Point cloud processing method, device, computer equipment and readable storage medium

Abstract

The present application relates to a point cloud processing method, apparatus, computer device, and readable storage medium. The method comprises: dividing the environmental point cloud of a target area to obtain at least two point cloud partitions; performing ground segmentation processing on the environmental point cloud within each point cloud partition to obtain an initial ground point cloud and an initial non-ground point cloud for each point cloud partition; determining the adjacent partition corresponding to each point cloud partition from each point cloud partition based on the initial non-ground point cloud and initial ground point cloud of each point cloud partition; determining the target ground point cloud from the initial non-ground point cloud of each point cloud partition based on the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition; and determining the ground information of the target area based on the target ground point cloud and the initial ground point cloud of each point cloud partition. The present method can improve the accuracy of ground information.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a point cloud processing method, apparatus, computer equipment, and readable storage medium. Background Art

[0002] With the continuous development of autonomous driving technology, in order to ensure the safety of vehicle driving, it is necessary to perform ground segmentation processing on unstructured roads such as those without clear signs, uneven road surfaces or complex terrain during vehicle driving, so as to determine the ground information required by the vehicle.

[0003] In related technologies, after using lidar to acquire point cloud data around the vehicle, the point clouds in the point cloud data that are below a height threshold can be used as the initial ground point cloud, and the ground point cloud can be fitted to obtain a fitting plane; then, based on the residual between the point cloud data and the fitting plane, the target ground point cloud is determined from the point cloud data, thereby constructing the ground information required by the vehicle.

[0004] However, the above method is only applicable to point cloud data corresponding to relatively gentle slopes or slight ground undulations. When faced with complex terrain, the fitting results obtained by the above method are poor, which reduces the accuracy of ground information acquisition. Summary of the Invention

[0005] Based on this, it is necessary to provide a point cloud processing method, device, computer equipment and readable storage medium that can improve the accuracy of ground information in response to the above technical problems.

[0006] In a first aspect, the present application provides a point cloud processing method, comprising:

[0007] Divide the environmental point cloud of the target area to obtain at least two point cloud partitions;

[0008] Perform ground segmentation processing on the environmental point cloud in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition;

[0009] Determine, from each point cloud partition, an adjacent partition corresponding to each point cloud partition according to the initial non-ground point cloud and the initial ground point cloud of each point cloud partition;

[0010] Determine the target ground point cloud from the initial non-ground point cloud of each point cloud partition according to the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition;

[0011] The ground information of the target area is determined based on the target ground point cloud and the initial ground point cloud of each point cloud partition.

[0012] In one embodiment, determining an adjacent partition corresponding to each point cloud partition from each point cloud partition based on the initial non-ground point cloud and the initial ground point cloud of each point cloud partition includes:

[0013] For each point cloud partition, determine the point cloud centroid of the point cloud partition according to the initial non-ground point cloud of the point cloud partition;

[0014] Selecting adjacent ground point clouds from the initial ground point clouds of the remaining point cloud partitions according to the distance between the initial ground point clouds and the point cloud centroids of the remaining point cloud partitions; wherein the remaining point cloud partitions are point cloud partitions other than the point cloud partition in each point cloud partition;

[0015] The point cloud partition to which the adjacent ground point cloud belongs is used as the adjacent partition corresponding to the point cloud partition.

[0016] In one embodiment, determining a target ground point cloud from the initial non-ground point cloud of each point cloud partition based on a distance between the initial non-ground point cloud of each point cloud partition and an initial ground point cloud in a corresponding adjacent partition includes:

[0017] For each point cloud partition, select a reference ground point cloud whose distance to the point cloud centroid of the point cloud partition is less than a first distance threshold from the initial ground point cloud of the adjacent partition corresponding to the point cloud partition;

[0018] Perform plane fitting processing on the reference ground point cloud to obtain a reference fitting plane;

[0019] According to the distance between the initial non-ground point cloud of the point cloud partition and the reference fitting plane, the initial non-ground point cloud in the point cloud partition whose distance to the reference fitting plane is less than a second distance threshold is used as the target ground point cloud.

[0020] In one embodiment, ground segmentation processing is performed on the environment point cloud in each point cloud partition to obtain an initial ground point cloud and an initial non-ground point cloud in each point cloud partition, including:

[0021] For each point cloud partition, plane fitting processing is performed on the environment point cloud within the point cloud partition to obtain the target fitting plane corresponding to the point cloud partition and the plane attribute information of the target fitting plane;

[0022] The environment point cloud located on the target fitting plane is regarded as the original ground point cloud, and the point cloud other than the original ground point cloud in the environment point cloud within the point cloud partition is regarded as the original non-ground point cloud;

[0023] According to the plane attribute information of the target fitting plane, the original ground point cloud and the original non-ground point cloud in the point cloud partition are optimized to obtain the initial ground point cloud and the initial non-ground point cloud of the point cloud partition.

[0024] In one embodiment, the environmental point cloud of the target area is divided to obtain at least two point cloud partitions, including:

[0025] Divide the environmental point cloud of the target area based on a preset distance interval, a preset angle interval, and a preset number of circles to obtain at least two point cloud partitions;

[0026] According to the plane attribute information of the target fitting plane, the original ground point cloud and the original non-ground point cloud in the point cloud partition are optimized to obtain the initial ground point cloud and the initial non-ground point cloud of the point cloud partition, including:

[0027] When the plane attribute information of the target fitting plane does not meet the standard plane information, the flatness probability of the point cloud partition is determined according to the plane attribute information of the target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs; wherein the plane attribute information includes at least flatness;

[0028] When the flatness probability is less than or equal to the probability threshold, both the original ground point cloud and the original non-ground point cloud in the point cloud partition are used as the initial non-ground point cloud;

[0029] When the flatness probability is greater than a probability threshold, the original ground point cloud in the point cloud partition is used as the initial ground point cloud, and the original non-ground point cloud is used as the initial non-ground point cloud.

[0030] In one embodiment, determining the flatness probability of a point cloud partition according to the plane attribute information of the target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs includes:

[0031] According to the flatness of the target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs, the average flatness and the flatness standard deviation of the target circle layer are determined;

[0032] Determine the flatness threshold of the target circle based on the average flatness and flatness standard deviation of the target circle;

[0033] The flatness probability of the point cloud partition is determined according to the flatness threshold and the flatness of the target fitting plane corresponding to the point cloud partition.

[0034] In one embodiment, plane fitting processing is performed on the environment point cloud within the point cloud partition to obtain the target fitting plane corresponding to the point cloud partition and the plane attribute information of the target fitting plane, including:

[0035] According to the height value of each environmental point cloud in the point cloud partition, the environmental point clouds are sorted in order from low to high, and the target number of environmental point clouds in the front are used as the initial fitting point clouds;

[0036] Perform plane fitting processing on the initial fitting point cloud to obtain the initial fitting plane;

[0037] The initial fitting plane is optimized according to the environment point cloud within the point cloud partition whose distance from the initial fitting plane is less than a third distance threshold to obtain the target fitting plane corresponding to the point cloud partition and the plane attribute information of the target fitting plane.

[0038] In a second aspect, the present application further provides a point cloud processing device, comprising:

[0039] A point cloud partitioning module is used to partition the environmental point cloud of the target area to obtain at least two point cloud partitions;

[0040] The ground segmentation module is used to perform ground segmentation processing on the environmental point cloud in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition;

[0041] A partition determination module is used to determine the adjacent partition corresponding to each point cloud partition from each point cloud partition based on the initial non-ground point cloud and the initial ground point cloud of each point cloud partition;

[0042] a point cloud determination module, configured to determine a target ground point cloud from the initial non-ground point cloud of each point cloud partition according to a distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition;

[0043] The information determination module is used to determine the ground information of the target area based on the target ground point cloud and the initial ground point cloud of each point cloud partition.

