Non-contact catenary parameter detection method and device

Abstract

The application provides a non-contact catenary parameter detection method and device, comprising: acquiring multiple contact line images; determining the spatial contact line contour of each contact line image; screening the data points in the contact line image according to a preset point screening condition to obtain screened effective data points; dividing the effective data points according to a preset plane contour division condition to determine a plane contact line contour composed of multiple effective data points; converting all the effective data points on the plane contact line contour into three-dimensional data points; dividing the three-dimensional data points according to a preset spatial contour division condition to determine a spatial contact line contour composed of multiple three-dimensional data points; and determining the contact line and the contact line parameter according to the spatial contact line contour of each contact line image. The application can improve the detection accuracy of catenary parameters.

Description

Technical Field

[0001] This application relates to the field of overhead contact line testing technology, and in particular to a non-contact method and apparatus for detecting overhead contact line parameters. Background Technology

[0002] The quality and operational status of the overhead contact system directly affect the transport capacity of electrified railways. To ensure the overhead contact system maintains normal and reliable operation, its parameters need to be checked regularly to detect and eliminate faults in a timely manner, ensuring safe and reliable power supply. Manual parameter testing is time-consuming, labor-intensive, and inefficient. Testing based on the flight time of the detection optical path has low accuracy and places high demands on the performance of the equipment. Summary of the Invention

[0003] In view of this, the purpose of this application is to propose a non-contact method and device for detecting overhead contact line parameters.

[0004] To achieve the above objectives, this application provides a non-contact method for detecting overhead contact line parameters, comprising:

[0005] Acquire multiple contact line images;

[0006] Determining the spatial contact line contour of each contact line image includes: filtering data points in the contact line image according to preset point filtering conditions to obtain filtered valid data points; dividing the valid data points according to preset planar contour division conditions to determine a planar contact line contour composed of multiple valid data points; converting all valid data points on the planar contact line contour into three-dimensional data points; and dividing the three-dimensional data points according to preset spatial contour division conditions to determine a spatial contact line contour composed of multiple three-dimensional data points.

[0007] Based on the spatial contact line contour of each contact line image, determine the contact line and its parameters.

[0008] Optionally, the step of filtering the data points in the contact line image according to preset point filtering conditions to obtain the filtered valid data points includes:

[0009] Calculate the centroid of all data points in the contact line image;

[0010] Based on the centroid point, a predetermined effective image region is defined in the contact line image;

[0011] Within the valid image area, data points with non-zero column coordinate values ​​are selected as the valid data points.

[0012] Optionally, the effective data points are divided according to preset planar contour division conditions to determine a planar contact line contour composed of multiple effective data points, including:

[0013] Calculate the pixel distance between any two adjacent valid data points;

[0014] Based on the pixel distance and the preset pixel distance threshold, the effective data points are clustered to obtain at least one planar line profile composed of multiple effective data points.

[0015] Select planar contact line profiles that meet preset planar profile conditions from at least one planar line profile.

[0016] Optionally, selecting planar contact line profiles that satisfy preset planar profile conditions from at least one planar line profile includes:

[0017] Count the number of valid data points on each plane line profile;

[0018] Determine at least one initial screening plane contact line profile whose number of plane points is within a preset plane point threshold range;

[0019] Select a planar contact line profile from at least one initial screening planar contact line profile to identify valid data points that do not exhibit abrupt changes.

[0020] Optionally, the three-dimensional data points are divided according to preset spatial contour division conditions to determine the spatial contact line contour composed of multiple three-dimensional data points, including:

[0021] Calculate the spatial distance between any two adjacent 3D data points;

[0022] Based on the spatial distance and a preset spatial distance threshold, the three-dimensional data points are clustered to obtain at least one spatial line profile composed of multiple three-dimensional data points.

[0023] Select a spatial contact line profile that meets the preset spatial profile conditions from at least one spatial line profile.

[0024] Optionally, selecting spatial contact line profiles that satisfy preset spatial profile conditions from at least one spatial line profile includes:

[0025] Count the number of spatial points of 3D data points on each spatial line contour;

[0026] Determine at least one initial screening spatial contact line profile where the number of spatial points is within a preset spatial point threshold range;

[0027] Spatial contact line profiles without abrupt changes in three-dimensional data points are selected from at least one initial screening spatial contact line profile.

[0028] Optionally, spatial contact line profiles without abrupt spatial data points are selected from at least one initial screening spatial contact line profile, including:

[0029] Calculate the distance between any two adjacent three-dimensional data points on the contour of the initial screening spatial contact line;

[0030] Based on the distance, calculate the average distance of the three-dimensional data points on the contour of the initial screening spatial contact line;

[0031] The initial screening spatial contact line profiles whose average distance is less than or equal to a preset spatial point distance threshold are taken as spatial contact line profiles without abrupt spatial data points.

