Target detection method and device for contact line

Abstract

The application provides a target detection method and device for a contact line, and the method comprises the following steps: obtaining a three-dimensional point cloud of the contact line, performing cross-section processing on the three-dimensional point cloud to obtain a point cloud cross-section, performing sampling processing on the point cloud cross-section to obtain a point cloud cross-section sequence, selecting a first detection sequence and a second detection sequence from the point cloud cross-section sequence according to the point cloud cross-section, performing similarity calculation on the first detection sequence and the second detection sequence respectively to determine a first feature position and a second feature position, and taking the first feature position and the second feature position as a starting point and an ending point of a target region of the contact line respectively to obtain the target region of the contact line. The application accurately determines the starting point and the ending point of the target region of the contact line by performing cross-section and sampling on the three-dimensional point cloud of the contact line and combining the similarity calculation on the detection sequence, effectively eliminates the interference of foreign matters, improves the target detection precision, has strong adaptability, and realizes accurate positioning of the position of the contact line in the three-dimensional scanning point cloud.

Description

Technical Field

[0001] This invention relates to the field of rail transit technology, and more particularly to a target detection method and apparatus for contact wires. Background Technology

[0002] The contact wire is a crucial component for the operation of urban rail transit vehicles, through which they obtain electrical energy. A good pantograph-catenary relationship is essential for the continuous and stable operation of the vehicle; abnormalities in this relationship will lead to operational malfunctions. During maintenance, the pantograph-catenary relationship can be detected using various measurement methods.

[0003] A 3D camera can be used to create a 3D image of the contact line. The 3D point cloud output by the device can be used for subsequent processing to obtain relevant geometric parameter values. Geometric parameter measurement based on the 3D point cloud requires first locating the lowest point of the contact line within the point cloud. Currently, this is often achieved by finding the lowest point of the point cloud along the z-axis, which is considered the contact point between the contact line and the pantograph. However, in actual measurements, there may be other interfering objects in the surrounding environment, and the acquired 3D point cloud may be deflected due to factors such as the device's installation angle and vehicle vibration. This means that the lowest point along the z-axis may not necessarily be the actual contact point between the contact line and the pantograph. Summary of the Invention

[0004] To address the problems existing in the prior art, the main objective of this invention is to provide a target detection method and apparatus for contact lines, enabling accurate positioning of the contact lines in a three-dimensional scanned point cloud.

[0005] To achieve the above objectives, embodiments of the present invention provide a target detection method for a contact wire, the method comprising:

[0006] Obtain the 3D point cloud of the contact line and perform cross-sectional processing on the 3D point cloud to obtain the point cloud cross-section;

[0007] The point cloud cross-section is sampled to obtain a point cloud cross-section sequence, and a first detection sequence and a second detection sequence are selected from the point cloud cross-section sequence based on the point cloud cross-section.

[0008] Similarity calculations are performed on the first detection sequence and the second detection sequence respectively to determine the first feature position and the second feature position;

[0009] The first feature position and the second feature position are used as the start and end points of the target area of ​​the contact line, respectively, to obtain the target area of ​​the contact line.

[0010] Optionally, in one embodiment of the present invention, the method further includes:

[0011] Determine the midpoint of the feature position based on the first feature position and the second feature position;

[0012] The rotation angle is determined based on the midpoint of the feature location, and the point cloud section is rotated using the rotation angle to obtain the rotated feature points.

[0013] Based on the first feature position, the second feature position, and the rotated feature point, coordinate transformation is performed on the points on the point cloud section to complete the three-dimensional point cloud attitude correction of the contact line.

[0014] Optionally, in one embodiment of the present invention, sampling the point cloud cross-section to obtain a point cloud cross-section sequence includes:

[0015] Determine the minimum spacing between adjacent sampling points based on the preset data coordinates on the point cloud cross section;

[0016] By using the minimum spacing between adjacent sampling points, the point cloud cross section is upsampled to obtain the point cloud cross section sequence.

[0017] Optionally, in one embodiment of the present invention, performing similarity calculations on the first detection sequence and the second detection sequence to determine the first feature position and the second feature position includes:

[0018] Similarity calculations are performed on each offset position in the first and second detection sequences to determine the correlation coefficient corresponding to each offset position;

[0019] Based on the correlation coefficients corresponding to each offset position, the similarity positions corresponding to the first detection sequence and the second detection sequence are determined respectively;

[0020] The highest points of the similar positions corresponding to the first detection sequence and the second detection sequence are obtained respectively to determine the first feature position and the second feature position.

