track data of the target to be measured according to the radar map.

S350. Determine a target on the same track among the targets to be measured according to the track data of the target to be measured; wherein the target on the same track is an object located on the railway where the target position point is located.

S360. If the distance between the target on the same track and the target location point is less than a preset distance, perform a safety warning.

According to the technical solution of the embodiment of the application, according to the intensity data of the reflected echoes at the adjacent position points equal to the radar distance in the adjacent detection direction of the radar, the intensity interpolation is performed between the adjacent position points, and the interpolation value equal to the radar distance is determined Intensity data at the position point; determine the position point corresponding to each pixel point in the radar image, determine the gray value of the radar image pixel point corresponding to each position point according to the intensity data of each position point, and according to the gray value Value generates a radar chart. This technical solution obtains the intensity data of the interpolated position points by interpolating the adjacent position points, expands the number of position points and intensity data detected by the radar, and determines the corresponding radar image pixel points according to the intensity data of each position point The gray value of the radar image can be quickly drawn to detect the target to be tested, which realizes the detection of the target to be tested in the area not detected by the radar, and improves the detection accuracy of the target to be tested.

Embodiment Four

FIG. 8 is a flow chart of a method for detecting incoming railway vehicles based on a radar map provided in Embodiment 4 of the present application. The embodiment of the present application is optimized based on the foregoing embodiments.

As shown in Figure 8, the method of the embodiment of the present application specifically includes the following steps:

S410. Determine the radar map according to the echo signal obtained by detection by the radar installed at the target position point on the railway.

S420. For the pixel points to be recognized in the radar image, determine the target detection position points corresponding to the pixel points to be recognized mapped in the radar detection area and the preset signal strength probability distribution models corresponding to the radar scanning the target detection position points.

Wherein, the pixel to be identified may be a pixel to be detected in the radar image. The target detection position point may be the detection position in the radar detection area corresponding to the pixel to be identified in the radar image, and there is a one-to-one correspondence between each pixel point in the radar image and each target detection position point in the radar detection area.

Specifically, the radar detection area is scanned by radar, and the radar map of the radar detection area is obtained, and then the target detection position points corresponding to each pixel to be identified in the radar map are determined in the radar detection area, so as to ensure that the pixels of the radar map are consistent with the corresponding The accuracy of the position of the target detection point ensures that the subsequent analysis and processing of the pixel points to be recognized can accurately correspond to the position of the target detection position point, which is convenient for processing the target detection position point; at the same time, it is also necessary to determine the target detection position point The corresponding preset signal strength probability distribution model facilitates subsequent determination of the probability distribution type corresponding to the pixel to be identified.

S430, Detect the matching result of the value of the pixel to be identified and the preset signal strength probability distribution model corresponding to the target detection position point, the preset signal probability distribution model is used to describe the detection of the target when the radar detection area does not include the foreground Probability distribution of the signal strength of the radar echo signal when the position point is scanned.

Specifically, after obtaining the radar image, the value of the pixel point to be identified in the radar image is brought into each normal distribution model in the preset signal strength probability distribution model to determine whether the value of the pixel point to be identified is consistent with the preset Signal strength probability distribution model adaptation, as long as it conforms to a normal distribution model in the preset signal strength probability distribution model, the value of the pixel to be identified is adapted to the preset signal strength probability distribution model.

In a feasible embodiment, detecting the matching result of the value of the pixel point to be identified and the preset signal strength probability distribution model corresponding to the target detection position point may include the following steps A1-A3:

Step A1, detecting whether at least one normal distribution model in the preset signal strength probability distribution model corresponding to the value of the pixel point to be identified and the target detection position satisfies the preset matching condition; wherein the preset matching condition includes the value of the pixel point to be identified Values with the mean of the normal distribution model satisfy the preset Raida criterion.

Step A2, if there is at least one normal distribution model satisfying the preset matching condition, then determine that the pixel to be identified belongs to the background pixel in the radar image.

Step A3, if there is no normal distribution model satisfying the preset matching condition, then determine that the pixel to be recognized belongs to the foreground pixel in the radar image.

Wherein, the preset matching condition may be used to judge whether the value of the pixel point to be recognized satisfies at least one normal distribution model in the preset signal strength probability distribution model corresponding to the target detection position point. The preset Raida criterion can be expressed by the following formula:

为目标检测位置点对应的预设信号强度概率分布模型中的均值，

为目标检测位置点对应的预设信号强度概率分布模型中的方差。In the formula, x _ij is the value of the pixel to be identified,

is the mean value in the preset signal strength probability distribution model corresponding to the target detection position point,

It is the variance in the preset signal strength probability distribution model corresponding to the target detection position point.