[0032] Optionally, based on the spatial contact line contour of each contact line image, the contact line and contact line parameters are determined, including:

[0033] Calculate the centroid of the principal line for all three-dimensional data points on the spatial contact line profile;

[0034] Calculate the principal line error distance between the centroids of the principal lines in the first and second consecutive contact line images;

[0035] In response to the main line error distance being less than a preset main line error threshold, the distance between the main line centroids of the second and third consecutive contact line images is calculated until the number of consecutive contact line images reaches the preset main line threshold.

[0036] Based on the spatial contact line contour of each contact line image, determine the main contact line;

[0037] The parameters of the main contact line are determined based on the centroid of the main line.

[0038] Optionally, the spatial contact line contour of the contact line image includes a first spatial contact line contour and a second spatial contact line contour.

[0039] The step of determining the main line of the contact line based on the spatial contact line contour of each contact line image includes:

[0040] The main line of the contact line is determined based on the first spatial contact line contour of each contact line image;

[0041] After determining the main contact wire, the following is also included:

[0042] Calculate the centroid of the branch lines for all three-dimensional data points on the second spatial contact line profile;

[0043] Calculate the branch error distance between the centroids of the branches in the first and second consecutive contact line images;

[0044] In response to the branch error distance being less than a preset branch error threshold, the distance between the centroids of the branches in the second and third consecutive contact line images is calculated until the number of consecutive contact line images reaches the preset branch threshold.

[0045] Based on the second spatial contact line contour of each contact line image, determine the contact line branches;

[0046] The parameters of the contact wire branch are determined based on the centroid of the branch.

[0047] This application embodiment also provides a non-contact contact network parameter detection device, including:

[0048] The acquisition module is used to acquire multiple contact line images;

[0049] The contour determination module is used to determine the spatial contact line contour of each contact line image, including: filtering data points in the contact line image according to preset point filtering conditions to obtain filtered valid data points; dividing the valid data points according to preset planar contour division conditions to determine a planar contact line contour composed of multiple valid data points; converting all valid data points on the planar contact line contour into three-dimensional data points; and dividing the three-dimensional data points according to preset spatial contour division conditions to determine a spatial contact line contour composed of multiple three-dimensional data points.

[0050] The parameter determination module is used to determine the contact line and its parameters based on the spatial contact line contour of each contact line image.

[0051] As can be seen from the above description, the non-contact contact wire parameter detection method and apparatus provided in this application, for the acquired contact wire image, filters the data points in the contact wire image according to preset point filtering conditions to obtain the filtered valid data points, divides the valid data points according to preset planar contour division conditions to determine the planar contact wire contour composed of multiple valid data points, converts all valid data points on the planar contact wire contour into three-dimensional data points, divides the three-dimensional data points according to preset spatial contour division conditions to determine the spatial contact wire contour composed of multiple three-dimensional data points, and determines the contact wire and contact wire parameters based on the spatial contact wire contour of each contact wire image. This application can improve the detection accuracy of contact wire parameters. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic diagram of the method flow of an embodiment of this application;

[0054] Figure 2 This is a schematic diagram of the detection process in an embodiment of this application;

[0055] Figure 3 This is a schematic diagram of the contact line image according to an embodiment of this application;

[0056] Figure 4 This is a schematic diagram of the contact line image after contour filtering according to an embodiment of this application;

[0057] Figure 5 This is a schematic diagram of the main line image of an embodiment of this application;

[0058] Figure 6 This is a structural block diagram of the detection device according to an embodiment of this application;

[0059] Figure 7 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0061] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0062] In related technologies, time-of-flight (TOF) detection of contact wire parameters based on probe optical paths involves emitting probe optical paths from a transmitter and receiving the return optical paths from a receiver. The distance of the contact wire under test is calculated by measuring the flight time of the probe and return optical paths, and then the guide height and pull-out value are calculated based on the distance. However, this method has low accuracy and requires high-performance detection devices. Moreover, in some scenarios, the contact wire has main and branch lines, requiring differentiation between them and the detection of their parameters. TOF detection methods cannot distinguish between main and branch lines.

[0063] To address the aforementioned issues, this application provides a non-contact contact wire parameter detection method. The method processes acquired contact wire images to determine the spatial contact wire contour. Based on the spatial contact wire contour from multiple consecutive contact wire images, the contact wire position and parameters are determined, resulting in high detection accuracy. Furthermore, the main line and branch lines, as well as their parameters, can be further determined based on the spatial contact wire contour.

[0064] The method for detecting overhead contact line parameters of this application will be described below with reference to the accompanying drawings and embodiments.

