Method, device and equipment for automatically filtering shielded ground element labels based on point cloud and storage medium

Abstract

The invention discloses an automatic shielded ground element label filtering method based on point cloud. The method comprises the following steps: acquiring self-vehicle attitude information of a vehicle; converting local map elements from a world coordinate system to a self-vehicle coordinate system according to the self-vehicle attitude information; based on the self-vehicle attitude information, filtering and cutting off the local map elements according to a preset self-vehicle sensing distance; acquiring point cloud data collected by the vehicle, and converting the point cloud data from a point cloud coordinate system to an own vehicle coordinate system, so that the point cloud data and the local map elements are aligned in the same coordinate system; expanding a local map element into a polygon, and detecting the number of point cloud data in the polygon; if the number of the point cloud data in the polygon is smaller than a preset threshold value, it is judged that the local map elements are shielded ground element labels, and the shielded ground element labels are filtered. The method can automatically filter the shielded ground element labels, and has higher accuracy and reliability.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly to an automatic filtering method, device, equipment and storage medium for occluded ground feature labels based on point cloud. Background Art

[0002] In the rapid development of autonomous driving technology, the accuracy and integrity of ground feature labels are crucial for the vehicle's perception and decision-making systems. These labels include lane lines, crosswalks, road boundary lines, stop lines, and ground arrows, etc., providing key environmental information for autonomous driving vehicles to assist in path planning, obstacle detection, and safe driving. However, there is a significant problem in the existing production method of ground feature labels: a large number of occluded ground feature labels are included in the generated labels. These occluded ground feature labels have no corresponding visual cues in multi-view images, which will have a negative impact on the training of the model, and then reduce the detection effect of the online vector map reconstruction model. In addition, manually filtering these occluded ground feature labels is not only time-consuming and laborious, but also further increases the production cost of ground feature labels. Therefore, automatically filtering occluded ground feature labels has become an important topic in the autonomous driving perception module.

[0003] Existing filtering methods usually adopt simple geometric or statistical methods, such as threshold judgment based on point cloud density. These methods have poor effects when dealing with complex scenarios and cannot accurately distinguish visible and occluded ground features. For example, simple point cloud density threshold judgment may fail in the case of sparse point clouds, resulting in misjudgment. On the other hand, existing filtering methods are mainly applied to specific scenarios, such as flat roads or simple occlusion situations. In complex scenarios, such as multi-layer occlusion, dynamic occlusion, or irregular occlusion, the effects of these methods are greatly reduced.

[0004] In summary, automatically filtering invisible ground feature labels is of great significance and necessity in autonomous driving technology. However, the existing filtering technologies cannot meet the requirements of autonomous driving for high-precision ground feature labels, and the accuracy and reliability of their filtering need to be further improved. Summary of the Invention

[0005] The purpose of the present invention is to solve the above technical problems and provide an automatic filtering method, device, equipment and storage medium for occluded ground feature labels based on point cloud, which has higher accuracy and reliability.

[0006] To solve the above problems, the present invention is implemented according to the following technical solutions:

[0007] In the first aspect, the present invention provides an automatic filtering method for occluded ground feature labels based on point cloud, and the method includes the following steps:

[0008] S100. Obtain the ego-vehicle pose information of the vehicle, where the ego-vehicle pose information includes the position and pose angle of the vehicle;

[0009] S200. According to the ego-vehicle pose information, transform the local map elements from the world coordinate system to the ego-vehicle coordinate system, where the local map elements include polyline map elements and polygon map elements;

[0010] S300. Based on the ego-vehicle pose information, filter and truncate the local map elements according to a preset ego-vehicle perception distance;

[0011] S400. Obtain the point cloud data collected by the vehicle, and transform the point cloud data from the point cloud coordinate system to the ego-vehicle coordinate system so that the point cloud data is aligned with the local map elements in the same coordinate system;

[0012] S500. Expand the local map elements into polyhedrons, and detect the number of point cloud data within the polyhedrons;

[0013] S600. If the number of point cloud data within the polyhedron is less than a preset threshold, determine that the local map element is an occluded ground element label, and filter the occluded ground element label.

