Point cloud-based airport station level straight line fitting method and device, and related equipment

Abstract

The invention provides an airport station level straight line fitting method and device based on point cloud and related equipment, and relates to the technical field of berth guiding systems.The method comprises the steps that original scanning point cloud data are acquired, and earth surface segmentation is conducted on the original scanning point cloud data to divide the original scanning point cloud data into a ground point cloud set and a non-ground point cloud set; calculating the position of a guide line or a stop line according to the ground point cloud set, and performing first-stage straight line fitting to form a first straight line; selecting point cloud data from the ground point cloud set to form a point cloud cluster, wherein the distance between the point cloud data and the first straight line is smaller than a preset threshold; and performing second-stage straight line fitting according to the point cloud cluster to form a second straight line. According to the invention, the straight line fitting of the guide line or the stop line is carried out on the ground point cloud data in two stages, so that the precision of the guide line or the stop line is improved.

Description

Background Art

[0002] The apron taxiway guiding lines at the airport are important facilities to ensure the safe and accurate parking and taxiing of aircraft. They not only help the flight crew follow the standard routes and parking positions, but also reduce the risk of collisions between aircraft and other aircraft, vehicles, and equipment through clear markings and instructions.

[0003] Under normal circumstances, the relative positions of the taxiway guiding lines and the Visual Docking Guidance System (VDGS) are fixed. However, there are many actual complex interference factors. For example, equipment aging, extreme weather effects, or accidental external collisions can cause varying degrees of deviation in the relative positions of the VDGS equipment and the guiding lines on the apron surface. Therefore, in order to accurately identify and position the pose of inbound aircraft over a long period of time, precise coordinate calibration and relative position acquisition are required from the VDGS. How to quickly, accurately, and reliably identify the guiding lines on the apron surface has become an effective solution.

[0004] Since the scattered point clouds extracted from the spraying reflection intensity differences of the apron guiding lines by a single lidar can basically not be effectively fitted into a straight line, the existing mainstream VDGS generally relies on a small number of selected reference points for distance threshold determination, with low reliability and accuracy; or a visible light camera is introduced, and effective key points are selected within the field of view by relying on the rich semantic information of the image for judgment. However, this solution has a high cost control and a high system complexity. Therefore, how to accurately fit the scattered point clouds of the guiding lines using a single radar sensor and then precisely calibrate the coordinate system is the key issue for the reliability of the use and maintenance of the VDGS.

[0005] It should be noted that the information disclosed in the above Background Art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The present disclosure provides a method, device, and related equipment for straight line fitting of an airport apron based on point clouds, which at least improves the accuracy of detecting and identifying the taxiway guiding lines at the airport apron to a certain extent.

[0007] Other features and advantages of the present disclosure will become apparent through the following detailed description, or will be partially learned through the practice of the present disclosure.

[0008] According to one aspect of the present disclosure, there is provided a method for straight line fitting of an airport apron based on point cloud, including: acquiring original scanned point cloud data, performing ground surface segmentation on the original scanned point cloud data and dividing it into a ground point cloud set and a non-ground point cloud set; calculating the position of a guiding line or a stop line according to the ground point cloud set, and performing a first-stage straight line fitting to form a first straight line; selecting point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud set to form a point cloud cluster; and performing a second-stage straight line fitting according to the point cloud cluster to form a second straight line.

[0009] In some exemplary embodiments of the present disclosure, based on the foregoing solution, performing ground surface segmentation on the original scanned point cloud data and dividing it into a ground point cloud set and a non-ground point cloud set includes: performing ground surface segmentation based on a preset height threshold or a clustering algorithm; and / or, performing angle correction on the original scanned point cloud data according to the installation angle of a pre-installed detection device to divide the original scanned point cloud data into a ground point cloud set and a non-ground point cloud set.

[0010] In some exemplary embodiments of the present disclosure, based on the foregoing solution, calculating the position of a guiding line or a stop line according to the ground point cloud set and performing a first-stage straight line fitting to form a first straight line includes: filtering the ground point cloud set based on a preset intensity threshold to extract a first point cloud set containing the guiding line or the stop line; calculating the position of the guiding line or the stop line according to the first point cloud set, and performing a first-stage straight line fitting to form a first straight line.

[0011] In some exemplary embodiments of the present disclosure, based on the foregoing solution, calculating the position of a guiding line or a stop line according to the first point cloud set and performing a first-stage straight line fitting to form a first straight line includes: obtaining a plane projection of the first point cloud set within a preset range on a plane perpendicular to the guiding line or the stop line; traversing the point cloud data in the plane projection to determine a reference point in the plane projection, and performing fitting with a straight line passing through the reference point and parallel to the coordinate axis of the coordinate system parallel to the guiding line or the stop line to form a first straight line.

[0012] In some exemplary embodiments of the present disclosure, based on the foregoing solution, traversing the point cloud data in the plane projection to determine a reference point in the plane projection includes: determining the maximum and minimum values of the first point cloud set along two axial directions on a plane perpendicular to the guiding line or the stop line, and creating a two-dimensional matrix according to the maximum and minimum values; and determining the reference point in the plane projection based on the maximum and minimum values of the first point cloud set along two axial directions on a plane perpendicular to the guiding line or the stop line and the two-dimensional matrix.