[0065] like Figure 1 , 2 As shown in the embodiments of this application, the non-contact contact network parameter detection method includes:

[0066] S101: Acquire multiple contact line images;

[0067] In this embodiment, the detection device is installed on the vehicle. The detection device includes an image acquisition unit and a laser. As the vehicle travels along the track, the laser emits laser light towards the contact wire, and the image acquisition unit continuously acquires multiple images of the contact wire. Optionally, such as... Figure 3 As shown, a line structured light sensor is used to acquire images of the contact line. The line structured light sensor includes a laser and an image acquisition unit. The laser emits laser light into the contact wire, and the image acquisition unit acquires a two-dimensional image of the contact line formed by the laser points.

[0068] S102: Determine the spatial contact line contour of each contact line image, including: filtering data points in the contact line image according to preset point filtering conditions to obtain filtered valid data points; dividing the valid data points according to preset planar contour division conditions to determine the planar contact line contour composed of multiple valid data points; converting all valid data points on the planar contact line contour into three-dimensional data points; dividing the three-dimensional data points according to preset spatial contour division conditions to determine the spatial contact line contour composed of multiple three-dimensional data points.

[0069] In this embodiment, each acquired contact line image is processed to obtain the spatial contact line contour. The processing method includes: for the acquired original contact line image, firstly, all data points in the image are filtered out, invalid data points unrelated to the contact line are removed, and valid data points that may be contact lines are retained; then, in the image coordinate system where the contact line image is located, all valid data points are divided according to the planar contour division conditions that may be contact lines, resulting in one or more planar contact line contours, each of which is composed of several valid data points; then, the valid data points constituting the planar contact line contours in the image coordinate system are converted into three-dimensional data points in the world coordinate system, and all three-dimensional data points are divided according to the spatial contour division conditions that may be contact lines, resulting in one or more spatial contact line contours, each of which is composed of several three-dimensional data points. By filtering valid data points, filtering planar contact line contours that may be contact lines in the image coordinate system, and then filtering spatial contact line contours that may be contact lines in the camera coordinate system, data processing efficiency and detection accuracy can be improved.

[0070] S103: Determine the contact line and contact line parameters based on the spatial contact line contour of each contact line image.

[0071] In this embodiment, after processing to obtain the spatial contact line contour of each contact line image, the contact line and its parameters are determined based on the spatial contact line contour of each contact line image.

[0072] In some application scenarios, contact lines can be divided into main lines and backup branch lines. The normally connected contact line is the main line, and during switching, it is switched from the main line to a branch line, with the branch line becoming the main line after the switch. In the normal main line connection state, the image acquisition unit of the detection device acquires contact line images including one main line. After processing this contact line image, a spatial contact line contour corresponding to the main line is obtained, and the parameters of the main line are determined based on this spatial contact line contour. During the switching process between the main line and the branch line, the image acquisition unit of the detection device acquires contact line images including both the main line and the branch line. After processing this contact line image, a first spatial contact line contour corresponding to the main line and a second spatial contact line contour corresponding to the branch line are obtained. The parameters of the main line are determined based on the first spatial contact line contour, and the parameters of the branch line are determined based on the second spatial contact line contour, thereby realizing the detection of the main line and the branch line.

[0073] The non-contact contact wire parameter detection method provided in this embodiment includes acquiring multiple contact wire images; for each contact wire image, filtering data points in the contact wire image according to preset point filtering conditions to obtain filtered valid data points; dividing the valid data points according to preset planar contour division conditions to determine a planar contact wire contour composed of multiple valid data points; converting all valid data points on the planar contact wire contour into three-dimensional data points; dividing the three-dimensional data points according to preset spatial contour division conditions to determine a spatial contact wire contour composed of multiple three-dimensional data points; and determining the contact wire and contact wire parameters based on the spatial contact wire contours of each contact wire image. The method of this embodiment can achieve non-contact contact wire parameter detection with high detection accuracy.

[0074] In some embodiments, data points in the contact line image are filtered according to preset point filtering conditions to obtain filtered valid data points, including:

[0075] Calculate the centroid of all data points in the contact line image;

[0076] Based on the center point, a predetermined effective image region is defined in the contact line image;

[0077] Within the valid image area, data points whose column coordinate values ​​are not zero in the pixel coordinates are selected as valid data points.

[0078] In this embodiment, to improve detection efficiency and accuracy, after acquiring the contact line image, the image is first analyzed. Valid data points in the contact line region are selected from the image, while data points unrelated to the contact line are filtered out. Subsequent processing is based on these valid data points. Specifically, the centroid of all data points in the contact line image is first calculated. Using this centroid as the center, a certain area is divided within the contact line image as the potentially valid image region where the contact line may exist. Within this defined valid image region, data points unrelated to the contact line are filtered out, while valid data points related to the contact line are retained for subsequent analysis. Thus, by dividing the contact line image into valid regions and filtering valid data points, detection efficiency can be improved.