Specifically, the radar map is obtained by scanning the radar detection area with the radar, and the value of the pixel point to be identified in the radar map is input into the target detection position point corresponding to the preset signal strength probability distribution model, and the target detection position point corresponds to the preset signal strength probability distribution model. Whether at least one normal distribution model in the probability distribution model satisfies the preset matching condition, if there is at least one normal distribution model satisfying the preset matching condition, then determine that the pixel to be identified belongs to the background pixel in the radar image; if there is no satisfying The normal distribution model with preset matching conditions determines that the pixel to be recognized belongs to the foreground pixel in the radar image.

S440. According to the matching result, separate the foreground and the background in the radar image, and determine the pixel area of the target to be detected according to the separated foreground.

Specifically, the value of each pixel point to be identified in the radar image is input into the preset signal strength probability distribution model corresponding to each target detection position point, and by judging at least one of the preset signal strength probability distribution models corresponding to the target detection position point Whether the normal distribution model meets the preset matching conditions determines that each pixel to be recognized belongs to a background pixel or a foreground pixel, and then can realize the separation of the foreground and background in the current radar image, and obtain the separated foreground.

Further, the foreground may include other objects besides the object to be detected, such as signs, etc., and contour detection can be performed on them, and the pixel area of the object to be detected can be determined according to the contour characteristics of the object to be detected.

In another feasible embodiment of the present application, separating the foreground and background of the radar map includes: performing image difference processing on the radar map and the preset average background image to obtain a difference image; performing binarization processing on the difference image , taking the binarized image as the foreground.

Wherein, the average background image may be an image reflecting a state where there is no target to be detected in the radar detection area, and may be obtained by averaging multiple background images. The background image may be a radar image acquired when there is no target to be detected in the radar detection area. The image difference processing may be to perform difference processing on the values of the pixels of the two images. The binarization process can be that each pixel on the image has only two possible values or grayscale states, that is, the grayscale value of any pixel in the image is 0 or 255, representing black and white respectively.

In the embodiment of the present application, the average background image avoids the problem that individual pixels may be abnormal in a single background image, and improves the error tolerance rate.

Specifically, use radar to obtain at least two background images, and each background image can be recorded as F, which has P rows and Q columns, that is, a grayscale image composed of P*Q pixels, and the matrix is expressed as follows:

用公式表达为：Further, the gray value of each pixel of the average background image is obtained by averaging the gray values of the corresponding pixels of each background image, taking f ₁₁ pixels as an example, the gray value of f ₁₁ pixels in the average background image, It is obtained by averaging the gray value of f ₁₁ pixels in each background image, and f ₁₁ is the target pixel in the process. By traversing all the target pixels, the average background image can be obtained

Expressed as a formula:

Wherein, F _i is the grayscale image of each image in each background image. U is the number of background images.

In the embodiment of the present application, image difference processing is performed on the microwave radar image and the average background image to obtain the difference image F ^Δ , which can be expressed as:

Among them, F is the grayscale image of the microwave radar image.

Specifically, binarization can be performed by the following formula:

为差值图像中对应像素点的灰度值，S为预设灰度值，预设灰度值可以是雷达图中对应像素点的灰度值转化为0或255的临界值，当雷达图中对应像素点的灰度值大于或等于预设灰度值，对应像素点的灰度值转化为255，反之转化为0。预设灰度值可以根据实际情况确定，本申请实施例对此不做限定。Among them, f _ij ' is the gray value of the corresponding pixel of the radar image after binarization processing,

is the gray value of the corresponding pixel in the difference image, S is the preset gray value, and the preset gray value can be the critical value at which the gray value of the corresponding pixel in the radar image is converted to 0 or 255. When the radar image The gray value of the corresponding pixel in is greater than or equal to the preset gray value, and the gray value of the corresponding pixel is converted to 255, otherwise it is converted to 0. The preset grayscale value may be determined according to actual conditions, which is not limited in this embodiment of the present application.

S450. Track the target to be measured according to the pixel area of the target to be measured, and determine track data of the target to be measured.

In the embodiment of the present application, optionally, tracking the target to be measured according to the pixel area of the target to be measured, and determining the track data of the target to be measured may include steps B1-B9:

In step B1, according to the separated foreground, the image A is obtained by performing a morphological expansion operation on the foreground.

