A method, apparatus, device and computer program product for determining an elevation of a ground point

Abstract

The present disclosure relates to a ground point height determination method, device, equipment and computer program product. In at least one embodiment of the present disclosure, after obtaining a ground point in a point cloud, the height of the points in the local area where the ground point is located is used to screen out target points for fitting a ground plane, so as to filter out local noise points for the ground point, without the need for full-quantity noise point filtering, thereby improving the efficiency; further, the ground plane fitted by the target points is more accurate; and then, the height of the ground point is updated by using the height of the projection point of the ground point on the fitted ground plane, so that the height of the ground point is more accurate, and the accuracy of the high-precision map is improved.

Description

Technical Field

[0001] This disclosure relates to the field of map technology, specifically to a method, apparatus, device, and computer program product for determining the elevation of ground points. Background Technology

[0002] High-precision maps are the infrastructure for navigation in intelligent driving vehicles. Currently, high-precision maps are mainly obtained by extracting and editing map features from point clouds collected by mobile measurement systems (such as vehicles equipped with LiDAR devices).

[0003] However, considering the high cost of high-precision LiDAR equipment, most map providers choose to use low-cost LiDAR equipment for map data updates. The point cloud quality acquired by low-cost LiDAR is poor, which affects measurement accuracy. A significant issue is the presence of noisy point clouds, which impacts the elevation accuracy of ground features and consequently the accuracy of high-precision maps. Therefore, this disclosure provides a method for determining the elevation of ground points in the presence of noisy point clouds. Summary of the Invention

[0004] At least one embodiment of this disclosure provides a method, apparatus, device, medium, and computer program product for determining the elevation of ground points.

[0005] In a first aspect, embodiments of this disclosure propose a method for determining the elevation of ground points, the method comprising:

[0006] Obtain ground points from the point cloud;

[0007] Determine the elevation of multiple points within a local area where the ground point is located;

[0008] Based on the elevation of multiple points, multiple target points are determined from the multiple points to fit the ground plane, and the ground plane is fitted based on the multiple target points;

[0009] The elevation of a ground point is determined as the elevation of its projection onto the ground plane.

[0010] In some embodiments, determining multiple target points for fitting a ground plane from multiple points based on the elevation of multiple points includes:

[0011] Based on the elevation of multiple points, determine the elevation distribution pattern of multiple points;

[0012] Based on the elevation distribution pattern, determine the elevation threshold used to filter out noise points;

[0013] Noise points are filtered out from multiple points based on elevation thresholds to obtain multiple target points for fitting the ground plane.

[0014] In some embodiments, determining the elevation distribution pattern of multiple points based on their elevations includes:

[0015] Based on the elevation of multiple points and the preset number of elevation segments, the elevation segments in which the multiple points are located are determined, and the number of points included in each elevation segment is obtained.

[0016] Based on the number of points included in each elevation segment, an elevation distribution histogram of multiple points is determined.

[0017] In some embodiments, based on the elevations of multiple points and a preset number of elevation segments, the elevation segments in which the multiple points are located are determined, and the number of points included in each elevation segment is obtained, including:

[0018] Determine the maximum and minimum elevation values ​​based on the elevations of multiple points.

[0019] The elevation segment step size is determined based on the maximum elevation value, the minimum elevation value, and the preset number of elevation segments;

[0020] Based on the elevation, minimum elevation value, and elevation segment step size of multiple points, the elevation segment in which the multiple points are located is determined, and the number of points included in each elevation segment is obtained.

[0021] In some embodiments, the elevation threshold for filtering noise points includes: a first elevation threshold and a second elevation threshold; wherein the first elevation threshold is lower than the second elevation threshold;

[0022] After filtering out noise points from multiple points based on an elevation threshold, several target points are obtained for fitting the ground plane, including:

[0023] From multiple points, points with elevations lower than or equal to a first elevation threshold are filtered out, and points with elevations higher than or equal to a second elevation threshold are filtered out, resulting in multiple target points for fitting the ground plane.

[0024] In some embodiments, determining the elevation threshold for filtering noise points based on elevation distribution patterns includes:

[0025] Based on the preset first ratio and the elevation distribution pattern, a first elevation threshold is determined, wherein the first ratio is the ratio of the number of points with elevations lower than or equal to the first elevation threshold to the number of multiple points.

