Three-dimensional point cloud ground identification method and device for ground moving vehicle

Abstract

The invention relates to a point cloud data identification technology, and discloses a three-dimensional point cloud ground identification method for a ground moving vehicle, and the method comprises the steps: obtaining point cloud data generated by the moving vehicle on the ground, and selecting a ground seed point from the point cloud data; selecting point clouds within a preset distance to obtain ground point clouds, and fitting ground information; projecting the point cloud data to a plane perpendicular to the ground according to the ground information, and clustering to obtain a clustered point cloud; calculating a normal vector of each point cloud in the clustered point clouds, and further separating ground point clouds from point cloud data generated by moving a vehicle on the ground according to the normal vectors to obtain refined ground point clouds; and fitting the ground information according to the refined ground point cloud to obtain target ground information, and performing curved surface smooth fitting on the target ground information by using a curved surface fitting algorithm to obtain complete ground information. The invention further provides a three-dimensional point cloud ground recognition device for the ground moving vehicle, electronic equipment and a storage medium. According to the invention, the ground identification precision can be improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of point cloud data recognition, and in particular relates to a three-dimensional point cloud ground recognition method and device for ground moving vehicles. Background Art

[0002] In the navigation of ground mobile vehicles such as autonomous driving and robots, ground segmentation based on point cloud data is a key point. If the points of obstacles cannot be effectively identified, path planning cannot be performed. Traditional point cloud recognition methods usually use a slope threshold-based method, but this method cannot completely remove the ground when the number of radar lines is low, which affects the detection of obstacles and makes the accuracy of ground recognition low. Summary of the invention

[0003] The present invention provides a three-dimensional point cloud ground recognition method and device for ground moving vehicles, which can improve the accuracy of ground recognition.

[0004] To achieve the above object, the present invention provides a three-dimensional point cloud ground recognition method for a ground moving vehicle, comprising:

[0005] Acquire point cloud data generated by a moving vehicle on the ground, and select ground seed points from the point cloud data generated by the moving vehicle on the ground;

[0006] Selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud, and fitting ground information according to the ground point cloud to obtain initial ground information;

[0007] Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud;

[0008] Calculating the normal vector of each point cloud in the clustered point cloud, and further separating the ground point cloud from the point cloud data generated by the moving vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud;

[0009] The target ground information is obtained by fitting the ground information according to the refined ground point cloud, the target ground information is transformed into a world coordinate system, and a preset surface fitting algorithm is used to perform surface smoothing fitting on the target ground information to obtain complete ground information.

[0010] Optionally, selecting ground seed points from the point cloud data generated by the mobile vehicle on the ground includes:

[0011] Fitting the point cloud data into a curved surface, and calculating curvature information of the curved surface;

[0012] identifying a wheel point cloud of the mobile vehicle and a ground point cloud of the ground according to the curvature information;

[0013] The normal vector of the wheel point cloud and the normal vector of the ground point cloud are calculated, and the contact points between the wheel point cloud and the ground point cloud are obtained according to the normal vector of the wheel point cloud and the normal vector of the ground point cloud, and the contact points are used as the ground seed points.

[0014] Optionally, obtaining the contact point between the wheel point cloud and the ground point cloud according to the normal vector of the wheel point cloud and the normal vector of the ground point cloud includes:

[0015] The angle between the normal vector of the wheel point cloud and the normal vector of the ground point cloud is calculated, and the point cloud with the angle of 90 degrees is extracted as the contact point.

[0016] Optionally, the step of selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud includes:

[0017] Calculate a fitted ground surface according to the ground seed points, and transform the fitted ground surface into a global coordinate system;

[0018] A point cloud within a preset distance is selected according to the position of the fitted ground point in the global coordinate system to obtain the ground point cloud.

[0019] Optionally, projecting the point cloud data generated by the moving vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud includes:

[0020] Get the resolution and number of beams of the LiDAR device that collected the point cloud data;

[0021] Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the resolution and the number of line bundles to obtain a projected point cloud;

[0022] The projected point cloud is segmented and clustered using a preset point cloud segmentation and clustering algorithm to obtain the clustered point cloud.