In the radar image, the background of the radar detection area and the target to be detected are included. After removing the background, the foreground can be obtained. The area in the foreground may be mistakenly divided into multiple small areas, so the morphological expansion operation is performed on the foreground to obtain the image A. This eliminates voids within small areas or voids in adjacent areas.

In step B2, image B is obtained by performing a morphological erosion operation on image A.

Because the area will become larger after expansion, it is necessary to perform a morphological erosion operation on image A to obtain image B, so as to restore the area of the area to that before expansion.

Step B3, performing Gaussian smoothing on image B to obtain image C.

There may be noise in image B, and Gaussian smoothing is performed on image B to obtain image C to eliminate some small noise points. The methods of removing noise include but are not limited to: mean filtering, Gaussian filtering, median filtering, etc.

Step B4, performing Canny edge detection on image C to obtain image D.

In this step, the peripheral contours of each region are obtained through edge detection.

Step B5, extracting the pixel coordinates of the outer boundary inflection points of each area in the image D to obtain a set of pixel coordinates of the outer boundary inflection points.

Use D to represent the set of pixel coordinates of all outer boundary inflection points, as follows:

表示第i个区域外边界的第m个拐点的行、列像素下标。Among them, Di represents the set of pixel coordinates of the outer boundary inflection point of the i-th region,

Indicates the row and column pixel subscripts of the m-th inflection point of the outer boundary of the i-th region.

In the above steps, the image processing algorithms used are all existing technologies, and the specific content will not be repeated in this embodiment of the present application.

Step B6, calculating the pixel coordinates of the geometric center of each area:

Among them, (r ⁱ , c ⁱ ) are the pixel coordinates of the geometric center of the i-th region.

Step B7, converting the pixel coordinates of the geometric center of each area into the coordinates of the Cartesian coordinate system:

Among them, P and Q are the number of rows and columns of the radar image, and its value can be an odd number to place the radar at the coordinate center. Δ is the width of the actual detection area corresponding to one pixel in the radar image. Traverse each area to get the center coordinate set X of each area,

X={(x ¹ ,y ¹ ),(x ² ,y ² ),...,(x ⁿ ,y ⁿ )}.

Step B8, clustering the central coordinate sets of each area to obtain a clustered coordinate set X′.

Step B9, according to at least two radar images, determine the position of the target to be measured at each time, determine the navigation speed and direction of the target to be measured, determine the latest position of the target to be measured according to the latest acquired radar image, and then place a target to be measured The track data of the measured target is expressed as: (id _n , x _n , y _n , vx _n , vy _n ).

S460. Determine a target on the same track among the targets to be measured according to the track data of the target to be measured; wherein the target on the same track is an object located on the railway where the target position point is located.

S470, if the distance between the target on the same track and the target point is less than a preset distance, perform a safety warning.

In the technical solution of the embodiment of the present application, by detecting whether the value of the pixel point to be recognized matches the preset signal strength probability distribution model corresponding to the target detection position point, it is determined that the pixel point to be recognized belongs to the foreground or the background, and according to the value of each pixel point to be recognized The matching result separates the background and the foreground in the current radar image to obtain the foreground, determines the pixel area of the target to be measured, and tracks the target to determine the track data of the target to be measured. The technical scheme quickly and accurately determines the target to be measured from the radar image, and determines the track data of the object to be measured according to at least two radar images.

Embodiment five

Fig. 9 is a schematic structural diagram of a radar map-based railway vehicle detection device provided in Embodiment 5 of the present application. The device can execute the radar map-based railway vehicle detection method provided in any embodiment of the present invention, and has an execution method Corresponding functional modules and beneficial effects. As shown in Figure 9, the device includes:

The track data determination module 510 is used to determine the radar map according to the echo signal obtained by detecting the radar at the target position point on the railway, and determine the track data of the target to be measured according to the radar map;

The same-track target determination module 520 is configured to determine the same-track target in the target to be measured according to the track data of the target to be measured; wherein, the same-track target is located on the railway where the target position point is located Target;

The safety warning module 530 is configured to perform a safety warning if the distance between the on-track target and the target location point is less than a preset distance.

Optionally, the same track target determination module 520 includes:

A preset area determining unit, configured to determine whether the position point of the target to be measured is located in a preset area according to the track data of the target to be measured;

A co-track target determining unit, configured to determine that the target to be measured is a co-track target if the position point of the area to be measured is within a preset area.

Optionally, the process of determining the preset area is specifically:

Determining the extent of the railway section within the radar detection area;

Use the polygon extent containing the extent of the railway segment as the default area.

