Vehicle positioning method and device, electronic equipment and readable storage medium

Abstract

The embodiment of the invention provides a vehicle positioning method and device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring a traffic light image shot by a camera in a vehicle and lane information corresponding to the vehicle; determining a first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera; determining a second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera and the first global pose; determining a relative angle of the traffic light relative to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose and the second global pose; and according to the second global pose, the relative angle and the lane information, determining positioning information for representing a lane where the vehicle is located in the road. According to the embodiment of the invention, the traffic light is used as a natural landmark, and the lane information is combined, so that high-precision lane-level positioning independent of a GPS signal is realized.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of autonomous driving technology, and in particular, to a vehicle positioning method, device, electronic device, and readable storage medium. Background Art

[0002] Currently, autonomous driving is in a stage of rapid development. With the progress of technology and the increasing demand for traffic safety and convenience, technologies related to autonomous driving have emerged continuously, promoting the transformation of the entire transportation industry. Autonomous vehicles require high-precision lane positioning information to achieve stable autonomous driving functions. In traditional autonomous driving technologies, vehicle positioning mainly relies on GPS (Global Positioning System) signals. However, during the driving process of the vehicle, GPS signals are easily affected by factors such as building occlusion, weather changes, and electromagnetic interference, resulting in a serious impact on the accuracy of vehicle positioning. Therefore, the current positioning technology relying on GPS signals is difficult to achieve high-precision vehicle positioning. Summary of the Invention

[0003] The embodiments of the present application provide a vehicle positioning method, device, electronic device, and readable storage medium, aiming to improve the problem that the current positioning technology relying on GPS signals is difficult to achieve high-precision vehicle positioning.

[0004] The embodiments of the present application disclose a vehicle positioning method, and the method includes:

[0005] Obtain a traffic light image captured by a camera in the vehicle and lane information corresponding to the vehicle; there is a traffic light in the traffic light image, the traffic light has corresponding type point information, the camera has corresponding parameters, and the lane information is used to characterize the information of each lane on the road where the vehicle travels;

[0006] Determine a first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera;

[0007] Determine a second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera, and the first global pose;

[0008] Determine a relative angle of the traffic light with respect to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose;

[0009] Determine positioning information for characterizing the lane in which the vehicle is located on the road according to the second global pose, the relative angle, and the lane information.

[0010] Optionally, the traffic light image at least includes a first image and a second image with a time difference, and the parameters corresponding to the camera include internal parameters and first external parameters, where the first external parameters are used to characterize the rotation and translation of the camera in the world coordinate system; determining the first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera includes:

[0011] Extract first feature points in the first image and second feature points in the second image; both the first feature points and the second feature points correspond to the target points of the traffic light;

[0012] Determine the first coordinates of the first feature points in the first image and the second coordinates of the second feature points in the second image;

[0013] Determine the measurement coordinates corresponding to the target points in the world coordinate system according to the first coordinates, the second coordinates, the internal parameters, and the first external parameters;

[0014] Determine the measurement coordinates as the first global pose corresponding to the traffic light.

[0015] Optionally, the parameters corresponding to the camera further include second external parameters, where the second external parameters are used to characterize the rotation and translation of the camera relative to the rear axle of the vehicle; determining the second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera, and the first global pose includes:

[0016] Determine the intermediate global pose corresponding to the camera according to the first coordinates, the internal parameters, and the first global pose; or determine the intermediate global pose corresponding to the camera according to the second coordinates, the internal parameters, and the first global pose;

[0017] Determine the second global pose corresponding to the vehicle according to the second external parameters and the intermediate global pose.

[0018] Optionally, the type point information includes the geographical coordinates corresponding to the target points provided by the navigation in the vehicle in the world coordinate system. Determining the relative angle of the traffic light with respect to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose includes:

[0019] Determine the perceived angle of the traffic light with respect to the vehicle according to the second external parameters and the first global pose;

[0020] Determine the geographical angle of the traffic light with respect to the vehicle according to the geographical coordinates and the second global pose;

[0021] Determine the perception angle and the geographical angle as the relative angle.

[0022] Optionally, determining the positioning information for characterizing the lane in which the vehicle is located on the road according to the second global pose, the relative angle, and the lane information includes:

[0023] Adjust the second global pose according to the relative angle to obtain the target global pose corresponding to the vehicle;

[0024] Determine the positioning information for characterizing the lane in which the vehicle is located on the road according to the target global pose and the lane information.

