High-precision map element feature extraction method, device and autonomous driving vehicle

Abstract

The present disclosure provides a method, device, electronic device, storage medium and product for extracting map element features, which relate to the fields of autonomous driving and intelligent transportation technology, and in particular to the technical field of element features of high-precision maps used for autonomous driving. The specific implementation scheme is: obtaining the linear element features of the map, and obtaining the path trajectory line of the autonomous driving vehicle; clustering the linear element features based on the distance between the linear element features and the path trajectory line to determine at least one linear element feature cluster; determining the missing linear element features in each of the linear element feature clusters, and generating virtual linear element features corresponding to the missing linear element features; extracting the virtual linear element features. The present disclosure can improve the efficiency of high-precision map generation operations.

Description

Technical Field

[0001] The present disclosure relates to the fields of autonomous driving and intelligent transportation technology, and in particular to the technical field of element features of high-precision maps for autonomous driving, and specifically to a method, device, electronic device, storage medium, product, and autonomous driving vehicle for extracting element features of high-precision maps. Background Art

[0002] High-precision maps, also known as high-accuracy maps, play a vital role in the perception, positioning, decision-making, and control processes of autonomous driving. Elements in HD maps are vectorized, such as lane markings, ground markings, stop signs, curbs, and guardrails.

[0003] However, in the process of extracting features from high-precision maps, there is a situation where line feature extraction is missing due to occlusion and other reasons. Summary of the Invention

[0004] The present disclosure provides a method, device, electronic device, storage medium, product and autonomous driving vehicle for extracting feature elements from a high-precision map.

[0005] According to a first aspect of the present disclosure, a method for extracting map element features is provided, the method comprising:

[0006] Obtain linear feature features of a map and obtain a path trajectory line of the autonomous driving vehicle; cluster the linear feature features based on the distance between the linear feature features and the path trajectory line to determine at least one linear feature feature cluster; determine the missing linear feature features in each of the linear feature feature clusters, and generate virtual linear feature features corresponding to the missing linear feature features; and extract the virtual linear feature features.

[0007] According to a second aspect of the present disclosure, a map element feature extraction device is provided, the device comprising:

[0008] An acquisition module is used to obtain linear feature features of a map and obtain the path trajectory line of the autonomous driving vehicle; a determination module is used to cluster the linear feature features based on the distance between the linear feature features and the path trajectory line to determine at least one linear feature feature cluster; the determination module is also used to determine the missing linear feature features in each linear feature feature cluster and generate virtual linear feature features corresponding to the missing linear feature features; an extraction module is used to extract the virtual linear feature features.

[0009] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0010] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in the first aspect.

[0011] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method according to the first aspect.

[0012] According to a fifth aspect of the present disclosure, a computer product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to the first aspect.

[0013] According to a sixth aspect of the present disclosure, an autonomous driving vehicle is provided, comprising the electronic device of the third aspect.

[0014] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0016] Figure 1 A schematic diagram showing an application environment of a map element feature extraction method provided by an embodiment of the present disclosure is shown;

[0017] Figure 2 A schematic diagram of a process for extracting map element features provided by an embodiment of the present disclosure is shown;

[0018] Figure 3 A schematic diagram of a process of a linear element feature clustering method provided by an embodiment of the present disclosure is shown;

[0019] Figure 4 A schematic flow chart of a method for determining missing linear element features provided by an embodiment of the present disclosure is shown;

[0020] Figure 5 A schematic flow chart of a method for extracting virtual linear element features provided by an embodiment of the present disclosure is shown;

[0021] Figure 6 A schematic diagram of a process for extracting map element features provided by an embodiment of the present disclosure is shown;

[0022] Figure 7A schematic diagram showing a high-precision map for supplementing linear element features provided by an embodiment of the present disclosure is shown;

[0023] Figure 8 A schematic structural diagram of a map element feature extraction device provided by an embodiment of the present disclosure is shown;

[0024] Figure 9 Schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0025] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be understood that the specific embodiments described herein are merely used to explain the present application and are not intended to limit the present application.

[0026] High-precision maps play an important role in the perception, positioning, decision-making, and control processes of autonomous driving. Elements in high-precision maps are vectorized, such as lane lines, ground markings, stop lines, curbs, and guardrails. Among them, linear element recognition in high-precision maps includes guardrails, curbs, and lane lines. During the feature extraction of guardrails and curbs, sensors (e.g., cameras, lidar, etc.) are unable to recognize some linear elements due to factors such as obstruction by obstacles. This results in the loss of some linear element features in the extraction results, thus affecting the subsequent production efficiency of high-precision maps.