[0013] In some exemplary embodiments of the present disclosure, based on the foregoing solution, determining a reference point in the plane projection based on the maximum and minimum values along two axial directions and the two-dimensional matrix of the first point cloud cluster on a plane perpendicular to the guiding line or the stopping line includes: the size of the two-dimensional matrix is m×n, where m and n are the resolutions of the two axial directions of the plane perpendicular to the guiding line or the stopping line respectively; traversing the two-dimensional matrix to find the element with the largest value and its corresponding coordinates, and converting them into the point cloud coordinate system to determine the reference point in the plane projection.

[0014] In some exemplary embodiments of the present disclosure, based on the foregoing solution, forming a second straight line by performing a second-stage straight line fitting according to the point cloud cluster includes: using the random sample consensus algorithm or the least squares method to perform the second-stage straight line fitting.

[0015] According to another aspect of the present disclosure, there is also provided a device for straight line fitting of an airport apron based on point cloud, including: a point cloud data acquisition module, configured to acquire original scanned point cloud data, perform ground segmentation on the original scanned point cloud data and divide it into a ground point cloud cluster and a non-ground point cloud cluster; a first straight line fitting module, configured to calculate the position of the guiding line or the stopping line according to the ground point cloud cluster and perform a first-stage straight line fitting to form a first straight line; a point cloud cluster forming module, configured to select point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud cluster to form a point cloud cluster; a second straight line fitting module, configured to perform a second-stage straight line fitting according to the point cloud cluster to form a second straight line.

[0016] According to still another aspect of the present disclosure, there is also provided an electronic device, including: a processor; and a memory, configured to store executable instructions of the processor; wherein, the processor is configured to execute any one of the above-mentioned methods for straight line fitting of an airport apron based on point cloud by executing the executable instructions.

[0017] According to yet another aspect of the present disclosure, there is also provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements any one of the above-mentioned methods for straight line fitting of an airport apron based on point cloud.

[0018] An airport apron straight line fitting method, device and related equipment based on point cloud provided in the embodiments of the present disclosure perform straight line fitting of the guiding line or stop line in two times. Among them, the first fitting can determine the position range of the guiding line or stop line, and quickly eliminate a large number of point clouds with low relevance, reducing the amount of calculation; and perform the second fitting on the ground point cloud data within the position range of the preliminarily determined guiding line or stop line that is less than a preset threshold from the first straight line, further improving the fitting accuracy. This phased method adopted in the embodiments of the present disclosure not only has a small amount of calculation, but also has a very high adjustment accuracy, and realizes efficient and accurate guiding line detection and recognition without complex parameter adjustment.

[0019] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0021] Figure 1 The schematic diagram of an exemplary application system architecture showing a method for straight line fitting of an airport apron based on point cloud in an embodiment of the present disclosure;

[0022] Figure 2 The schematic diagram showing a method for straight line fitting of an airport apron based on point cloud in an embodiment of the present disclosure;

[0023] Figure 3 The schematic diagram showing the double-stage data screening after projection of ground point cloud data in an embodiment of the present disclosure;

[0024] Figure 4 The schematic diagram showing the process of a straight line fitting method for double-stage scattered ground point cloud data in an embodiment of the present disclosure;

[0025] Figure 5 The schematic diagram showing a device for straight line fitting of an airport apron based on point cloud in an embodiment of the present disclosure;

[0026] Figure 6 The schematic diagram showing an electronic device applying a method for straight line fitting of an airport apron based on point cloud in an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0028] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be used. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the present disclosure.

[0029] The flowchart shown in the accompanying drawings is merely illustrative and not necessarily inclusive of all content and operations / steps, nor is it necessarily executed in the order described. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0030] Figure 1 An exemplary application system architecture diagram is shown to which the point cloud-based guide line straight line fitting method in the embodiments of the present disclosure can be applied. As Figure 1 shown, the system architecture may include a terminal device 101, a network 102, and a server 103.

[0031] The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103, and can be a wired network or a wireless network.

[0032] Optionally, the above-mentioned wireless network or wired network uses standard communication technologies and / or protocols. The network is usually the Internet, but can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or a virtual private network. In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent data exchanged through the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can be used to encrypt all or some of the links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0033] The terminal device 101 can be various electronic devices, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, wearable devices, augmented reality devices, virtual reality devices, etc.

[0034] Optionally, the clients of the application programs installed in different terminal devices 101 are the same, or are clients of the same type of application program based on different operating systems. Depending on the different terminal platforms, the specific form of the client of the application program can also be different. For example, the client of the application program can be a mobile phone client, a PC client, etc.

[0035] The server 103 can be a server that provides various services, such as a background management server that supports the operations performed by the user using the terminal device 301. The background management server can analyze and process data such as requests received, and feedback the processing results to the terminal device.

[0036] Optionally, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, and this application does not make any restrictions here.

[0037] Those skilled in the art can know that Figure 1 the number of terminal devices, networks, and servers in

[0038] is only illustrative. According to actual needs, there can be any number of terminal devices, networks, and servers. The embodiments of the present disclosure do not make any limitations in this regard.