[0014] Preferably, in step S300, the preset ego-vehicle perception distance extends 60 meters forward and backward, and 30 meters left and right with the center of the vehicle as the reference.

[0015] Preferably, the specific process of step S500 includes: expanding the polyline map element along the three coordinate axes of the ego-vehicle coordinate system by a preset polyline distance to form a first polyhedron, and detecting the number of point cloud data within the first polyhedron.

[0016] Preferably, the preset polyline distance is 0.2 meters.

[0017] Preferably, the specific process of step S500 further includes: expanding the polygon map element along the Z-axis direction of the ego-vehicle coordinate system by a preset polygon distance to form a second polyhedron, and detecting the number of point cloud data within the second polyhedron.

[0018] Preferably, the preset polygon distance is 0.2 meters.

[0019] Preferably, the specific process of step S600 includes: when the number of point cloud data in the first polyhedron is less than 200, determining that the polyline map element is a first occluded ground element label and filtering the first occluded ground element label; when the number of point cloud data in the second polyhedron is less than 20, determining that the polygon map element is a second occluded ground element label and filtering the second occluded ground element label.

[0020] In a second aspect, an automatic filtering device for occluded ground element labels based on point clouds is configured to execute the automatic filtering method for occluded ground element labels based on point clouds. The automatic filtering device for occluded ground element labels based on point clouds includes:

[0021] A self-vehicle attitude information acquisition module for acquiring the self-vehicle attitude information of the vehicle, where the self-vehicle attitude information includes the position and attitude angle of the vehicle;

[0022] A local map element coordinate system conversion module for converting local map elements from the world coordinate system to the self-vehicle coordinate system according to the self-vehicle attitude information, where the local map elements include polyline map elements and polygon map elements;

[0023] A local map element filtering and truncating module for filtering and truncating the local map elements based on the self-vehicle attitude information according to a preset self-vehicle perception distance;

[0024] A point cloud data coordinate system conversion module for acquiring the point cloud data collected by the vehicle and converting the point cloud data from the point cloud coordinate system to the self-vehicle coordinate system so that the point cloud data is aligned with the local map elements in the same coordinate system;

[0025] A local map element expansion module for expanding the local map elements into polyhedrons and detecting the number of point cloud data in the polyhedrons;

[0026] An occluded ground element label determination module for determining that the local map element is an occluded ground element label and filtering the occluded ground element label when the number of point cloud data in the polyhedron is less than a preset threshold.

[0027] In a third aspect, the present invention further provides an electronic device, which includes:

[0028] At least one processor; and a memory communicatively connected to the at least one processor;

[0029] Among them, the memory stores a computer program executable by the at least one processor, and the computer program is

[0030] executed by the at least one processor, so that the at least one processor can execute a method for automatically filtering occluded ground feature labels based on point cloud according to any one of claims 1 to 7.

[0031] Fourthly, the present invention further provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program,

[0032] and the computer program is used to implement a method for automatically filtering occluded ground feature labels based on point cloud according to any one of claims 1 to 7 when executed by a processor.

[0033] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0034] The present invention provides a method for automatically filtering occluded ground feature labels based on point cloud. First of all, the present invention realizes the accurate conversion of local map elements from the world coordinate system to the ego-vehicle coordinate system by combining the ego-vehicle attitude information of the vehicle and high-precision map data. This process not only ensures the consistency between the map elements and the current attitude of the vehicle, but also provides a solid foundation for subsequent point cloud data fusion and processing. Secondly, in the processing of point cloud data, the present invention aligns the point cloud data with local map elements and detects the number of point cloud data by expanding the polyhedron to judge whether the ground elements are occluded. Compared with the traditional simple threshold judgment based on point cloud density, this method can more accurately identify occluded ground elements, especially in complex scenarios such as multi-layer occlusion, dynamic occlusion or irregular occlusion, and its advantages are more obvious. Furthermore, the present invention filters and truncates local map elements through a preset ego-vehicle perception distance. This operation effectively reduces unnecessary computational amount, improves the processing efficiency of the system, and also makes the filtering process more targeted and adaptable. In addition, the present invention also sets different preset thresholds to distinguish multi-segment line map elements and polygon map elements. This differential processing further improves the filtering accuracy and can better adapt to the characteristics of different types of ground elements. Description of the Drawings