[0025] Optionally, adjusting the second global pose according to the relative angle to obtain the target global pose corresponding to the vehicle includes:

[0026] Calculate the angle difference between the perception angle and the geographical angle;

[0027] Construct a factor graph according to the angle difference and the second global pose; wherein, the factor nodes of the factor graph are residual functions constructed based on the angle difference, and the variable nodes of the factor graph are the second global pose;

[0028] Update the second global pose in the factor graph according to the sum of the residual functions in the factor graph to obtain an intermediate factor graph;

[0029] Determine a sliding window;

[0030] Perform local optimization on the intermediate factor graph based on the data within the sliding window to obtain a target factor graph;

[0031] Extract the optimized second global pose from the target factor graph as the target global pose corresponding to the vehicle.

[0032] Optionally, the lane information includes the coordinates corresponding to the centerlines of each lane in the world coordinate system. Determining the positioning information for characterizing the lane in which the vehicle is located on the road according to the target global pose and the lane information includes:

[0033] Determine the horizontal distance between the vehicle and the centerlines of each lane according to the target global pose and the coordinates corresponding to the centerlines;

[0034] Determine the target lane in which the vehicle is located on the road according to the horizontal distance;

[0035] Generate positioning information for characterizing that the vehicle is located in the target lane.

[0036] An embodiment of the present application also discloses a positioning device for a vehicle, which is characterized by comprising:

[0037] An acquisition module, configured to acquire a traffic light image captured by a camera in the vehicle and lane information corresponding to the vehicle; there is a traffic light in the traffic light image, the traffic light has corresponding type point information, the camera has corresponding parameters, and the lane information is used to characterize information of each lane on the road where the vehicle travels;

[0038] A first global pose module, configured to determine a first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera;

[0039] A second global pose module, configured to determine a second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera, and the first global pose;

[0040] A relative angle determination module, configured to determine a relative angle of the traffic light relative to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose;

[0041] A positioning module, configured to determine positioning information for characterizing the lane in which the vehicle is located on the road according to the second global pose, the relative angle, and the lane information.

[0042] An embodiment of the present application also discloses an electronic device, including a processor and a memory. Among them, the memory is used to store a computer program; the processor is used to execute the program stored on the memory to implement the vehicle positioning method according to any one of the embodiments of the present application.

[0043] An embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the vehicle positioning method according to any one of the embodiments of the present application is implemented.

[0044] The embodiments of the present application have the following advantages:

[0045] In an embodiment of the present application, a traffic light image captured by a camera in a vehicle and lane information corresponding to the vehicle are obtained; there is a traffic light in the traffic light image, the traffic light has corresponding type point information, the camera has corresponding parameters, and the lane information is used to characterize the information of each lane on the road where the vehicle travels; a first global pose corresponding to the traffic light is determined according to the traffic light image and the parameters corresponding to the camera; a second global pose corresponding to the vehicle is determined according to the traffic light image, the parameters corresponding to the camera, and the first global pose; a relative angle of the traffic light with respect to the vehicle is determined according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose; positioning information for characterizing the lane in which the vehicle is located on the road is determined according to the second global pose, the relative angle, and the lane information. In the embodiment of the present application, by using the traffic light image captured by the camera and the lane information, combining the camera parameters, through multi-step pose calculation and relative angle analysis, the lane in which the vehicle is located is finally determined, breaking through the limitation that traditional GPS positioning is vulnerable to environmental interference. Through the collaboration of visual features (traffic lights) and high-precision map data (lane information and type point information), autonomous positioning based on the spatial position of traffic lights and the geometric relationship of lanes is realized, which can avoid the risk of inaccurate positioning caused by the loss of GPS signals. Using traffic lights as natural landmarks and combining lane information, a high-precision lane-level positioning that does not rely on GPS signals is realized. Description of the Drawings

[0046] Figure 1 is a flowchart of a vehicle positioning method provided by an embodiment of the present application;

[0047] Figure 2 is a flowchart of a vehicle positioning method provided by another embodiment of the present application;

[0048] Figure 3 is a structural diagram of a vehicle positioning device provided by an embodiment of the present application;

[0049] Figure 4 is a structural diagram of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0050] In order to make the technical problems, technical solutions, and beneficial effects solved by the present application more clearly understood, the present application will be further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] With the continuous development of autonomous driving technology, ADAS (Advanced Driving Assistance System) as an important part of autonomous driving technology is also growing and evolving. ADAS needs to assist the driver in driving through a series of sensors and algorithms to improve driving safety. Currently, a variety of ADAS products have emerged in the market, such as lane departure warning systems, adaptive cruise control systems, etc.