[0026] Based on the preset second ratio and the elevation distribution pattern, a second elevation threshold is determined, wherein the second ratio is the ratio of the number of points with elevations higher than or equal to the second elevation threshold to the number of multiple points.

[0027] In some embodiments, determining the elevation of a ground point as the elevation of its projection onto the ground plane includes:

[0028] Projecting ground points onto a ground plane yields the projected points;

[0029] Calculate the distance from the projection point along the vertical direction to the preset reference plane, and obtain the elevation of the projection point as the distance;

[0030] The elevation of the ground point is determined as the elevation of the projection point.

[0031] Secondly, embodiments of this disclosure also provide a ground point elevation determination device, the device comprising:

[0032] The acquisition unit is used to acquire ground points in the point cloud;

[0033] The first determining unit is used to determine the elevation of multiple points within a local area where the ground point is located;

[0034] A fitting unit is used to determine multiple target points from multiple points for fitting a ground plane based on the elevation of multiple points, and to fit a ground plane based on the multiple target points;

[0035] The second determining unit is used to determine the elevation of the ground point as the elevation of the projection point of the ground point on the ground plane.

[0036] Thirdly, embodiments of this disclosure also provide a computer device, comprising at least one computing device and at least one storage device for storing instructions; the instructions, when executed by the at least one computing device, cause the at least one computing device to perform the steps of the ground point elevation determination method as described in any embodiment of the first aspect.

[0037] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a program or instructions that cause a computer to perform the steps of the ground point elevation determination method as described in any embodiment of the first aspect.

[0038] Fifthly, embodiments of this disclosure also provide a computer program product, wherein the computer program product includes a computer program stored in a computer-readable storage medium, and at least one processor of the computer reads from the storage medium and executes the computer program, causing the computer to perform the steps of the ground point elevation determination method as described in any embodiment of the first aspect.

[0039] As can be seen, in at least one embodiment of this disclosure, after acquiring ground points in the point cloud, the elevation of points within the local area where the ground points are located is used to filter out target points for fitting the ground plane. This achieves the filtering out of local noise points for ground points without the need for full noise point filtering, thus improving efficiency. Furthermore, the ground plane fitted using the target points is more accurate. Consequently, the elevation of the ground point is updated using the elevation of the projection point of the ground point on the fitted ground plane, making the elevation of the ground point more accurate and improving the accuracy of the high-precision map. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings.

[0041] Figure 1 A flowchart illustrating a method for determining the elevation of ground points provided in an embodiment of this disclosure;

[0042] Figure 2 A flowchart of a method for filtering out local noise points provided in this disclosure embodiment;

[0043] Figure 3 A flowchart illustrating a method for determining an elevation distribution histogram provided in this disclosure embodiment;

[0044] Figure 4 A flowchart illustrating another method for determining ground point elevation provided in this embodiment of the disclosure;

[0045] Figure 5 A schematic diagram of a ground point elevation determination device provided in an embodiment of this disclosure;

[0046] Figure 6 An exemplary block diagram of a computer device provided in an embodiment of this disclosure. Detailed Implementation

[0047] To better understand the above-described objectives, features, and advantages of this disclosure, the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It is to be understood that the described embodiments are only some, not all, of the embodiments of this disclosure. The specific embodiments described herein are merely for explaining this disclosure and are not intended to limit it. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure are within the scope of protection of this disclosure.

[0048] It should be noted that in this article, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0049] In related technologies, high-precision maps are drawn or updated based on point clouds collected by radar equipment. Radar equipment, such as LiDAR (Light Detection and Ranging) devices, emits laser pulses that reflect off the ground surface and objects. Each laser pulse emitted by the LiDAR can be considered a point, and a large number of points together form a point cloud. The information for each point in the point cloud includes its planar position and elevation. The elevation is the distance from a point along a vertical direction to a preset reference surface. The preset reference surface can be any of the following: a geodetic datum, a quasi-geodetic datum, a reference ellipsoid, etc. It should be noted that the determination of the preset reference surface is a mature technology in the field of mapping and will not be elaborated further.

[0050] However, because the related technologies use low-cost LiDAR equipment, the quality of the collected point clouds is poor, affecting measurement accuracy. This results in a large amount of noisy point clouds in the ground point cloud, affecting the elevation accuracy of ground features and thus impacting the accuracy of high-precision maps. Ground features in high-precision maps include, but are not limited to: directional arrows, lane lines, stop lines, and ground text.