[0021] This invention also provides a target detection device for contact lines, the device comprising:

[0022] The point cloud section module is used to acquire the three-dimensional point cloud of the contact line and perform cross-sectional processing on the three-dimensional point cloud to obtain the point cloud section.

[0023] The detection sequence module is used to sample the point cloud cross section to obtain the point cloud cross section sequence, and select the first detection sequence and the second detection sequence from the point cloud cross section sequence based on the point cloud cross section;

[0024] The feature location module is used to perform similarity calculations on the first detection sequence and the second detection sequence respectively, and determine the first feature location and the second feature location;

[0025] The target area module is used to take the first feature position and the second feature position as the start and end points of the contact line target area, respectively, to obtain the target area of ​​the contact line.

[0026] Optionally, in one embodiment of the present invention, the apparatus further includes:

[0027] The midpoint module is used to determine the midpoint of the feature position based on the first feature position and the second feature position.

[0028] The section rotation module is used to determine the rotation angle based on the midpoint of the feature location, and then use the rotation angle to rotate the point cloud section to obtain the rotated feature points.

[0029] The attitude correction module is used to perform coordinate transformation on the points on the point cloud section based on the first feature position, the second feature position, and the rotated feature points, so as to complete the attitude correction of the three-dimensional point cloud of the contact line.

[0030] Optionally, in one embodiment of the present invention, the detection sequence module includes:

[0031] The sampling interval unit is used to determine the minimum spacing between adjacent sampling points based on the preset data coordinates on the point cloud cross section;

[0032] The upsampling unit is used to upsample the point cloud cross section using the minimum spacing between adjacent sampling points to obtain the point cloud cross section sequence.

[0033] Optionally, in one embodiment of the present invention, the feature location module includes:

[0034] The correlation coefficient unit is used to calculate the similarity of each offset position on the first detection sequence and the second detection sequence, and to determine the correlation coefficient corresponding to each offset position.

[0035] The similarity position unit is used to determine the similarity positions corresponding to the first detection sequence and the second detection sequence respectively based on the correlation coefficients corresponding to each offset position.

[0036] The feature location unit is used to find the highest point of the similar positions corresponding to the first detection sequence and the second detection sequence respectively, and to determine the first feature location and the second feature location.

[0037] The present invention 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 above-described method.

[0038] The present invention also provides a computer-readable storage medium storing a computer program that performs the above-described methods by a computer.

[0039] The present invention also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the above-described method.

[0040] This invention accurately determines the start and end points of the target area of ​​the contact line by cross-sectioning and sampling the three-dimensional point cloud of the contact line, combined with similarity calculation of the detection sequence, thus obtaining the target area of ​​the contact line. It effectively eliminates interference from foreign objects, improves the target detection accuracy, has strong adaptability, and realizes accurate positioning of the contact line in the three-dimensional scanning point cloud. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of a target detection method for a contact wire according to an embodiment of the present invention;

[0043] Figure 2 This is a flowchart of three-dimensional point cloud attitude correction in an embodiment of the present invention;

[0044] Figure 3 This is a flowchart of point cloud cross-section sampling in an embodiment of the present invention;

[0045] Figure 4 This is a flowchart illustrating the determination of feature locations in an embodiment of the present invention;

[0046] Figure 5 This is a schematic diagram of the three-dimensional point cloud of the contact line in an embodiment of the present invention;

[0047] Figure 6 This is a partial schematic diagram of the three-dimensional point cloud of the contact line in an embodiment of the present invention;

[0048] Figure 7 This is a schematic diagram of a three-dimensional point cloud cross-section in an embodiment of the present invention;

[0049] Figure 8 This is a schematic diagram of the point cloud cross-section projection in an embodiment of the present invention;

[0050] Figure 9 This is a schematic diagram showing the location of the contact line features in an embodiment of the present invention;

[0051] Figure 10 This is a schematic diagram of the feature location template sequence in an embodiment of the present invention;

[0052] Figure 11 This is a schematic diagram of the start and end areas of the contact line target detected in an embodiment of the present invention;

[0053] Figure 12 This is a schematic diagram of point cloud rotation in an embodiment of the present invention;

[0054] Figure 13 This is a schematic diagram of the structure of a target detection device for a contact line according to an embodiment of the present invention;

[0055] Figure 14 This is a schematic diagram of the target detection device for contact lines in another embodiment of the present invention;

[0056] Figure 15 This is a schematic diagram of the detection sequence module in an embodiment of the present invention;

[0057] Figure 16 This is a schematic diagram of the feature location module in an embodiment of the present invention;

[0058] Figure 17 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0059] This invention provides a target detection method and apparatus for contact wires.