[0027] In related technologies, in order to address the problem of missing features of some linear elements in the extraction results, it is proposed to judge the left and right sides of each trajectory point based on the continuous trajectory points of the autonomous driving car. If the trajectory points within a certain range before and after have features, but the current trajectory point has no features, the missing features are supplemented based on the features on both sides of the previous and next trajectory points.

[0028] However, in related technologies, only one linear feature (e.g., curb / guardrail) on each side of the continuous trajectory of the autonomous vehicle can be strung together. This approach is reasonable and effective for simple scenarios such as highways. However, in complex urban scenarios, due to the existence of auxiliary roads, there may be multiple guardrails / curbs on both sides of the road, making it impossible to supplement the missing features of all linear feature lines.

[0029] In response to the above technical problems, the present disclosure provides a map feature feature extraction method and device, which clusters the extracted linear feature features so that the linear feature features in each cluster belong to the same guardrail / curb. Thus, for the linear feature features belonging to the same guardrail / curb, the missing ones are determined, and the missing linear feature features are supplemented to extract the supplemented linear feature features. By clustering the extracted linear feature features, it is possible to supplement multiple missing linear feature features belonging to the same guardrail / curb at the same time based on the clustering results, thereby improving the efficiency of high-precision map generation.

[0030] The map feature extraction method provided in this application can be applied to Figure 1 In the application environment shown. The terminal 101 communicates with the server 102 through the network. The terminal 101 can be a vehicle-mounted device. The vehicle-mounted device of the autonomous driving vehicle obtains the linear feature features after vectorization of the high-precision map through the terminal 101, and sends the obtained linear feature features to the server 102, so that the server 102 can cluster according to the received linear feature features to supplement the missing linear feature features. The terminal 101 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices or vehicle-mounted devices, etc. The server 102 can be implemented with an independent server or a server cluster composed of multiple servers.

[0031] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.

[0032] The present disclosure can be applied to positioning layers for autonomous driving, and can also be applied to the high-precision map generation business for self-driving taxis (Robotaxi). The following embodiments will illustrate the map element feature extraction method provided by the present disclosure with reference to the accompanying drawings.

[0033] Figure 2 A flow chart of a method for extracting map element features provided by an embodiment of the present disclosure is shown. Figure 2 As shown in , the method may include:

[0034] In step S210, the linear element features of the map are obtained, and the path trajectory line of the autonomous driving vehicle is obtained.

[0035] In the embodiment of the present disclosure, the map may be a high-precision map for use in autonomous driving vehicles, and the linear element features are vectorized linear element features of the high-precision map.

[0036] In this disclosure, the sensors of autonomous vehicles can identify linear elements in high-precision maps. These linear elements can be vectorized versions of lane lines, ground markings, stop lines, curbs, guardrails, and other features. Linear element features can be vectorized features of lane lines, ground markings, stop lines, curbs, guardrails, and other features in high-precision maps.

[0037] Among them, the obtained path trajectory line of the autonomous driving vehicle can be used as a reference position.

[0038] It is understandable that the present disclosure is described using curbs and / or guardrails as examples, but the application environment of the present disclosure is not limited to curbs and / or guardrails.

[0039] In step S220 , the linear feature features are clustered based on the distance between the linear feature features and the path trajectory line to determine at least one linear feature feature cluster.

[0040] In the embodiment of the present disclosure, after obtaining the vectorized linear element feature, the position between the linear element feature and the path trajectory line can be determined based on the path trajectory line of the autonomous driving vehicle, so as to further calculate the distance from the linear element feature to the path trajectory line.

[0041] According to the calculated distance between the linear feature and the path trajectory line, the obtained linear feature features are clustered to determine the linear feature features belonging to the same straight line, and to obtain at least one linear feature cluster.

[0042] For example, after clustering, two linear feature clusters are obtained, one of which belongs to the same guardrail, and the other to the same curb. Furthermore, the two lines belonging to the two linear feature clusters can be on the same side of the path trajectory, or on the left and right sides of the path trajectory.

[0043] In step S230 , the missing linear element features in each linear element feature cluster are determined, and virtual linear element features corresponding to the missing linear element features are generated.

[0044] In the disclosed embodiment, based on the clustered linear feature clusters, the missing linear feature features in each linear feature cluster are determined. In other words, the missing linear feature features in each linear feature cluster are determined. The missing linear feature features are supplemented to generate virtual linear feature features.