[0023] Optionally, calculating the normal vector of each point cloud in the clustered point cloud includes:

[0024] Using a KD tree algorithm to obtain a K-neighborhood point cloud of each point cloud in the clustered point cloud;

[0025] Calculate the covariance matrix of the K-neighborhood point clouds of each point cloud;

[0026] Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors;

[0027] The eigenvector corresponding to the minimum eigenvalue among the eigenvalues ​​is selected as the normal vector corresponding to each point cloud.

[0028] Optionally, further separating the ground point cloud from the point cloud data generated by the mobile vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud includes:

[0029] Obtain the ground normal vector, calculate the deviation between the normal vector of each point cloud and the ground normal vector, segment the point cloud whose deviation is greater than a preset deviation threshold into a non-ground point cloud, and segment the point cloud whose deviation is not greater than the preset deviation threshold into a refined ground point cloud.

[0030] In order to solve the above problems, the present invention also provides a three-dimensional point cloud ground recognition device for a ground moving vehicle, the device comprising:

[0031] A point cloud data processing module, used to obtain point cloud data generated by a moving vehicle on the ground, and select ground seed points from the point cloud data generated by the moving vehicle on the ground;

[0032] A point cloud data clustering module is used to select point clouds within a preset distance according to the ground seed point to obtain a ground point cloud, and fit ground information according to the ground point cloud to obtain initial ground information; project the point cloud data generated by the moving vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and perform segmentation and clustering processing to obtain a clustered point cloud;

[0033] The ground recognition module is used to calculate the normal vector of each point cloud in the clustered point cloud, and further separate the ground point cloud from the point cloud data generated by the mobile vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud; fit the ground information according to the refined ground point cloud to obtain target ground information, transform the target ground information into a world coordinate system, and use a preset surface fitting algorithm to perform surface smoothing fitting on the target ground information to obtain complete ground information.

[0034] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0035] at least one processor; and,

[0036] a memory communicatively connected to the at least one processor; wherein,

[0037] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned three-dimensional point cloud ground recognition method for ground mobile vehicles.

[0038] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned three-dimensional point cloud ground recognition method for ground mobile vehicles.

[0039] The present invention can solve the problem of selecting initial ground points in point cloud data by selecting ground seed points from point cloud data generated by moving vehicles on the ground, and can improve the initial accuracy of subsequent ground fitting. In addition, the point cloud data generated by the moving vehicle on the ground is projected onto a plane perpendicular to the ground according to the initial ground information and segmented and clustered, which can achieve accurate classification of the point cloud data, and then further separate the ground point cloud from the point cloud data generated by the moving vehicle on the ground according to the normal vector of each point cloud, so that obstacles in contact with the ground can be segmented and the ground point cloud can be further refined, thereby improving the accuracy of ground recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic flow chart of a three-dimensional point cloud ground recognition method for a ground moving vehicle provided by an embodiment of the present invention;

[0041] Figure 2 A functional module diagram of a three-dimensional point cloud ground recognition device for a ground moving vehicle provided by an embodiment of the present invention;

[0042] Figure 3 A schematic structural diagram of an electronic device for implementing a three-dimensional point cloud ground recognition method for a ground moving vehicle provided in one embodiment of the present invention.

[0043] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0045] The embodiment of the present application provides a three-dimensional point cloud ground recognition method for ground mobile vehicles. The execution subject of the three-dimensional point cloud ground recognition method for ground mobile vehicles includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the three-dimensional point cloud ground recognition method for ground mobile vehicles can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0046] Reference Figure 1 FIG. 1 is a flow chart of a three-dimensional point cloud ground recognition method for a ground moving vehicle provided by an embodiment of the present invention. In this embodiment, the three-dimensional point cloud ground recognition method for a ground moving vehicle includes:

[0047] S1. Acquire point cloud data generated by a moving vehicle on the ground, and select ground seed points from the point cloud data generated by the moving vehicle on the ground.

[0048] In the embodiment of the present invention, the point cloud data generated by the vehicle moving on the ground refers to the point cloud data of the vehicle moving on the ground collected by a laser radar device.

[0049] As an embodiment of the present invention, the step of selecting ground seed points from the point cloud data generated by the moving vehicle on the ground includes:

[0050] Fitting the point cloud data into a curved surface, and calculating curvature information of the curved surface;

[0051] identifying a wheel point cloud of the mobile vehicle and a ground point cloud of the ground according to the curvature information;

[0052] The normal vector of the wheel point cloud and the normal vector of the ground point cloud are calculated, and the contact points between the wheel point cloud and the ground point cloud are obtained according to the normal vector of the wheel point cloud and the normal vector of the ground point cloud, and the contact points are used as the ground seed points.