[0051] To improve the accuracy of high-precision maps, some related technologies use outlier filtering to filter noisy point clouds. However, this method is to denoise the entire point cloud, which is inefficient. In addition, this method uses a fixed elevation threshold for filtering, which may accidentally delete key points in sparse point cloud scenarios, thus reducing the accuracy of the high-precision map.

[0052] Therefore, at least one embodiment of this disclosure provides a method, apparatus, device, medium, or computer program product for determining the elevation of ground points. After acquiring ground points in a point cloud, the elevation of points within the local area where the ground points are located is used to filter out target points for fitting a ground plane. This achieves the filtering out of local noise points for ground points without the need for full noise point filtering, thus improving efficiency. Furthermore, the ground plane fitted using the target points is more accurate. Consequently, the elevation of the ground point is updated using the elevation of the projection point of the ground point on the fitted ground plane, making the elevation of the ground point more accurate and improving the precision of the high-precision map.

[0053] Figure 1This is a flowchart illustrating a method for determining ground point elevation according to an embodiment of this disclosure. The execution entity of this method is a point cloud processing device. The point cloud processing device can be an electronic device or a server. Electronic devices include, but are not limited to, smartphones, PDAs, tablets, wearable devices with displays, desktop computers, laptops, all-in-one computers, smart home devices, and in-vehicle devices. The server can be a standalone server or a cluster of multiple servers, and can include locally located servers and cloud-based servers.

[0054] like Figure 1 As shown, the processing method for this point may include, but is not limited to, steps 101 to 104:

[0055] In step 101, ground points in the point cloud are acquired.

[0056] In this disclosed example, a radar device emits a laser pulse at preset intervals and collects the corresponding point cloud; after obtaining the point cloud collected by the radar device, the ground points in the collected point cloud can be determined.

[0057] The method for determining ground points is a mature technology in the field of point cloud processing. This embodiment does not limit the specific method. For example, it can combine images acquired by image acquisition devices to perform semantic segmentation on point clouds acquired by radar devices to obtain ground point clouds belonging to the ground.

[0058] In some embodiments, the image acquired by the image acquisition device is semantically segmented to obtain the ground region and non-ground region in the image; then, the point cloud is projected onto the image to obtain the point cloud projection position; thus, the point cloud acquired by the radar device is semantically segmented based on the point cloud projection position, that is, the point cloud whose projection position is within the ground region is determined as the ground point cloud.

[0059] In step 102, the elevations of multiple points within the local area where the ground point is located are determined.

[0060] In this disclosed example, after acquiring ground points in the point cloud, the planar position and elevation of the ground points can be determined. It should be noted that after the radar device collects the point cloud, it can output the point cloud information to the execution subject (i.e., the point cloud processing device) of this embodiment, including but not limited to: the planar position and elevation of each point in the point cloud; then, based on the planar position of the ground points, the point cloud in the local area where the ground points are located can be determined; thus, the elevation of the points in the local area where the ground points are located can be determined, and the elevation of multiple points around the ground points can be obtained.

[0061] In some embodiments, the local area where the ground point is located is defined by a preset range (the radius of the preset range is R), thereby obtaining multiple points within the preset range around the ground point.

[0062] For example, let the ground point be denoted as G. Search for the set S of nearest neighbors centered at G with a radius R. Specifically, search for points whose planar distance from G is less than or equal to R, satisfying Formula 1:

[0063] Formula 1

[0064] Where X and Y are the planar coordinates of neighboring points, X G Y G Let G be the plane coordinates of the ground point G.

[0065] In step 103, multiple target points for fitting the ground plane are determined from the multiple points based on the elevation of the multiple points, and the ground plane is fitted based on the multiple target points.

[0066] In this embodiment of the disclosure, the elevation of points within the local area where the ground point is located is used to screen target points for fitting the ground plane, thereby filtering out local noise points for the ground point without having to filter out all noise points, thus improving efficiency.