[0044] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0045] Divide the environmental point cloud of the target area to obtain at least two point cloud partitions;

[0046] Perform ground segmentation processing on the environmental point cloud in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition;

[0047] Determine, from each point cloud partition, an adjacent partition corresponding to each point cloud partition according to the initial non-ground point cloud and the initial ground point cloud of each point cloud partition;

[0048] Determine the target ground point cloud from the initial non-ground point cloud of each point cloud partition according to the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition;

[0049] The ground information of the target area is determined based on the target ground point cloud and the initial ground point cloud of each point cloud partition.

[0050] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0051] Divide the environmental point cloud of the target area to obtain at least two point cloud partitions;

[0052] Perform ground segmentation processing on the environmental point cloud in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition;

[0053] Determine, from each point cloud partition, an adjacent partition corresponding to each point cloud partition according to the initial non-ground point cloud and the initial ground point cloud of each point cloud partition;

[0054] Determine the target ground point cloud from the initial non-ground point cloud of each point cloud partition according to the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition;

[0055] The ground information of the target area is determined based on the target ground point cloud and the initial ground point cloud of each point cloud partition.

[0056] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0057] Divide the environmental point cloud of the target area to obtain at least two point cloud partitions;

[0058] Perform ground segmentation processing on the environmental point cloud in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition;

[0059] Determine, from each point cloud partition, an adjacent partition corresponding to each point cloud partition according to the initial non-ground point cloud and the initial ground point cloud of each point cloud partition;

[0060] Determine the target ground point cloud from the initial non-ground point cloud of each point cloud partition according to the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition;

[0061] The ground information of the target area is determined based on the target ground point cloud and the initial ground point cloud of each point cloud partition.

[0062] The above-mentioned point cloud processing method, device, computer equipment and readable storage medium divide the environmental point cloud of the target area into at least two point cloud partitions, and perform ground segmentation processing on the environmental point cloud in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition; then, based on the initial non-ground point cloud and initial ground point cloud of each point cloud partition, the adjacent partition corresponding to each point cloud partition is determined from each point cloud partition, and based on the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition, the target ground point cloud is determined from the initial non-ground point cloud of each point cloud partition; finally, the ground information of the target area is determined based on the target ground point cloud and the initial ground point cloud of each point cloud partition. Using the above method, after the initial ground point cloud and the initial non-ground point cloud are preliminarily segmented, the target ground point cloud is again screened out from the initial non-ground point cloud of the point cloud partition based on the initial ground point cloud in the corresponding adjacent partition, and then ground information is generated based on the initial ground point cloud and the target ground point cloud. This can avoid the problem of dividing the ground point cloud into non-ground point cloud in complex terrain, improve the accuracy of ground point cloud determination, and thus improve the accuracy of ground information. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0064] Figure 1 1 is a flow chart of a point cloud processing method according to an embodiment;

[0065] Figure 2 A schematic diagram of a process for determining adjacent partitions in one embodiment;

[0066] Figure 3 Schematic diagram of a process for determining a target ground point cloud in one embodiment;

[0067] Figure 4 A schematic diagram of a flow chart of ground segmentation processing in one embodiment;

[0068] Figure 5 A schematic diagram of target area division in one embodiment;

[0069] Figure 6 A schematic diagram of neighborhood partitioning in one embodiment;

[0070] Figure 7 A schematic diagram of a partition identification in one embodiment;

[0071] Figure 8 A schematic diagram of a process for point cloud optimization in one embodiment;

[0072] Figure 9 FIG. 1 is a flow chart of determining a flatness probability in one embodiment;

[0073] Figure 10 A schematic diagram of a process for determining a target fitting plane in one embodiment;

[0074] Figure 11 is a flowchart of a point cloud processing method in another embodiment;

[0075] Figure 12 is a structural block diagram of a point cloud processing device in one embodiment;

[0076] Figure 13 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0078] With the continuous development of autonomous driving technology, in order to ensure the safety of vehicle driving, it is necessary to perform ground segmentation processing on unstructured roads such as those without clear signs, uneven road surfaces or complex terrain during vehicle driving, so as to determine the ground information required by the vehicle.

[0079] In related technologies, after using lidar to acquire point cloud data around the vehicle, the point clouds in the point cloud data that are below a height threshold can be used as the initial ground point cloud, and the ground point cloud can be fitted to obtain a fitting plane; then, based on the residual between the point cloud data and the fitting plane, the target ground point cloud is determined from the point cloud data, thereby constructing the ground information required by the vehicle.

[0080] However, the above method is only applicable to point cloud data corresponding to relatively gentle slopes or slight ground undulations. When faced with complex terrain, the fitting results obtained by the above method are poor, which reduces the accuracy of ground information acquisition.

[0081] Based on this, in an exemplary embodiment, a point cloud processing method is provided, and the method is described by taking the application of the method to a point cloud processing device as an example. Figure 1 As shown, the specific steps include:

[0082] S101, dividing the environment point cloud of the target area to obtain at least two point cloud partitions.

[0083] Among them, the so-called target area is the area where the vehicle with point cloud processing requirements is located. For example, the target area can be an area generated based on a fixed radius with the vehicle as the center; the so-called environmental point cloud is the point cloud data obtained based on the environment where the vehicle is located. For example, it can include ground point cloud and non-ground point cloud; the so-called point cloud partition is the point cloud set obtained after dividing the environmental point cloud.

[0084] In an optional embodiment, a sensor deployed on the vehicle (e.g., a LiDAR) can be used to acquire an environmental point cloud within the target area where the vehicle is located. The target area can then be divided into multiple partitions using a preset segmentation method. Based on the location of the environmental point cloud, the environmental point cloud is then populated into the corresponding partition to obtain each point cloud partition.

[0085] In another optional implementation, the acquired environmental point cloud may be input into a trained segmentation model, and the segmentation model may output each point cloud partition based on the environmental point cloud and model parameters.

[0086] S102 , performing ground segmentation processing on the environment point cloud in each point cloud partition to obtain an initial ground point cloud and an initial non-ground point cloud of each point cloud partition.

[0087] Among them, the so-called ground segmentation processing is to segment the ground point cloud from the environmental point cloud; the so-called initial ground point cloud is the environmental point cloud judged as the ground point cloud in the ground segmentation processing; the so-called initial non-ground point cloud is the environmental point cloud judged as the non-ground point cloud in the ground segmentation processing.

[0088] In one optional approach, singular value decomposition (SVD) plane fitting can be used to perform ground segmentation processing to obtain an initial ground point cloud and an initial non-ground point cloud for each point cloud partition. For example, for each point cloud partition, an environmental point cloud below a height threshold can be fitted to obtain a fitting plane corresponding to the point cloud partition; then, the environmental point cloud in the point cloud partition whose distance from the fitting plane is less than or equal to the distance threshold is used as the initial ground point cloud, and the environmental point cloud whose distance from the fitting plane is greater than the distance threshold is used as the initial non-ground point cloud.

[0089] In another optional method, for each point cloud partition, the environmental point cloud in the point cloud partition can be input into a trained ground segmentation model, and the ground segmentation model outputs the initial ground point cloud and the initial non-ground point cloud based on the positional relationship between the environmental point clouds and the model parameters.

[0090] S103 , determining an adjacent partition corresponding to each point cloud partition from each point cloud partition according to the initial non-ground point cloud and the initial ground point cloud of each point cloud partition.