[0053] In the embodiment of the present invention, the curvature information of the curved surface refers to a physical quantity that describes the degree of curvature of the curved surface.

[0054] Further, obtaining the contact point between the wheel point cloud and the ground point cloud according to the normal vector of the wheel point cloud and the normal vector of the ground point cloud includes:

[0055] The angle between the normal vector of the wheel point cloud and the normal vector of the ground point cloud is calculated, and the point cloud with the angle of 90 degrees is extracted as the contact point.

[0056] S2. Selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud, and fitting ground information according to the ground point cloud to obtain initial ground information.

[0057] In the embodiment of the present invention, the preset distance refers to a preset distance threshold, and within this distance threshold it means that the correlation of the point clouds is high.

[0058] As an embodiment of the present invention, the step of selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud includes:

[0059] Calculate a fitted ground according to the ground seed points, and transform the fitted ground into a global coordinate system;

[0060] A point cloud within a preset distance is selected according to the position of the fitted ground in the global coordinate system to obtain the ground point cloud.

[0061] In the embodiment of the present invention, the global coordinate system is a coordinate reference system used to define the positions of all points in space.

[0062] In the embodiment of the present invention, the distance between the point cloud and the seed point on the ground can be calculated using the Euclidean distance.

[0063] S3. Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud.

[0064] As an embodiment of the present invention, projecting the point cloud data generated by the moving vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud includes:

[0065] Get the resolution and number of beams of the LiDAR device that collected the point cloud data;

[0066] Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the resolution and the number of line bundles to obtain a projected point cloud;

[0067] The projected point cloud is segmented and clustered using a preset point cloud segmentation and clustering algorithm to obtain the clustered point cloud.

[0068] In an embodiment of the present invention, the preset point cloud segmentation and clustering algorithm may adopt a point cloud clustering algorithm based on a depth map.

[0069] In the embodiment of the present invention, in order to prevent noise interference such as leaves, points with less than 30 points in the cluster point cloud are removed.

[0070] S4. Calculate the normal vector of each point cloud in the clustered point cloud, and further separate the ground point cloud from the point cloud data generated by the moving vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud.

[0071] As an embodiment of the present invention, the calculating of the normal vector of each point cloud in the clustered point cloud includes:

[0072] Using a KD tree algorithm to obtain a K-neighborhood point cloud of each point cloud in the clustered point cloud;

[0073] Calculate the covariance matrix of the K-neighborhood point clouds of each point cloud;

[0074] Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors;

[0075] The eigenvector corresponding to the minimum eigenvalue among the eigenvalues ​​is selected as the normal vector corresponding to each point cloud.

[0076] In an embodiment of the present invention, the KD tree algorithm is a data structure similar to a binary search tree for organizing points in a k-dimensional space. The KD tree is constructed by recursively dividing the space into two sub-areas, each of which is based on the median of the current dimension, and is suitable for processing point cloud data in high-dimensional space.

[0077] The embodiment of the present invention calculates the normal vector of the clustered point cloud in order to segment the point cloud more finely, especially to segment obstacles connected to the ground, such as curbs. Such obstacles are connected to the ground and are difficult to cluster directly, but the normal vector of such point cloud generally has a mutation, and such point cloud can be segmented according to the point cloud normal vector.

[0078] S5. Fitting ground information according to the refined ground point cloud to obtain target ground information, transforming the target ground information into a world coordinate system, and performing surface smoothing fitting on the target ground information using a preset surface fitting algorithm to obtain complete ground information.

[0079] The present invention can solve the problem of selecting initial ground points in point cloud data by selecting ground seed points from point cloud data generated by moving vehicles on the ground, and can improve the initial accuracy of subsequent ground fitting. In addition, the point cloud data generated by the moving vehicle on the ground is projected onto a plane perpendicular to the ground according to the initial ground information and segmented and clustered, which can achieve accurate classification of the point cloud data, and then further separate the ground point cloud from the point cloud data generated by the moving vehicle on the ground according to the normal vector of each point cloud, so that obstacles in contact with the ground can be segmented and the ground point cloud can be further refined, thereby improving the accuracy of ground recognition.