[0079] In some methods, for all data points in the contact line image, the centroid is calculated based on the pixel coordinates of all data points. The effective image region is then divided around the centroid. Within the effective image region, data points with a column coordinate value of 0 in the pixel coordinates are removed as invalid data points, retaining only the valid data points related to the contact line. Here, in data point P(x,y), x is the row coordinate value of point P in the pixel coordinates, and y is the column coordinate value of point P in the pixel coordinates.

[0080] In some embodiments, the effective data points are divided according to preset planar contour division conditions to determine the planar contact line contour composed of multiple effective data points, including:

[0081] Calculate the pixel distance between any two adjacent valid data points;

[0082] Based on the pixel distance and a preset pixel distance threshold, the effective data points are clustered to obtain at least one planar line profile composed of multiple effective data points.

[0083] Select planar contact line profiles that meet preset planar profile conditions from at least one planar line profile.

[0084] In this embodiment, after selecting valid data points, the planar contact line contour in the contact line image is determined based on these valid data points. Specifically, the pixel distance between any two adjacent valid data points is first calculated. The pixel distance between each pair of valid data points is then compared with a preset pixel distance threshold. Valid data points with a pixel distance less than or equal to the threshold are grouped into a cluster. Multiple valid data points within the same cluster constitute a planar line contour. Due to various interference factors, multiple clusters may be formed, each cluster corresponding to a planar line contour. For example, the main line corresponds to one planar line contour, the branch line to one planar line contour, the catenary cable to one planar line contour, and other interfering objects to one planar line contour, etc. To eliminate interference, each planar line contour is filtered according to the condition that it is likely a contact line contour. Planar line contours corresponding to non-contact lines are removed, and planar contact line contours that are likely contact lines are retained, thereby improving the detection accuracy of the contact line.

[0085] In some methods, the pixel distance threshold is 10 pixels, which means that effective data points with a pixel distance of less than or equal to 10 pixels between two adjacent effective data points are divided into a cluster, and multiple effective data points form a planar line profile.

[0086] In some embodiments, selecting planar contact line profiles that satisfy preset planar profile conditions from at least one planar line profile includes:

[0087] Count the number of valid data points on each plane line profile;

[0088] Determine at least one initial screening plane contact line profile whose number of plane points is within a preset plane point threshold range;

[0089] Select the planar contact line profiles from at least one initial screening planar contact line profiles to identify valid data points that do not exhibit abrupt changes.

[0090] In this embodiment, after dividing several valid data points into one or more planar line contours, planar contact line contours that may be contact lines are selected from the planar line contours based on the length and shape of the contact line. The method for selecting based on the length of the contact line is as follows: the number of planar points on all valid data points on the planar line contour is used as the contour length of the planar line contour. Then, the number of planar points is compared with a set threshold range for planar points, that is, the contour length of the planar line contour is compared with the length threshold of the contact line. Initially screened planar contact line contours whose number of planar points is within the threshold range are retained, i.e., those whose contour length is within the length threshold range are retained. After selecting based on the length of the contact line, further selection is made based on the shape of the contact line. Since the contact line is generally arc-shaped and does not contain broken lines, contours with abrupt changes in valid data points are removed from the initial screened planar contact line contours. The final retained contours are the determined planar contact line contours.

[0091] Optionally, a profile with abrupt change in valid data points refers to a profile of the initial screening plane contact line containing two valid data points, where one valid data point has the maximum column coordinate value in the profile, and the other valid data point has the minimum column coordinate value in the profile, and the difference between the maximum and minimum column coordinate values ​​is greater than a preset abrupt change threshold. For example, for valid data point P1(x,y) in the initial screening plane contact line profile... max P2(x,y) min When y max With y min When the difference is greater than or equal to 10, the contour of the initial screening plane contact line is confirmed to be the contour of valid data points with abrupt changes and needs to be filtered out.

[0092] Thus, combined Figure 4 As shown, in the image coordinate system, contour segmentation, contour length filtering, and contour shape filtering can filter out all possible interference points, improving the accuracy of contact line detection. Considering that some interference points cannot be filtered in the two-dimensional image coordinate system, the filtering results in the image coordinate system are transformed to the camera coordinate system for further filtering in three-dimensional space, effectively removing all possible interference points.

[0093] In some embodiments, the three-dimensional data points are divided according to preset spatial contour division conditions to determine the spatial contact line contour composed of multiple three-dimensional data points, including:

[0094] Calculate the spatial distance between any two adjacent 3D data points;

[0095] Based on the spatial distance and a preset spatial distance threshold, the three-dimensional data points are clustered to obtain at least one spatial line profile composed of multiple three-dimensional data points.

[0096] Select a spatial contact line profile that meets the preset spatial profile conditions from at least one spatial line profile.