[0039] In some embodiments, the method for fitting a straight line of an airport apron based on point cloud provided in the embodiments of the present disclosure can be executed by the terminal device of the above system architecture; in some other embodiments, the method for fitting a straight line of an airport apron based on point cloud provided in the embodiments of the present disclosure can be executed by the server in the above system architecture; in some other embodiments, the method for fitting a straight line of an airport apron based on point cloud provided in the embodiments of the present disclosure can be implemented by the terminal device and the server in the above system architecture through interaction.

[0040] First, embodiments of the present disclosure provide a method for detecting and recognizing airport apron guiding lines or stop lines that can be applied but are not limited to such scenarios, and can also be extended to other scenarios that require precise straight line fitting, such as road marking detection, object positioning on industrial production lines, etc. Its flexible design and efficient performance make it widely applicable. Specifically, compared with the problem in related technologies that scattered point clouds extracted from the spraying reflection intensity differences of lidar for apron guiding lines or stop lines can hardly be effectively used for straight line fitting, embodiments of the present disclosure perform straight line fitting of the guiding lines or stop lines in two steps. Among them, the first fitting can determine the position range of the guiding lines or stop lines, and quickly eliminate a large number of point clouds with low relevance, reducing the amount of computation; and in the position range of the preliminarily determined guiding lines or stop lines, the ground point cloud data within a preset threshold distance from the first straight line is screened for the second fitting to obtain the second straight line, further improving the fitting accuracy. The phased method adopted in embodiments of the present disclosure not only has a small amount of computation, but also has a very high adjustment accuracy, and realizes efficient and accurate guiding line detection and recognition without complex parameter adjustment.

[0041] Figure 2 Schematic diagram showing a method for straight line fitting of airport apron based on point cloud in embodiments of the present disclosure, as Figure 2 shown, the method includes the following steps:

[0042] S202, Obtain the original scanned point cloud data, perform ground surface segmentation on the original scanned point cloud data, and divide it into a ground point cloud set and a non-ground point cloud set.

[0043] It should be noted that the original scanned point cloud data obtained in embodiments of the present disclosure refers to a three-dimensional point cloud data set containing airport apron parking guiding lines or stop lines obtained through lidar or other three-dimensional scanning devices. These data not only include the spatial coordinates (x, y, z) of each scanned point, but may also include additional information such as reflection intensity and color; in addition, the guiding lines or stop lines in embodiments of the present disclosure can be any airport apron parking guiding lines or stop lines. Among them, the guiding lines are divided into physical guiding lines and virtual guiding lines. The physical guiding lines are drawn or installed on the ground by actual materials (such as paint, reflective tape, metal inlays, etc.) to form clearly visible lines; while the virtual guiding lines are generated by sensors and display devices such as lidar, cameras, projectors, etc., and projected onto the ground or presented to the driver in other ways. More specifically, the parking guiding lines in embodiments of the present disclosure are important facilities to ensure flight safety and improve operation efficiency; and the stop line usually consists of two solid yellow lines and a yellow dashed line. The dashed line is closer to the runway side. When the aircraft reaches this point, it must stop and wait for further instructions from air traffic control. Through these clear and standardized guiding lines and stop lines, the airport can effectively manage and control ground traffic, reduce the risk of collisions, and improve the overall operation efficiency and safety.

[0044] In some embodiments, the embodiments of the present disclosure first obtain the original point cloud data, and perform angle correction according to the factory installation angle of the lidar to make the apron plane parallel to the XOY plane and the normal line parallel to the Z axis. By adjusting the factory installation angle of the lidar, subsequent operations can be facilitated, errors can be reduced, and calculation accuracy can be improved. Then, the original point cloud data is subjected to ground segmentation to divide the original point cloud data into a ground point cloud set and a non-ground point cloud set. Among them, there are many methods for ground segmentation, such as the method based on height threshold, the method based on clustering algorithm, etc. The embodiments of the present disclosure do not limit them again. By screening out the ground point cloud data, irrelevant non-ground point cloud sets can be removed, which can greatly reduce the number of point clouds participating in the operation. Moreover, removing irrelevant interfering point clouds from the fitting operation can reduce the algorithm operation delay and improve the fitting accuracy at the same time.

[0045] S204. Calculate the position of the guiding line or the stop line according to the ground point cloud set, and perform the first-stage straight line fitting to form the first straight line.

[0046] It should be noted that the embodiments of the present disclosure can adopt any algorithm for fitting discrete point cloud data. For example, the Random Sample Consensus (RANSAC) algorithm: use the RANSAC algorithm to perform straight line fitting on the point cloud data, and eliminate abnormal points through multiple random samplings and model validations to improve the robustness of the fitting; the least squares method: use the least squares method to perform straight line fitting on the point cloud data, and obtain the optimal straight line parameters by minimizing the sum of the squares of the distances from the point cloud to the straight line. This method is simple and efficient and applicable to most scenarios. In addition, the purpose of the first fitting operation on the ground point cloud data in the embodiments of the present disclosure is to preliminarily calculate the position where the guiding line or the stop line appears in space and perform rough fitting. Based on the rough fitting result, the search space of the subsequent optimization algorithm can be reduced and the efficiency can be improved.