[0035] The following further elaborates in detail the specific embodiments of the present invention with reference to the drawings, where:

[0036] Figure 1 is a technical flowchart of a method for automatically filtering occluded ground feature labels based on point cloud according to an embodiment of the present invention;

[0037] Figure 2It is a module diagram of an automatic filtering device for occluded ground feature labels based on point cloud according to an embodiment of the present invention;

[0038] Figure 3 It is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Detailed implementation manners

[0039] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0040] The terms used in this application are only for the purpose of describing specific embodiments, and are not intended to limit this application. Unless otherwise defined, the technical terms or scientific terms used in this specification should be understood in the ordinary sense by those of ordinary skill in the art to which this application belongs. The "first", "second" and similar terms used in this specification and the claims do not denote any order, quantity or importance, but are only used to distinguish different technical features.

[0041] The following describes the preferred embodiments of the present invention in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0042] Refer to Figure 1 , an embodiment of the present invention provides a schematic flowchart of a method for automatically filtering occluded ground feature labels based on point cloud. This method can be executed by an automatic filtering device for occluded ground feature labels based on point cloud. This device can be implemented in the form of hardware and / or software, and this device can be configured in a computer. As Figure 1 shown, it includes the following steps:

[0043] S100. Obtain the ego-vehicle pose information of the vehicle, where the ego-vehicle pose information includes the position and pose angle of the vehicle.

[0044] It should be noted that the position of the vehicle (such as longitude, latitude, altitude, etc.) and the pose angle (such as yaw angle, pitch angle, roll angle, etc.) are usually provided by the inertial measurement unit (IMU) and the global positioning system (GPS) of the vehicle.

[0045] In the present invention, obtaining the ego-vehicle attitude information of the vehicle is the basis for realizing subsequent coordinate transformation and alignment of map elements, ensuring the consistency between the map elements and the current attitude and position of the vehicle. By accurately obtaining the real-time attitude of the vehicle, a reliable benchmark can be provided for subsequent coordinate transformation and data fusion, thereby improving the accuracy and reliability of the entire system. The advantage of this step is to improve the adaptability and flexibility of the system, enabling it to respond to the dynamic changes of the vehicle in real time and ensuring the accuracy of subsequent processing.

[0046] S200. According to the ego-vehicle attitude information, transform the local map elements from the world coordinate system to the ego-vehicle coordinate system, where the local map elements include polyline map elements and polygon map elements.

[0047] It should be noted that the local map elements refer to the map elements related to the vehicle's surrounding environment extracted from the high-precision map, including polyline map elements (such as lane lines, road boundary lines, stop lines) and polygon map elements (such as crosswalks, ground arrows). The world coordinate system is a global coordinate system with the earth as the reference. The ego-vehicle coordinate system is a local coordinate system centered on the vehicle, used to describe the relative positions of the vehicle's surrounding environment.

[0048] In the present invention, transforming the local map elements from the world coordinate system to the ego-vehicle coordinate system is to align the map elements in the high-precision map with the current attitude and position of the vehicle. This process is achieved through a coordinate transformation matrix, ensuring the accurate relative position relationship between the map elements and the vehicle. Through this transformation, the system can more effectively process the map information related to the vehicle, reduce the errors caused by inconsistent coordinate systems, and improve the efficiency and accuracy of subsequent processing.

[0049] S300. Based on the ego-vehicle attitude information, filter and truncate the local map elements according to a preset ego-vehicle perception distance.

[0050] In the present invention, filtering and truncating the local map elements based on the ego-vehicle attitude information according to a preset ego-vehicle perception distance aims to reduce the processing range and improve the calculation efficiency. Through this operation, the system can focus on the map elements within the vehicle's perception range and avoid processing information irrelevant to the current vehicle. This step not only reduces unnecessary computational load but also improves the system's response speed and resource utilization efficiency, enabling the system to process real-time data more efficiently.