[0097] In this embodiment, based on the filtering results in the image coordinate system, all valid data points on the planar contact line contour in the image coordinate system are converted into three-dimensional data points in the camera coordinate system, further filtering out possible interference points and improving the detection accuracy of the contact line. Specifically, for all three-dimensional data points, the spatial distance between any two adjacent three-dimensional data points is calculated, and the spatial distance between each pair of three-dimensional data points is compared with a preset spatial distance threshold. Three-dimensional data points with a spatial distance less than or equal to the spatial distance threshold are grouped into a cluster, and multiple three-dimensional data points within the same cluster constitute a spatial line contour. Due to the influence of various interference factors, multiple clusters may be formed, and each cluster corresponds to a spatial line contour. To eliminate interference, each spatial line contour is filtered according to the condition that it may be a contact line, removing spatial line contours corresponding to non-contact lines and retaining spatial contact line contours that may be contact lines.

[0098] In some methods, the spatial distance threshold is set to 10 millimeters, which means that three-dimensional data points with a spatial distance of less than or equal to 10 millimeters between two adjacent three-dimensional data points are divided into a cluster, and multiple spatial data points constitute a spatial line profile.

[0099] In some embodiments, selecting spatial contact line profiles that satisfy preset spatial profile conditions from at least one spatial line profile includes:

[0100] Count the number of spatial points of 3D data points on each spatial line contour;

[0101] Determine at least one initial screening spatial contact line profile where the number of spatial points is within a preset spatial point threshold range;

[0102] Spatial contact line profiles without abrupt changes in three-dimensional data points are selected from at least one initial screening spatial contact line profile.

[0103] In this embodiment, after dividing several spatial data points into one or more spatial line contours, spatial contact line contours that may be contact lines are selected from the spatial line contours based on the length and shape of the contact line. The method for selecting based on the length of the contact line is as follows: the number of spatial points of all three-dimensional data points on the spatial line contour is used as the contour length of the spatial line contour. Then, the number of spatial points is compared with a set spatial point threshold range, that is, the contour length of the spatial line contour is compared with the length threshold of the contact line. Initially screened spatial contact line contours whose number of spatial points is within the spatial point threshold range are retained, i.e., those whose contour length is within the length threshold range are retained. After selecting based on the length of the contact line, further selection is made based on the shape of the contact line. Since the contact line is generally a continuous, gently curving arc, there are no broken lines on the contact line. Therefore, in the initial screening of spatial contact line contours, contours with abrupt changes in three-dimensional data points are removed, and the remaining contours are the determined spatial contact line contours.

[0104] In some embodiments, selecting spatial contact line profiles without abrupt spatial data points from at least one initial screening spatial contact line profile includes:

[0105] Calculate the distance between any two adjacent three-dimensional data points on the initial screening spatial contact line profile;

[0106] Based on the distance, calculate the average distance of the three-dimensional data points on the initial screening spatial contact line profile;

[0107] The initial screening of spatial contact line profiles with an average distance less than or equal to a preset spatial point distance threshold is taken as spatial contact line profiles without abrupt changes in spatial data points.

[0108] In this embodiment, when screening the initial screening spatial contact line according to the shape of the contact line, the distance between any two adjacent three-dimensional data points on the contour of the initial screening spatial contact line is calculated. Based on the distance between any two three-dimensional data points, the average distance between any two adjacent three-dimensional data points on the contour of the initial screening spatial contact line is calculated. If the average distance is greater than the spatial point distance threshold, it is considered that there are abrupt spatial data points on the contour of the initial screening spatial contact line, which need to be filtered out. The initial screening spatial contact line contours with an average distance less than or equal to the spatial point distance threshold are retained as the selected spatial contact line contours.

[0109] For example, if there are A1, A2, ... on the initial screening spatial contact line profile, A... 10 There are ten spatial data points in total. Calculate the distance between any two adjacent spatial data points: D1 = A1 - A2, D2 = A2 - A3, ..., D9 = A9 - A2. 10Next, the average distance D = (D1 + D2 + ... + D9) / 9 is calculated, and then compared with the spatial point distance threshold to determine whether the initial screening spatial contact line profile shape conforms to the actual shape of the contact line. Optionally, the point spacing on the contact line should be relatively dense, and the spatial point distance threshold is set to 1-2 mm.

[0110] The method in this embodiment, after acquiring the contact line image, first filters out valid data points and removes interference points unrelated to the contact line; then, it performs contour division on the valid data points in the image coordinate system, and filters out all possible interference points in the image coordinate system based on contour length and contour shape; subsequently, based on the filtering results in the image coordinate system, it performs contour division on the three-dimensional data points in the camera coordinate system, and filters out all possible interference points in the camera coordinate system based on contour length and contour shape, finally obtaining the spatial contact line contour of the contact line image, which can improve data processing efficiency and contact line detection accuracy.