[0067] In some embodiments, a plane fitting algorithm is used to fit the ground plane based on multiple target points. Various plane fitting algorithms exist; this embodiment employs the RANSAC (Random Sample Consensus) algorithm. Specifically, a target point is randomly selected from the multiple target points to calculate its corresponding plane equation, and the relationship between other target points and this plane is calculated. This process is repeated to obtain multiple relationships. Then, the plane equation corresponding to the optimal relationship is selected as the plane equation of the ground plane. Based on the plane equation of the ground plane, multiple target points are fitted to the ground plane. The advantage of the RANSAC algorithm is its robustness to noise interference; that is, even with noise interference, the plane equation resulting from noise interference will not be selected as the optimal plane equation when choosing the optimal relationship. The selected optimal plane equation is independent of the noise points.

[0068] In step 104, the elevation of the ground point is determined as the elevation of the projection point of the ground point on the ground plane.

[0069] In this embodiment of the disclosure, after fitting the ground plane, the ground points are projected onto the ground plane to obtain the projection points; then, the elevation of the projection points can be determined. Specifically, the distance from the projection point along the vertical direction to the preset reference plane is calculated to obtain the elevation of the projection point as the distance; thus, the elevation of the ground points is determined as the elevation of the projection points, thereby updating the elevation of the ground points.

[0070] As can be seen, in this embodiment of the present disclosure, the ground plane obtained by fitting the target point after filtering out local noise points is more accurate; thus, the elevation of the ground point is updated by using the elevation of the projection point of the ground point on the fitted ground plane, making the elevation of the ground point more accurate and improving the accuracy of the high-precision map.

[0071] Based on the above embodiments, step 103, "determining multiple target points for fitting the ground plane from multiple points based on the elevation of multiple points," may include, but is not limited to, the following: Figure 2 The steps 201 to 203 shown below achieve the purpose of filtering out local noise points for ground points:

[0072] In step 201, the elevation distribution pattern of multiple points is determined based on their elevations.

[0073] Since the elevations of different points vary, the elevation distribution pattern of multiple points can be statistically obtained based on their elevations. This elevation distribution pattern can be displayed in different forms; in some embodiments, it can be presented as an elevation distribution histogram.

[0074] In step 202, an elevation threshold for filtering out noise points is determined based on the elevation distribution pattern.

[0075] In this embodiment, the elevation threshold is determined based on the statistical elevation distribution pattern. Compared with the fixed elevation threshold used in related technologies, this embodiment is more robust and will not accidentally delete key points in sparse point scenarios, thus not reducing the accuracy of the high-precision map.

[0076] In step 203, noise points among multiple points are filtered out based on an elevation threshold to obtain multiple target points for fitting the ground plane.

[0077] In this embodiment of the disclosure, since the multiple target points are obtained after filtering out noise points, the ground plane fitted based on the multiple target points is more accurate; therefore, the elevation of the ground point is updated by using the elevation of the projection point of the ground point on the fitted ground plane, making the elevation of the ground point more accurate and improving the accuracy of the high-precision map.

[0078] In some embodiments, based on the elevation distribution pattern, the determined elevation thresholds for filtering noise points include: a first elevation threshold and a second elevation threshold; wherein the first elevation threshold is lower than the second elevation threshold. Then, from multiple points, points with elevations lower than or equal to the first elevation threshold are filtered out, and points with elevations higher than or equal to the second elevation threshold are filtered out, resulting in multiple target points for fitting the ground plane.

[0079] As can be seen, in this embodiment, based on the elevation distribution pattern, two elevation thresholds can be determined. These two elevation thresholds constitute an elevation interval, thereby filtering out points whose elevations are outside the elevation interval and retaining points whose elevations are within the elevation interval as target points. This filtering method no longer filters points according to fixed elevation thresholds. Therefore, this embodiment is more robust and will not accidentally delete key points in sparse point scenarios, thus not reducing the accuracy of the high-precision map.

[0080] In other embodiments, the ratio of the number of points with elevations lower than or equal to a first elevation threshold to the total number of points is a preset first ratio; the ratio of the number of points with elevations higher than or equal to a second elevation threshold to the total number of points is a preset second ratio. For example, if the first ratio is 1% and the second ratio is 1%, then in this embodiment, based on the elevation distribution pattern, a certain proportion (e.g., 1%) of high points and a certain proportion (e.g., 1%) of low points can be filtered out to obtain multiple target points for fitting the ground plane.

