Lane-based vehicle positioning method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a lane-based vehicle positioning method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring longitude and latitude information of a vehicle collected in a preset time window, and determining a lane line map of a road where the vehicle is located; acquiring a map type of a road map of a road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle; performing matching processing on the lane line map and the road map according to the map type of the road map to obtain positioning information of the vehicle on the road; wherein the positioning information represents the lane where the vehicle is located on the road. According to the method, by generating the lane line map, the problem of lane-level data missing in an area without HD map coverage is effectively solved, and the lane-level positioning precision is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular, to a lane-based vehicle positioning method, device, electronic device, and storage medium. Background Art

[0002] With the development of urban roads, users have higher and higher requirements for vehicle navigation. When performing vehicle navigation, users often hope to clarify the lane where the vehicle is located.

[0003] Currently, in the field of lane-level navigation and positioning, it mainly relies on the combination of high-precision maps and global navigation satellite systems. However, there are some areas without high-precision maps, making it difficult to provide detailed lane-level data, resulting in the inability to achieve lane-level navigation and positioning in these areas. Summary of the Invention

[0004] Embodiments of this application provide a lane-based vehicle positioning method, device, electronic device, and storage medium to improve lane-level positioning accuracy.

[0005] In a first aspect, embodiments of this application provide a lane-based vehicle positioning method, including:

[0006] Obtain the longitude and latitude information of the vehicle collected within a preset time window, and determine the lane line map of the road where the vehicle is located;

[0007] According to the longitude and latitude information of the vehicle, obtain the map type of the road map of the road where the vehicle is located from a preset map database;

[0008] According to the map type of the road map, perform matching processing on the lane line map and the road map to obtain the positioning information of the vehicle on the road; wherein, the positioning information represents the lane where the vehicle is located on the road.

[0009] In a possible implementation manner, performing matching processing on the lane line map and the road map according to the map type of the road map to obtain the positioning information of the vehicle on the road includes:

[0010] Determine the lane similarity between the lane line map and the road map according to the map type of the road map;

[0011] Determine the positioning information of the vehicle on the road according to the lane similarity and the longitude and latitude information of the vehicle.

[0012] In a possible implementation manner, the map type of the road map is a standard-precision map; the determining the positioning information of the vehicle on the road according to the lane similarity and the longitude and latitude information of the vehicle includes:

[0013] If the lane similarity is greater than a preset similarity threshold, the lane line map and the road map are fused to obtain a fused map; wherein, the fused map is a road map with lane lines.

[0014] Based on the fused map and the longitude and latitude information of the vehicle, determine the positioning information of the vehicle on the road.

[0015] In a possible implementation, the map type of the road map is a high-precision map; the determining the positioning information of the vehicle on the road according to the lane similarity and the longitude and latitude information of the vehicle includes:

[0016] If the lane similarity is greater than a preset similarity threshold, determine the position of the vehicle on the road according to the lane line map as a first position point, and determine the position of the vehicle on the road according to the longitude and latitude information of the vehicle as a second position point.

[0017] Determine an offset according to the first position point and the second position point; wherein, the offset represents the distance between the first position point and the second position point.

[0018] Determine the positioning information of the vehicle on the road according to the offset, the longitude and latitude information of the vehicle, and the road map.

[0019] In a possible implementation, determining the lane similarity between the lane line map and the road map according to the map type of the road map includes:

[0020] Obtain lane line attribute information from the lane line map, and obtain lane attribute information from the road map according to the map type of the road map.

[0021] Determine the lane similarity between the lane line map and the road map according to the lane line attribute information and the lane attribute information.

[0022] In a possible implementation, obtaining the map type of the road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle includes:

[0023] Determine the road identifier of the road where the vehicle is located according to the longitude and latitude information of the vehicle.

[0024] Search in the preset map database for the map type of the map data corresponding to the road identifier, which is the map type of the road where the vehicle is located.

[0025] In a possible implementation, determining the road identifier of the road where the vehicle is located according to the longitude and latitude information of the vehicle includes:

[0026] Determining the longitude and latitude range to which the longitude and latitude information of the vehicle belongs as the target range according to a plurality of preset longitude and latitude ranges;

[0027] Determining the road identifier corresponding to the target range as the road identifier of the road where the vehicle is located.

[0028] In a possible implementation, determining the lane line map of the road where the vehicle is located includes:

[0029] Obtaining the road image of the road where the vehicle is located and the pose information of the vehicle collected within a preset time window;

[0030] Generating a lane line map of the road passed by the vehicle within the preset time window according to the lane line attribute information in each road image in the preset time window and the pose information corresponding to each road image.

[0031] In a second aspect, an embodiment of the present application provides a lane-based vehicle positioning device, including:

[0032] An information acquisition module, configured to acquire the longitude and latitude information of the vehicle collected within a preset time window and determine the lane line map of the road where the vehicle is located;

[0033] A type determination module, configured to obtain the map type of the road map of the road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle;

[0034] A lane positioning module, configured to perform matching processing on the lane line map and the road map according to the map type of the road map to obtain the positioning information of the vehicle on the road; wherein, the positioning information represents the lane where the vehicle is located on the road.