[0047] S206. Select the point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud set to form a point cloud cluster.

[0048] It should be noted that although the guiding line or the stop line in the embodiments of the present disclosure cannot completely coincide with the first straight line, the deviation will not be large. Therefore, the ground point cloud data with a distance less than the preset threshold from the first straight line can be selected to form a point cloud cluster, and other point clouds with low relevance can be removed again.

[0049] In some embodiments, the embodiments of the present disclosure screen out the point cloud data close to the first straight line by setting a threshold value, which can effectively remove the background noise and other interference factors far from the straight line, making the subsequent processing more focused on the relevant area; and the point cloud clusters after clustering usually contain the data points that best represent the characteristics of the guiding line, thus providing a good basis for a more accurate second fitting; in addition, compared with directly fitting all the point cloud data, screening out the relevant point cloud and clustering it first in the embodiments of the present disclosure can greatly reduce the amount of data participating in the operation and improve the calculation efficiency.

[0050] S208, perform a second-stage straight line fitting according to the point cloud clusters to form a second straight line.

[0051] It should be noted that the process of adjusting the first straight line according to the second straight line in the embodiments of the present disclosure is to more accurately fit the guiding line or the stop line. In actual situations, although the guiding line or the stop line cannot completely coincide with the first straight line, the deviation will not be large. Therefore, point cloud clusters with a distance less than a specified preset threshold from the first straight line can be selected for the second fitting to eliminate other point clouds with low relevance again. Specifically, in the embodiments of the present disclosure, a second-stage straight line fitting is first performed through the point cloud clusters to form a second straight line, and the parameters of the second straight line are initially calculated. Then, an appropriate model (such as a two-dimensional straight line equation) can be selected, and the random sample consensus algorithm or the least squares method or the robust regression technique is used to optimize the parameters, and at the same time, the distance threshold is adjusted to screen out the inliers; then, the distances from all the inliers to the fitted straight line are calculated to evaluate the fitting accuracy. According to the evaluation results, the parameters and the threshold are appropriately adjusted, and the optimization process is repeated until the most accurate fitted straight line is obtained. Through multiple iterative optimizations, the finally obtained straight line equation can very accurately describe the actual position of the guiding line and maintain good robustness even in the presence of noise or outliers.

[0052] An airport apron straight line fitting method based on point cloud provided in an embodiment of the present disclosure. First, obtain the original scanned point cloud data, and perform ground surface segmentation on the original scanned point cloud data to divide it into a ground point cloud set and a non-ground point cloud set. Secondly, calculate the position of the guiding line or the stop line according to the ground point cloud set, and perform the first-stage straight line fitting to form the first straight line. Then, select the point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud set to form a point cloud cluster. Finally, perform the second-stage straight line fitting according to the point cloud cluster to form the second straight line. Compared with the problem in the related technology that the scattered point clouds extracted from the spraying reflection intensity difference of the apron guiding line or the stop line by lidar can hardly be effectively used for straight line fitting, the embodiment of the present disclosure performs the straight line fitting of the guiding line in two times. Among them, the first fitting can determine the position range of the guiding line or the stop line, and quickly eliminate a large number of point clouds with low correlation, reducing the amount of calculation; and perform the second fitting on the selected ground point cloud data with a distance less than the preset threshold from the first straight line within the position range of the preliminarily determined guiding line or stop line to obtain the second straight line, further improving the fitting accuracy. The phased method adopted in the embodiment of the present disclosure not only has a small amount of calculation, but also has a very high adjustment accuracy, and realizes efficient and accurate guiding line detection and recognition without complex parameter adjustment.

[0053] It should be noted that the embodiment of the present disclosure only relies on lidar point cloud data for the straight line fitting of the guiding line or the stop line, without adding a visible light camera or other multi-modal sensors, which not only reduces the hardware cost of the system, but also simplifies the complexity of the system, making maintenance and deployment more convenient.

[0054] In some embodiments, the embodiment of the present disclosure performs ground surface segmentation on the original scanned point cloud data and divides it into a ground point cloud set and a non-ground point cloud set, including: performing ground surface segmentation based on a preset height threshold or a clustering algorithm; and / or, performing angle correction on the original scanned point cloud data according to the installation angle of the pre-installed detection device to divide the original scanned point cloud data into a ground point cloud set and a non-ground point cloud set. Specifically, the embodiment of the present disclosure filters out the point cloud data close to the first straight line through a preset height threshold or a clustering algorithm, which can effectively remove the background noise and other interference factors far from the straight line, making the subsequent processing more focused on the relevant area; in addition, there may be a certain tilt or offset when the detection device is installed. By performing angle correction on the original scanned point cloud data, these installation errors can be eliminated to ensure the authenticity and accuracy of the data. It can be seen that compared with directly fitting all the point cloud data, the embodiment of the present disclosure first filters out the relevant point clouds and divides the original scanned point cloud data into a ground point cloud set and a non-ground point cloud set, which can greatly reduce the amount of data participating in the calculation and improve the calculation efficiency.