[0051] In a preferred embodiment, the preset ego-vehicle perception distance extends 60 meters forward and backward and 30 meters left and right with the center of the vehicle as the reference.

[0052] S400. Obtain the point cloud data collected by the vehicle and transform the point cloud data from the point cloud coordinate system to the ego-vehicle coordinate system, so that the point cloud data is aligned with the local map features in the same coordinate system.

[0053] It should be noted that the point cloud data is three-dimensional point data obtained by a lidar sensor and is used to describe the geometric shape of the vehicle's surrounding environment. The point cloud coordinate system is a coordinate system centered on the lidar and is used to describe the original position of the point cloud data.

[0054] In the present invention, obtaining the point cloud data collected by the vehicle and transforming it from the point cloud coordinate system to the ego-vehicle coordinate system is to achieve the precise alignment of the point cloud data with the local map features. By transforming the point cloud data to the ego-vehicle coordinate system, the system can process the point cloud data and the local map features in the same coordinate system, thereby providing a unified framework for subsequent geometric relationship analysis. This step ensures the accuracy and reliability of data fusion and improves the overall performance of the system.

[0055] S500. Expand the local map features into a polyhedron and detect the number of point cloud data within the polyhedron.

[0056] It should be noted that a polyhedron refers to a geometric body formed by expanding a certain distance around the local map features and is used to detect the distribution of point cloud data.

[0057] Specifically, S510. Expand the polyline map feature along the three coordinate axes of the ego-vehicle coordinate system by a preset polyline distance to form a first polyhedron, and detect the number of point cloud data within the first polyhedron.

[0058] It should be noted that the "preset polyline distance" refers to a fixed expansion distance set to detect whether the polyline map feature is occluded when processing the polyline map feature. Specifically, it is the fixed distance by which the polyline map feature expands outward along the three coordinate axes of the ego-vehicle coordinate system to form a three-dimensional polyhedron, and then the number of point cloud data within the polyhedron is detected.

[0059] In a preferred embodiment, the preset polyline distance is 0.2 meters.

[0060] Specifically, S520. Expand the polygon map feature along the Z-axis direction of the ego-vehicle coordinate system by a preset polygon distance to form a second polyhedron, and detect the number of point cloud data within the second polyhedron.

[0061] It should be noted that the "preset polygon distance" refers to a fixed expansion distance set to detect whether a polygon map feature is occluded when processing polygon map features. Specifically, it is the fixed distance that the polygon map feature expands outward in the Z-axis direction of the ego-vehicle coordinate system, used to form a three-dimensional polyhedron, and then detect the number of point cloud data within the polyhedron.

[0062] In the present invention, by detecting the number of point cloud data within these polyhedrons, the system can accurately determine whether the map feature is occluded. This step can effectively identify occluded ground features, especially in complex scenarios such as multi-layer occlusion, dynamic occlusion, or irregular occlusion, where its advantages are more obvious, significantly improving the accuracy and reliability of filtering.

[0063] In a preferred embodiment, the preset polygon distance is 0.2 meters.

[0064] S600. If the number of point cloud data within the polyhedron is less than the preset threshold, determine that the local map feature is an occluded ground feature label and filter the occluded ground feature label.

[0065] Specifically, S610. If the number of point cloud data within the first polyhedron is less than 200, determine that the polyline map feature is a first occluded ground feature label and filter the first occluded ground feature label;

[0066] Specifically, S620. If the number of point cloud data within the second polyhedron is less than 20, determine that the polygon map feature is a second occluded ground feature label and filter the second occluded ground feature label.

[0067] In the present invention, by setting a reasonable threshold, visible and invisible ground features can be accurately distinguished, thereby realizing the automatic filtering of invisible labels. This method not only improves the filtering accuracy of the system, but also reduces the need for manual intervention, lowers production costs, and provides a strong guarantee for the safety and stability of the autonomous driving system.