[0081] Based on the above embodiments, a first elevation threshold can be determined based on a preset first ratio and elevation distribution pattern; and a second elevation threshold can be determined based on a preset second ratio and elevation distribution pattern. The first ratio is the ratio of the number of points with elevations lower than or equal to the first elevation threshold to the total number of points; the second ratio is the ratio of the number of points with elevations higher than or equal to the second elevation threshold to the total number of points. For example, if there are 100 points, and both the first and second ratios are 1%, then the number of points with elevations lower than or equal to the first elevation threshold is 10, and the number of points with elevations higher than or equal to the second elevation threshold is 10. Therefore, based on the elevation distribution pattern, the elevations corresponding to the first and second elevation thresholds can be determined such that the number of points with elevations lower than or equal to the first elevation threshold is 10, and the number of points with elevations higher than or equal to the second elevation threshold is 10.

[0082] Based on the above embodiments, step 201, which involves determining the elevation distribution pattern of multiple points based on their elevations, may include, but is not limited to, the following: Figure 3 The following steps 301 and 302 are shown:

[0083] In step 301, based on the elevation of multiple points and the preset number of elevation segments, the elevation segments in which the multiple points are located are determined, and the number of points included in each elevation segment is obtained.

[0084] In this embodiment of the disclosure, based on the elevation of multiple points, the maximum elevation value and the minimum elevation value can be determined; then, based on the maximum elevation value, the minimum elevation value and the preset number of elevation segments, the elevation segment step size is determined; thus, based on the elevation of multiple points, the minimum elevation value and the elevation segment step size, the elevation segment in which the multiple points are located is determined, and the number of points included in each elevation segment is obtained.

[0085] For example, among multiple points, the maximum elevation is H2, the minimum elevation is H1, the preset number of elevation segments is 512, and the elevation segment step size Step satisfies Formula 2:

[0086] Formula 2

[0087] For any point M among the plurality of points, the elevation segment I at which point M is located satisfies Formula 3:

[0088] Formula 3

[0089] Among them, Z M Let M be the elevation.

[0090] In step 302, an elevation distribution histogram of multiple points is determined based on the number of points included in each elevation segment.

[0091] In some embodiments, after determining the elevation distribution histogram, a first elevation threshold and a second elevation threshold are determined based on the elevation distribution histogram, a preset first ratio, and a preset second ratio. For example, with 100 points, and both the first and second ratios being 1%, the number of points with elevations lower than or equal to the first elevation threshold is 10, and the number of points with elevations higher than or equal to the second elevation threshold is 10. Therefore, based on the elevation distribution histogram, the elevations corresponding to the first and second elevation thresholds can be determined, ensuring that the number of points with elevations lower than or equal to the first and second elevation thresholds is 10. Furthermore, from the 100 points, points with elevations lower than or equal to the first elevation threshold and points with elevations higher than or equal to the second elevation threshold are filtered out, resulting in multiple target points for fitting the ground plane.

[0092] Based on the above embodiments, Figure 4 This is a flowchart illustrating another method for determining ground point elevation provided in an embodiment of this disclosure, as shown below. Figure 4 As shown, the method for determining the elevation of ground points specifically includes the following steps 401 to 406:

[0093] 401. Obtain ground point G in the point cloud.

[0094] In this disclosed example, a radar device emits a laser pulse at preset intervals and collects the corresponding point cloud; after obtaining the point cloud collected by the radar device, the ground point G in the collected point cloud can be determined.

[0095] 402. Search for the set of nearest neighbors S with radius R centered at point G.

[0096] In this disclosed example, the radius R is the radius of a preset range. By searching with G as the center and radius R, the points within the local area where the ground point G is located can be determined, and the searched points constitute the point set S.

[0097] Specifically, with G as the center, search for points whose planar distance to G is less than or equal to R, satisfying Formula 1:

[0098] Formula 1

[0099] Where X and Y are the planar coordinates of neighboring points, X G Y G Let G be the plane coordinates of the ground point G.

[0100] 403. Statistical histogram of elevation distribution of neighboring point set S.

[0101] In this public example, the system iterates through S, determining the maximum elevation value as H2 and the minimum elevation value as H1. The preset number of elevation segments is 512, and the elevation segment step size Step satisfies Formula 2:

[0102] Formula 2

[0103] For any point M in S, the elevation segment I at point M satisfies Formula 3:

[0104] Formula 3

[0105] Among them, Z M Let M be the elevation.

[0106] Based on the number of points included in each elevation segment, determine the elevation distribution histogram of S.