[0055] In some embodiments, the embodiments of the present disclosure calculate the position of the guiding line or the stop line based on the ground point cloud set, and perform the first-stage straight line fitting to form the first straight line, including: filtering the ground point cloud set based on a preset intensity threshold, and extracting the first point cloud set containing the guiding line or the stop line; calculating the position of the guiding line or the stop line according to the first point cloud set, and performing the first-stage straight line fitting to form the first straight line. Specifically, the ground point cloud data is adaptively dynamically threshold-filtered according to the preset intensity threshold, and the guiding line and a point cloud set of some high-intensity reflections are preliminarily extracted. In actual data, the point cloud distribution of the guiding line is from near to far from the radar, with a large range and a large difference in density. There are many interference noise points in the high-intensity reflection area near and the weak reflection area far. If some classic algorithms such as Hough straight line fitting are directly used, the effect will be very poor and the operation time will be long due to a large number of search operations. The embodiments of the present disclosure can effectively remove the high-intensity reflection noise points through the adaptive dynamic threshold filtering of the intensity information, reduce the influence of interference factors on the fitting result, which enables the algorithm to maintain high precision and high reliability in a complex environment.

[0056] In some embodiments, the embodiments of the present disclosure calculate the position of the guiding line or the stop line according to the first point cloud set, and perform the first-stage straight line fitting to form the first straight line, including: obtaining the plane projection of the first point cloud set within a preset range on the plane perpendicular to the guiding line or the stop line; traversing the point cloud data in the plane projection, determining the reference point in the plane projection, and performing fitting with the straight line passing through the reference point and parallel to the coordinate axis of the coordinate system parallel to the guiding line or the stop line to form the first straight line. Specifically, the embodiments of the present disclosure can set the direction of the guiding line as the Y axis, the direction of the stop line as the X axis, and the normal direction of the ideal plane of the apron as the Z axis. Then the plane projection can be XOZ; through the maximum and minimum values of the ground point cloud data on the X axis and the Z axis, the range of the ground point cloud data on the plane projection XOZ is determined. The preset range in the embodiments of the present disclosure can be the range between the maximum and minimum values of the ground point cloud data on the X axis and the Z axis, which can be denoted as (X max , X min ), (Z max , Z min ). The embodiments of the present disclosure make the subsequent processing more focused on the relevant area by screening out the point cloud data close to the plane projection, thereby improving the accuracy of the final fitting result.

[0057] In some embodiments, the embodiments of the present disclosure traverse the point cloud data in the planar projection to determine the reference points in the planar projection, including: determining the maximum and minimum values of the first point cloud set along two axes on a plane perpendicular to the guiding line or the stop line, and creating a two-dimensional matrix according to the maximum and minimum values; determining the reference points in the planar projection based on the maximum and minimum values of the first point cloud set along two axes on a plane perpendicular to the guiding line or the stop line and the two-dimensional matrix. Specifically, the point cloud data after matrix processing is easier to perform structured analysis, which helps to capture the true position of the guiding line more accurately; in addition, compared with directly fitting all the point cloud data, first screening out the relevant point cloud and performing matrix processing can greatly reduce the amount of data participating in the operation and improve the calculation efficiency.

[0058] In some embodiments, the embodiments of the present disclosure determine the reference points in the planar projection based on the maximum and minimum values of the first point cloud set along two axes on a plane perpendicular to the guiding line or the stop line and the two-dimensional matrix, including: the size of the two-dimensional matrix is m×n, where m and n are the resolutions of the two axes of the plane perpendicular to the guiding line or the stop line respectively; traversing the two-dimensional matrix to find the element with the largest value and its corresponding coordinates, and converting them into the point cloud coordinate system to determine the reference points in the planar projection. Specifically, the embodiments of the present disclosure first obtain the ground point cloud data, form the range of the point cloud set S in the planar projection XOZ, determine the maximum and minimum values of the point cloud set S on the X-axis and Z-axis, denoted as X max , X min , Z max , Z min ; then, create a two-dimensional target matrix A: according to X max , X min , Z max , Z min create a two-dimensional matrix A, the size of the matrix is m×n, where m and n are the resolutions of the X-axis and Z-axis respectively (it can also be that n and m are the resolutions of the X-axis and Z-axis respectively); then, project the point cloud set S onto the planar projection XOZ: for each point (X i , Y i , Z i ) in the point cloud set S, project it onto the planar projection XOZ to obtain the projection point (X i , Z i ); finally, obtain the coordinates with the largest value in the two-dimensional matrix A: traverse the two-dimensional matrix A to find the element with the largest value and its corresponding coordinates (i max , j max ), according to the resolutions m and n of the two-dimensional matrix A, and the start and end values X max , X min , Z max , Z min of the point cloud set S on the X-axis and Z-axis, convert the matrix coordinates (imax , j max ) Coordinates (X m , Z m ) converted to the point cloud coordinate system. At this time, it can be preliminarily considered that the guiding line or the stop line is the first straight line passing through the point (X m , 0, z max ) and parallel to the Y-axis.

[0059] More specifically, the embodiments of the present disclosure can calculate the first straight line through the following formulas (1) - (2):

[0060] X m = X min + i max × Δx (1)

[0061] Z m = Z min + j max × Δz (2)

[0062] Where Δx = X max - X min / (m - 1) and Δz = (Z max - Z min ) / (n - 1) are the resolution step sizes.