[0052] Autonomous vehicles and ADAS systems typically use multiple sensors (such as cameras, radars, lidars, etc.) to obtain information about the vehicle's surrounding environment. However, how to effectively fuse data from different sensors to improve the accuracy and reliability of positioning remains a technical challenge.

[0053] Secondly, in vehicle navigation and positioning services, map matching is usually an important step. However, due to the complexity and variability of roads, map matching often has errors, resulting in inaccurate vehicle positioning.

[0054] Moreover, in order to improve the accuracy and stability of positioning, the algorithm needs to be continuously optimized. However, algorithm optimization often involves complex mathematical models and calculation processes, which require a large amount of time and resources.

[0055] In addition, traditional vehicle positioning methods often experience unstable positioning when facing changes in the road environment, such as wear, occlusion, or changes in lane lines, and weather conditions (such as rainy days, foggy days, etc.) may also affect the stability of positioning.

[0056] Obviously, traditional lane positioning methods often highly rely on external environmental conditions, such as the strength of GPS signals, the performance of radar sensors, weather conditions, road environment, etc. In the case of poor or limited external environments, the positioning effects of these methods will be severely affected.

[0057] In the existing technology, sensor switching can also be performed by determining whether GNSS (Global Navigation Satellite System) is normal. When GNSS is normal, GNSS information is used for positioning. When GNSS is abnormal and the lidar is normal, lidar information is used for positioning. However, this method does not consider the problem of position jumps that occur when switching from GNSS to lidar, which in turn leads to jumps in the positioning results, and the accuracy of vehicle positioning will also be severely affected.

[0058] Therefore, in the embodiments of the present application, by providing a vehicle positioning method, traffic lights installed beside the road are used as known reference points, and the global positioning of the traffic lights is obtained through the traffic light images captured by the camera, so as to perform lane positioning, and the three-dimensional position of the vehicle in the current lane can be accurately determined, providing stable and high-precision lane positioning information for autonomous vehicles, helping the vehicle to maintain the correct driving trajectory, avoiding lane deviation, and thus improving the safety and reliability of autonomous driving.

[0059] In the present application, the type point information refers to the precise three-dimensional coordinate information (such as height, position, orientation, etc.) of the traffic light in the physical world, usually from a high-precision map or a navigation system. The type point information can be used as a known "spatial anchor point" for comparison with the position of the traffic light sensed by the camera to achieve the fusion of visual positioning and map data.

[0060] In the present application, the global pose (the first global pose / second global pose / intermediate global pose / target global pose) refers to a complete description of the position (translation) and direction (rotation) of an object (such as a traffic light, vehicle, or camera) in the world coordinate system.

[0061] In the present application, the extrinsic parameters (the first extrinsic parameter / second extrinsic parameter) refer to the geometric relationship parameters between the camera and an external coordinate system (such as a vehicle or the world coordinate system), including the rotation matrix and the translation vector.

[0062] In the present application, the factor graph refers to a probabilistic graphical model composed of "variable nodes" (parameters to be optimized, such as vehicle pose) and "factor nodes" (observation constraints, such as angle differences), and is used for the mathematical optimization of multi-source data fusion.

[0063] In the present application, the sliding window refers to a dynamic data processing strategy that only retains the observation data of the most recent several moments for calculation and discards historical data to control the computational complexity.

[0064] In the present application, the residual function refers to a mathematical function of the difference between the observed value and the predicted value (such as the square of the angle difference), which is used to measure the error size in an optimization problem. In the factor graph, physical constraints (such as angle differences) are quantified into optimizable mathematical metrics to drive pose correction.

[0065] In the present application, the perceived angle refers to the azimuth angle (such as the yaw angle) of the traffic light relative to the vehicle directly calculated from the camera image.

[0066] In the present application, the geographical angle refers to the theoretical azimuth angle calculated through geometric relationships based on the geographical coordinates of the traffic light provided by the map.