[0035] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0036] The memory stores computer execution instructions;

[0037] The processor executes the computer execution instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored, and when the computer execution instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation manners of the first aspect.

[0039] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program which, when executed by a processor, implements the first aspect and / or various possible implementation manners of the first aspect as described above.

[0040] A lane-based vehicle positioning method, device, electronic device and storage medium provided by an embodiment of the present application obtain multiple frames of road images collected by a vehicle within a period of time, as well as corresponding pose information and longitude and latitude information. According to the road images and the corresponding pose information, a lane line map of the road where the vehicle is currently located can be determined, that is, relevant data of the lane lines can be obtained. According to the longitude and latitude information, the map type of the road map where the vehicle is located can be determined. Based on different types, the lane line map and the road map are matched specifically, so as to determine which lane the vehicle is located on the road, realizing lane-level positioning of the vehicle. By determining the lane line map, accurate positioning can be performed regardless of whether there is a high-precision map on the current road, improving the efficiency and accuracy of positioning and enhancing the user's navigation experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0042] Figure 1 It is a schematic flowchart of a lane-based vehicle positioning method provided by an embodiment of the present application;

[0043] Figure 2 It is a schematic diagram of a lane line map of an intersection provided by an embodiment of the present application;

[0044] Figure 3 It is a schematic flowchart of a lane-based vehicle positioning method provided by an embodiment of the present application;

[0045] Figure 4 It is a schematic flowchart of a lane-based vehicle positioning method provided by an embodiment of the present application;

[0046] Figure 5 It is a schematic diagram of the working process of a sensor provided by an embodiment of the present application;

[0047] Figure 6 It is a schematic structural diagram of a lane-based vehicle positioning device provided by an embodiment of the present application;

[0048] Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0049] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and will be described in more detail hereinafter. These drawings and written descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by reference to specific embodiments. Detailed Description of the Embodiments

[0050] Here, exemplary embodiments will be described in detail, and examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0051] In the field of lane-level navigation and positioning, current positioning technologies mainly rely on the combination of HD (High Definition Map, high-precision) and GNSS (Global Navigation Satellite System). The HD map provides detailed lane-level data, including lane lines, traffic signs, and other road elements, through highly accurate geographical information. The core feature of the HD map is its high resolution, which can support the precise lane-level positioning of the autonomous driving system in a specific area.

[0052] For areas without HD map coverage, current technologies usually use SD (Standard Definition Map, standard-precision) maps in combination with GNSS or INS (Inertial Navigation System) for positioning. However, the accuracy of the SD map is limited and it is difficult to provide detailed lane-level data, resulting in the inability to achieve lane-level navigation and positioning in these areas.

[0053] To address the above problems, the embodiments of the present application propose a lane-based vehicle positioning method, which solves the lane-level positioning problem in sections without HD maps by locally reconstructing the lane line map, significantly improves the stability and robustness of positioning, reduces the dependence on HD map coverage, and enhances the user's navigation experience.

[0054] A lane-based vehicle positioning method, device, electronic device, and storage medium provided by the present application aim to solve the above technical problems of the prior art.

[0055] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0056] Figure 1 It is a schematic flowchart of a lane-based vehicle positioning method provided by an embodiment of this application. This method can be executed by a lane-based vehicle positioning device. The embodiments of this application can be applied to in-vehicle terminals. For example, they can be deployed in a preset vehicle-mounted system or a smart driving domain with smart driving functions. With the help of an in-vehicle computing unit, such as an ECU (Electronic Control Unit), or an in-vehicle GPU / CPU (Graphics Processing Unit / Central Processing Unit), etc., the positioning of the vehicle is completed. As Figure 1 shown, this method includes:

[0057] S101. Obtain the longitude and latitude information of the vehicle collected within a preset time window, and determine the lane line map of the road where the vehicle is located.

[0058] Exemplarily, a time window is preset. The time window is a time period of a preset length. For example, every ten minutes is a time window. During the driving process of the vehicle, it can continuously collect the road images of the road where it is located and its own position information within each time window. For example, a variety of sensors can be installed on the vehicle, and the sensors can collect data in real time or at regular intervals. The sensors on the vehicle can include cameras, lidar, IMU (Inertial Measurement Unit), wheel speed, and GNSS, etc. Among them, the cameras and lidar can be used to collect road images. For example, 17 road images can be collected within a time window, and the IMU, wheel speed, and GNSS can be used to collect position information.

[0059] The road image is image data containing lane lines, that is, the camera on the vehicle can capture the road surface. The road image corresponds one-to-one with the position information. The position information can include pose information and longitude and latitude information. The pose information represents the relative position and pose of the vehicle relative to the departure place, that is, the relative pose. The relative position can be the distance and azimuth between the vehicle and the departure place, and the pose can be the steering angle and pitch angle of the vehicle head, etc. The longitude and latitude information of the vehicle can be obtained through the GNSS sensor; through sensors such as IMU and wheel speed, DR (Dead Reckoning) is calculated to obtain continuous and smooth relative position and pose.