[0063] In some embodiments, the embodiments of the present disclosure project each point (X i , Y i , Z i ) in the ground point cloud data onto a plane projection (for example, the XOZ plane exemplified above) to obtain the projection point (X i , Z i ). Through projection, the point cloud data originally distributed in the three-dimensional space is mapped onto a two-dimensional plane, reducing the data dimension, making the processing more intuitive and simple, reducing the computational complexity. Especially when performing geometric transformation, clustering analysis or model fitting, two-dimensional processing is usually more efficient than three-dimensional processing; in addition, after being projected onto the target plane, it can reflect the distribution of the original point cloud as accurately as possible, better highlighting important features such as the guiding line and reducing the interference of irrelevant background information.

[0064] In some embodiments, the embodiments of the present disclosure adopt efficient ground surface segmentation and projection statistical methods in the process of point cloud processing, and can complete the preliminary screening and rough fitting of the point cloud in a short time, which enables the algorithm to quickly respond in real-time applications and meet the actual requirements.

[0065] In some embodiments, as Figure 4 shown, the method for the embodiments of the present disclosure to determine the guiding line straight line by using two fittings specifically includes:

[0066] S402. Obtain the original scanned point cloud data.

[0067] S404. Perform ground segmentation on the original scanned point cloud data to divide the original scanned point cloud data into a ground point cloud set and a non - ground point cloud set.

[0068] S406. Filter the ground point cloud set based on a preset intensity threshold.

[0069] S408. Project the filtered ground point cloud set 2D onto a planar projection.

[0070] S410. In the planar projection within a preset range, perform a first fitting operation on the ground point cloud set to determine a first straight line for the initial positioning of the guiding line.

[0071] S412. Although the guiding line cannot completely coincide with the first straight line, the deviation is not large. Therefore, select a point cloud cluster whose distance from the first straight line is less than a specified preset threshold for a second fitting to obtain a second straight line.

[0072] S414. Adjust the first straight line according to the second straight line to generate a guiding line straight line.

[0073] It should be noted that the embodiments of the present disclosure can use the same method to determine the guiding line straight line. By changing the projection along the X - axis onto the plane YOZ, the stop line can be obtained.

[0074] In some embodiments, the method for fitting a straight line on the apron of an airport based on point cloud in the embodiments of the present disclosure realizes efficient and accurate detection and recognition of the guiding line through a phased processing method. This method only relies on lidar point cloud data, without the need for additional sensors, has low cost, and a simple system. Moreover, the algorithm adopted in the embodiments of the present disclosure has a simple and clear design, is easy to implement and maintain. Through the phased processing method, each step has a clear goal and operation, making the development and debugging process more efficient. At the same time, the modular design of the algorithm also facilitates subsequent optimization and expansion. Through the two - stage fitting method, the high precision and high reliability of the final result are ensured, providing strong support for the use and maintenance of the VDGS system.

[0075] Based on the same inventive concept, an apparatus for fitting a straight line on the apron of an airport based on point cloud is also provided in the embodiments of the present disclosure, as shown in the following embodiments. Since the principle of solving problems in this apparatus embodiment is similar to that of the above - mentioned method embodiment, the implementation of this apparatus embodiment can refer to the implementation of the above - mentioned method embodiment, and the repeated parts will not be elaborated.

[0076] Figure 5 The schematic diagram of an apparatus for fitting a straight line on the apron of an airport based on point cloud in the embodiments of the present disclosure is shown as Figure 5 As shown, the apparatus includes:

[0077] The point cloud data acquisition module 501 is configured to acquire the original scanned point cloud data, perform ground surface segmentation on the original scanned point cloud data, and divide it into a ground point cloud set and a non-ground point cloud set.

[0078] The first fitting module 502 is configured to calculate the position of the guiding line or the stop line based on the ground point cloud set, and perform the first-stage straight line fitting to form the first straight line.

[0079] The point cloud cluster determination module 503 is configured to select the point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud set to form a point cloud cluster.

[0080] The second fitting module 504 is configured to perform the second-stage straight line fitting based on the point cloud cluster to form the second straight line.

[0081] An apparatus for straight line fitting of an airport apron based on point cloud provided in an embodiment of the present disclosure acquires the original scanned point cloud data through the point cloud data acquisition module, performs ground surface segmentation on the original scanned point cloud data, and divides it into a ground point cloud set and a non-ground point cloud set; through the first fitting module, calculates the position of the guiding line or the stop line based on the ground point cloud set, and performs the first-stage straight line fitting to form the first straight line; through the point cloud cluster determination module, selects the point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud set to form a point cloud cluster; through the second fitting module, performs the second-stage straight line fitting based on the point cloud cluster to form the second straight line. Compared with the problem in the related art that the scattered point clouds extracted from the spraying reflection intensity difference of the apron guiding line by lidar are basically unable to effectively perform straight line fitting, the embodiment of the present disclosure performs the straight line fitting of the guiding line in two times. Among them, the first fitting can determine the position range of the guiding line or the stop line, and quickly eliminate a large number of point clouds with low relevance, reducing the amount of computation; and perform the second fitting on the selected ground point cloud data with a distance less than the preset threshold from the first straight line within the preliminarily determined position range of the guiding line or the stop line to obtain the second straight line, further improving the fitting accuracy. The phased method adopted in the embodiment of the present disclosure not only has a small amount of computation, but also has a very high adjustment accuracy, and realizes efficient and accurate guiding line detection and recognition without complex parameter adjustment.