[0091] Among them, for each point cloud partition, the adjacent partition corresponding to the point cloud partition is the other point cloud partition in which the environmental point clouds in the point cloud partition are located and have an adjacent relationship with the environmental point clouds in the point cloud partition. Furthermore, the distance between the two environmental point clouds under the so-called adjacent relationship is less than the preset adjacent threshold.

[0092] It is understandable that in practical applications, there may be two ground planes at different heights within a point cloud partition. In this case, the higher ground plane will be classified as non-ground. Therefore, to avoid this problem, the presence of ground point clouds within non-ground point clouds can be determined based on the positional relationship between the environmental point clouds in the adjacent partitions corresponding to the point cloud partition and the point clouds in the point cloud partition.

[0093] For example, in point cloud partition A and point cloud partition B that have an adjacent relationship, the distance between the non-ground point cloud A1 in point cloud partition A and the ground point cloud B1 in point cloud partition B is relatively close. At this time, it can be determined that the non-ground point cloud A1 is also a ground point cloud.

[0094] In an optional embodiment, in order to ensure the reliability of the adjacent partition determination, for each point cloud partition, the point cloud partition where the initial ground point cloud that has an adjacent relationship with the initial non-ground point cloud in the point cloud partition is located can be used as the adjacent partition corresponding to the point cloud partition based on the positional relationship between the initial non-ground point cloud in the point cloud partition and the initial ground point cloud in other point cloud partitions.

[0095] Exemplarily, for each point cloud partition, the point cloud partitions adjacent to the point cloud partition can be first selected as candidate adjacent partitions based on the positional relationship between the point cloud partitions; then, one or more initial ground point clouds that are closer to the initial non-ground point clouds in the point cloud partition are selected from the initial ground point clouds of the candidate adjacent partitions, and the candidate adjacent partition where the selected initial ground point clouds are located is selected as the adjacent partition corresponding to the point cloud partition.

[0096] For example, the point cloud partition in which the initial ground point cloud in each initial ground point cloud of the candidate adjacent partition is located, which is closest to the initial non-ground point cloud in the current point cloud partition, can be directly used as the adjacent partition corresponding to the current point cloud partition; or, based on the distance between each initial ground point cloud in the candidate adjacent partition and the initial non-ground point cloud in the current point cloud partition, the candidate adjacent partitions can be sorted in order from near to far, and a preset number of candidate adjacent partitions in the front order can be used as the adjacent partitions corresponding to the current point cloud partition.

[0097] S104 , determining a target ground point cloud from the initial non-ground point cloud of each point cloud partition according to the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition.

[0098] The so-called target ground point cloud is the ground point cloud determined from the initial non-ground point cloud.

[0099] In an optional embodiment, for each point cloud partition, the adjacent partition corresponding to the point cloud partition can be determined based on the identification information of the point cloud partition, and the initial ground point cloud that is closer to the point cloud partition can be selected from the adjacent partition corresponding to the point cloud partition; then, the selected initial ground point cloud is subjected to plane fitting processing to obtain a fitting plane, and the initial non-ground point cloud in the point cloud partition whose distance from the above-mentioned fitting plane is less than a preset threshold is used as the target ground point cloud in the point cloud partition.

[0100] In another optional embodiment, for each point cloud partition, the initial non-ground point cloud within the point cloud partition and the initial ground point cloud of the corresponding adjacent partition can be simultaneously input into a trained point cloud selection model, and the point cloud selection model determines the target ground point cloud from the initial non-ground point cloud of the point cloud partition based on the distance between the initial non-ground point cloud and the initial ground point cloud.

[0101] S105 , determining ground information of the target area according to the target ground point cloud of each point cloud partition and the initial ground point cloud.

[0102] The so-called ground information refers to information related to the ground in the target area, for example, it may include but is not limited to prompt information of complex terrain and related information of the vehicle driving direction.

[0103] In an optional implementation, the road surface within each point cloud partition can be constructed based on the target ground point cloud and the initial ground point cloud, thereby splicing the target road surface in the target area. Ground prompt information can then be generated based on the differences between the standard road surface and the target road surface, and the target road surface and ground prompt information can be simultaneously transmitted as ground information to a display device within the vehicle.

[0104] After receiving the ground information, the display device can display the target road surface and mark the target road surface based on the ground prompt information. In addition, if the vehicle is in navigation mode, it can also issue warnings based on the vehicle's driving route for ground prompt information located on the vehicle's driving route to remind the user to drive safely.

[0105] In the above point cloud processing method, the environmental point cloud of the target area is divided to obtain at least two point cloud partitions, and the environmental point cloud in each point cloud partition is subjected to ground segmentation processing to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition; then, based on the initial non-ground point cloud and initial ground point cloud of each point cloud partition, the adjacent partition corresponding to each point cloud partition is determined from each point cloud partition, and based on the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition, the target ground point cloud is determined from the initial non-ground point cloud of each point cloud partition; finally, based on the target ground point cloud and initial ground point cloud of each point cloud partition, the ground information of the target area is determined. Using the above method, after the initial ground point cloud and the initial non-ground point cloud are preliminarily segmented, the target ground point cloud is again screened out from the initial non-ground point cloud of the point cloud partition based on the initial ground point cloud in the corresponding adjacent partition, and then ground information is generated based on the initial ground point cloud and the target ground point cloud. This can avoid the problem of dividing the ground point cloud into non-ground point cloud in complex terrain, improve the accuracy of ground point cloud determination, and thus improve the accuracy of ground information.

[0106] In order to ensure the rationality of the determination of adjacent partitions, based on the above embodiment, an optional method for determining adjacent partitions is provided in the embodiment of the present application, such as Figure 2 As shown, the specific steps include:

[0107] S201 : For each point cloud partition, determine the point cloud centroid of the point cloud partition according to the initial non-ground point cloud of the point cloud partition.

[0108] The so-called point cloud centroid is the average position coordinate corresponding to each initial non-ground point cloud coordinate.

[0109] In an optional implementation, for each point cloud partition, an average polar coordinate may be calculated based on the polar coordinates of each initial non-ground point cloud in the point cloud partition, and the average polar coordinate may be used as the point cloud centroid of the point cloud partition.

[0110] In another optional embodiment, for each point cloud partition, each initial non-ground point cloud in the point cloud partition can be directly input into a trained center of gravity determination model, and the center of gravity determination model outputs the point cloud center of gravity of the point cloud partition based on the polar coordinates and model parameters of each initial non-ground point cloud.

[0111] S202 : selecting adjacent ground point clouds from the initial ground point clouds of the remaining point cloud partitions according to the distance between the initial ground point clouds of the remaining point cloud partitions and the point cloud centroids.

[0112] Among them, the remaining point cloud partitions are the point cloud partitions other than the point cloud partition in each point cloud partition; the so-called adjacent ground point cloud is the initial ground point cloud that is closer to the point cloud center of gravity in the remaining point cloud partitions. Furthermore, at most one adjacent ground point cloud can be selected in a remaining point cloud partition, and the number of adjacent ground point clouds is the same as the number of adjacent partitions.

[0113] In an optional embodiment, for each initial ground point cloud in the remaining point cloud partitions, the distance between the initial ground point cloud and the point cloud center of gravity can be calculated based on the polar coordinates of the initial ground point cloud and the polar coordinates of the point cloud center of gravity; then, based on the distance between each initial ground point cloud and the point cloud center of gravity, adjacent ground point clouds are selected from each initial ground point cloud.