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] like Figure 1 The diagram shows a flowchart of a target detection method for contact lines according to an embodiment of the present invention. The execution subject of the target detection method for contact lines provided in this embodiment includes, but is not limited to, a computer. The present invention accurately determines the start and end points of the target region of the contact line by performing cross-sectional sampling on the three-dimensional point cloud of the contact line and combining this with similarity calculation of the detection sequence, thereby obtaining the target region of the contact line. This effectively eliminates interference from foreign objects, improves target detection accuracy, and has strong adaptability, achieving accurate positioning of the contact line in a three-dimensional scanned point cloud. The method shown in the diagram includes:

[0062] Step S1: Obtain the three-dimensional point cloud of the contact line and perform cross-sectional processing on the three-dimensional point cloud to obtain the point cloud cross-section.

[0063] Step S2: Sample the point cloud cross-section to obtain a point cloud cross-section sequence, and select the first detection sequence and the second detection sequence from the point cloud cross-section sequence based on the point cloud cross-section.

[0064] Step S3: Perform similarity calculations on the first detection sequence and the second detection sequence respectively to determine the first feature position and the second feature position;

[0065] Step S4: The first feature position and the second feature position are respectively used as the start and end points of the contact line target area to obtain the target area of ​​the contact line.

[0066] This process involves using a 3D camera to acquire a 3D point cloud of the contact line, and then processing the point cloud into screenshots. Specifically, point cloud screenshots can be obtained by taking random screenshots.

[0067] Furthermore, the acquired 3D point cloud, such as Figure 5 As shown, a magnified view of the contact line area is as follows: Figure 6 As shown.

[0068] Furthermore, for each calculation, one section is taken, shaped like... Figure 7 As shown in the figure, the area with the lowest height is not necessarily the contact point between the contact wire and the pantograph, and its shape is somewhat deflected. Projecting this point cloud cross-section onto an XY plane yields the following result: Figure 8 The curve shown.

[0069] As one embodiment of the present invention, such as Figure 3 As shown, sampling processing of the point cloud cross-section yields a point cloud cross-section sequence including:

[0070] Step S31: Determine the minimum spacing between adjacent sampling points based on the preset data coordinates on the point cloud cross section;

[0071] Step S32: Upsample the point cloud cross section using the minimum spacing between adjacent sampling points to obtain the point cloud cross section sequence.

[0072] In this process, the point cloud screenshots undergo sampling processing. Considering the varying density of sampling points at different locations, the sequence needs to be upsampled beforehand to normalize its resolution for subsequent signal-related operations. Specifically, let the original point cloud cross-sectional data coordinates be P. src ={(x src,i ,y src,i )}, i∈[1,M src ], totaling M src One point.

[0073] Furthermore, the minimum spacing between all adjacent sampling points in the x-axis direction is calculated as shown in formula (1).

[0074] Δx=min(x src,i+1 -x src,i ), i∈[1,M src -1] (1)

[0075] Upsampling the original sequence yields a new sequence P = {(x i ,y i)}, i∈[1,N], the spacing of the new sequence on the x-axis remains x i+1 =Δx+x i ,i∈[1,M-1], and the y-axis is obtained by linear interpolation, as shown in formula (2).

[0076]

[0077] Among them, (x l y l ),(x r y r ) are the original sequences P src Located in (x i y i ), i∈[1,M] the point on the left and right sides that is closest to it.

[0078] As one embodiment of the present invention, such as Figure 4 As shown, similarity calculations are performed on the first detection sequence and the second detection sequence to determine the first feature position and the second feature position, including:

[0079] Step S41: Calculate the similarity of each offset position on the first detection sequence and the second detection sequence respectively, and determine the correlation coefficient corresponding to each offset position;

[0080] Step S42: Determine the similarity positions corresponding to the first detection sequence and the second detection sequence respectively based on the correlation coefficients corresponding to each offset position;

[0081] Step S43: Find the highest point of the similar position corresponding to the first detection sequence and the second detection sequence respectively, and determine the first feature position and the second feature position.

[0082] Among them, such as Figure 9 As shown, there are two feature positions, P1 and P2, on the left and right sides of the contact line area. These feature positions mark the start and end points of the contact line on the point cloud cross section. Only the area between P1 and P2 belongs to the target of the contact line to be detected, while the area outside is background interference.