[0082] In some embodiments, the point cloud data acquisition module in the embodiment of the present disclosure is further configured to perform ground surface segmentation based on a preset height threshold or a clustering algorithm; and / or, perform angle correction on the original scanned point cloud data according to the installation angle of a pre-installed detection device, so as to divide the original scanned point cloud data into a ground point cloud set and a non-ground point cloud set.

[0083] In some embodiments, the first fitting module in the embodiments of the present disclosure is further configured to filter the ground point cloud set based on a preset intensity threshold, and extract a first point cloud set including a guiding line or a stop line; calculate the position of the guiding line or the stop line according to the first point cloud set, and perform a first-stage straight line fitting to form a first straight line.

[0084] In some embodiments, the first fitting module in the embodiments of the present disclosure is further configured to obtain a plane projection of the first point cloud set within a preset range on a plane perpendicular to the guiding line or the stop line; traverse the point cloud data in the plane projection, determine a reference point in the plane projection, and perform fitting with a straight line passing through the reference point and parallel to the coordinate axis of the coordinate system parallel to the guiding line or the stop line to form a first straight line.

[0085] In some embodiments, the first fitting module in the embodiments of the present disclosure is further configured to determine the maximum and minimum values of the first point cloud set along two axial directions on a plane perpendicular to the guiding line or the stop line, and create a two-dimensional matrix according to the maximum and minimum values; determine a reference point in the plane projection based on the maximum and minimum values of the first point cloud set along two axial directions on a plane perpendicular to the guiding line or the stop line and the two-dimensional matrix.

[0086] In some embodiments, the first fitting module in the embodiments of the present disclosure is further configured that the size of the two-dimensional matrix is m×n, where m and n are the resolutions of the two axial directions of the plane perpendicular to the guiding line or the stop line respectively; traverse the two-dimensional matrix to find the element with the largest value and its corresponding coordinates, and convert them into the point cloud coordinate system to determine the reference point in the plane projection.

[0087] In some embodiments, the second fitting module in the embodiments of the present disclosure is further configured to perform a second-stage straight line fitting by using a random sample consensus algorithm or a least squares method.

[0088] Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, a method, or a program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation manner, a complete software implementation manner (including firmware, microcode, etc.), or an implementation manner combining hardware and software aspects, which can be collectively referred to as "circuit", "module", or "system" here.

[0089] Based on the same inventive concept, an electronic device is further provided in the embodiments of the present disclosure. The electronic device includes: a processor; and a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the method for straight line fitting of an airport apron based on point cloud as described in any one of the above via executing the executable instructions. Since the principle of solving problems in the embodiment of this electronic device is similar to that in the above method embodiment, the implementation of the embodiment of this electronic device can refer to the implementation of the above method embodiment, and the repeated parts will not be described again.

[0090] Reference will now be made to Figure 6 to describe the electronic device 600 according to this embodiment of the present disclosure. Figure 6 The electronic device 600 shown is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present disclosure.

[0091] As Figure 6 shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one of the above-mentioned processing units 601, at least one of the above-mentioned storage units 602, and a bus 603 connecting different system components (including the storage unit 602 and the processing unit 601).

[0092] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 601, so that the processing unit 601 executes the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0093] In some embodiments, when the electronic device is used to control, for example, the above-mentioned point cloud-based straight line fitting method for airport apron, the processing unit 601 may execute the following steps of the above method embodiments:

[0094] Obtain the original scanned point cloud data, perform ground segmentation on the original scanned point cloud data and divide it into a ground point cloud set and a non-ground point cloud set; calculate the position of the guiding line or the stop line according to the ground point cloud set, and perform the first-stage straight line fitting to form a first straight line; select the point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud set to form a point cloud cluster; perform the second-stage straight line fitting according to the point cloud cluster to form a second straight line.

[0095] The storage unit 602 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6021 and / or a cache storage unit 6022, and may further include a read-only storage unit (ROM) 6023.

[0096] The storage unit 602 may further include a program / utility 6024 having a set (at least one) of program modules 6025. Such program modules 6025 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0097] The bus 603 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0098] The electronic device 600 can also communicate with one or more external devices 604 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device (such as a router, a modem, etc.) that enables the electronic device 600 to communicate with one or more other computing devices. Such communication can be carried out through the input / output (I / O) interface 605. Moreover, the electronic device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 606. As shown in the figure, the network adapter 606 communicates with other modules of the electronic device 600 through the bus 603. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0099] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or can be implemented by the way of software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0100] Based on the same inventive concept, an embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method for straight line fitting of an airport apron based on point cloud as described in any one of the above. Since the principle of solving the problem in the embodiment of this computer-readable storage medium is similar to that in the above method embodiment, the implementation of the embodiment of this computer-readable storage medium can refer to the implementation of the above method embodiment, and the repeated parts will not be described again.