[0067] In this application, the target point refers to a point on the traffic light with clear geometric features (such as the center point, border corner points), which is used for image matching and 3D reconstruction. The target point serves as a reference point for feature extraction and spatial positioning to ensure the consistency among multiple frames of images.

[0068] In this application, the coordinates corresponding to the center line refer to the continuous coordinate sequence of the lane center line in the high-precision map, which describes the geometric shape of the lane. By mapping the vehicle pose to the lane topological structure, it is possible to determine the lane where the vehicle is located through distance calculation.

[0069] A vehicle positioning method provided by an embodiment of this application includes: obtaining a traffic light image captured by a camera in the vehicle and lane information corresponding to the vehicle; there is a traffic light in the traffic light image, the traffic light has corresponding type point information, the camera has corresponding parameters, and the lane information is used to characterize the information of each lane on the road where the vehicle travels;

[0070] Determine the first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera;

[0071] Determine the second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera, and the first global pose;

[0072] Determine the relative angle of the traffic light with respect to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose;

[0073] Determine the positioning information used to characterize the lane where the vehicle is located on the road according to the second global pose, the relative angle, and the lane information.

[0074] The embodiment of this application uses the traffic light image captured by the camera and the lane information, combines the camera parameters, and through multi-step pose calculation and relative angle analysis, finally determines the lane where the vehicle is located, breaking through the limitation that traditional GPS positioning is vulnerable to environmental interference. Through the collaboration of visual features (traffic lights) and high-precision map data (lane information and type point information), it realizes autonomous positioning based on the spatial position of the traffic light and the geometric relationship of the lane, can avoid the risk of inaccurate positioning caused by the loss of GPS signals, uses the traffic light as a natural landmark, combines the lane information, and realizes a high-precision lane-level positioning that does not rely on GPS signals.

[0075] Embodiment 1

[0076] An embodiment of this application provides a vehicle positioning method. Please refer to Figure 1 , including the following steps:

[0077] S110. Obtain the traffic light image captured by a camera in the vehicle and the lane information corresponding to the vehicle; there is a traffic light in the traffic light image, the traffic light has corresponding type point information, the camera has corresponding parameters, and the lane information is used to characterize the information of each lane on the road where the vehicle travels;

[0078] S120. Determine the first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera;

[0079] S130. Determine the second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera, and the first global pose;

[0080] S140. Determine the relative angle of the traffic light with respect to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose;

[0081] S150. Determine the positioning information used to characterize the lane where the vehicle is located on the road according to the second global pose, the relative angle, and the lane information.

[0082] In step S110, an image containing a traffic light is captured by an in-vehicle camera, the lane information (such as the number of lanes, the coordinates of the center line, etc.) of the current road is extracted from a high-precision map or a navigation system, and the calibration parameters of the camera are obtained. Specifically, two consecutive frames of images containing the traffic light are captured by the camera, and it is necessary to ensure that there is sufficient parallax between the two frames of images, that is, the position of the traffic light changes significantly in the two images.

[0083] As an example, during the driving of the vehicle, two frames of images are quickly captured by the camera in front of the vehicle. In theory, as long as the vehicle is moving, there will surely be parallax between the two frames of images within a certain period of time.

[0084] To ensure sufficient parallax between the two frames of images, it can be verified whether there is sufficient parallax between the two frames of images through feature point matching and displacement quantization. If not, re-capture is required to ensure the effective parallax between the images, thereby supporting subsequent high-precision positioning.

[0085] In the embodiment of the present application, the traffic light image is used as the input for visual positioning to provide a fixed landmark (traffic light) in a dynamic environment. By obtaining lane information, the positioning range of the vehicle can be restricted. Through the camera parameters, the conversion relationship between the image pixel coordinates and the real-world coordinates can be established, realizing the conversion from the pixel coordinates of the traffic light in the image to the world coordinates of the vehicle in the real world.

[0086] In step S120, based on the traffic light image and the parameters corresponding to the camera, the global three-dimensional coordinates of the traffic light, that is, the first global pose, can be calculated using the triangulation principle.

[0087] Specifically, the triangulation principle is based on observing the same point on the same object by two cameras or at two times. By calculating the positions of this point in the two camera coordinate systems, the position of the object in the three-dimensional space can be obtained, that is, the three-dimensional coordinates of the object in the world coordinate system can be obtained.