[0083] Furthermore, to detect feature locations P1 and P2 in the point cloud cross-section, a two-dimensional sequence can be taken from the upsampled sequence P beforehand as a detection template, i.e., the detection sequence, such as... Figure 10 The area shown in the dashed box contains a small region before and after P1, denoted as Seq1={(x s,i ,y s,i )}, i∈[1,N], which is the first detection sequence, with a total of N sampling points. Simultaneously, reversing the sequence Seq1 yields the symmetrical sequence Seq2={(x s,N-i ,y s,N-i)}, i∈[1,N], which is the second detection sequence. Detection sequences Seq1 and Seq2 can be used to detect feature positions P1 and P2, respectively.

[0084] Specifically, for the detection sequence Seq1, the offset of its starting detection position in the upsampled sequence is set to offset∈[0,M-N+1], and the correlation coefficient is calculated as shown in formula (3).

[0085]

[0086] This coefficient measures the relationship between the sequence Seq1 and P = {(x) at that offset position. i ,y i The similarity of i∈[i+offset,i+offset+N-1].

[0087] Furthermore, based on the calculation method in formula (3), all offset positions of the detection sequence are traversed, and the similarity of the sequence at each offset position is calculated. Based on the similarity calculation results, the position most similar to Seq1 can be obtained (e.g., Figure 11 (As shown in the dashed box area), within this sequence, find the highest point, which is feature point P1, i.e., the first feature position. For the mirror image detection sequence Seq2 of detection sequence Seq1, use the above calculation process to obtain the position most similar to Seq2 (e.g., ...). Figure 11 (As shown in the dashed circle area), within this sequence, find the highest point, which is feature point P2, i.e., the second feature position. After the above processing, the target area of ​​the contact line can be obtained.

[0088] The target detection and attitude correction method for three-dimensional point clouds of contact lines provided by this invention can locate the position of the contact line in a three-dimensional scanned point cloud and correct the attitude of the point cloud. This can reduce the influence of foreign objects, installation angles, vehicle vibrations, and other factors on the measurement results, providing reliable input for subsequent data processing.

[0089] As one embodiment of the present invention, such as Figure 2 As shown, the method also includes:

[0090] Step S21: Determine the midpoint of the feature position based on the first feature position and the second feature position;

[0091] Step S22: Determine the rotation angle based on the midpoint of the feature location, and use the rotation angle to rotate the point cloud section to obtain the rotated feature points;

[0092] Step S23: Based on the first feature position, the second feature position, and the rotated feature points, perform coordinate transformation on the points on the point cloud cross section to complete the three-dimensional point cloud attitude correction of the contact line.

[0093] After obtaining the target area of ​​the contact line, attitude correction can be performed on the 3D point cloud of the contact line. Specifically, after detecting feature positions P1 and P2, the midpoint of the feature positions is determined, and then the midpoint of P1 and P2 is used as the basis for the adjustment. The point cloud's orientation is corrected by rotating it by a certain angle θ around the center, so that the line connecting points P1' and P2' obtained after rotation remains parallel to the x-axis. For example... Figure 12 As shown, the two-dimensional rotation matrix to be determined is shown in formula (4).

[0094]

[0095] An equation can be established, as shown in formula (5).

[0096]

[0097] Therefore, the rotation angle θ can be obtained by solving this equation.

[0098] Furthermore, after obtaining the rotation angle θ, a reverse rotation is performed on the original sequence P around the point to complete the point cloud correction. Let p be the points before and after correction. src ,p trans p trans These are the feature points after rotation, and their transformation relationship is as follows:

[0099] Therefore, by performing the above coordinate transformation on all points in the point cloud cross section, the attitude correction of the three-dimensional point cloud of the contact line can be completed.

[0100] The point cloud sequence upsampling method proposed in this invention can handle situations where the point cloud sampling interval is unstable, improving the accuracy of subsequent processing and demonstrating strong adaptability. The contact line target detection method proposed in this invention can accurately locate the start and end positions of the contact line region based on the morphological characteristics of the point cloud sequence, eliminating interference from foreign objects. The point cloud correction method proposed in this invention fully utilizes the morphological characteristics of the target location to correct the point cloud sequence, reducing the impact of factors such as installation angle deviation and equipment vibration on subsequent processing.