[0045] In step S240 , virtual linear element features are extracted.

[0046] In the present disclosure, the generated virtual linear feature features can be filtered to extract the virtual linear feature features corresponding to the missing linear feature features, so that the extracted virtual linear feature features can be marked in the high-precision map as driving information of the autonomous driving vehicle.

[0047] For example, after obtaining the linear feature of a guardrail, it is determined that the linear feature of the guardrail is missing, that is, there are linear feature features that were not obtained due to occlusion or other reasons. The missing linear feature can be supplemented. Through the solution provided by the present disclosure, the supplemented linear feature of the guardrail is a virtual linear feature.

[0048] The map feature extraction method provided by the present disclosure can cluster the extracted linear feature features according to their attributes to determine multiple linear feature clusters. Missing linear feature features are determined for each linear feature cluster and supplemented. In other words, the present disclosure can simultaneously supplement missing linear feature features on multiple straight lines, thereby improving the recall rate of linear feature extraction results and enhancing the production efficiency of high-precision map operations.

[0049] In the disclosed embodiments, high-precision feature vectorization can be used to obtain feature features, and these features can be discretely filtered based on linear shapes to obtain linear feature features. For example, a bounding box containing a feature is determined, and rays are emitted from the center line of the bounding box to both ends. If the ray cannot find any collinear bounding boxes within a certain range (e.g., 15 meters), the feature is determined to be a discrete feature.

[0050] The following embodiment will illustrate an implementation method for clustering linear feature features based on the distance between the linear feature features and the driving route.

[0051] Figure 3 A schematic diagram of a linear feature clustering method provided by an embodiment of the present disclosure is shown in FIG. Figure 3 As shown in , the method may include:

[0052] In step S310 , the position attribute of the linear element feature is determined based on the path trajectory line.

[0053] In step S320, the distance from the linear element feature to the path trajectory line is calculated according to the position attribute.

[0054] In step S330 , linear feature features on the same straight line are clustered based on distance and position attributes.

[0055] In the disclosed embodiment, the acquired linear element features are divided based on the path trajectory of the autonomous vehicle, and the positional attributes of the linear element features relative to the path trajectory are determined. Specifically, the linear element features are determined to be located to the left of the path trajectory, or to the right of the path trajectory. This results in a set of left-side linear element features located to the left of the path trajectory, and a set of right-side linear element features located to the right of the path trajectory.

[0056] In the present disclosure, the distance from each linear feature in the left linear feature set to the path trajectory line can be further calculated, and the distance from each linear feature in the right linear feature set to the path trajectory line can be calculated. The distance can be the vertical distance from the linear feature to the path trajectory line.

[0057] Based on the calculated vertical distance and location attributes, linear feature features on the same line are clustered. Furthermore, linear feature features with equal vertical distance and located on the same side of the path trajectory can be clustered into the same linear feature cluster.

[0058] The following embodiment will illustrate an implementation method for determining the missing linear feature of each linear feature feature set.

[0059] Figure 4 FIG. 1 shows a flow chart of a method for determining missing linear element features provided by an embodiment of the present disclosure, such as Figure 4 As shown in , the method may include:

[0060] In step S410 , for each linear feature cluster, endpoints of all linear feature features in the linear feature set are determined.

[0061] In step S420, the endpoints are sorted based on their adjacent positions to obtain a linear feature sequence.

[0062] In step S430, the missing linear feature features between adjacent endpoints in the linear feature feature sequence are determined.

[0063] In the disclosed embodiments, a linear feature can be understood as a line segment. For each linear feature cluster, the two endpoints of all linear features in the cluster are determined. Based on their positional relationships, the endpoints are sorted to obtain a linear feature sequence. Specifically, the positional pairs corresponding to each endpoint are filled into the corresponding positions on the same line. Missing linear features are further determined based on the adjacent positions between the endpoints of the linear feature.

[0064] The following embodiment will illustrate the implementation method of extracting virtual linear element features.

[0065] Figure 5 A flow chart of a method for extracting virtual linear element features provided by an embodiment of the present disclosure is shown. Figure 5 As shown in , the method may include:

[0066] In step S510 , the route structure of the map is acquired, and the confidence level of the virtual linear element feature is determined based on the route structure.

[0067] In step S520, a first confidence level greater than or equal to a confidence level threshold is determined in the confidence levels, and a virtual linear element feature corresponding to the first confidence level is extracted.