[0088] In the real world space, as an infrastructure of the road, the position of the traffic light is relatively fixed, and the position provided by the high-precision map or navigation system is also accurate. Using the traffic light as a reference point for triangulation can significantly improve the positioning accuracy.

[0089] Therefore, in the embodiment of the present application, the two-dimensional image coordinates in the traffic light image can be converted into three-dimensional coordinates through the parameters corresponding to the camera, and used as a reference anchor point for subsequent vehicle positioning, without relying on the GPS signal, and directly realizing the positioning of the vehicle in space through visual perception.

[0090] In step S130, according to the first global pose of the traffic light and the camera parameters, the position and direction of the vehicle itself in the world coordinate system are deduced, that is, the second global pose. The embodiment of the present application converts the absolute pose information of the traffic light into the positioning result of the vehicle itself, realizes real-time positioning based on a single landmark (traffic light), without multi-sensor fusion, and avoids the problem of low positioning result caused by the low accuracy of multi-sensor fusion.

[0091] In step S140, combining the type point information (known geographical coordinates) of the traffic light, the camera parameters and the vehicle pose, the relative angle of the traffic light with respect to the vehicle is calculated, so as to verify the consistency of the pose calculation based on the geometric relationship between the traffic light and the vehicle in the subsequent process, perform error correction, and further improve the reliability of the positioning.

[0092] In step S150, according to the second global pose, relative angle and lane information of the vehicle, the lane where the vehicle is currently located can be obtained through spatial geometric calculation. The embodiment of the present application maps the abstract global pose to the specific lane topology structure, and outputs a lane-level positioning result that can be directly used by the autonomous driving decision-making system, such as the positioning information that "the vehicle is located in the second lane from the left".

[0093] In the embodiment of the present application, the traffic light image captured by the camera and the lane information are used. Combining with the camera parameters, through multi-step pose calculation and relative angle analysis, the lane where the vehicle is located is finally determined, breaking through the limitation that traditional GPS positioning is vulnerable to environmental interference. Through the cooperation of visual features (traffic lights) and high-precision map data (lane information and type point information), autonomous positioning based on the spatial position of traffic lights and the geometric relationship of lanes is realized, which can avoid the risk of inaccurate positioning caused by the loss of GPS signals. Using traffic lights as natural landmarks and combining with lane information, a high-precision lane-level positioning that does not rely on GPS signals is realized.

[0094] In an embodiment of the present application, the traffic light image at least includes a first image and a second image with a time difference. The parameters corresponding to the camera include an internal parameter and a first external parameter. The first external parameter is used to characterize the rotation and translation of the camera in the world coordinate system. The step S120 of determining the first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera includes:

[0095] Extract a first feature point in the first image and a second feature point in the second image; both the first feature point and the second feature point correspond to the target point of the traffic light;

[0096] Determine the first coordinate of the first feature point in the first image and the second coordinate of the second feature point in the second image;

[0097] Determine the measurement coordinate corresponding to the target point in the world coordinate system according to the first coordinate, the second coordinate, the internal parameter and the first external parameter;

[0098] Determine the measurement coordinate as the first global pose corresponding to the traffic light.

[0099] In step S110, by acquiring two consecutive frames of images containing traffic lights, that is, the first image and the second image, and there is sufficient parallax between the first image and the second image, that is, the first image and the second image have a time difference.

[0100] In the embodiment of the present application, through feature point extraction, feature point matching and triangulation, the traffic lights in the first image and the second image can be converted into traffic lights in the real space, and then the first global pose corresponding to the traffic lights can be obtained.

[0101] Specifically, first, the method of deep learning can be used to identify the overall traffic lights in two frames of images (the first image and the second image), and extract the feature points of the traffic lights, such as the corner points of the traffic light border, the center point of the traffic light, or the identification vertices of the arrows, etc. These feature points will be used for subsequent feature point matching and triangulation. As an example, in the embodiments of the present application, the feature points of the traffic lights can be extracted by traditional vision algorithms (such as Canny edge detection and Harris corner localization) or deep learning models (such as a key point detection network based on the attention mechanism).

[0102] After extracting the feature points of the traffic lights in the two frames of images respectively, it is necessary to determine which feature points represent the same part of the traffic light in the two frames of images through image processing and computer vision algorithms (such as feature matching algorithms like SIFT, SURF, etc.). As an example, when the target point refers to the upper right corner point of the traffic light border, then the upper right corner point of the traffic light border in the first image is the first feature point, and the upper right corner point of the traffic light border in the second image is the second feature point. Both the first feature point and the second feature point correspond to the upper right corner point of the traffic light border.