[0114] For example, when only one adjacent partition is selected, the initial ground point cloud closest to the point cloud's center of gravity can be selected from the initial ground point clouds of the remaining point cloud partitions as the adjacent ground point cloud. When multiple adjacent partitions are selected, for each remaining point cloud partition, the first ground point cloud closest to the point cloud's center of gravity can be selected from the initial ground point clouds of the remaining point cloud partitions. Thereafter, the first ground point clouds are sorted in order from near to far based on the distance between each first ground point cloud and the point cloud's center of gravity, and a preset number of first ground point clouds ranked first are selected as the adjacent ground point clouds.

[0115] In another optional embodiment, in order to reduce the amount of calculation of the point cloud distance, the remaining point cloud partitions adjacent to the point cloud partition can be first selected from the remaining point cloud partitions as candidate point cloud partitions; for each candidate point cloud partition, according to the polar coordinates of each initial ground point cloud in the candidate point cloud partition, the second ground point cloud closest to the point cloud center of gravity is selected from each initial ground point cloud.

[0116] Furthermore, according to the distance between the second ground point cloud and the point cloud centroid in each candidate point cloud partition, the second ground point clouds are sorted in order from near to far, and a preset number of second ground point clouds in the front order are used as adjacent ground point clouds.

[0117] S203 : The point cloud partition to which the adjacent ground point cloud belongs is used as the adjacent partition corresponding to the point cloud partition.

[0118] In an optional implementation, after the adjacent ground point cloud is determined, the point cloud partition to which the adjacent ground point cloud belongs may be directly used as the adjacent partition corresponding to the point cloud partition.

[0119] It can be understood that when only one adjacent partition is selected, the amount of data processing can be greatly reduced during the subsequent reference plane fitting processing, thereby improving the efficiency of determining the subsequent target ground point cloud; and when multiple adjacent partitions are selected, the target ground point cloud that has an adjacent relationship with the ground point cloud in the adjacent partitions in multiple directions can be selected from the initial non-ground point cloud, thereby ensuring the comprehensiveness and accuracy of the subsequent target ground point cloud determination.

[0120] In an embodiment of the present application, by using the point cloud partition to which the adjacent ground point cloud that is closer to the point cloud centroid belongs as the adjacent partition corresponding to the point cloud partition, the rationality of the adjacent partition determination can be effectively guaranteed.

[0121] In order to ensure the accuracy of the target ground point cloud, based on the above embodiment, in the embodiment of the present application, an optional method for determining the target ground point cloud is provided, such as Figure 3 As shown, the specific steps include:

[0122] S301 , for each point cloud partition, selecting a reference ground point cloud whose distance to the point cloud centroid of the point cloud partition is less than a first distance threshold from the initial ground point cloud of the adjacent partition corresponding to the point cloud partition.

[0123] The so-called first distance threshold is a value used to measure the distance between the initial ground point cloud and the point cloud's centroid. It is worth noting that the first distance threshold can be determined based on multiple experiments or set by technicians based on historical experience, and there is no restriction on this. The so-called reference ground point cloud is the initial ground point cloud in the adjacent partition that is closest to the point cloud's centroid.

[0124] In an optional embodiment, for each point cloud partition, the point cloud distance between the initial ground point cloud and the point cloud centroid of the adjacent partition corresponding to the point cloud partition can be calculated respectively; then the initial ground point cloud with a point cloud distance less than a first distance threshold is used as a reference ground point cloud.

[0125] For example, when only one adjacent partition is selected, the initial ground point cloud in the adjacent partition whose distance from the point cloud center of gravity is less than the first distance threshold can be directly used as the reference ground point cloud; when multiple adjacent partitions are selected, the initial ground point cloud in the adjacent partition whose distance from the point cloud center of gravity is less than the first distance threshold can be determined separately for each adjacent partition, and then the initial ground point clouds determined in each adjacent partition can be used as reference ground point clouds at the same time.

[0126] S302: Perform plane fitting processing on the reference ground point cloud to obtain a reference fitting plane.

[0127] The so-called reference fitting plane is the fitting plane obtained after plane fitting processing is performed on the reference ground point cloud.

[0128] In an optional implementation, a plane fitting process may be performed on the reference ground point clouds according to the polar coordinates of each reference ground point cloud to obtain a reference fitting plane.

[0129] For example, the average coordinates of the reference ground point clouds can be calculated based on the polar coordinates of each reference ground point cloud. The average coordinates are then subtracted from the polar coordinates of each reference ground point cloud to obtain a decentralized point cloud coordinate matrix. Furthermore, the point cloud coordinate matrix can be subjected to singular value decomposition to obtain the normal vector of the reference fitting plane, and the reference fitting plane can be determined based on the average coordinates and the normal vector.

[0130] S303 , based on the distance between the initial non-ground point cloud of the point cloud partition and the reference fitting plane, the initial non-ground point cloud in the point cloud partition whose distance to the reference fitting plane is less than a second distance threshold is used as the target ground point cloud.

[0131] The so-called second distance threshold is a value used to measure the distance between the initial non-ground point cloud and the reference fitting plane. It is worth noting that the second distance threshold can be determined based on multiple experiments or set by technicians based on historical experience, and there is no limitation on this.

[0132] It can be understood that since the reference fitting plane is obtained by fitting the reference ground point cloud that is closer to the point cloud center of gravity in the adjacent point cloud, the reference fitting plane can be regarded as the ground at a higher position in the point cloud partition.

[0133] Based on this, based on the reference distance between each initial non-ground point cloud in the point cloud partition and the reference fitting plane, the initial non-ground point cloud with a reference distance less than the second distance threshold can be selected from the initial non-ground point clouds as the target ground point cloud. In this case, the remaining initial non-ground point clouds remain non-ground point clouds.

[0134] In this embodiment of the present application, by introducing a reference fitting plane that can be considered as a higher ground surface and using the initial non-ground point cloud whose distance from the reference fitting plane is less than a second distance threshold as the target ground point cloud, the accuracy of the target ground point cloud can be guaranteed. Furthermore, by further filtering the target ground point cloud from the initial non-ground point cloud, the accuracy of the ground information can be guaranteed.

[0135] In order to ensure the reliability of the initial ground segmentation process, based on the above embodiment, an optional method of ground segmentation process is provided in the embodiment of the present application, such as Figure 4 As shown, the specific steps include:

[0136] S401 , for each point cloud partition, performing plane fitting processing on the environment point cloud within the point cloud partition to obtain a target fitting plane corresponding to the point cloud partition and plane attribute information of the target fitting plane.

[0137] Among them, the so-called target fitting plane is the fitting plane obtained after plane fitting processing of the environment point cloud; the so-called plane attribute information is the relevant attributes of the fitting plane, which may include but is not limited to information such as the flatness of the plane, the inclination of the plane, and the height of the plane.

[0138] In an optional embodiment, for each point cloud partition, a plane fitting process can be performed on the environment point cloud in the point cloud partition to obtain a target fitting plane corresponding to the point cloud partition; then, based on the plane parameters of the target fitting plane, the plane attribute information of the target fitting plane is determined.

[0139] Exemplarily, for each point cloud partition, SVD plane fitting processing can be performed on the environmental point cloud in the point cloud partition that is below the height threshold to obtain the target fitting plane corresponding to the point cloud partition; then, the plane attribute information of the target fitting plane is determined based on the normal vector of the target fitting plane, the minimum matrix singular value in the plane fitting process, and the average height of the target fitting plane.

[0140] For example, n2 in the normal vector (n0, n1, n2) of the target fitting plane can represent the degree of inclination of the target fitting plane in space, so n2 can be used as the plane inclination; the minimum matrix singular value S can represent the distribution degree of the target fitting plane on the normal vector, so S can be used as the flatness of the fitting plane.