[0060] Obtain the pose information from the position information. According to the road image and the pose information, the lane lines on the road where the vehicle is currently located can be recognized. Based on the recognized lane lines, a lane line map of the road can be obtained, that is, the lane lines of the road can be represented on the lane line map. For example, the lane lines can be recognized from each frame of the road image, and according to the pose information, the orientation of the lane lines can be determined. According to the orientation of the lane lines, the lane lines in each frame of the road image are connected to obtain the lane line map.

[0061] An image recognition algorithm for lane lines can be preset. For example, according to the preset algorithm, solid lines and dashed lines can be recognized from the road image as lane lines. In this embodiment, the preset image recognition algorithm is not specifically limited. According to the pose information, the lane lines in each frame of the image can be spliced. For example, when the vehicle enters the intersection through an entrance lane and then turns right to an exit lane of the intersection after entering the intersection, the lane lines can be spliced into lane lines that first go straight and then turn right. Figure 2 It is a schematic diagram of the lane line map of the intersection. The lane line map contains lane lines, and the lane lines show that the vehicle goes straight to the intersection and then turns right to exit the intersection.

[0062] In this embodiment, the preset time window can only collect a section of the lane lines in the road, that is, the lane line map constructed according to the road image and the pose information can represent the local lane lines in the road. If the complete lane lines of the road are needed, the local lane line maps corresponding to each consecutive time window can be spliced to obtain the complete lane line map of the road.

[0063] In this embodiment, a time window includes multiple frames of road images. For each frame of the road image, the lane lines in the road image can be recognized and processed to obtain the attribute information of the lane lines in the road image. For example, an image recognition algorithm can be preset to recognize the straight lines of solid lines or dashed lines in the road image as lane lines, and the type, color, curvature, orientation, etc. of the lane lines are used as attribute information.

[0064] In this embodiment, the method further includes: for each road image in the preset time window, perform denoising processing on the road image to obtain the denoised road image; perform lane line recognition processing on each denoised road image in the preset time window to obtain the lane line attribute information in the road image.

[0065] Specifically, since the environment of image acquisition cannot be controlled, the acquired images can be denoised. That is, for each frame of road image in a preset time window, a preset denoising algorithm can be used for denoising to obtain the denoised road image. In this embodiment, the specific preset denoising algorithm is not limited. After obtaining the denoised road image, lane line recognition processing is performed on the denoised road image to obtain the lane line attribute information in the road image.

[0066] The beneficial effect of such a setting is that by performing denoising processing, the errors caused by environmental interferences such as lighting and weather can be eliminated, and the accuracy of vehicle positioning can be improved.

[0067] According to the lane line attribute information in each road image in the preset time window and the pose information corresponding to each road image in the preset time window, a lane line map of the road passed by the vehicle within the preset time window is generated.

[0068] Exemplarily, a plurality of pose information may be included in the preset time window. For example, each time a frame of road image is acquired, the pose information is acquired once. That is, the road images can be in one-to-one correspondence with the pose information. For each frame of road image, the corresponding pose information is determined.

[0069] In this embodiment, according to the lane line attribute information in each road image in the preset time window and the pose information corresponding to each road image, generating a lane line map of the road passed by the vehicle within the preset time window includes: performing lane line recognition processing on each road image in the preset time window to obtain the lane line attribute information in the road image; according to the pose information corresponding to the road images in the preset time window, aggregating the lane line attribute information of each road image to obtain a lane line map of the road passed by the vehicle within the preset time window.

[0070] For each preset time window, determine the lane line attribute information in all the road images in this time window and the pose information corresponding to these road images. According to the lane line attribute information and the corresponding pose information in these road images, generate a lane line map of the road passed by the vehicle within this time window. For example, according to the pose information corresponding to two adjacent frames of road images, the lane line attribute information of these two frames of road images can be spliced and duplicate removed until the lane line attribute information in all the road images is spliced to complete all the lane line attribute information of the road passed within this time window, and thus a lane line map can be constructed according to these lane line attribute information. The constructed lane line map can be stored and optimized as a key frame. For example, a Ceres optimizer can be used for optimization. The lane line map can also be encapsulated to ensure the format is unified with the HD map for subsequent map matching operations.

[0071] S102. Obtain the map type of the road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle.

[0072] Exemplarily, a map database is preset. The map database stores road maps of various places. The road maps can represent the layout of roads. For example, they can represent the length, type, curvature, etc. of roads. The types of maps stored in the map database can be SD maps or HD maps. The deployment and maintenance costs of HD maps are extremely high, especially in complex urban environments and remote suburban areas. Therefore, the coverage of HD maps is usually limited, that is, there are only SD maps for the road maps in some areas. The map type corresponding to a location can be only one, that is, for the same location, the map at that location is either an SD map or an HD map.

[0073] Each road map in the map database corresponds to its own longitude and latitude range, and the longitude and latitude range represents the regional range of the road map. Determine the longitude and latitude information of the vehicle, and find out which longitude and latitude range the longitude and latitude information is located in, so as to determine the road map corresponding to the longitude and latitude information as the road map of the road where the vehicle is located.