Optionally, the polygon range containing the range of the railway section is used as the preset area, specifically:

The range of the railway section, or the expanded range of the railway section along the width direction of the railway, is used as the preset area.

Optionally, the track data determination module 510 includes:

The intensity interpolation unit is used to perform intensity interpolation between adjacent position points according to the intensity data of echo signals at adjacent position points equal to the distance from the radar in the adjacent detection direction of the radar, and determine an interpolation position point equal to the distance from the radar intensity data at

A location point determining unit, configured to determine a location point corresponding to each pixel point in the radar image; wherein, the location point includes a location point corresponding to each intensity data after intensity interpolation;

The radar image generation unit is configured to determine the grayscale value of the radar image pixel corresponding to each location point according to the intensity data of each location point, and generate the radar image according to the grayscale value.

Optionally, the intensity interpolation unit includes:

The intensity interpolation subunit is used to perform intensity interpolation on the concentric arc with the adjacent position point as the endpoint to obtain the interpolated position point; the concentric arc is centered on the radar, and the adjacent The position point is on the arc of the radius;

The first weight value determination subunit is used to use the ratio of the concentric arc length from the first position point to the interpolation position point in the adjacent position points to the concentric arc length between adjacent position points as the adjacent position point The first weight value of the intensity data of the second position point in the middle;

The second weight value determines the subunit, which is used to use the ratio of the concentric arc length from the second position point to the interpolation position point in the adjacent position points to the concentric arc length between adjacent position points as the adjacent position point The second weight value of the intensity data of the first position point in ;

The intensity data determining subunit is configured to perform weighted summation of the intensity data of adjacent position points according to the first weight value and the second weight value, as the intensity data of the interpolation position point.

Optionally, the track data determination module 510 includes:

The model determination unit is used to determine the target detection position point corresponding to the pixel point to be recognized in the radar detection area mapped to the pixel point to be recognized in the radar image and the corresponding preset signal strength probability when the radar scans the target detection position point distribution model;

The model matching unit is used to detect the matching result of the preset signal strength probability distribution model corresponding to the value of the pixel point to be identified and the target detection position point, and the preset signal probability distribution model is used to describe the situation that the radar detection area does not include the foreground The probability distribution of the signal strength of the radar echo signal when scanning the target detection position point;

A pixel area determining unit, configured to separate the foreground and background in the radar image according to the matching result, and determine the pixel area of the target to be measured according to the separated foreground;

The track data determination unit is configured to track the target to be measured according to the pixel area of the target to be measured, and determine the track data of the target to be measured.

A radar map-based railway vehicle detection device provided in an embodiment of the present application can execute a radar map-based railway vehicle detection method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method .

Embodiment six

FIG. 10 shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (eg, helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the inventions described and/or claimed herein.

As shown in FIG. 10 , the electronic device 10 includes at least one processor 11, and a memory communicatively connected with the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores There is a computer program executable by at least one processor, and the processor 11 can operate according to a computer program stored in a read-only memory (ROM) 12 or loaded from a storage unit 18 into a random access memory (RAM) 13. Various appropriate actions and processes are performed. In the RAM 13, various programs and data necessary for the operation of the electronic device 10 are also stored. The processor 11 , ROM 12 , and RAM 13 are connected to each other through a bus 14 . An input/output (I/O) interface 15 is also connected to the bus 14 .

Multiple components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Processor 11 may be various general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes various methods and processes described above, for example, a radar map-based railway vehicle detection method.

In some embodiments, the radar image-based railway vehicle detection method can be implemented as a computer program, which is tangibly embodied in a computer-readable storage medium, such as the storage unit 18 . In some embodiments, part or all of the computer program may be loaded and/or installed on the electronic device 10 via the ROM 12 and/or the communication unit 19 . When the computer program is loaded into the RAM 13 and executed by the processor 11 , one or more steps of the method for detecting a railway vehicle based on the radar map described above can be executed. Alternatively, in other embodiments, the processor 11 may be configured in any other appropriate way (for example, by means of firmware) to execute a method for detecting a railway vehicle based on a radar image.

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the computer program causes the functions/operations specified in the flowcharts and/or block diagrams to be implemented when executed by the processor. A computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus or device. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

In order to provide interaction with the user, the systems and techniques described herein can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display)) for displaying information to the user. monitor); and a keyboard and pointing device (eg, a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

A computing system can include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or a cloud host. It is a host product in the cloud computing service system to solve the problems of difficult management and weak business expansion in traditional physical hosts and VPS services. defect.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present invention may be executed in parallel, sequentially, or in a different order, as long as the expected result of the technical solution of the present invention can be achieved, there is no limitation herein.