[0141] In another optional embodiment, for each point cloud partition, the environmental point cloud in the point cloud partition can be directly input into a trained plane fitting model, and the plane fitting model outputs the target fitting plane and the plane attribute information of the target fitting plane based on the polar coordinates and model parameters of each environmental point cloud.

[0142] S402 : The environment point cloud located on the target fitting plane is used as the original ground point cloud, and the point cloud other than the original ground point cloud in the environment point cloud within the point cloud partition is used as the original non-ground point cloud.

[0143] The so-called original ground point cloud is the environment point cloud located on the target fitting plane; the so-called original non-ground point cloud is the environment point cloud located outside the target fitting plane.

[0144] In an optional embodiment, in order to verify the accuracy of the ground point cloud division, the environmental point cloud located on the target fitting plane can be first used as the original ground point cloud, and the point cloud in the environmental point cloud within the point cloud partition except the original ground point cloud can be used as the original non-ground point cloud.

[0145] S403 , optimizing the original ground point cloud and the original non-ground point cloud in the point cloud partition according to the plane attribute information of the target fitting plane, to obtain the initial ground point cloud and the initial non-ground point cloud of the point cloud partition.

[0146] In an optional embodiment, the original ground point cloud and the original non-ground point cloud that are initially divided can be verified based on the plane attribute information of the target fitting plane, and the initial ground point cloud and the initial non-ground point cloud of the point cloud partition can be determined according to the verification results.

[0147] For example, when it is determined based on the plane attribute information of the target fitting plane that the target fitting plane meets the standard plane requirements, it is proved that the fitted plane is relatively standard. At this time, the original ground point cloud in the point cloud partition can be directly used as the initial ground point cloud, and the original non-ground point cloud can be used as the initial non-ground point cloud.

[0148] When it is determined that the target fitting plane does not meet the standard plane requirements based on the plane attribute information of the target fitting plane, it is proved that the fitted plane contains non-ground point clouds. Therefore, it is necessary to filter out the non-ground point clouds from the original ground point clouds based on the plane attribute information, so as to determine the initial ground point clouds and the initial non-ground point clouds.

[0149] In another optional embodiment, the plane attribute information, the original ground point cloud and the original non-ground point cloud can be directly input into the trained point cloud optimization model at the same time, and the point cloud optimization model outputs the initial ground point cloud and the initial non-ground point cloud of the point cloud partition based on the plane attribute information, the original ground point cloud, the original non-ground point cloud and the model parameters.

[0150] In an embodiment of the present application, the original ground point cloud and the original non-ground point cloud obtained by the preliminary division are optimized by introducing plane attribute information, and the initial ground point cloud and the initial non-ground point cloud are obtained, which can ensure the rationality of the ground segmentation, and then ensure the accuracy of the determination of the initial ground point cloud and the initial non-ground point cloud, laying the foundation for the subsequent determination of ground information.

[0151] In order to ensure the reliability of area division, based on the above embodiments, an optional method of point cloud partitioning is provided in an embodiment of the present application. Specifically, the environmental point cloud of the target area is divided based on a preset distance interval, a preset angle interval and a preset number of circles to obtain at least two point cloud partitions.

[0152] Among them, the so-called preset distance interval is the preset distance interval between adjacent point cloud partitions; the so-called preset angle interval is the preset angle interval between adjacent point cloud partitions; the so-called preset number of circles is the number of hierarchical divisions of the target area.

[0153] In an optional embodiment, the vehicle can be used as the origin of the vehicle coordinate system and the standard detection distance of the sensor as the radius to construct a target area and obtain an environmental point cloud in the target area; then, based on the origin as a reference, the target area is divided based on a preset distance interval, a preset angle interval and a preset number of circles to obtain at least two partitions.

[0154] For example, reference Figure 5 As shown in the target area division diagram, there are three preset layers, and each layer has a corresponding preset distance interval and preset angle interval. Figure 5 After the dotted circular area on the left is obtained, the first layer of partitions can be divided based on the preset distance interval and preset angle interval corresponding to the first circle layer with the origin as the reference; then the second layer of partitions and the third layer of partitions can be divided in sequence based on the preset distance interval and preset angle interval corresponding to each circle layer.

[0155] It is understandable that since the acquisition accuracy of sensors such as lidar decreases with increasing distance, in order to ensure that the number of point clouds in each point cloud partition is similar, the area of the partitions in each circle layer can be gradually increased when dividing each circle layer, that is, the size information between the partitions of each circle layer (for example, Figure 5 Therefore, when determining the adjacent point cloud partitions of the current partition, it is necessary to determine the number of its adjacent partitions according to the position of the current partition.

[0156] For example, for each partition that is not located at the circle boundary, the number of adjacent partitions is 8; for each partition located at the circle boundary, the number of adjacent partitions needs to be determined based on the size relationship between the partition size in another circle adjacent to the partition and the partition size. Figure 6 As shown in the neighborhood partition diagram, the neighborhood partitions of partition M are 7; the neighborhood partitions of partition N are 8.

[0157] After determining each partition, for each partition, the unique identification information of the partition can be determined based on the partition level, the partition level within the level, and the angular position relative to the vehicle coordinate system. For example, Figure 7 As shown in the partition identification diagram, for partition P, since partition P is located in the 4th circle in the 2nd layer, it is divided into the 1st partition according to the angle (counterclockwise), so the identification information of partition P is (2, 4, 1).

[0158] In an optional implementation, the environmental point cloud can be filled into each partition according to its position relative to the vehicle coordinate system, and it can be determined whether there is an environmental point cloud in each partition; then only the partition containing the environmental point cloud is used as the point cloud partition.

[0159] Furthermore, in order to ensure the reliability of point cloud optimization, based on the above embodiment, an optional method of point cloud optimization is provided in the embodiment of the present application, such as Figure 8 As shown, the specific steps include:

[0160] S801 , when the plane attribute information of the target fitting plane does not satisfy the standard plane information, determine the flatness probability of the point cloud partition according to the plane attribute information of the target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs.

[0161] Plane attribute information includes at least flatness. Standard plane information refers to the parameter ranges of attribute information in each dimension corresponding to the standard fitted plane. The target circle of a point cloud partition is the circle within which the point cloud partition resides. Flatness probability refers to the probability that the fitted plane within the point cloud partition is flat.

[0162] In an optional embodiment, for the plane attribute information in each dimension, the plane attribute information in that dimension can be compared with the standard plane information in that dimension to obtain a comparison result in that dimension; then, when the comparison results in each dimension all meet the standard plane information, it is determined that the plane attribute information of the target fitting plane meets the standard plane information; when the comparison result in any dimension does not meet the standard plane information, it is determined that the plane attribute information of the target fitting plane does not meet the standard plane information.

[0163] Exemplarily, the plane attribute information includes flatness, plane inclination, and plane height, and the standard plane information includes a flatness threshold, a plane inclination threshold, and a plane height threshold. If the flatness of the target fitting plane is greater than the flatness threshold, the plane inclination is less than the plane inclination threshold, and the plane height is less than the plane height threshold, the plane attribute information of the target fitting plane is determined to meet the standard plane information.

[0164] Furthermore, if any of the flatness, plane inclination, and plane height dimensions do not meet the aforementioned conditions, the plane attribute information of the target fitting plane is determined to not meet the standard plane information. For example, if the flatness of the target fitting plane is less than a flatness threshold, the plane inclination is less than a plane inclination threshold, and the plane height is less than a plane height threshold, the plane attribute information of the target fitting plane is determined to not meet the standard plane information.