[0074] In this embodiment, obtaining the map type of the road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle includes: determining the road identifier of the road where the vehicle is located according to the longitude and latitude information of the vehicle; searching in the preset map database for the map type of the map data corresponding to the road identifier, which is the map type of the road where the vehicle is located.

[0075] Specifically, each road in the city corresponds to a unique road identifier, and the association relationship between different road identifiers and longitude and latitude information can be stored in advance. According to the known longitude and latitude information, the road identifier associated with the longitude and latitude information can be found as the road identifier of the road where the vehicle is located.

[0076] Each road identifier corresponds to its own road map and is stored in a preset map database. According to the determined road identifier, search in the map database for the road map corresponding to the road identifier as the road map of the road where the vehicle is located. Search for the map type corresponding to the road map. The map type of the road map may be an SD map or an HD map.

[0077] The beneficial effect of such a setting is that during the driving of the vehicle, the corresponding SD or HD map data is loaded from the map database according to the current longitude and latitude. Whether it is an SD map or an HD map, subsequent positioning operations can be performed, improving the efficiency and flexibility of vehicle positioning.

[0078] In this embodiment, determining the road identifier of the road where the vehicle is located according to the longitude and latitude information includes: determining the longitude and latitude range to which the longitude and latitude information belongs according to a plurality of preset longitude and latitude ranges as the target range; determining the road identifier corresponding to the target range as the road identifier of the road where the vehicle is located.

[0079] Specifically, each road in the city corresponds to a unique road identifier. The regional positions of each road are different, that is, the regional positions corresponding to each road identifier are different. The regional position can be represented by a longitude and latitude range. For example, the road identifier is 001, and the corresponding longitude and latitude range is from 117°E, 39°N to 117°E, 40°N. Each road identifier and the corresponding longitude and latitude range are associated and stored in advance.

[0080] Determine which longitude and latitude range the longitude and latitude information of the vehicle is located in, that is, determine the longitude and latitude range to which the longitude and latitude information belongs, and determine this longitude and latitude range as the target range. Search for the road identifier corresponding to the target range as the road identifier of the road where the vehicle is currently located. For example, if the longitude and latitude information is 117°E, 39.5°N, it can be determined that the road identifier of the road where the vehicle is located is 001.

[0081] The beneficial effect of such a setting is that by determining which range the current longitude and latitude information belongs to, the corresponding map can be quickly found, improving the efficiency of vehicle positioning.

[0082] S103. Match the lane line map and the road map according to the map type of the road map to obtain the positioning information of the vehicle on the road; wherein, the positioning information represents the lane where the vehicle is located on the road.

[0083] Exemplarily, after obtaining the lane line map, the vehicle can be positioned at the lane level by combining the lane line map and the longitude and latitude information of the vehicle to obtain the positioning information, that is, determine which lane the vehicle is on the road. For example, the position point of the vehicle on the road can be determined according to the longitude and latitude information. Then, according to the lane line map, determine how many lanes there are on the road. According to the width of the road, determine the width range of each lane, and determine which lane range the position point is located in, that is, obtain the lane where the vehicle is located.

[0084] It is also possible to obtain the pre-stored road map corresponding to the longitude and latitude information according to the longitude and latitude information of the vehicle. There may be no lane lines in the pre-stored road map. Overlap the lane line map and the road map so that the road map contains lane lines, and determine the position point of the longitude and latitude information in the road map, thereby obtaining the lane where the vehicle is located.

[0085] In this embodiment, the map type of the road map can be an SD map or an HD map, and the map type of the road map where the vehicle is located is determined. Different matching processes can be performed on the lane line map and the road map according to the map type, and the positioning information of the vehicle on the road is determined after matching. For example, for an SD map, since there is no information about lane lines in the SD map, the lane line map can be fused with the SD map, and the positioning information of the vehicle is determined according to the fused map. For an HD map, since the HD map contains information about lane lines, the positioning information of the vehicle can be directly determined according to the HD map, and then the determined positioning information is verified according to the lane line map. For example, the lane line map and the HD map can be fused to determine whether the lane lines in the lane line map overlap with the lane lines in the HD map. If so, it is determined that the positioning information is correct; if not, the lane lines in the HD map are replaced with the lane lines in the lane line map, and then the positioning information is determined according to the new lane lines in the HD map.

[0086] For different map types, different processing methods can be used for the lane line map and the road map, improving the flexibility of data processing. Even for a low-precision SD map, the accuracy of vehicle positioning can be improved. Different strategies are adopted in the SD and HD map areas respectively according to the map accuracy, reducing the dependence on high-precision maps and ensuring the global positioning effect.

[0087] A lane-based vehicle positioning method provided by an embodiment of the present application obtains multiple frames of road images collected by a vehicle within a period of time, as well as corresponding pose information and longitude and latitude information. According to the road images and the corresponding pose information, the lane line map of the road where the vehicle is currently located can be determined, that is, the relevant data of the lane lines are obtained. According to the lane line map and the longitude and latitude information, it is determined which lane the vehicle is located on the road, realizing lane-level positioning of the vehicle. By determining the lane line map, accurate positioning can be performed regardless of whether there is a high-precision map on the current road, improving the efficiency and accuracy of positioning and enhancing the user's navigation experience.