The above specific implementation methods do not constitute a limitation to the protection scope of the present invention. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. A method for detecting a railway coming car based on a radar map is characterized by comprising the following steps:

determining a radar chart according to an echo signal obtained by detecting a radar arranged at a target position point on a railway, and determining track data of a target to be detected according to the radar chart;

determining a co-orbit target in the target to be detected according to the flight path data of the target to be detected; wherein the common-rail target is a target located on a railway where the target location point is located;

and if the distance between the co-orbit target and the target position point is less than the preset distance, carrying out safety early warning.

2. The method of claim 1, wherein determining the co-rail target in the target to be measured according to the track data of the target to be measured comprises:

determining whether the position point of the target to be detected is located in a preset area or not according to the flight path data of the target to be detected;

and if the position point of the area to be detected is located in a preset area, determining that the target to be detected is the same-track target.

3. The method according to claim 2, wherein the determining of the preset area comprises:

determining a railway section range located in a radar detection area;

and taking a polygonal range containing the range of the railway section as a preset area.

4. The method according to claim 3, wherein regarding a polygon range including a range of the railway section as the preset region, comprises:

the range of the railway section or the range of the expanded railway section along the width direction of the railway is taken as a preset area.

5. The method of claim 1, wherein determining the radar map from the echo signals detected by the radar at the target location comprises:

according to the intensity data of the echo signals at adjacent position points which are equal to the radar distance in the adjacent detection direction of the radar, intensity interpolation is carried out between the adjacent position points, and the intensity data at the interpolation position points which are equal to the radar distance are determined;

determining a position point corresponding to each pixel point in the radar map; the position points comprise position points corresponding to the intensity data after intensity interpolation;

and determining the gray value of the radar map pixel point corresponding to each position point according to the intensity data of each position point, and generating the radar map according to the gray value.

6. The method according to claim 5, wherein the intensity data at the interpolated position point equal to the radar distance is determined by interpolating the intensity between the adjacent position points based on the intensity data of the echo reflected at the adjacent position points equal to the radar distance in the radar adjacent detection direction, and the method comprises:

performing intensity interpolation on a concentric circular arc with the adjacent position points as end points to obtain interpolation position points; the concentric circular arcs take the radar as the center of a circle and take the radar to the adjacent position points as the radius;

taking the ratio of the length of the concentric arc from the first position point to the interpolation position point in the adjacent position points to the length of the concentric arc between the adjacent position points as a first weight value of the intensity data of the second position point in the adjacent position points;

taking the ratio of the length of the concentric arc from the second position point to the interpolation position point in the adjacent position points to the length of the concentric arc between the adjacent position points as a second weight value of the intensity data of the first position point in the adjacent position points;

and according to the first weight value and the second weight value, carrying out weighted summation on the intensity data of the adjacent position points to be used as the intensity data of the interpolation position points.

7. The method of claim 1, wherein determining the flight path data of the target to be measured from the radar map comprises:

aiming at a pixel point to be identified in a radar map, determining a target detection position point corresponding to the pixel point to be identified mapped in a radar detection area and a corresponding preset signal intensity probability distribution model when a radar scans at the target detection position point;

detecting a matching result of a preset signal intensity probability distribution model corresponding to the pixel value to be identified and the target detection position point, wherein the preset signal probability distribution model is used for describing the signal intensity probability distribution of the radar echo signal when the target detection position point is scanned under the condition that a radar detection area does not comprise a foreground;

according to a matching result, separating the foreground and the background in the radar map, and determining a pixel area of a target to be detected according to the foreground obtained by separation;

tracking the target to be detected according to the pixel area of the target to be detected, and determining the track data of the target to be detected.

8. A radar map based railway arrival detection apparatus, the apparatus comprising:

the track data determining module is used for determining a radar chart according to an echo signal obtained by detecting a radar arranged at a target position point on a railway and determining the track data of a target to be detected according to the radar chart;

the co-orbit target determination module is used for determining a co-orbit target in the target to be detected according to the flight path data of the target to be detected; wherein the common-rail target is a target located on a railway where the target location point is located;

and the safety early warning module is used for carrying out safety early warning if the distance between the co-orbit target and the target position point is less than a preset distance.

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the radar map based railroad car detection method of any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions for causing a processor to implement the radar-map based railroad car detection method of any one of claims 1-7 when executed.

Images