[0080] like Figure 2 1 is a functional module diagram of a three-dimensional point cloud ground recognition device for a ground mobile vehicle provided by an embodiment of the present invention.

[0081] The three-dimensional point cloud ground recognition device 100 for ground moving vehicles of the present invention can be installed in an electronic device. According to the functions to be implemented, the three-dimensional point cloud ground recognition device 100 for ground moving vehicles can include a point cloud data processing module 101, a point cloud data clustering module 102 and a ground recognition module 103.

[0082] The module described in the present invention may also be referred to as a unit, which refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and is stored in a memory of the electronic device.

[0083] In this embodiment, the functions of each module / unit are as follows:

[0084] The point cloud data processing module 101 is used to obtain point cloud data generated by a moving vehicle on the ground, and select ground seed points from the point cloud data generated by the moving vehicle on the ground.

[0085] In the embodiment of the present invention, the point cloud data generated by the vehicle moving on the ground refers to the point cloud data of the vehicle moving on the ground collected by a laser radar device.

[0086] As an embodiment of the present invention, the step of selecting ground seed points from the point cloud data generated by the moving vehicle on the ground includes:

[0087] Fitting the point cloud data into a curved surface, and calculating curvature information of the curved surface;

[0088] identifying a wheel point cloud of the mobile vehicle and a ground point cloud of the ground according to the curvature information;

[0089] The normal vector of the wheel point cloud and the normal vector of the ground point cloud are calculated, and the contact points between the wheel point cloud and the ground point cloud are obtained according to the normal vector of the wheel point cloud and the normal vector of the ground point cloud, and the contact points are used as the ground seed points.

[0090] In the embodiment of the present invention, the curvature information of the curved surface refers to a physical quantity that describes the degree of curvature of the curved surface.

[0091] Further, obtaining the contact point between the wheel point cloud and the ground point cloud according to the normal vector of the wheel point cloud and the normal vector of the ground point cloud includes:

[0092] The angle between the normal vector of the wheel point cloud and the normal vector of the ground point cloud is calculated, and the point cloud with the angle of 90 degrees is extracted as the contact point.

[0093] The point cloud data clustering module 102 is used to select point clouds within a preset distance based on the ground seed point to obtain a ground point cloud, and fit ground information based on the ground point cloud to obtain initial ground information; based on the initial ground information, the point cloud data generated by the moving vehicle on the ground is projected onto a plane perpendicular to the ground and segmented and clustered to obtain a clustered point cloud.

[0094] In the embodiment of the present invention, the preset distance refers to a preset distance threshold, and within this distance threshold it means that the correlation of the point clouds is high.

[0095] As an embodiment of the present invention, the step of selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud includes:

[0096] Calculate a fitted ground according to the ground seed points, and transform the fitted ground into a global coordinate system;

[0097] A point cloud within a preset distance is selected according to the position of the fitted ground in the global coordinate system to obtain the ground point cloud.

[0098] In the embodiment of the present invention, the global coordinate system is a coordinate reference system used to define the positions of all points in space.

[0099] In the embodiment of the present invention, the distance between the point cloud and the seed point on the ground can be calculated using the Euclidean distance.

[0100] As an embodiment of the present invention, projecting the point cloud data generated by the moving vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud includes:

[0101] Get the resolution and number of beams of the LiDAR device that collected the point cloud data;

[0102] Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the resolution and the number of line bundles to obtain a projected point cloud;

[0103] The projected point cloud is segmented and clustered using a preset point cloud segmentation and clustering algorithm to obtain the clustered point cloud.

[0104] In an embodiment of the present invention, the preset point cloud segmentation and clustering algorithm may adopt a point cloud clustering algorithm based on a depth map.

[0105] In the embodiment of the present invention, in order to prevent noise interference such as leaves, points with less than 30 points in the cluster point cloud are removed.

[0106] The ground recognition module 103 is used to calculate the normal vector of each point cloud in the clustered point cloud, and further separate the ground point cloud from the point cloud data generated by the mobile vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud; fit the ground information according to the refined ground point cloud to obtain target ground information, transform the target ground information into a world coordinate system, and use a preset surface fitting algorithm to perform surface smoothing fitting on the target ground information to obtain complete ground information.