[0107] 404. Using the elevation distribution histogram of S, a certain proportion of noise points in S are filtered out to obtain the point set S1.

[0108] In this embodiment of the disclosure, after determining the elevation distribution histogram of S, a first elevation threshold and a second elevation threshold are determined based on the elevation distribution histogram of S, a preset first ratio, and a preset second ratio; then, points in S with elevations lower than or equal to the first elevation threshold are filtered out, and points in S with elevations higher than or equal to the second elevation threshold are filtered out, resulting in multiple target points for fitting the ground plane, forming a point set S1.

[0109] For example, if S contains 100 points, with both the first and second proportions being 1%, then the number of points with elevations lower than or equal to the first elevation threshold is 10, and the number of points with elevations higher than or equal to the second elevation threshold is 10. Therefore, based on the elevation distribution histogram, the elevations corresponding to the first and second elevation thresholds can be determined, ensuring that the number of points with elevations lower than or equal to the first and second elevation thresholds is 10. Furthermore, from these 100 points, points with elevations lower than or equal to the first and second elevation thresholds are filtered out, resulting in multiple target points used to fit the ground plane, forming a point set S1 containing 80 points.

[0110] 405. Fit the ground plane P using the point set S1.

[0111] In this embodiment, a plane fitting algorithm is used to fit the ground plane P based on the point set S1. Various plane fitting algorithms exist; this embodiment employs the RANSAC algorithm. Specifically, a point is randomly selected from the point set S1 to calculate its corresponding plane equation, and the relationship between other points in S1 and the plane is calculated. This process is repeated to obtain multiple relationships. Then, the plane equation corresponding to the optimal relationship is selected as the plane equation of the ground plane. Based on the plane equation of the ground plane, multiple points in S1 are fitted to the ground plane P. The advantage of the RANSAC algorithm is its resistance to noise interference. That is, even with noise interference, the plane equation caused by noise interference will not be selected as the optimal plane equation when choosing the optimal relationship; the selected optimal plane equation is independent of the noise points.

[0112] 406. Project the ground point G onto the ground plane P to obtain the projection point G1, and update the elevation of G using the elevation of G1.

[0113] In this embodiment of the disclosure, after fitting the ground plane P, the ground point G is projected onto the ground plane P to obtain the projection point G1; then, the elevation of the projection point G1 can be determined; thus, the elevation of the projection point G1 is used as the elevation of the ground point G to update the elevation of the ground point G.

[0114] As can be seen, in this embodiment, after obtaining the ground point G in the point cloud, the elevation distribution histogram of the point set S in the local area where the ground point G is located is used to filter out a certain proportion of noise points in S, resulting in a point set S1 for fitting the ground plane P. This achieves the filtering out of local noise points for the ground point G without the need for full noise point filtering, thus improving efficiency. Furthermore, the ground plane P fitted using the point set S1 is more accurate. Therefore, the elevation of the ground point G is updated using the elevation of the projection point G1 of the ground point G on the fitted ground plane P, making the elevation of the ground point G more accurate and improving the accuracy of the high-precision map.

[0115] Figure 5 This diagram illustrates a ground point elevation determination device provided in an embodiment of this disclosure. The device can be a point cloud processing device as described in the above embodiments, or it can be a component or assembly of a point cloud processing device as described above. The ground point elevation determination device provided in this embodiment can execute the processing flow provided in the ground point elevation determination method embodiments, such as... Figure 5 As shown, the ground point elevation determination device includes: an acquisition unit 51, a first determination unit 52, a fitting unit 53, and a second determination unit 54.

[0116] Acquisition unit 51 is used to acquire ground points in the point cloud;

[0117] The first determining unit 52 is used to determine the elevation of multiple points within the local area where the ground point is located;

[0118] Fitting unit 53 is used to determine multiple target points for fitting the ground plane from multiple points based on the elevation of multiple points, and to fit the ground plane based on the multiple target points;

[0119] The second determining unit 54 is used to determine the elevation of the ground point as the elevation of the projection point of the ground point on the ground plane.

[0120] In some embodiments, the fitting unit 53 determines multiple target points for fitting a ground plane from multiple points based on the elevation of multiple points, including:

[0121] Based on the elevation of multiple points, determine the elevation distribution pattern of multiple points;

[0122] Based on the elevation distribution pattern, determine the elevation threshold used to filter out noise points;

[0123] Noise points are filtered out from multiple points based on elevation thresholds to obtain multiple target points for fitting the ground plane.