[0111] In some embodiments, the contact line and contact line parameters are determined based on the spatial contact line contour of each contact line image, including:

[0112] Calculate the centroid of the principal line for all three-dimensional data points on the spatial contact line profile;

[0113] Calculate the principal line error distance between the centroids of the principal lines in the first and second consecutive contact line images;

[0114] In response to the principal line error distance being less than the preset principal line error threshold, the distance between the principal line centroids of the second and third consecutive contact line images is calculated until the number of consecutive contact line images reaches the preset principal line threshold.

[0115] Based on the spatial contact line contour of each contact line image, determine the main contact line;

[0116] Determine the parameters of the main contact wire based on the centroid of the main wire.

[0117] In this embodiment, after determining the spatial contact line contour of each contact line image, the contact line and its parameters are determined based on the spatial contact line contour. First, the principal line is detected based on the spatial contact line contour. For each contact line image, the centroid of the principal line for all three-dimensional data points on its spatial contact line contour is calculated. Then, according to the order of the acquired contact line images, the principal line error distance between the centroids of the principal lines of two consecutive contact line images is calculated sequentially. The principal line error distance is compared with a set principal line error threshold. If the principal line error distance between two contact line images is less than the principal line error threshold, the principal line error distance for the next two consecutive contact line images is calculated. This process of calculation and comparison is repeated sequentially. When the number of consecutive contact line images reaches the principal line threshold, it can be determined that the principal line has been detected. Based on the spatial contact line contour of each contact line image, the principal line (e.g., ...) is determined. Figure 5 As shown in the figure, the parameters of the main line are determined based on the centroid of the main line.

[0118] In some implementations, a linked list can be used to implement the above detection process. Contact line images acquired by the image acquisition unit are acquired sequentially. After processing the contact line images, the spatial contact line contour of the contact line image is obtained. The centroid of the principal line for all three-dimensional data points on the spatial contact line contour is calculated. The coordinate values ​​of the centroids of the principal line in the acquired contact line images are sequentially stored in a linked list. When detecting the principal line, the principal line error distance between the centroids of the first and second contact line images is calculated based on the coordinate values ​​of the centroids of the principal line in the first and second nodes of the linked list. It is then determined whether the principal line error distance is less than the principal line error threshold. If the principal line error distance is less than the threshold, the principal line error distance between the centroids of the second and third contact line images is calculated based on the coordinate values ​​of the centroids of the principal line in the second and third nodes of the linked list. If this principal line error distance is less than the threshold, the principal line error distances of the centroids stored in the third and fourth nodes are calculated and judged. Following the above process, when the calculated principal line error distances for multiple consecutive nodes are all less than the principal line error threshold, and the number of nodes reaches a certain value, it is determined that the principal line has been detected in multiple consecutive contact line images. After confirming that the principal line has been detected, the position of the principal line is determined based on the spatial contact line contour of each contact line image, and the parameters of the principal line are determined by the centroid point of the principal line in the spatial contact line contour. For example, in the three-dimensional coordinates of the centroid point of the principal line, the coordinate value perpendicular to the track plane is the guide height value, and the coordinate value perpendicular to the vehicle's direction of travel in the track plane is the pull-out value. Optionally, to reduce errors, the average coordinate value of the centroid point of the principal line in each contact line image can be calculated first, and the parameters of the principal line can be determined based on the average coordinate value.

[0119] Considering the influence of external environment and equipment factors during actual engineering applications, interfering contact line images may be acquired, where the spatial contact line outline cannot be found, affecting the detection of the main line. To avoid the influence of interference factors and ensure detection accuracy, during the detection of the main line, if a node in the linked list does not have the centroid of the main line, the next node is used as the starting point, and the detection process described above is repeated to determine whether the main line exists.

[0120] In some embodiments, the spatial contact line profile of the contact line image includes a first spatial contact line profile and a second spatial contact line profile.

[0121] Based on the spatial contact line contour of each contact line image, the main contact line is determined, including:

[0122] Based on the first spatial contact line contour of each contact line image, determine the main contact line;

[0123] After determining the main contact wire, the following is also included:

[0124] Calculate the centroid of the branch lines for all three-dimensional data points on the second spatial contact line profile;

[0125] Calculate the branch error distance between the centroids of the branches in the first and second consecutive contact line images;

[0126] In response to the branch error distance being less than a preset branch error threshold, the distance between the centroids of the branches in the second and third consecutive contact line images is calculated until the number of consecutive contact line images reaches the preset branch threshold.

[0127] Based on the second spatial contact line contour of each contact line image, determine the contact line branches;

[0128] Determine the parameters of the contact wire branch based on the centroid of the branch.