[0101] This invention accurately determines the start and end points of the target area of ​​the contact line by cross-sectioning and sampling the three-dimensional point cloud of the contact line, combined with similarity calculation of the detection sequence, thus obtaining the target area of ​​the contact line. It effectively eliminates interference from foreign objects, improves the target detection accuracy, has strong adaptability, and realizes accurate positioning of the contact line in the three-dimensional scanning point cloud.

[0102] like Figure 13 The figure shows a schematic diagram of a target detection device for a contact line according to an embodiment of the present invention. The device shown in the figure includes:

[0103] The point cloud section module 10 is used to acquire the three-dimensional point cloud of the contact line and perform section processing on the three-dimensional point cloud to obtain the point cloud section.

[0104] The detection sequence module 20 is used to sample the point cloud cross section to obtain the point cloud cross section sequence, and select the first detection sequence and the second detection sequence from the point cloud cross section sequence according to the point cloud cross section;

[0105] The feature location module 30 is used to perform similarity calculations on the first detection sequence and the second detection sequence respectively, and determine the first feature location and the second feature location;

[0106] The target area module 40 is used to take the first feature position and the second feature position as the start and end points of the contact line target area, respectively, to obtain the target area of ​​the contact line.

[0107] As one embodiment of the present invention, such as Figure 14 As shown, the device also includes:

[0108] The midpoint module 50 is used to determine the midpoint of the feature position based on the first feature position and the second feature position;

[0109] The section rotation module 60 is used to determine the rotation angle based on the midpoint of the feature position, and to rotate the point cloud section using the rotation angle to obtain the rotated feature points;

[0110] The attitude correction module 70 is used to perform coordinate transformation on the points on the point cloud section based on the first feature position, the second feature position, and the rotated feature points, so as to complete the attitude correction of the three-dimensional point cloud of the contact line.

[0111] As one embodiment of the present invention, such as Figure 15 As shown, the detection sequence module 20 includes:

[0112] The sampling interval unit 21 is used to determine the minimum spacing between adjacent sampling points based on the preset data coordinates on the point cloud cross section.

[0113] Upsampling unit 22 is used to upsample the point cloud cross section using the minimum spacing between adjacent sampling points to obtain the point cloud cross section sequence.

[0114] As one embodiment of the present invention, such as Figure 16 As shown, the feature location module 30 includes:

[0115] The correlation coefficient unit 31 is used to calculate the similarity of each offset position on the first detection sequence and the second detection sequence respectively, and to determine the correlation coefficient corresponding to each offset position.

[0116] The similarity position unit 32 is used to determine the similarity positions corresponding to the first detection sequence and the second detection sequence respectively based on the correlation coefficients corresponding to each offset position.

[0117] The feature position unit 33 is used to calculate the highest point of the similar positions corresponding to the first detection sequence and the second detection sequence respectively, and to determine the first feature position and the second feature position.

[0118] Based on the same concept as the aforementioned target detection method for contact lines, this invention also provides a target detection device for contact lines. Since the principle by which this target detection device solves the problem is similar to that of the target detection method for contact lines, the implementation of this target detection device can refer to the implementation of the target detection method for contact lines, and will not be repeated here.

[0119] This invention accurately determines the start and end points of the target area of ​​the contact line by cross-sectioning and sampling the three-dimensional point cloud of the contact line, combined with similarity calculation of the detection sequence, thus obtaining the target area of ​​the contact line. It effectively eliminates interference from foreign objects, improves the target detection accuracy, has strong adaptability, and realizes accurate positioning of the contact line in the three-dimensional scanning point cloud.

[0120] The present invention 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 above-described method.

[0121] The present invention also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the above-described method.

[0122] The present invention also provides a computer-readable storage medium storing a computer program that performs the above-described methods by a computer.

[0123] like Figure 17 As shown, the electronic device 600 may also include: a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily need to include these components. Figure 17 All components shown; in addition, the electronic device 600 may also include Figure 17 For components not shown, please refer to existing technologies.

[0124] like Figure 17 As shown, the central processing unit 100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device. The central processing unit 100 receives inputs and controls the operation of various components of the electronic device 600.

[0125] The memory 140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 100 may execute the program stored in the memory 140 to perform information storage or processing, etc.

[0126] Input unit 120 provides input to central processing unit 100. Input unit 120 may be, for example, a keypad or touch input device. Power supply 170 provides power to electronic device 600. Display 160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0127] The memory 140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 140 can also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application / function storage unit 142 for storing application programs and function programs or processes for executing the operation of the electronic device 600 via the central processing unit 100.