[0088] Figure 3 It is a flowchart of a lane-based vehicle positioning method provided by an embodiment of the present application. As Figure 3 shown, on the basis of the Figure 1 embodiment, a lane-based vehicle positioning method is described in detail. The method includes:

[0089] S301. Obtain the road image of the road where the vehicle is located and the position information of the vehicle collected within a preset time window; wherein, the position information includes pose information and longitude and latitude information, and the pose information represents the relative position and attitude of the vehicle relative to the departure place.

[0090] Exemplarily, this step can refer to the above step S101 and will not be elaborated here.

[0091] S302. Generate a lane line map of the road traveled by the vehicle within a preset time window based on the lane line attribute information in each road image and the pose information corresponding to each road image in the preset time window.

[0092] Exemplarily, this step can refer to the above step S102 and will not be elaborated here.

[0093] S303. Obtain the map type of the road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle.

[0094] Exemplarily, this step can refer to the above step S103 and will not be elaborated here.

[0095] S304. Determine the lane similarity between the lane line map and the road map according to the map type of the road map.

[0096] Exemplarily, for road maps of different map types, the lane similarity between the lane line map and the road map can be determined. The lane similarity can represent the similarity degree between the lanes in the lane line map and the lanes in the road map, that is, determine whether the lanes in the lane line map are similar to the lanes in the road map. For example, it can be judged whether the road curvature in the lane line is consistent with the road curvature in the road map. The higher the degree of consistency, the higher the lane similarity.

[0097] In this embodiment, determining the lane similarity between the lane line map and the road map according to the map type of the road map includes: obtaining the lane line attribute information from the lane line map, and obtaining the lane attribute information from the road map according to the map type of the road map; determining the lane similarity between the lane line map and the road map according to the lane line attribute information and the lane attribute information.

[0098] Specifically, the lane line map contains the attribute information of the lane line. The attribute information of the lane line can include the color, type, curvature, orientation, etc. of the lane line. The type can be a solid line or a dashed line, etc. There are no lane lines in the road map, but it contains the attribute information of the lane. The attribute information of the lane can include the curvature, orientation, etc. of the road.

[0099] According to the lane line attribute information and the lane attribute information, the lane similarity between the lane line map and the road map can be determined. For example, if the difference between the curvature in the lane line attribute information and the curvature in the lane attribute information is less than a preset difference threshold, it is determined that the lane similarity is high; or, if the orientation in the lane line attribute information is opposite to the orientation in the lane attribute information, it is determined that the lane similarity is low.

[0100] For example, if the map type of the road map where the vehicle is located is an HD map, lane line attribute information can be obtained from the lane line map. Since the HD map contains lane lines, lane line attribute information can also be obtained from the HD map. By comparing the lane line attribute information of the two, if the lane line attribute information of the two is consistent, the lane similarity is relatively high.

[0101] If the map type of the road map where the vehicle is located is an SD map, it can be determined whether the road curvature in the lane line is consistent with the road curvature in the road map. The higher the degree of consistency, the higher the lane similarity. In this embodiment, the method for determining the lane similarity is not specifically limited.

[0102] The beneficial effect of such a setting is that map matching is performed through attribute information, improving the map matching efficiency, and thus improving the vehicle positioning efficiency.

[0103] S305. Determine the vehicle's positioning information on the road according to the lane similarity and the vehicle's longitude and latitude information.

[0104] Exemplarily, for different types of road maps, according to the lane similarity and the vehicle's longitude and latitude information, the lane line map and the road map are matched or fused, and relevant information about the lane line is added to the road map, so as to perform lane-level positioning for the vehicle. For example, the lane line map can be overlaid on the road map to determine which lane the vehicle's current longitude and latitude position is located in, so as to obtain the positioning information.

[0105] In this embodiment, the map type of the road map is a standard precision map; determining the vehicle's positioning information on the road according to the lane similarity and the vehicle's longitude and latitude information includes: if the lane similarity is greater than a preset similarity threshold, the lane line map and the road map are fused to obtain a fused map; wherein, the fused map is a road map containing lane lines; according to the fused map and the vehicle's longitude and latitude information, determine the vehicle's positioning information on the road.

[0106] Specifically, a similarity threshold is preset. If the lane similarity is less than or equal to the preset similarity threshold, it means that the lane line map and the road map do not match successfully, and the lane where the vehicle is located cannot be determined; if the lane similarity is greater than the preset similarity threshold, the lane line map and the road map can be fused, and the fused road map is determined as the fused map, and the fused map is a road map containing lane lines. According to the fused map and the longitude and latitude information, find the position of the longitude and latitude information in the fused map, determine the lane where the position is located, and obtain the vehicle's positioning information on the road. For example, based on the pose information estimated by DR, the fused map, and the longitude and latitude information of GNSS, a preset Kalman filter algorithm can be used to achieve lane-level positioning.