[0129] In this embodiment, the contact line images acquired during the switching process between the main line and the branch line are processed to obtain a first spatial contact line profile corresponding to the main line and a second spatial contact line profile corresponding to the branch line. Based on these two spatial contact line profiles, the main line and the branch line, as well as the main line parameters and the branch line parameters, can be detected. After determining the main line and its parameters based on the first spatial contact line profile, the branch line and its parameters can be further determined based on the second spatial contact line profile. When detecting branch lines, the same method as for detecting main lines is used. The centroid of the branch line is calculated for all three-dimensional data points on the second spatial contact line contour of each contact line image. Then, the branch line error distance between the centroids of the branch lines in two consecutive contact line images is calculated and compared with a branch line error threshold. If the branch line error distance is less than the threshold, the calculation continues for the centroids of the branch lines in the next two contact line images, and this is compared with the threshold. Following this calculation and comparison process, when the number of consecutive contact line images reaches the branch line threshold, it can be determined that a branch line has been detected. The branch line is then determined based on the second spatial contact line contour of each contact line image, and its parameters are determined based on the centroid of the branch line. For example, in the three-dimensional coordinates of the centroid of the branch line, the coordinate value perpendicular to the track plane is the guide height value, and the coordinate value perpendicular to the vehicle's direction of travel within the track plane is the pull-out value. Optionally, to reduce error, the average coordinates of the centroids of the branch lines in each contact line image can be calculated first, and the parameters of the branch line can be determined based on this average coordinate value.

[0130] In some implementations, when using a linked list to detect the main line and branches, the numbers of the first spatial contact line contours and the coordinates of the main line centroids, and the numbers of the second spatial contact line contours and the coordinates of the branch centroids are sequentially stored in the linked list according to the order of the acquired contact line images. When detecting the main line, the centroids of adjacent nodes are calculated and compared sequentially until the number of consecutive nodes reaches the main line threshold. The position of the main line is determined based on the first spatial contact line contour, and the main line parameters are determined based on the main line centroids. Then, the centroids of adjacent nodes are calculated and compared sequentially until the number of consecutive nodes reaches the branch line threshold. The position of the branch line is determined based on the second spatial contact line contour, and the branch line parameters are determined based on the branch line centroids.

[0131] The non-contact contact wire parameter detection method provided in this application acquires contact wire images during vehicle operation, processes these images, and filters out interference points in both two-dimensional and three-dimensional coordinate systems to obtain a spatial contact wire contour that is likely the contact wire. Based on the spatial contact wire contour from multiple consecutive contact wire images, the position and parameters of the main line are detected, improving the detection accuracy of the contact wire. In cases where branches exist, both the main line and branches, as well as their parameters, can be detected simultaneously, meeting diverse detection needs.

[0132] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0133] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0134] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a non-contact contact network parameter detection device.

[0135] refer to Figure 6 The detection device includes:

[0136] The acquisition module is used to acquire multiple contact line images;

[0137] The contour determination module is used to determine the spatial contact line contour of each contact line image, including: filtering data points in the contact line image according to preset point filtering conditions to obtain filtered valid data points; dividing the valid data points according to preset planar contour division conditions to determine the planar contact line contour composed of multiple valid data points; converting all valid data points on the planar contact line contour into three-dimensional data points; and dividing the three-dimensional data points according to preset spatial contour division conditions to determine the spatial contact line contour composed of multiple three-dimensional data points.

[0138] The parameter determination module is used to determine the contact line and its parameters based on the spatial contact line contour of each contact line image.

[0139] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.

[0140] The apparatus described above is used to implement the corresponding non-contact contact network parameter detection method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0141] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the non-contact contact wire parameter detection method described in any of the above embodiments.

[0142] Figure 7 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0143] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0144] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0145] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0146] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0147] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0148] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0149] The electronic devices described above are used to implement the corresponding non-contact contact network parameter detection methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0150] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the non-contact contact network parameter detection method as described in any of the above embodiments.

[0151] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0152] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the non-contact contact network parameter detection method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0153] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0154] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0155] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0156] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A non-contact method for detecting overhead contact line parameters, characterized in that, include: As the vehicle travels along the track, multiple images of the contact line, composed of laser dots, are acquired using a line structured light sensor. Determining the spatial contact line contour of each contact line image includes: filtering data points in the contact line image according to preset point filtering conditions to obtain the filtered valid data points corresponding to the contact line; dividing the valid data points according to preset planar contour division conditions to determine a planar contact line contour composed of multiple valid data points; converting all valid data points on the planar contact line contour into three-dimensional data points; and dividing the three-dimensional data points according to preset spatial contour division conditions to determine a spatial contact line contour composed of multiple three-dimensional data points. Based on the spatial contact line contour of each contact line image, determine the contact line and its parameters, including: Calculate the centroid of the principal line for all three-dimensional data points on the spatial contact line profile; Calculate the principal line error distance between the centroids of the principal lines in the first and second consecutive contact line images; In response to the main line error distance being less than a preset main line error threshold, the distance between the main line centroids of the second and third consecutive contact line images is calculated until the number of consecutive contact line images reaches the preset main line threshold. Based on the spatial contact line contour of each contact line image, determine the main contact line; The parameters of the main contact line are determined based on the centroid of the main line.