[0068] In the disclosed embodiments, the route structure of the map can also be obtained, that is, the route structure of the high-precision map used to assist the autonomous vehicle. Based on the route structure of the high-precision map, structural features such as intersections that exist on the same straight line are determined. Based on the route structure features of the high-precision map, the confidence level of each virtual linear element feature is calculated. Thus, among the generated virtual linear element features, it is determined whether there are virtual linear element features that complement structural features such as intersections.

[0069] A preset confidence threshold is determined, a first confidence level greater than or equal to the confidence threshold is obtained from the confidence levels, and a second confidence level is obtained by filtering out the confidence levels less than or equal to the confidence threshold. It will be appreciated that, for ease of distinction, this disclosure refers to confidence levels greater than or equal to the confidence threshold as first confidence levels, and confidence levels less than or equal to the confidence threshold as second confidence levels.

[0070] Furthermore, the virtual linear feature features corresponding to the first confidence level are extracted, and the virtual linear feature features corresponding to the second confidence level are filtered to obtain virtual linear feature features that can be marked in the high-precision map.

[0071] The present disclosure can filter the generated virtual linear element features at the intersection, thereby avoiding marking redundant virtual linear element features in the high-precision map, and improving the accuracy of linear element feature recall.

[0072] Figure 6 A flow chart of a method for extracting map element features provided by an embodiment of the present disclosure is shown. Figure 6 As shown in , the implementation process of the map element feature extraction method disclosed in the present invention may include data preprocessing, clustering of the same object, object completion, and generation of virtual features.

[0073] Data preprocessing involves discrete filtering of discrete linear feature features. The same object can be considered as belonging to the same straight line. Clustering the same object involves calculating the left and right attributes of the linear feature and the perpendicular distance from the linear feature to the trajectory. Object completion involves sorting the left and right endpoints of each linear feature within the same object and connecting all endpoints in sequence. Virtual feature generation involves evaluating each line segment and generating virtual linear feature features for those that meet the gap criteria. Low-confidence virtual linear feature features are then filtered. This results in feature features for the HD map that supplement the linear feature features.

[0074] Figure 7 A schematic diagram of a high-precision map for supplementing linear element features provided by an embodiment of the present disclosure is shown. Figure 7 As shown in , the dotted line represents the supplemented linear feature, and the solid line represents the extracted linear feature. Figure 7 It can be determined that the present disclosure can supplement the missing features on multiple straight lines at the same time by clustering the linear element features on different straight lines, so as to improve the recall rate of feature extraction results and improve the production efficiency of high-precision map operations.

[0075] Based on Figure 2 The same principle as shown in the method, Figure 8 A schematic diagram of the structure of a map element feature extraction device provided by an embodiment of the present disclosure is shown. Figure 8 As shown, the map element feature extraction device 800 may include:

[0076] The acquisition module 801 is used to obtain the linear feature of the map and obtain the path trajectory line of the autonomous driving vehicle; the determination module 802 is used to cluster the linear feature features based on the distance between the linear feature features and the path trajectory line to determine at least one linear feature feature cluster; the determination module 802 is also used to determine the missing linear feature features in each of the linear feature feature clusters and generate virtual linear feature features corresponding to the missing linear feature features; the extraction module 803 is used to extract the virtual linear feature features.

[0077] In the embodiment of the present disclosure, the acquisition module 801 is used to acquire vectorized element features of a map, and filter the vectorized element features to obtain the linear element features.

[0078] In an embodiment of the present disclosure, the determination module 802 is used to determine the position attribute of the linear feature based on the path trajectory line; calculate the distance from the linear feature to the path trajectory line according to the position attribute; and cluster the linear feature features on the same straight line based on the distance and the position attribute.

[0079] In the embodiment of the present disclosure, the determination module 802 is used to determine the endpoints of all linear feature features in each linear feature cluster; sort the endpoints based on the adjacent positions of the endpoints to obtain a linear feature sequence; and determine the missing linear feature features between adjacent endpoints in the linear feature sequence.

[0080] In an embodiment of the present disclosure, the extraction module 803 is used to obtain the route structure of the map and determine the confidence of the virtual linear element feature based on the route structure; determine a first confidence level greater than or equal to a confidence threshold among the confidence levels, and extract the virtual linear element feature corresponding to the first confidence level.

[0081] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0082] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0083] According to an embodiment of the present disclosure, the present disclosure also provides an autonomous driving vehicle, including an electronic device.