[0107] As an embodiment of the present invention, the calculating of the normal vector of each point cloud in the clustered point cloud includes:

[0108] Using a KD tree algorithm to obtain a K-neighborhood point cloud of each point cloud in the clustered point cloud;

[0109] Calculate the covariance matrix of the K-neighborhood point clouds of each point cloud;

[0110] Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors;

[0111] The eigenvector corresponding to the minimum eigenvalue among the eigenvalues ​​is selected as the normal vector corresponding to each point cloud.

[0112] In an embodiment of the present invention, the KD tree algorithm is a data structure similar to a binary search tree for organizing points in a k-dimensional space. The KD tree is constructed by recursively dividing the space into two sub-areas, each of which is based on the median of the current dimension, and is suitable for processing point cloud data in high-dimensional space.

[0113] The embodiment of the present invention calculates the normal vector of the clustered point cloud in order to segment the point cloud more finely, especially to segment obstacles connected to the ground, such as curbs. Such obstacles are connected to the ground and are difficult to cluster directly, but the normal vector of such point cloud generally has a mutation, and such point cloud can be segmented according to the point cloud normal vector.

[0114] The target ground information is obtained by fitting the ground information according to the refined ground point cloud, the target ground information is transformed into a world coordinate system, and a preset surface fitting algorithm is used to perform surface smoothing fitting on the target ground information to obtain complete ground information.

[0115] like Figure 3 , is a schematic diagram of the structure of an electronic device for implementing a three-dimensional point cloud ground recognition method for a ground mobile vehicle provided by an embodiment of the present invention.

[0116] The electronic device may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a three-dimensional point cloud ground recognition method program for ground mobile vehicles.

[0117] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, executing a three-dimensional point cloud ground recognition method program for ground mobile vehicles, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device and process data.

[0118] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as a code of a three-dimensional point cloud ground recognition method program for a ground mobile vehicle, but can also be used to temporarily store data that has been output or is to be output.

[0119] The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0120] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0121] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3The structure shown does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0122] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0123] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0124] The memory 11 in the electronic device stores a three-dimensional point cloud ground recognition method program for a ground moving vehicle, which is a combination of multiple instructions. When running in the processor 10, the following can be achieved:

[0125] Acquire point cloud data generated by a moving vehicle on the ground, and select ground seed points from the point cloud data generated by the moving vehicle on the ground;

[0126] Selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud, and fitting ground information according to the ground point cloud to obtain initial ground information;

[0127] Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud;

[0128] Calculating the normal vector of each point cloud in the clustered point cloud, and further separating the ground point cloud from the point cloud data generated by the moving vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud;

[0129] The target ground information is obtained by fitting the ground information according to the refined ground point cloud, the target ground information is transformed into a world coordinate system, and a preset surface fitting algorithm is used to perform surface smoothing fitting on the target ground information to obtain complete ground information.

[0130] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0131] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0132] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0133] Acquire point cloud data generated by a moving vehicle on the ground, and select ground seed points from the point cloud data generated by the moving vehicle on the ground;

[0134] Selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud, and fitting ground information according to the ground point cloud to obtain initial ground information;

[0135] Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud;

[0136] Calculating the normal vector of each point cloud in the clustered point cloud, and further separating the ground point cloud from the point cloud data generated by the moving vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud;

[0137] The target ground information is obtained by fitting the ground information according to the refined ground point cloud, the target ground information is transformed into a world coordinate system, and a preset surface fitting algorithm is used to perform surface smoothing fitting on the target ground information to obtain complete ground information.

[0138] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0139] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0141] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0142] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0143] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0144] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0145] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A three-dimensional point cloud ground recognition method for ground moving vehicles, characterized in that: The method comprises: Acquire point cloud data generated by a moving vehicle on the ground, and select ground seed points from the point cloud data generated by the moving vehicle on the ground; Selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud, and fitting ground information according to the ground point cloud to obtain initial ground information; Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud; Calculating the normal vector of each point cloud in the clustered point cloud, and further separating the ground point cloud from the point cloud data generated by the moving vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud; The target ground information is obtained by fitting the ground information according to the refined ground point cloud, the target ground information is transformed into a world coordinate system, and a preset surface fitting algorithm is used to perform surface smoothing fitting on the target ground information to obtain complete ground information.