[0107] In this embodiment, the lane line map and the road map can be matched for similarity according to a preset map matching algorithm. For example, the preset map matching algorithm can be HMM (Hidden Markov Model). After successful matching, the lane line map and the road map are fused to construct a fused map, and the fused map is a quasi-HD map. When performing map matching, the lane line map can be segmented to obtain multiple lane line map segments, and the road map can be segmented to obtain multiple road map segments. For example, it can be evenly divided according to a preset distance, or divided according to lane line types. Each lane line map segment in the lane line map is matched with the corresponding road map segment in the road map using the preset map matching algorithm. If a preset number of map segments are successfully matched, it is considered that the lane line map and the road map are successfully matched.

[0108] The beneficial effect of such a setting is that for an SD map, if the lane line map and the road map are similar, these two maps can be fused to obtain a quasi-HD map, enabling lane-level positioning in the area covered by the SD map.

[0109] In this embodiment, the map type of the road map is a high-precision map; the positioning information of the vehicle on the road is determined according to the lane similarity and the longitude and latitude information of the vehicle, including: if the lane similarity is greater than a preset similarity threshold, then according to the lane line map, the position of the vehicle on the road is determined as the first position point, and according to the longitude and latitude information of the vehicle, the position of the vehicle on the road is determined as the second position point; the offset is determined according to the first position point and the second position point; wherein, the offset represents the distance between the first position point and the second position point; the positioning information of the vehicle on the road is determined according to the offset, the longitude and latitude information of the vehicle, and the road map.

[0110] Specifically, a similarity threshold is preset. If the lane similarity is less than or equal to the preset similarity threshold, it indicates that the lane line map and the road map are not successfully matched, and there is an error in the road map, and the positioning information cannot be determined; if the lane similarity is greater than the preset similarity threshold, the positioning information of the vehicle on the road can be determined according to the road map and the longitude and latitude information.

[0111] When constructing a lane line map, it is necessary to construct it through real-time road images and pose information. The road images and pose information can represent the position of the vehicle on the road. Therefore, the lane line map contains the position of the vehicle on the road. For example, the vehicle is on the third lane of the road, 1 meter away from the left lane line and 2 meters away from the right lane line. Obtain the position of the vehicle on the road from the lane line map, and determine this position as the first position point. The longitude and latitude information can directly represent the geographical location. Therefore, the geographical location represented by the longitude and latitude information can be determined as the second position point.

[0112] Determine the offset between the first position point and the second position point. For example, the distance between the first position point and the second position point can be calculated, and this distance is used as the offset. Through this offset, adjust the longitude and latitude information to make the second position point closer to the first position point, improving the positioning accuracy. For example, based on the pose information deduced by DR, the HD map, the longitude and latitude information of GNSS, and the offset, a preset Kalman filtering algorithm can be used to achieve lane-level positioning. In this embodiment, the calculation method of the Kalman filtering algorithm is not specifically limited.

[0113] The beneficial effect of such a setting is that for the HD map, if the lane line map is similar to the road map, the offset between the position in the high-precision map obtained by GNSS and the position in the lane obtained in real time can be calculated, realizing the auxiliary positioning of the high-precision map through the lane line map, reducing the error caused by the interference of the environment on the GNSS sensor, and improving the accuracy and robustness of the positioning.

[0114] A lane-based vehicle positioning method provided by an embodiment of the present application, by acquiring multiple frames of road images collected by a vehicle within a period of time, as well as the corresponding pose information and longitude and latitude information. According to the road images and the corresponding pose information, the lane line map of the road where the vehicle is currently located can be determined, that is, the relevant data of the lane line is obtained. According to the lane line map and the longitude and latitude information, it is determined which lane the vehicle is on the road, realizing the lane-level positioning of the vehicle. By determining the lane line map, accurate positioning can be performed regardless of whether there is a high-precision map on the current road, improving the efficiency and accuracy of positioning and enhancing the user's navigation experience.

[0115] Figure 4 It is a schematic flow chart of a lane-based vehicle positioning method provided by an embodiment of the present application. As Figure 4 shown, on the basis of the Figure 1 embodiment, a lane-based vehicle positioning method is described in detail. The method includes:

[0116] S401. The vehicle-mounted interface triggers a navigation task, and the lane-level positioning navigation program starts.

[0117] Exemplarily, during the process of driving a vehicle, a user can trigger a navigation task through the in-vehicle interface. For example, the user can issue a navigation instruction through the touch screen, and the vehicle responds to the navigation instruction and starts a lane-level positioning navigation program, that is, starts to execute a lane-based vehicle positioning method.

[0118] S402. Data collection and preprocessing.

[0119] Exemplarily, a variety of sensors are installed on the vehicle, including perception sensors, position inference sensors, GNSS sensors, etc. The perception sensors can include cameras and lidars, etc., and the position inference sensors can include IMUs and wheel speeds, etc. The perception sensors can be used to collect road images, the position inference sensors can be used to perform DR inference to determine pose information, and the GNSS sensors can be used to collect longitude and latitude information. After obtaining the road image, preprocessing such as denoising can be performed on the road image to reduce environmental interference.