[0128] The memory 140 may also include a data storage unit 143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 144 of the memory 140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0129] The communication module 110 is a transmitter / receiver 110 that transmits and receives signals via antenna 111. The communication module (transmitter / receiver) 110 is coupled to the central processing unit 100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0130] Based on different communication technologies, multiple communication modules 110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132, thereby enabling typical telecommunications functions. The audio processor 130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 130 is coupled to a central processing unit 100, enabling on-device recording via the microphone 132 and on-device playback of stored audio via the speaker 131.

[0131] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0133] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0135] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A target detection method for a contact line, characterized in that, The method includes: A three-dimensional point cloud of the contact line is obtained, and the three-dimensional point cloud is subjected to cross-sectional processing to obtain a point cloud cross-section. The point cloud cross-section is sampled to obtain a point cloud cross-section sequence, and a first detection sequence and a second detection sequence are selected from the point cloud cross-section sequence based on the point cloud cross-section. Similarity calculations are performed on the first detection sequence and the second detection sequence respectively to determine the first feature position and the second feature position; The first feature position and the second feature position are respectively used as the start and end points of the target area of ​​the contact line to obtain the target area of ​​the contact line. The step of performing similarity calculations on the first detection sequence and the second detection sequence respectively to determine the first feature position and the second feature position includes: Similarity calculations are performed on each offset position in the first detection sequence and the second detection sequence respectively to determine the correlation coefficient corresponding to each offset position; Based on the correlation coefficients corresponding to each offset position, the similar positions corresponding to the first detection sequence and the second detection sequence are determined respectively; The highest point is obtained from the similar positions corresponding to the first detection sequence and the second detection sequence respectively, and the first feature position and the second feature position are determined.

2. The method according to claim 1, characterized in that, The method further includes: Determine the midpoint of the feature position based on the first feature position and the second feature position; The rotation angle is determined based on the midpoint of the feature location, and the point cloud section is rotated using the rotation angle to obtain the rotated feature points. Based on the first feature position, the second feature position, and the rotated feature point, coordinate transformation is performed on the points on the point cloud cross section to complete the three-dimensional point cloud attitude correction of the contact line.

3. The method according to claim 1, characterized in that, The point cloud cross-section is sampled to obtain a point cloud cross-section sequence including: The minimum spacing between adjacent sampling points is determined based on the preset data coordinates on the point cloud cross section. The point cloud cross section is upsampled using the minimum spacing between adjacent sampling points to obtain the point cloud cross section sequence.

4. A target detection device for a contact line, characterized in that, The device includes: The point cloud section module is used to acquire the three-dimensional point cloud of the contact line and perform section processing on the three-dimensional point cloud to obtain the point cloud section. The detection sequence module is used to sample the point cloud cross section to obtain a point cloud cross section sequence, and select a first detection sequence and a second detection sequence from the point cloud cross section sequence based on the point cloud cross section; The feature location module is used to perform similarity calculations on the first detection sequence and the second detection sequence respectively, and determine the first feature location and the second feature location; The target region module is used to take the first feature position and the second feature position as the start and end points of the target region of the contact line, respectively, to obtain the target region of the contact line. The feature location module includes: The correlation coefficient unit is used to calculate the similarity of each offset position on the first detection sequence and the second detection sequence respectively, and determine the correlation coefficient corresponding to each offset position; The similarity position unit is used to determine the similarity positions corresponding to the first detection sequence and the second detection sequence respectively based on the correlation coefficients corresponding to each offset position. The feature location unit is used to calculate the highest point of the similar positions corresponding to the first detection sequence and the second detection sequence respectively, and to determine the first feature location and the second feature location.

5. The apparatus according to claim 4, characterized in that, The device further includes: The midpoint module is used to determine the midpoint of the feature position based on the first feature position and the second feature position; A section rotation module is used to determine the rotation angle based on the midpoint of the feature position, and to rotate the point cloud section using the rotation angle to obtain the rotated feature points; The attitude correction module is used to perform coordinate transformation on the points on the point cloud cross section based on the first feature position, the second feature position, and the rotated feature points, so as to complete the attitude correction of the three-dimensional point cloud of the contact line.

6. The apparatus according to claim 4, characterized in that, The detection sequence module includes: The sampling interval unit is used to determine the minimum spacing between adjacent sampling points based on the preset data coordinates on the point cloud cross section; An upsampling unit is used to upsample the point cloud cross section using the minimum spacing between adjacent sampling points to obtain the point cloud cross section sequence.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that enables a computer to execute the method according to any one of claims 1 to 3.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 3.

Images