[0124] In some embodiments, the fitting unit 53 determines the elevation distribution pattern of multiple points based on their elevations, including:

[0125] Based on the elevation of multiple points and the preset number of elevation segments, the elevation segments in which the multiple points are located are determined, and the number of points included in each elevation segment is obtained.

[0126] Based on the number of points included in each elevation segment, an elevation distribution histogram of multiple points is determined.

[0127] In some embodiments, the fitting unit 53 determines the elevation segment in which the multiple points are located based on the elevation of multiple points and a preset number of elevation segments, and obtains the number of points included in each elevation segment, including:

[0128] Determine the maximum and minimum elevation values ​​based on the elevations of multiple points.

[0129] The elevation segment step size is determined based on the maximum elevation value, the minimum elevation value, and the preset number of elevation segments;

[0130] Based on the elevation, minimum elevation value, and elevation segment step size of multiple points, the elevation segment in which the multiple points are located is determined, and the number of points included in each elevation segment is obtained.

[0131] In some embodiments, the elevation threshold for filtering noise points includes: a first elevation threshold and a second elevation threshold; wherein the first elevation threshold is lower than the second elevation threshold;

[0132] Fitting unit 53 filters out noise points from multiple points based on an elevation threshold, obtaining multiple target points for fitting the ground plane, including:

[0133] From multiple points, points with elevations lower than or equal to a first elevation threshold are filtered out, and points with elevations higher than or equal to a second elevation threshold are filtered out, resulting in multiple target points for fitting the ground plane.

[0134] In some embodiments, the fitting unit 53 determines an elevation threshold for filtering noise points based on the elevation distribution pattern, including: determining a first elevation threshold based on a preset first ratio and the elevation distribution pattern, wherein the first ratio is the ratio of the number of points with elevations lower than or equal to the first elevation threshold to the number of multiple points; and determining a second elevation threshold based on a preset second ratio and the elevation distribution pattern, wherein the second ratio is the ratio of the number of points with elevations higher than or equal to the second elevation threshold to the number of multiple points.

[0135] In some embodiments, the second determining unit 54 is configured to: project a ground point onto a ground plane to obtain a projection point; calculate the distance from the projection point along the vertical direction to a preset reference plane to obtain the elevation of the projection point as the distance; and determine the elevation of the ground point as the elevation of the projection point.

[0136] For details of the various embodiments of the ground point elevation determination device disclosed above, please refer to the details of the various embodiments of the ground point elevation determination method described above. To avoid repetition, they will not be repeated.

[0137] Figure 6 This is an exemplary block diagram of a computer device provided in an embodiment of this disclosure. Figure 6 As shown, the computer device includes: at least one computing device 61 and at least one storage device 62 for storing instructions. It is understood that the storage device 62 in this embodiment may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0138] In some implementations, storage device 62 stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating systems and applications.

[0139] The operating system includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic tasks and handle hardware-based tasks. The application programs include various applications, such as media players and browsers, used to implement various application tasks. The program implementing the ground point elevation determination method provided in this disclosure can be included in the application programs.

[0140] In this embodiment of the disclosure, at least one computing device 61 executes the steps of the various embodiments of the ground point elevation determination method provided in this disclosure by calling a program or instruction stored in at least one storage device 62, specifically, a program or instruction stored in an application program.

[0141] The ground point elevation determination method provided in this disclosure can be applied to or implemented by a computing device 61. The computing device 61 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the hardware or by instructions in software within the computing device 61. The computing device 61 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor.

[0142] The steps of the ground point elevation determination method provided in this disclosure can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in storage device 62, and computing device 61 reads the information in storage device 62 and combines it with its hardware to complete the steps of the method.

[0143] This disclosure also proposes a computer-readable storage medium that stores a program or instructions that cause a computer to perform the steps of the various embodiments of the ground point elevation determination method, which will not be repeated here to avoid repetition. The computer-readable storage medium can be a non-transitory computer-readable storage medium.

[0144] This disclosure also proposes a computer program product, wherein the computer program product includes a computer program stored in a non-transitory computer-readable storage medium, and at least one processor of the computer reads from the storage medium and executes the computer program, causing the computer to perform the steps of the various embodiments of the ground point elevation determination method, which will not be repeated here to avoid repetition.