[0120] S403. Construction of the lane line map.

[0121] Exemplarily, lane line attribute information is recognized from the road image, and combined with the pose information, a lane line map of the local road is constructed.

[0122] S404. Grab the road map of the current section according to the longitude and latitude information of GNSS and determine the map type.

[0123] Exemplarily, after obtaining the longitude and latitude information, the road map corresponding to the longitude and latitude information can be obtained from a preset map database. Figure 5 It is a schematic diagram of the working process of the sensor. The road image is obtained through the perception sensor, and the relative pose is obtained through the position inference sensor. The lane line map is obtained by combining the road image and the relative pose. The longitude and latitude information is obtained according to GNSS, and the road map is obtained according to the longitude and latitude information and the map database.

[0124] Judge the map type of the road map. The map type is SD map or HD map. If the map type is SD map, execute S405; if the map type is HD map, execute S406.

[0125] S405. SD map matching.

[0126] Exemplarily, the lane line map is matched with the SD map to obtain a quasi-HD map.

[0127] S406. HD map matching.

[0128] Exemplarily, the lane-level map is matched with the HD map, and the lane-level map is used to assist the positioning of the HD map to improve the robustness of the positioning.

[0129] S407. Update and output the lane-level positioning result.

[0130] Exemplarily, regardless of whether the road map is an SD map or an HD map, the current positioning information can be output, that is, it is determined which lane the vehicle is currently in.

[0131] Figure 6 The structural schematic diagram of a lane-based vehicle positioning device provided by this application is as Figure 6 shown. A lane-based vehicle positioning device 60 provided in this embodiment includes:

[0132] An information acquisition module 601, configured to acquire the longitude and latitude information of the vehicle collected within a preset time window, and determine the lane line map of the road where the vehicle is located;

[0133] A type determination module 602, configured to obtain the map type of the road map of the road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle;

[0134] A lane positioning module 603, configured to perform a matching process on the lane line map and the road map according to the map type of the road map, and obtain the positioning information of the vehicle on the road; wherein, the positioning information represents the lane where the vehicle is located on the road.

[0135] In a possible implementation manner, the lane positioning module 603 includes:

[0136] A similarity determination unit, configured to determine the lane similarity between the lane line map and the road map according to the map type of the road map;

[0137] A positioning unit, configured to determine the positioning information of the vehicle on the road according to the lane similarity and the longitude and latitude information of the vehicle.

[0138] In a possible implementation manner, the map type of the road map is a standard precision map; the positioning unit is specifically configured to:

[0139] If the lane similarity is greater than a preset similarity threshold, perform a fusion process on the lane line map and the road map to obtain a fusion map; wherein, the fusion map is a road map containing lane lines;

[0140] Determine the positioning information of the vehicle on the road according to the fusion map and the longitude and latitude information of the vehicle.

[0141] In a possible implementation manner, the map type of the road map is a high-precision map; the positioning unit is specifically configured to:

[0142] If the lane similarity is greater than a preset similarity threshold, determine, based on the lane line map, the position of the vehicle on the road as a first position point, and determine, based on the longitude and latitude information of the vehicle, the position of the vehicle on the road as a second position point;

[0143] Determine an offset based on the first position point and the second position point; wherein the offset represents the distance between the first position point and the second position point;

[0144] Determine the positioning information of the vehicle on the road based on the offset, the longitude and latitude information of the vehicle, and the road map.

[0145] In a possible implementation manner, the similarity determination unit is specifically configured to:

[0146] Obtain lane line attribute information from the lane line map, and obtain lane attribute information from the road map according to the map type of the road map;

[0147] Determine the lane similarity between the lane line map and the road map according to the lane line attribute information and the lane attribute information.

[0148] In a possible implementation manner, the type determination module 602 includes:

[0149] An identification determination unit, configured to determine the road identification of the road where the vehicle is located according to the longitude and latitude information of the vehicle;

[0150] A type determination unit, configured to find, from the preset map database, the map type of the map data corresponding to the road identification as the map type of the road where the vehicle is located.

[0151] In a possible implementation manner, the identification determination unit is specifically configured to:

[0152] Determine the longitude and latitude range to which the longitude and latitude information of the vehicle belongs as a target range according to a plurality of preset longitude and latitude ranges;

[0153] Determine the road identification corresponding to the target range as the road identification of the road where the vehicle is located.

[0154] In a possible implementation manner, the information acquisition module 601 is specifically configured to:

[0155] Acquire the road image of the road where the vehicle is located and the pose information of the vehicle collected within a preset time window;

[0156] Generate a lane line map of the road traveled by the vehicle within the preset time window according to the lane line attribute information in each road image and the pose information corresponding to each road image within the preset time window.

[0157] A vehicle positioning device based on lanes provided in this embodiment can execute the method provided in the above method embodiment. The implementation principle and technical effect are similar, and will not be elaborated here in this embodiment.

[0158] Figure 7 It is a schematic structural diagram of an electronic device provided by this application. As Figure 7 shown, the electronic device 70 provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. Among them, the processor 701, the memory 702, and the communication component 703 are connected through a bus 704.