[0084] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. 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 assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0085] like Figure 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the device 900 can also be stored in the RAM 903. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0086] Various components in the device 900 are connected to the I / O interface 905, including an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0087] The computing unit 901 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the map feature feature extraction method. For example, in some embodiments, the map feature feature extraction method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the map feature feature extraction method described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the map feature feature extraction method by any other suitable means (e.g., via firmware).

[0088] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0089] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0090] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0091] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0092] The systems and techniques described herein can be implemented in a computing system that includes back-end 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 front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0093] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0094] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0095] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A map element feature extraction method, applied to an autonomous driving vehicle, comprising: Obtaining linear feature features of a map and obtaining a path trajectory line of the autonomous driving vehicle; Clustering the linear feature features based on the distance between the linear feature features and the path trajectory line to determine at least one linear feature cluster; clustering the linear feature features based on the distance between the linear feature features and the path trajectory line to determine at least one linear feature cluster comprises: determining the position of the linear feature features and the path trajectory line, calculating the distance between the linear feature features and the path trajectory line based on the position, clustering the linear feature features based on the distance, determining linear feature features belonging to the same straight line, and obtaining at least one linear feature cluster; Determining the missing linear feature in each linear feature cluster, and generating a virtual linear feature corresponding to the missing linear feature; Extract the virtual linear element features.

2. The method according to claim 1, wherein The step of obtaining linear feature features of a map includes: Vectorized feature features of a map are acquired, and the vectorized feature features are filtered to obtain the linear feature features.

3. The method according to claim 1 or 2, wherein: The clustering of the linear feature features based on the distance between the linear feature features and the path trajectory line includes: Determining the position attributes of the linear element features based on the path trajectory; Calculating the distance from the linear element feature to the path trajectory line according to the position attribute; The linear element features on the same straight line are clustered based on the distance and the location attribute.

4. The method according to claim 1 or 2, wherein: The determining of the missing linear feature in each linear feature cluster includes: For each linear feature cluster, determining endpoints of all linear feature features in the linear feature cluster; Sort the endpoints based on adjacent positions of the endpoints to obtain a linear feature sequence; Determine the linear feature features missing between adjacent endpoints in the linear feature feature sequence.

5. The method according to claim 1 or 2, wherein: The extracting of the virtual linear element feature includes: Acquiring a route structure of the map, and determining a confidence level of the virtual linear element feature based on the route structure; A first confidence level greater than or equal to a confidence level threshold is determined among the confidence levels, and the virtual linear element feature corresponding to the first confidence level is extracted.

6. A map element feature extraction device, applied to an autonomous driving vehicle, comprising: An acquisition module, configured to acquire linear feature features of a map and obtain a path trajectory line of the autonomous driving vehicle; a determination module configured to cluster the linear feature features based on the distance between the linear feature features and the path trajectory line to determine at least one linear feature cluster; the determination module further configured to determine the position of the linear feature features and the path trajectory line, calculate the distance between the linear feature features and the path trajectory line based on the position, cluster the linear feature features based on the distance, determine linear feature features belonging to the same straight line, and obtain at least one linear feature cluster; The determining module is further configured to determine the missing linear element features in each of the linear element feature clusters, and generate virtual linear element features corresponding to the missing linear element features; The extraction module is used to extract the features of the virtual linear elements.

7. The device according to claim 6, wherein The acquisition module is used to: Vectorized feature features of a map are acquired, and the vectorized feature features are filtered to obtain the linear feature features.

8. The device according to claim 6 or 7, wherein: The determining module is configured to: Determining the position attributes of the linear element features based on the path trajectory; Calculating the distance from the linear element feature to the path trajectory line according to the position attribute; The linear element features on the same straight line are clustered based on the distance and the location attribute.

9. The device according to claim 6 or 7, wherein: The determining module is configured to: For each linear feature cluster, determining endpoints of all linear feature features in the linear feature cluster; Sort the endpoints based on adjacent positions of the endpoints to obtain a linear feature sequence; Determine the linear feature features missing between adjacent endpoints in the linear feature feature sequence.

10. The device according to claim 6 or 7, wherein: The extraction module is used to: Acquiring a route structure of the map, and determining a confidence level of the virtual linear element feature based on the route structure; A first confidence level greater than or equal to a confidence level threshold is determined among the confidence levels, and the virtual linear element feature corresponding to the first confidence level is extracted.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

14. An autonomous driving vehicle comprising the electronic device according to claim 11.

Images