2. The method according to claim 1, characterized in that, The step of filtering data points in the contact line image according to preset point filtering conditions to obtain filtered valid data points includes: Calculate the centroid of all data points in the contact line image; Based on the centroid point, a predetermined effective image region is defined in the contact line image; Within the valid image area, data points with non-zero column coordinate values ​​are selected as the valid data points.

3. The method according to claim 2, characterized in that, According to preset planar contour division conditions, the effective data points are divided to determine the planar contact line contour composed of multiple effective data points, including: Calculate the pixel distance between any two adjacent valid data points; Based on the pixel distance and the preset pixel distance threshold, the effective data points are clustered to obtain at least one planar line profile composed of multiple effective data points. Select planar contact line profiles that meet preset planar profile conditions from at least one planar line profile.

4. The method according to claim 3, characterized in that, Selecting planar contact line profiles that meet preset planar profile conditions from at least one planar line profile includes: Count the number of valid data points on each plane line profile; Determine at least one initial screening plane contact line profile whose number of plane points is within a preset plane point threshold range; Select a planar contact line profile from at least one initial screening planar contact line profile to identify valid data points that do not exhibit abrupt changes.

5. The method according to any one of claims 1-4, characterized in that, According to preset spatial contour division conditions, the three-dimensional data points are divided to determine the spatial contact line contour composed of multiple three-dimensional data points, including: Calculate the spatial distance between any two adjacent 3D data points; Based on the spatial distance and a preset spatial distance threshold, the three-dimensional data points are clustered to obtain at least one spatial line profile composed of multiple three-dimensional data points. Select a spatial contact line profile that meets the preset spatial profile conditions from at least one spatial line profile.

6. The method according to claim 5, characterized in that, Selecting spatial contact line profiles that meet preset spatial profile conditions from at least one spatial line profile includes: Count the number of spatial points of 3D data points on each spatial line contour; Determine at least one initial screening spatial contact line profile where the number of spatial points is within a preset spatial point threshold range; Spatial contact line profiles without abrupt changes in three-dimensional data points are selected from at least one initial screening spatial contact line profile.

7. The method according to claim 6, characterized in that, Selecting spatial contact line profiles from at least one initial screening spatial contact line profile that do not contain abrupt spatial data points includes: Calculate the distance between any two adjacent three-dimensional data points on the contour of the initial screening spatial contact line; Based on the distance, calculate the average distance of the three-dimensional data points on the contour of the initial screening spatial contact line; The initial screening spatial contact line profiles whose average distance is less than or equal to a preset spatial point distance threshold are taken as spatial contact line profiles without abrupt spatial data points.

8. The method according to claim 1, characterized in that, The spatial contact line contour of the contact line image includes a first spatial contact line contour and a second spatial contact line contour. The step of determining the main line of the contact line based on the spatial contact line contour of each contact line image includes: The main line of the contact line is determined based on the first spatial contact line contour of each contact line image; After determining the main contact wire, the following is also included: Calculate the centroid of the branch lines for all three-dimensional data points on the second spatial contact line profile; Calculate the branch error distance between the centroids of the branches in the first and second consecutive contact line images; In response to the branch error distance being less than a preset branch error threshold, the distance between the centroids of the branches in the second and third consecutive contact line images is calculated until the number of consecutive contact line images reaches the preset branch threshold. Based on the second spatial contact line contour of each contact line image, determine the contact line branches; The parameters of the contact wire branch are determined based on the centroid of the branch.

9. A non-contact contact network parameter detection device, characterized in that, include: The acquisition module is used to acquire multiple images of the contact line composed of laser dots using a line structured light sensor as the vehicle travels along the track. The contour determination module is used to determine the spatial contact line contour of each contact line image, including: filtering data points in the contact line image according to preset point filtering conditions to obtain the filtered valid data points corresponding to the contact line; dividing the valid data points according to preset planar contour division conditions to determine a planar contact line contour composed of multiple valid data points; converting all valid data points on the planar contact line contour into three-dimensional data points; and dividing the three-dimensional data points according to preset spatial contour division conditions to determine a spatial contact line contour composed of multiple three-dimensional data points. The parameter determination module is used to determine the contact line and contact line parameters based on the spatial contact line contour of each contact line image, including: calculating the centroid of the principal line of all three-dimensional data points on the spatial contact line contour; calculating the principal line error distance between the centroids of the principal lines of a first and a second consecutive contact line image; in response to the principal line error distance being less than a preset principal line error threshold, calculating the distance between the centroids of the principal lines of a second and a third consecutive contact line image, until the number of consecutive contact line images reaches the preset principal line threshold; determining the contact line principal line based on the spatial contact line contour of each contact line image; and determining the parameters of the contact line principal line based on the centroids of the principal lines.

Images