[0165] In an optional embodiment, when the plane attribute information of the target fitting plane does not meet the standard plane information, the plane attribute information of the target fitting plane corresponding to each point cloud partition in the target circle to which the point cloud partition belongs can be obtained; then, based on the plane attribute information of each point cloud partition, the flatness probability of the point cloud partition is determined.

[0166] For example, the flatness probability of the point cloud partition can be calculated based on the flatness in the plane attribute information; alternatively, the plane attribute information can be directly input into a trained probability calculation model, and the probability calculation model can determine the flatness probability of the point cloud partition based on the plane attribute information and model parameters.

[0167] S802 : When the flatness probability is less than or equal to the probability threshold, both the original ground point cloud and the original non-ground point cloud in the point cloud partition are used as initial non-ground point clouds.

[0168] The so-called probability threshold is a value used to measure the flatness probability. For example, the probability threshold may be 0.5.

[0169] In an optional embodiment, the flatness probability can be compared with a probability threshold. If the flatness probability is less than or equal to the probability threshold, it proves that the flatness of the fitted plane in the point cloud partition is less likely, that is, the ground may not exist in the point cloud partition. At this time, the original ground point cloud and the original non-ground point cloud in the point cloud partition can be used as the initial non-ground point cloud.

[0170] S803 : When the flatness probability is greater than the probability threshold, the original ground point cloud in the point cloud partition is used as the initial ground point cloud, and the original non-ground point cloud is used as the initial non-ground point cloud.

[0171] In an optional embodiment, the flatness probability can be compared with a probability threshold. If the flatness probability is greater than the probability threshold, it proves that the flatness of the fitted plane in the point cloud partition is more likely, that is, there is ground in the point cloud partition. At this time, the original ground point cloud in the point cloud partition can be used as the initial ground point cloud, and the original non-ground point cloud can be used as the initial non-ground point cloud.

[0172] In an embodiment of the present application, by comparing the flatness probability of the point cloud partition with a preset probability threshold, it is determined whether there is a ground point cloud in the point cloud partition. Then, based on the result of the existence of the ground point cloud, the original ground point cloud and the original non-ground point cloud initially divided are optimized, which can effectively ensure the rationality of the point cloud optimization.

[0173] In order to ensure the accuracy of the flatness probability, based on the above embodiment, an optional method for determining the flatness probability is provided in the embodiment of the present application, such as Figure 9 As shown, the specific steps include:

[0174] S901 , determining an average flatness and a flatness standard deviation of a target circle layer according to the flatness of a target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs.

[0175] The so-called average flatness is the mean of the flatness of each target fitting plane; the so-called flatness standard deviation is the standard deviation corresponding to the flatness of each target fitting plane.

[0176] In an optional embodiment, after obtaining the flatness of the target fitting plane corresponding to each point cloud partition in the target circle, the mean of each flatness can be directly used as the average flatness; then, the flatness standard deviation is calculated based on the difference between the flatness of each target fitting plane and the average flatness.

[0177] S902: Determine a flatness threshold of the target circle according to the average flatness and flatness standard deviation of the target circle.

[0178] The so-called flatness threshold is a value used to measure the degree of flatness.

[0179] In an optional embodiment, referring to the following formula (1), the flatness standard deviation can be weighted based on a preset weighting parameter, and the sum of the weighted flatness standard deviation and the average flatness is used as the flatness threshold of the target circle. Here, F_th is the flatness threshold; S_m is the average flatness; S_std is the flatness standard deviation; and X1 is a preset weighting parameter, which can be 1.5.

[0180] (1)

[0181] In another optional embodiment, the average flatness and flatness standard deviation of the target circle can be simultaneously input into a trained flatness threshold determination model, and the flatness threshold determination model outputs the flatness threshold of the target circle based on the average flatness, flatness standard deviation and model parameters.

[0182] S903 : Determine the flatness probability of the point cloud partition according to the flatness threshold and the flatness of the target fitting plane corresponding to the point cloud partition.

[0183] In an optional embodiment, referring to the following formula (2), an exponential function can be used to calculate the flatness and flatness threshold of the target fitting plane corresponding to the point cloud partition based on a preset divisor parameter, thereby obtaining the flatness probability of the point cloud partition. Wherein, F_prob is the flatness probability; X2 is the preset divisor parameter, which can be 10.

[0184] (2)

[0185] In an embodiment of the present application, the flatness probability of the point cloud partition is determined based on the average flatness and flatness standard deviation of the target circle to which the point cloud partition belongs, and the flatness of the target fitting plane corresponding to the point cloud partition, thereby ensuring the accuracy of the flatness probability determination.

[0186] In order to ensure the accuracy of the target fitting plane, based on the above embodiment, an optional method for determining the target fitting plane is provided in the embodiment of the present application, such as Figure 10 As shown, the specific steps include:

[0187] S1001 , sorting the environmental point clouds in descending order according to the height values of the environmental point clouds in the point cloud partition, and using a target number of environmental point clouds in the front order as initial fitting point clouds.

[0188] The so-called target number is the preset number of point clouds, which may be 20; the so-called initial fitting point cloud is the environment point cloud that is first subjected to plane fitting processing.

[0189] In an optional embodiment, for each point cloud partition, the environmental point clouds within the point cloud partition can be sorted from low to high, and a target number of environmental point clouds ranked first can be used as the initial fitting point clouds. For example, the 20 environmental point clouds with the lowest height values can be used as the initial fitting point clouds.

[0190] S1002: Perform plane fitting processing on the initial fitting point cloud to obtain an initial fitting plane.

[0191] The so-called initial fitting plane is the fitting plane obtained after performing plane fitting processing on the initial fitting point cloud.

[0192] In an optional implementation, a plane fitting process may be performed on the initial fitting point clouds according to the polar coordinates of each initial fitting point cloud to obtain an initial fitting plane.

[0193] S1003: Optimize the initial fitting plane based on the environment point cloud within the point cloud partition whose distance from the initial fitting plane is less than a third distance threshold to obtain a target fitting plane corresponding to the point cloud partition and plane attribute information of the target fitting plane.

[0194] The so-called third distance threshold is a value used to measure the distance between the environment point cloud and the initial fitting plane.

[0195] In an optional embodiment, environmental point clouds whose distance from the initial fitting plane is less than a third distance threshold can be screened out from the environmental point cloud; then, plane fitting processing is continued based on a preset number of plane fitting times, the screened environmental point clouds, and the initial fitting plane to obtain the target fitting plane and the plane attribute information of the target fitting plane.

[0196] Exemplarily, when the number of plane fitting times is 3, after filtering out the environmental point cloud whose distance to the initial fitting plane is less than the third distance threshold from the environmental point cloud, the filtered environmental point cloud can be used to fit the initial fitting plane to obtain an alternative fitting plane; thereafter, the environmental point cloud whose distance to the alternative fitting plane is less than the third distance threshold can be further filtered out from the environmental point cloud, and the filtered environmental point cloud can be used to fit the alternative fitting plane to obtain the target fitting plane and the plane attribute information of the target fitting plane.

[0197] In the embodiment of the present application, the target fitting plane and the plane attribute information of the target fitting plane are obtained by optimizing the fitting plane multiple times, thereby ensuring the accuracy of the target fitting plane and the plane attribute information.

[0198] Figure 11 This is a flow chart of a point cloud processing method in another embodiment. Based on the above embodiment, this embodiment provides an optional example of a point cloud processing method. Figure 11 The specific implementation process is as follows:

[0199] S1101 : Divide the environmental point cloud of the target area based on a preset distance interval, a preset angle interval, and a preset number of circles to obtain at least two point cloud partitions.