[0068] In a specific embodiment, the implementation process is as follows:

[0069] Suppose an autonomous driving vehicle is driving on an urban road, and the vehicle is equipped with a lidar and a high-precision map system. The vehicle's inertial measurement unit (IMU) and global positioning system (GPS) provide the vehicle's ego-vehicle pose information in real time, including the vehicle's position and attitude angle.

[0070] First, according to these ego-vehicle pose information, the local map elements (such as lane lines, crosswalks, etc.) extracted from the high-precision map are transformed from the world coordinate system to the ego-vehicle coordinate system. Then, based on the preset ego-vehicle perception distance (60 meters forward and backward, 30 meters left and right), the local map elements are filtered and truncated to reduce unnecessary computational workload. Subsequently, the point cloud data collected by the vehicle's lidar is obtained, and the point cloud data is transformed from the point cloud coordinate system to the ego-vehicle coordinate system to ensure that the point cloud data is aligned with the local map elements in the same coordinate system. After that, the polyline map elements are extended along the three coordinate axes of the ego-vehicle coordinate system by a preset polyline distance (0.2 meters) to form a first polyhedron, and the number of point cloud data within this polyhedron is detected. Similarly, the polygon map elements are extended along the Z-axis direction of the ego-vehicle coordinate system by a preset polygon distance (0.2 meters) to form a second polyhedron, and the number of point cloud data within this polyhedron is detected. Finally, when the number of point cloud data within the first polyhedron is less than the preset threshold (200), it is determined that this polyline map element is an occluded ground element label, and this occluded ground element label is filtered; similarly, when the number of point cloud data within the second polyhedron is less than the preset threshold (20), it is determined that this polygon map element is an occluded ground element label, and this occluded ground element label is filtered. Through this series of steps, the system can automatically identify and filter out the occluded ground element labels, thereby improving the safety and reliability of the autonomous driving system.

[0071] As Figure 2 shown, an automatic filtering device for occluded ground element labels based on point cloud according to the present invention includes:

[0072] An ego-vehicle pose information acquisition module, which is used to acquire the ego-vehicle pose information of the vehicle, and the ego-vehicle pose information includes the position and attitude angle of the vehicle;

[0073] A local map element coordinate system transformation module, which is used to transform the local map elements from the world coordinate system to the ego-vehicle coordinate system according to the ego-vehicle pose information, and the local map elements include polyline map elements and polygon map elements;

[0074] A local map element filtering and truncating module, which is used to filter and truncate the local map elements based on the ego-vehicle pose information according to the preset ego-vehicle perception distance;

[0075] A point cloud data coordinate system transformation module, which is used to acquire the point cloud data collected by the vehicle and transform the point cloud data from the point cloud coordinate system to the ego-vehicle coordinate system so that the point cloud data is aligned with the local map elements in the same coordinate system;

[0076] The local map element expansion module is used to expand the local map element into a polyhedron and detect the number of point cloud data within the polyhedron;

[0077] The occluded ground element label determination module is used to determine that the local map element is an occluded ground element label and filter the occluded ground element label if the number of point cloud data within the polyhedron is less than a preset threshold.

[0078] Figure 3 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0079] As Figure 3 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0080] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0081] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as solving an automatic filtering method for occluded ground feature labels based on point clouds.

[0082] In some embodiments, an automatic filtering method for occluded ground feature labels based on point clouds may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the automatic filtering method for occluded ground feature labels based on point clouds described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute an automatic filtering method for occluded ground feature labels based on point clouds in any other suitable manner (e.g., by means of firmware).

[0083] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0084] A computer program for implementing the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer program may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0085] In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0086] In order to provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0087] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0088] The computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client - server relationship is created by computer programs that run on respective computers and have a client - server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0089] An embodiment of the present invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements an automatic filtering method for occluded ground feature labels based on point clouds as provided in the embodiment of the present invention.

[0090] In the process of implementing the computer program product, computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object - oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user computer, partially on the user computer, executed as a stand - alone software package, partially on the user computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user computer through any type of network - including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., by connecting through an Internet service provider via the Internet).