[0145] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0146] Those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of this disclosure and form different embodiments.

[0147] Those skilled in the art will understand that the descriptions of the various embodiments have different focuses, and for parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0148] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for determining the elevation of a ground point, the method comprising: Obtain ground points from the point cloud; Determine the elevation of multiple points within the local area where the ground point is located; Based on the elevation of the multiple points, local noise points are filtered out, multiple target points for fitting the ground plane are determined from the multiple points, and the ground plane is fitted based on the multiple target points; The elevation of the ground point is determined as the elevation of the projection point of the ground point on the ground plane.

2. The method according to claim 1, wherein, Based on the elevation of the plurality of points, local noise points are filtered out, and multiple target points for fitting the ground plane are determined from the plurality of points, including: Based on the elevations of the multiple points, determine the elevation distribution pattern of the multiple points; Based on the elevation distribution pattern, determine the elevation threshold used to filter out noise points; Based on the elevation threshold, noise points are filtered out from the plurality of points to obtain a plurality of target points for fitting the ground plane.

3. The method according to claim 2, wherein, Determining the elevation distribution pattern of the multiple points based on their elevations includes: Based on the elevation of the multiple points and the preset number of elevation segments, the elevation segment in which the multiple points are located is determined, and the number of points included in each elevation segment is obtained. Based on the number of points included in each elevation segment, an elevation distribution histogram of the multiple points is determined.

4. The method according to claim 3, wherein, The elevation segment in which the multiple points are located is determined based on the elevation of the multiple points and the preset number of elevation segments, resulting in the number of points included in each elevation segment, including: Based on the elevations of the multiple points, determine the maximum and minimum elevation values; The elevation segment step size is determined based on the maximum elevation value, the minimum elevation value, and the preset number of elevation segments; Based on the elevation of the multiple points, the lowest elevation value, and the elevation segment step size, the elevation segment in which the multiple points are located is determined, and the number of points included in each elevation segment is obtained.

5. The method according to claim 2, wherein, The elevation threshold for filtering noise points includes: a first elevation threshold and a second elevation threshold; wherein the first elevation threshold is lower than the second elevation threshold; The step of filtering out noise points from the plurality of points based on the elevation threshold to obtain a plurality of target points for fitting the ground plane includes: From the plurality of points, points with elevations lower than or equal to the first elevation threshold are filtered out, and points with elevations higher than or equal to the second elevation threshold are filtered out, to obtain a plurality of target points for fitting the ground plane.

6. The method according to claim 5, wherein, The step of determining the elevation threshold for filtering noise points based on the elevation distribution pattern includes: Based on a preset first ratio and the elevation distribution pattern, a first elevation threshold is determined, wherein the first ratio is the ratio of the number of points with elevations lower than or equal to the first elevation threshold to the number of the plurality of points; Based on a preset second ratio and the elevation distribution pattern, a second elevation threshold is determined, wherein the second ratio is the ratio of the number of points with elevations higher than or equal to the second elevation threshold to the total number of points.

7. The method according to any one of claims 1-6, wherein, Determining the elevation of the ground point as the elevation of its projection point on the ground plane includes: Projecting the ground points onto the ground plane yields the projected points; Calculate the distance from the projection point along the vertical direction to the preset reference plane, and obtain the elevation of the projection point as the distance; The elevation of the ground point is determined as the elevation of the projection point.

8. A ground point elevation determination device, the device comprising: The acquisition unit is used to acquire ground points in the point cloud; The first determining unit is used to determine the elevation of multiple points within the local area where the ground point is located; A fitting unit is used to filter out local noise points based on the elevation of the plurality of points, determine a plurality of target points from the plurality of points for fitting the ground plane, and fit the ground plane based on the plurality of target points; The second determining unit is used to determine the elevation of the ground point as the elevation of the projection point of the ground point on the ground plane.

9. A computer device, wherein, The device includes at least one computing device and at least one storage device for storing instructions; when the instructions are executed by the at least one computing device, they cause the at least one computing device to perform the steps of the ground point elevation determination method as described in any one of claims 1 to 7.

10. A computer program product, wherein, The computer program product includes a computer program stored in a computer-readable storage medium, wherein at least one processor of the computer reads from the storage medium and executes the computer program, causing the computer to perform the steps of the ground point elevation determination method as described in any one of claims 1 to 7.

Images