[0200] S1102 , sorting the environmental point clouds of each point cloud partition in descending order according to the height values of the environmental point clouds in each point cloud partition, and using a target number of environmental point clouds in the front order as the initial fitting point clouds in each point cloud partition.

[0201] S1103 , performing plane fitting processing on the initial fitting point cloud in each point cloud partition to obtain an initial fitting plane for each point cloud partition.

[0202] S1104, for each point cloud partition, based on the environmental point cloud within the point cloud partition whose distance from the initial fitting plane is less than a third distance threshold, the initial fitting plane is optimized to obtain the target fitting plane corresponding to the point cloud partition and the plane attribute information of the target fitting plane.

[0203] S1105 , taking the environment point cloud located on the target fitting plane in each point cloud partition as the original ground point cloud, and taking the point cloud other than the original ground point cloud in the environment point cloud in each point cloud partition as the original non-ground point cloud.

[0204] S1106. When the plane attribute information of the target fitting plane in the point cloud partition does not meet the standard plane information, the average flatness and flatness standard deviation of the target circle are determined based on the flatness in the plane attribute information of the target fitting plane corresponding to each point cloud partition in the target circle to which the point cloud partition belongs.

[0205] The plane attribute information at least includes flatness.

[0206] S1107 , determining a flatness threshold of the target circle layer according to the average flatness and flatness standard deviation of the target circle layer to which the point cloud partition belongs.

[0207] S1108 , determining the flatness probability of the point cloud partition according to the flatness threshold of the target circle layer and the flatness of the target fitting plane corresponding to the point cloud partition.

[0208] S1109, when the flatness probability is less than or equal to the probability threshold, the original ground point cloud and the original non-ground point cloud in the point cloud partition are both used as the initial non-ground point cloud, and, when the flatness probability is greater than the probability threshold, the original ground point cloud in the point cloud partition is used as the initial ground point cloud, and the original non-ground point cloud is used as the initial non-ground point cloud.

[0209] S1110 , determining the point cloud centroid of the point cloud partition according to the initial non-ground point cloud of the point cloud partition.

[0210] S1111, for each point cloud partition, select the adjacent ground point cloud that is closest to the point cloud center of gravity from the initial ground point clouds of the remaining point cloud partitions in each point cloud partition except the point cloud partition, and use the point cloud partition to which the adjacent ground point cloud belongs as the adjacent partition corresponding to the point cloud partition.

[0211] S1112, from the initial ground point cloud of the adjacent partition corresponding to the point cloud partition, select a reference ground point cloud whose distance to the point cloud centroid of the point cloud partition is less than a first distance threshold, and perform plane fitting processing on the reference ground point cloud to obtain a reference fitting plane.

[0212] S1113 , based on the distance between the initial non-ground point cloud of the point cloud partition and the reference fitting plane, the initial non-ground point cloud in the point cloud partition whose distance to the reference fitting plane is less than a second distance threshold is used as the target ground point cloud.

[0213] S1114 , determining ground information of the target area based on the target ground point cloud of each point cloud partition and the initial ground point cloud.

[0214] The specific process of the above S1101-S1114 can be found in the description of the above method embodiment. The implementation principle and technical effects are similar and will not be repeated here.

[0215] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0216] Based on the same inventive concept, embodiments of the present application also provide a point cloud processing device for implementing the aforementioned point cloud processing method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more point cloud processing device embodiments provided below can be found in the above-described limitations of the point cloud processing method and will not be further elaborated here.

[0217] In an exemplary embodiment, Figure 12 As shown, a point cloud processing device 1 is provided, comprising: a point cloud segmentation module 10, a ground segmentation module 20, a partition determination module 30, a point cloud determination module 40 and an information determination module 50, wherein:

[0218] The point cloud partitioning module 10 is used to partition the environment point cloud of the target area to obtain at least two point cloud partitions;

[0219] The ground segmentation module 20 is used to perform ground segmentation processing on the environment point cloud in each point cloud partition to obtain an initial ground point cloud and an initial non-ground point cloud of each point cloud partition;

[0220] A partition determination module 30 is configured to determine, from each point cloud partition, an adjacent partition corresponding to each point cloud partition based on the initial non-ground point cloud and the initial ground point cloud of each point cloud partition;

[0221] a point cloud determination module 40 for determining a target ground point cloud from the initial non-ground point cloud of each point cloud partition based on a distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of a corresponding adjacent partition;

[0222] The information determination module 50 is used to determine the ground information of the target area according to the target ground point cloud and the initial ground point cloud of each point cloud partition.

[0223] In an exemplary embodiment, the partition determination module 30 is specifically configured to:

[0224] For each point cloud partition, the point cloud centroid of the point cloud partition is determined according to the initial non-ground point cloud of the point cloud partition; the adjacent ground point cloud is selected from the initial ground point cloud of the remaining point cloud partitions according to the distance between the initial ground point cloud and the point cloud centroid; the remaining point cloud partitions are the point cloud partitions other than the point cloud partition in each point cloud partition; the point cloud partition to which the adjacent ground point cloud belongs is used as the adjacent partition corresponding to the point cloud partition.

[0225] In an exemplary embodiment, the point cloud determination module 40 is specifically configured to:

[0226] For each point cloud partition, a reference ground point cloud whose distance to the point cloud centroid of the point cloud partition is less than a first distance threshold is selected from the initial ground point cloud of the adjacent partition corresponding to the point cloud partition; plane fitting processing is performed on the reference ground point cloud to obtain a reference fitting plane; according to the distance between the initial non-ground point cloud of the point cloud partition and the reference fitting plane, the initial non-ground point cloud in the point cloud partition whose distance to the reference fitting plane is less than a second distance threshold is used as the target ground point cloud.

[0227] In an exemplary embodiment, the ground segmentation module 20 includes:

[0228] The initial fitting unit is used to perform plane fitting processing on the environment point cloud in each point cloud partition, and obtain the target fitting plane corresponding to the point cloud partition and the plane attribute information of the target fitting plane;

[0229] a point cloud partitioning unit, configured to treat the environment point cloud located on the target fitting plane as the original ground point cloud, and treat the point cloud other than the original ground point cloud in the environment point cloud within the point cloud partition as the original non-ground point cloud;

[0230] The point cloud optimization unit is used to optimize the original ground point cloud and the original non-ground point cloud in the point cloud partition according to the plane attribute information of the target fitting plane, so as to obtain the initial ground point cloud and the initial non-ground point cloud of the point cloud partition.

[0231] In an exemplary embodiment, the point cloud segmentation module 10 is specifically configured to:

[0232] Divide the environmental point cloud of the target area based on a preset distance interval, a preset angle interval, and a preset number of circles to obtain at least two point cloud partitions;

[0233] Accordingly, the point cloud optimization unit is specifically used for:

[0234] When the plane attribute information of the target fitting plane does not meet the standard plane information, the flatness probability of the point cloud partition is determined according to the plane attribute information of the target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs; wherein the plane attribute information at least includes flatness; when the flatness probability is less than or equal to the probability threshold, the original ground point cloud and the original non-ground point cloud in the point cloud partition are both used as the initial non-ground point cloud; when the flatness probability is greater than the probability threshold, the original ground point cloud in the point cloud partition is used as the initial ground point cloud, and the original non-ground point cloud is used as the initial non-ground point cloud.