[0091] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0092] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for automatically filtering labels of obscured ground features based on point cloud, characterized in that: The method comprises the following steps: S100, obtaining vehicle posture information of the vehicle, wherein the vehicle posture information includes the position and posture angle of the vehicle; S200, converting local map elements from a world coordinate system to a vehicle coordinate system according to the vehicle posture information, the local map elements including polyline map elements and polygonal map elements; S300, filtering and truncating the local map elements based on the self-vehicle posture information and according to a preset self-vehicle perception distance; S400, acquiring point cloud data collected by the vehicle, and converting the point cloud data from a point cloud coordinate system to a vehicle coordinate system, so that the point cloud data and the local map elements are aligned in the same coordinate system; S500, expanding the local map element into a polygon, and detecting the number of point cloud data in the polygon; S600: If the number of point cloud data in the polygon is less than a preset threshold, determine that the local map element is an obscured ground element label, and filter the obscured ground element label.

2. The method for automatically filtering labels of obscured ground elements based on point cloud according to claim 1, characterized in that: In step S300, the preset vehicle sensing distance is based on the center of the vehicle, extending 60 meters forward and backward, and 30 meters left and right.

3. The method for automatically filtering labels of obscured ground elements based on point cloud according to claim 1, characterized in that: The specific process of step S500 includes: The polyline map element is expanded into a first polygon along the three coordinate axis directions of the vehicle coordinate system at a preset polyline distance, and the number of point cloud data in the first polygon is detected.

4. The method for automatically filtering labels of obscured ground elements based on point cloud according to claim 3, characterized in that: The preset polyline distance is 0.2 meters.

5. The method for automatically filtering labels of obscured ground elements based on point cloud according to claim 3, characterized in that: The specific process of step S500 also includes: The polygonal map element is expanded into a second polygonal body along the Z-axis direction of the vehicle coordinate system at a preset polygonal distance, and the number of point cloud data in the second polygonal body is detected.

6. The method for automatically filtering labels of obscured ground elements based on point cloud according to claim 5, characterized in that: The preset polygon distance is 0.2 meters.

7. The method for automatically filtering labels of obscured ground elements based on point cloud according to claim 5, characterized in that: The specific process of step S600 includes: If the number of point cloud data in the first polygon is less than 200, the polyline map element is determined to be a first obscured ground element label, and the first obscured ground element label is filtered; If the number of point cloud data in the second polygon is less than 20, the polygonal map element is determined to be a second obscured ground element label, and the second obscured ground element label is filtered.

8. A point cloud-based automatic filtering device for labels of obscured ground elements, characterized in that: The point cloud-based automatic filtering device for obstructed ground feature labels is configured to execute the point cloud-based automatic filtering method for obstructed ground feature labels, and the point cloud-based automatic filtering device for obstructed ground feature labels includes: A vehicle posture information acquisition module, wherein the vehicle posture information acquisition module is used to acquire the vehicle posture information of the vehicle, wherein the vehicle posture information includes the position and posture angle of the vehicle; A local map element coordinate system conversion module, the local map element coordinate system conversion module is used to convert the local map elements from the world coordinate system to the vehicle coordinate system according to the vehicle posture information, the local map elements include polyline map elements and polygonal map elements; A local map element filtering and truncation module, the local map element filtering and truncation module is used to filter and truncate the local map elements based on the self-vehicle posture information and according to a preset self-vehicle perception distance; A point cloud data coordinate system conversion module, the point cloud data coordinate system conversion module is used to obtain the point cloud data collected by the vehicle and convert the point cloud data from the point cloud coordinate system to the vehicle coordinate system so that the point cloud data and the local map elements are aligned in the same coordinate system; A local map element expansion module, the local map element expansion module is used to expand the local map element into a polygon and detect the number of point cloud data in the polygon; The obscured ground feature label determination module is used to determine that the local map element is an obscured ground feature label and filter the obscured ground feature label if the number of point cloud data in the polygon is less than a preset threshold.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; In which, 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 point cloud-based automatic filtering method for obscured ground element labels as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium stores a computer program, The computer program is used to enable a processor to implement a method for automatically filtering labels of obscured ground elements based on point clouds as described in any one of claims 1 to 7 when executed.

Images