[0159] In a specific implementation process, at least one processor 701 executes computer execution instructions stored in the memory 702, so that at least one processor 701 executes the above method.

[0160] The specific implementation process of the processor 701 can refer to the above method embodiment. The implementation principle and technical effect are similar, and will not be elaborated here in this embodiment.

[0161] In the above embodiment, it should be understood that the processor may be a central processing unit (English: Central Processing Unit, abbreviated: CPU), or other general-purpose processors, digital signal processors (English: Digital Signal Processor, abbreviated: DSP), application specific integrated circuits (English: Application Specific Integrated Circuit, abbreviated: ASIC), etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or executed and completed by a combination of hardware and software modules in the processor.

[0162] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0163] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the buses in the drawings of the present application are not limited to only one bus or one type of bus.

[0164] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0165] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the above method is implemented.

[0166] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0167] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0168] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0169] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units can be selected according to actual needs to achieve the objectives of the solution of this embodiment.

[0170] In addition, in each embodiment of the present invention, the functional units may be integrated into one processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit.

[0171] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., all kinds of media that can store program codes.

[0172] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When this program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROMs, RAMs, magnetic disks, or optical discs, etc., all kinds of media that can store program codes.

[0173] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily think of other implementation schemes of the present invention. The present invention is intended to cover any variations, uses, or adaptive changes of the present invention. These variations, uses, or adaptive changes follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A lane-based vehicle positioning method, characterized in that, Including: Obtain the longitude and latitude information of the vehicle collected within a preset time window, and determine the lane line map of the road where the vehicle is located; According to the longitude and latitude information of the vehicle, obtain the map type of the road map of the road where the vehicle is located from a preset map database; According to the map type of the road map, perform matching processing on the lane line map and the road map to obtain the positioning information of the vehicle on the road; wherein, the positioning information represents the lane where the vehicle is located on the road.

2. The method according to claim 1, characterized in that, The step of performing matching processing on the lane line map and the road map according to the map type of the road map to obtain the positioning information of the vehicle on the road includes: Determine the lane similarity between the lane line map and the road map according to the map type of the road map; Determine the positioning information of the vehicle on the road according to the lane similarity and the longitude and latitude information of the vehicle.

3. The method according to claim 2, wherein The map type of the road map is a standard-precision map; the step of determining the positioning information of the vehicle on the road according to the lane similarity and the longitude and latitude information of the vehicle includes: If the lane similarity is greater than a preset similarity threshold, perform fusion processing on the lane line map and the road map to obtain a fusion map; wherein, the fusion map is a road map containing lane lines; Determine the positioning information of the vehicle on the road according to the fusion map and the longitude and latitude information of the vehicle.

4. The method according to claim 2, characterized in that The map type of the road map is a high-precision map; the step of determining the positioning information of the vehicle on the road according to the lane similarity and the longitude and latitude information of the vehicle includes: If the lane similarity is greater than a preset similarity threshold, determine the position of the vehicle in the road as a first position point according to the lane line map, and determine the position of the vehicle in the road as a second position point according to the longitude and latitude information of the vehicle; Determine an offset according to the first position point and the second position point; wherein, the offset represents the distance between the first position point and the second position point; Determine the positioning information of the vehicle on the road according to the offset, the longitude and latitude information of the vehicle, and the road map.

5. The method according to claim 2, wherein The step of determining the lane similarity between the lane line map and the road map according to the map type of the road map includes: Obtain lane line attribute information from the lane line map, and obtain lane attribute information from the road map according to the map type of the road map; Determine the lane similarity between the lane line map and the road map according to the lane line attribute information and the lane attribute information.

6. The method according to claim 1, characterized in that, The step of obtaining the map type of the road map of the road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle includes: Determine the road identifier of the road where the vehicle is located according to the longitude and latitude information of the vehicle; Search in the preset map database for the map type of the map data corresponding to the road identifier, which is the map type of the road map of the road where the vehicle is located.

7. The method according to claim 6, wherein Determining the road sign of the road where the vehicle is located according to the longitude and latitude information of the vehicle includes: Determining the longitude and latitude range to which the longitude and latitude information of the vehicle belongs according to a plurality of preset longitude and latitude ranges as the target range; Determining the road sign corresponding to the target range as the road sign of the road where the vehicle is located.

8. A lane-based vehicle positioning device, characterized in that, Including: An information acquisition module, configured to acquire the longitude and latitude information of the vehicle collected within a preset time window and determine the lane line map of the road where the vehicle is located; A type determination module, configured to obtain the map type of the road map of the road where the vehicle is located from a preset map database according to the longitude and latitude information of the vehicle; A lane positioning module, configured to perform matching processing on the lane line map and the road map according to the map type of the road map to obtain the positioning information of the vehicle on the road; wherein, the positioning information represents the lane where the vehicle is located on the road.

9. An electronic device, characterized in that, Including: A memory, a processor; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method according to any one of claims 1-7.

10. A computer-readable storage medium / computer program product, characterized in that, The computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method according to any one of claims 1-7; and / or, The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the method according to any one of claims 1-7.

Images