[0101] More specific examples of the computer-readable storage medium in the present disclosure can include but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0102] In the present disclosure, a computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than the readable storage medium, and the readable medium may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0103] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0104] In specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0105] Based on the same inventive concept, an embodiment of the present disclosure also provides a computer program product, including: a computer program or instruction, which when executed by a processor implements the method for straight line fitting of an airport apron based on point cloud in any one of the above method embodiments. Since the principle of solving problems in this embodiment of the computer program product is similar to that of the above method embodiments, the implementation of this embodiment of the computer program product may refer to the implementation of the above method embodiments, and the repeated parts will not be described again.

[0106] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of the two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided and embodied by multiple modules or units.

[0107] In addition, although the steps of the methods in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in that specific order, or that all of the steps shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0108] From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of the present disclosure.

[0109] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed herein. The specification and examples are only considered exemplary, and the true scope and spirit of the present disclosure are pointed out by the appended claims.

Claims

1. A method for fitting a straight line on the apron of an airport based on point cloud, characterized in that Including: Obtain the original scanned point cloud data, perform ground segmentation on the original scanned point cloud data, and divide it into a ground point cloud set and a non-ground point cloud set; Calculate the position of the guiding line or the stop line according to the ground point cloud set, and perform the first-stage straight line fitting to form the first straight line; Select the point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud set to form a point cloud cluster; Perform the second-stage straight line fitting according to the point cloud cluster to form the second straight line.

2. The method for straight line fitting of airport apron based on point cloud according to claim 1, wherein Performing ground segmentation on the original scanned point cloud data and dividing it into a ground point cloud set and a non-ground point cloud set includes: Performing ground segmentation based on a preset height threshold or a clustering algorithm; and / or, performing angle correction on the original scanned point cloud data according to the installation angle of a pre-installed detection device to divide the original scanned point cloud data into a ground point cloud set and a non-ground point cloud set.

3. The method for fitting a straight line on an airport apron based on point cloud according to claim 1, wherein Calculating the position of the guiding line or the stop line according to the ground point cloud set and performing the first-stage straight line fitting to form the first straight line includes: Filter the ground point cloud set based on a preset intensity threshold, and extract the first point cloud set containing the guiding line or the stop line; Calculate the position of the guiding line or the stop line according to the first point cloud set, and perform the first-stage straight line fitting to form the first straight line.

4. The method for straight line fitting of airport apron based on point cloud according to claim 3, characterized in that, Calculating the position of the guiding line or the stop line according to the first point cloud set and performing the first-stage straight line fitting to form the first straight line includes: Obtain the plane projection of the first point cloud set within a preset range on the plane perpendicular to the guiding line or the stop line; Traverse the point cloud data in the plane projection, determine the reference point in the plane projection, and perform fitting with a straight line passing through the reference point and parallel to the coordinate axis of the coordinate system parallel to the guiding line or the stop line to form the first straight line.

5. The method for straight line fitting of airport apron based on point cloud according to claim 4, characterized in that Traversing the point cloud data in the plane projection and determining the reference point in the plane projection includes: Determine the maximum and minimum values of the first point cloud set along two axes on the plane perpendicular to the guiding line or the stop line, and create a two-dimensional matrix according to the maximum and minimum values; Determine the reference point in the plane projection based on the maximum and minimum values of the first point cloud set along two axes on the plane perpendicular to the guiding line or the stop line and the two-dimensional matrix.

6. The method for straight line fitting of airport apron based on point cloud according to claim 5, characterized in that Determining the reference point in the plane projection based on the maximum and minimum values of the first point cloud set along two axes on the plane perpendicular to the guiding line or the stop line and the two-dimensional matrix includes: The size of the two-dimensional matrix is m×n, where m and n are the resolutions of the two axes of the plane perpendicular to the guiding line or the stop line respectively; Traverse the two-dimensional matrix to find the element with the largest value and its corresponding coordinates, and convert it into the point cloud coordinate system to determine the reference point in the plane projection.

7. The method for straight line fitting of airport apron based on point cloud according to claim 1, wherein, Performing the second-stage straight line fitting according to the point cloud cluster to form the second straight line includes: Adopt the random sample consensus algorithm or the least squares method for the second-stage straight line fitting.

8. An apparatus for straight line fitting of an airport apron based on point cloud, characterized in that, Including: A point cloud data acquisition module, configured to obtain the original scanned point cloud data, perform ground segmentation on the original scanned point cloud data, and divide it into a ground point cloud set and a non-ground point cloud set; The first straight line fitting module is used to calculate the position of the guiding line or the stop line according to the ground point cloud set, and perform the first-stage straight line fitting to form the first straight line; The point cloud cluster forming module is used to select the point cloud data with a distance less than a preset threshold from the first straight line in the ground point cloud set to form a point cloud cluster; The second straight line fitting module is used to perform the second-stage straight line fitting according to the point cloud cluster to form the second straight line.

9. An electronic device, characterized in that, Comprising: A processor; And A memory for storing the executable instructions of the processor; Wherein, the processor is configured to execute the point cloud-based airport apron straight line fitting method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the point cloud-based airport apron straight line fitting method according to any one of claims 1 to 7.

Images