2. The three-dimensional point cloud ground recognition method for ground moving vehicles according to claim 1, characterized in that: The selecting of ground seed points from the point cloud data generated by the mobile vehicle on the ground comprises: Fitting the point cloud data into a curved surface, and calculating curvature information of the curved surface; identifying a wheel point cloud of the mobile vehicle and a ground point cloud of the ground according to the curvature information; The normal vector of the wheel point cloud and the normal vector of the ground point cloud are calculated, and the contact points between the wheel point cloud and the ground point cloud are obtained according to the normal vector of the wheel point cloud and the normal vector of the ground point cloud, and the contact points are used as the ground seed points.

3. The three-dimensional point cloud ground recognition method for ground moving vehicles according to claim 2, characterized in that: The step of obtaining the contact point between the wheel point cloud and the ground point cloud according to the normal vector of the wheel point cloud and the normal vector of the ground point cloud comprises: The angle between the normal vector of the wheel point cloud and the normal vector of the ground point cloud is calculated, and the point cloud with the angle of 90 degrees is extracted as the contact point.

4. The three-dimensional point cloud ground recognition method for ground moving vehicles according to claim 1, 2 or 3, characterized in that: The step of selecting a point cloud within a preset distance according to the ground seed point to obtain a ground point cloud comprises: Calculate a fitted ground according to the ground seed points, and transform the fitted ground into a global coordinate system; A point cloud within a preset distance is selected according to the position of the fitted ground point in the global coordinate system to obtain the ground point cloud.

5. The three-dimensional point cloud ground recognition method for ground moving vehicles according to claim 1, characterized in that: The step of projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and performing segmentation and clustering processing to obtain a clustered point cloud includes: Get the resolution and number of beams of the LiDAR device that collected the point cloud data; Projecting the point cloud data generated by the mobile vehicle on the ground onto a plane perpendicular to the ground according to the resolution and the number of line bundles to obtain a projected point cloud; The projected point cloud is segmented and clustered using a preset point cloud segmentation and clustering algorithm to obtain the clustered point cloud.

6. The three-dimensional point cloud ground recognition method for ground moving vehicles according to claim 1, characterized in that: The calculating the normal vector of each point cloud in the clustered point cloud comprises: Using a KD tree algorithm to obtain a K-neighborhood point cloud of each point cloud in the clustered point cloud; Calculate the covariance matrix of the K-neighborhood point clouds of each point cloud; Performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors; The eigenvector corresponding to the minimum eigenvalue among the eigenvalues ​​is selected as the normal vector corresponding to each point cloud.

7. The three-dimensional point cloud ground recognition method for ground moving vehicles according to claim 1, characterized in that: The further separating the ground point cloud from the point cloud data generated by the mobile vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud includes: Obtain the ground normal vector, calculate the deviation between the normal vector of each point cloud and the ground normal vector, segment the point cloud whose deviation is greater than a preset deviation threshold into a non-ground point cloud, and segment the point cloud whose deviation is not greater than the preset deviation threshold into a refined ground point cloud.

8. A three-dimensional point cloud ground recognition device for ground moving vehicles, characterized in that: The device can implement the three-dimensional point cloud ground recognition method for a ground moving vehicle as claimed in any one of claims 1 to 7, and the device comprises: A point cloud data processing module, used to obtain point cloud data generated by a moving vehicle on the ground, and select ground seed points from the point cloud data generated by the moving vehicle on the ground; A point cloud data clustering module is used to select point clouds within a preset distance according to the ground seed point to obtain a ground point cloud, and fit ground information according to the ground point cloud to obtain initial ground information; project the point cloud data generated by the moving vehicle on the ground onto a plane perpendicular to the ground according to the initial ground information and perform segmentation and clustering processing to obtain a clustered point cloud; The ground recognition module is used to calculate the normal vector of each point cloud in the clustered point cloud, and further separate the ground point cloud from the point cloud data generated by the mobile vehicle on the ground according to the normal vector of each point cloud to obtain a refined ground point cloud; fit the ground information according to the refined ground point cloud to obtain target ground information, transform the target ground information into a world coordinate system, and use a preset surface fitting algorithm to perform surface smoothing fitting on the target ground information to obtain complete ground information.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the three-dimensional point cloud ground recognition method for a ground mobile vehicle as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the three-dimensional point cloud ground recognition method for a ground mobile vehicle as described in any one of claims 1 to 7 is implemented.

Images