[0235] In an exemplary embodiment, the point cloud optimization unit is further configured to:

[0236] According to the flatness of the target fitting plane corresponding to each point cloud partition in the target circle to which the point cloud partition belongs, the average flatness and flatness standard deviation of the target circle are determined; according to the average flatness and flatness standard deviation of the target circle, the flatness threshold of the target circle is determined; according to the flatness threshold and the flatness of the target fitting plane corresponding to the point cloud partition, the flatness probability of the point cloud partition is determined.

[0237] In an exemplary embodiment, the initial fitting unit is specifically configured to:

[0238] According to the height value of each environmental point cloud in the point cloud partition, the environmental point clouds are sorted in order from low to high, and the target number of environmental point clouds in the front sorting are used as the initial fitting point clouds; the initial fitting point clouds are plane fitting processed to obtain the initial fitting plane; according to the environmental point clouds in the point cloud partition whose distance from the initial fitting plane is less than the third distance threshold, the initial fitting plane is optimized to obtain the target fitting plane corresponding to the point cloud partition and the plane attribute information of the target fitting plane.

[0239] Each module in the aforementioned point cloud processing device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0240] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 13As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means. The wireless means can be implemented via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a point cloud processing method. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0241] Those skilled in the art will understand that Figure 13 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0242] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0243] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0244] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0245] It should be noted that the data involved in this application (including but not limited to environmental point cloud data, etc.) are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0246] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0247] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0248] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A point cloud processing method, characterized in that: The method comprises: Divide the environmental point cloud of the target area to obtain at least two point cloud partitions; Perform ground segmentation processing on the environmental point cloud in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition; Determine, from each point cloud partition, an adjacent partition corresponding to each point cloud partition according to the initial non-ground point cloud and the initial ground point cloud of each point cloud partition; Determine the target ground point cloud from the initial non-ground point cloud of each point cloud partition according to the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition; Determining ground information of the target area based on the target ground point cloud and the initial ground point cloud of each point cloud partition; The target ground point cloud is determined from the initial non-ground point cloud of each point cloud partition according to the distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud in the corresponding adjacent partition, including: For each point cloud partition, select, from the initial ground point clouds of adjacent partitions corresponding to the point cloud partition, a reference ground point cloud whose distance to the point cloud centroid of the point cloud partition is less than a first distance threshold; Performing plane fitting processing on the reference ground point cloud to obtain a reference fitting plane; According to the distance between the initial non-ground point cloud of the point cloud partition and the reference fitting plane, the initial non-ground point cloud in the point cloud partition whose distance to the reference fitting plane is less than a second distance threshold is used as the target ground point cloud.

2. The method according to claim 1, characterized in that According to the initial non-ground point cloud and the initial ground point cloud of each point cloud partition, the adjacent partition corresponding to each point cloud partition is determined from each point cloud partition, including: For each point cloud partition, determining the point cloud centroid of the point cloud partition according to the initial non-ground point cloud of the point cloud partition; Selecting adjacent ground point clouds from the initial ground point clouds of the remaining point cloud partitions according to the distance between the initial ground point clouds of the remaining point cloud partitions and the center of gravity of the point cloud; wherein the remaining point cloud partitions are point cloud partitions other than the point cloud partition in each point cloud partition; The point cloud partition to which the adjacent ground point cloud belongs is used as the adjacent partition corresponding to the point cloud partition.

3. The method according to any one of claims 1-2, characterized in that Perform ground segmentation processing on the environmental point clouds in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud in each point cloud partition, including: For each point cloud partition, performing plane fitting processing on the environment point cloud within the point cloud partition to obtain a target fitting plane corresponding to the point cloud partition and plane attribute information of the target fitting plane; The environment point cloud located on the target fitting plane is used as the original ground point cloud, and the point cloud other than the original ground point cloud in the environment point cloud within the point cloud partition is used as the original non-ground point cloud; According to the plane attribute information of the target fitting plane, the original ground point cloud and the original non-ground point cloud in the point cloud partition are optimized to obtain the initial ground point cloud and the initial non-ground point cloud of the point cloud partition.

4. The method according to claim 3, characterized in that Divide the environmental point cloud of the target area to obtain at least two point cloud partitions, including: Divide the environmental point cloud of the target area based on a preset distance interval, a preset angle interval, and a preset number of circles to obtain at least two point cloud partitions; The optimizing the original ground point cloud and the original non-ground point cloud in the point cloud partition according to the plane attribute information of the target fitting plane to obtain the initial ground point cloud and the initial non-ground point cloud of the point cloud partition includes: When the plane attribute information of the target fitting plane does not satisfy the standard plane information, determining the flatness probability of the point cloud partition according to the plane attribute information of the target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs; wherein the plane attribute information includes at least flatness; When the flatness probability is less than or equal to a probability threshold, both the original ground point cloud and the original non-ground point cloud in the point cloud partition are used as the initial non-ground point cloud; When the flatness probability is greater than the probability threshold, the original ground point cloud in the point cloud partition is used as the initial ground point cloud, and the original non-ground point cloud is used as the initial non-ground point cloud.

5. The method according to claim 4, characterized in that Determining the flatness probability of the point cloud partition according to the plane attribute information of the target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs includes: Determining the average flatness and flatness standard deviation of the target circle layer according to the flatness of the target fitting plane corresponding to each point cloud partition in the target circle layer to which the point cloud partition belongs; Determining a flatness threshold of the target circle layer according to the average flatness and flatness standard deviation of the target circle layer; The flatness probability of the point cloud partition is determined according to the flatness threshold and the flatness of the target fitting plane corresponding to the point cloud partition.

6. The method according to claim 3, characterized in that Performing plane fitting processing on the environment point cloud within the point cloud partition to obtain a target fitting plane corresponding to the point cloud partition and plane attribute information of the target fitting plane, including: According to the height values of the environmental point clouds in the point cloud partition, the environmental point clouds are sorted in ascending order, and the target number of environmental point clouds in the top order are used as the initial fitting point clouds; Performing plane fitting processing on the initial fitting point cloud to obtain an initial fitting plane; The initial fitting plane is optimized based on the environment point cloud within the point cloud partition whose distance from the initial fitting plane is less than a third distance threshold to obtain a target fitting plane corresponding to the point cloud partition and plane attribute information of the target fitting plane.

7. A point cloud processing device, characterized in that: The device comprises: A point cloud partitioning module is used to partition the environmental point cloud of the target area to obtain at least two point cloud partitions; The ground segmentation module is used to perform ground segmentation processing on the environmental point cloud in each point cloud partition to obtain the initial ground point cloud and initial non-ground point cloud of each point cloud partition; A partition determination module is used to determine the adjacent partition corresponding to each point cloud partition from each point cloud partition based on the initial non-ground point cloud and the initial ground point cloud of each point cloud partition; a point cloud determination module, configured to determine a target ground point cloud from the initial non-ground point cloud of each point cloud partition according to a distance between the initial non-ground point cloud of each point cloud partition and the initial ground point cloud of the corresponding adjacent partition; An information determination module, configured to determine ground information of the target area based on the target ground point cloud and the initial ground point cloud of each point cloud partition; Among them, the point cloud determination module is also used to: For each point cloud partition, select, from the initial ground point clouds of adjacent partitions corresponding to the point cloud partition, a reference ground point cloud whose distance to the point cloud centroid of the point cloud partition is less than a first distance threshold; Performing plane fitting processing on the reference ground point cloud to obtain a reference fitting plane; According to the distance between the initial non-ground point cloud of the point cloud partition and the reference fitting plane, the initial non-ground point cloud in the point cloud partition whose distance to the reference fitting plane is less than a second distance threshold is used as the target ground point cloud.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images