[0103] By calculating the positions of the target point in the two image coordinate systems (the position of the first feature point in the first image and the position of the second feature point in the second image), the position of the traffic light in the three-dimensional space can be obtained.

[0104] It should be noted that from the perspective of the pure mathematical triangulation principle, as long as a corresponding point on the same object can be found in two frames of images, and parameters such as the relative poses (intrinsic and extrinsic parameters) of the cameras that captured the images are known, the position of this point in the three-dimensional space can be determined by calculating its positions in the two image coordinate systems. For example, under ideal calibration and imaging conditions, only one feature point can also construct the geometric relationship for triangulation calculation, and then obtain its corresponding three-dimensional coordinates.

[0105] However, in the actual application process, in order to improve the accuracy and stability of three-dimensional reconstruction, multiple points are usually required. Because a single point may have measurement errors, matching errors, etc., which will lead to inaccurate calculation results of the three-dimensional coordinates. Therefore, data redundancy and averaging can be performed through multiple points to reduce the influence of errors. For example, in the fields of robot navigation and autonomous driving, a large amount of environmental point information needs to be obtained to accurately perceive the three-dimensional structure of the surrounding environment.

[0106] Therefore, in the embodiments of the present application, multiple target points can be obtained through feature point matching, and the corresponding feature points of each target point can be obtained. The embodiments of the present application introduce the process of determining the first global pose corresponding to the traffic light through the feature points corresponding to one target point.

[0107] A camera (image sensor) is usually modeled as a pinhole camera model, and its projection equation is expressed as follows:

[0108] λp = PX

[0109] where λ is the depth value, p is the pixel coordinate on the image plane, P is the projection matrix, which contains the internal and external parameters (the first external parameter) corresponding to the camera, and X is the point coordinate of the traffic light in the three-dimensional space, that is, the first global pose.

[0110] The projection matrix P can be expressed as follows:

[0111] P = K[R|t]

[0112] where K is the internal parameter matrix of the camera, including information such as the focal length and the principal point coordinate, R is the rotation matrix of the camera, representing the rotation of the camera relative to the world coordinate system, and t is the translation vector of the camera, representing the translation of the camera relative to the world coordinate system.

[0113] Assume that the traffic light appears in two images respectively. Therefore, the pixel coordinate p1 (the first coordinate) of the first feature point in the first image, and the pixel coordinate p2 (the second coordinate) of the second feature point in the second image, as well as the corresponding projection matrices P1 and P2 can be obtained. According to the projection equation (i.e., formula (1)), a system of equations containing two equations can be obtained as follows:

[0114]

[0115] Combining the above two equations, a linear system of equations about X can be obtained. However, since λ1 and λ2 are the depth values of the positions, this system of equations is homogeneous and cannot be directly solved.

[0116] To solve for X, the method of singular value decomposition (SVD) is adopted. Specifically, first, the system of equations needs to be converted into a matrix form, which is specifically expressed as follows:

[0117] AX = 0

[0118] where A is a matrix composed of the projection matrix P (P1 / P2) and the pixel coordinate (p1 / p2). Then, perform SVD decomposition on A to obtain: A = U∑VT, where U and V are orthogonal matrices, and ∑ is a diagonal matrix containing the singular values of A.

[0119] Finally, take the column vector corresponding to the smallest singular value in the orthogonal matrix V (i.e., the last column of the orthogonal matrix V), and normalize it. The obtained X is the three-dimensional coordinate (measurement coordinate) corresponding to the target point in the world coordinate system, that is, the first global pose corresponding to the traffic light.

[0120] In the embodiment of the present application, the infrastructure of the road (traffic light) is used as a reference point for triangulation. Only one sensor (camera) is required to obtain the accurate position of the traffic light, without the combination of multiple sensors, avoiding the reduction in the accuracy of traffic light positioning caused by the low accuracy of multiple sensor fusion, improving the accuracy of traffic light positioning, so as to better realize the positioning of the vehicle based on the positioning result of the traffic light in the subsequent process.

[0121] In an embodiment of the present application, the parameters corresponding to the camera further include a second extrinsic parameter, and the second extrinsic parameter is used to characterize the rotation and translation of the camera relative to the rear axle of the vehicle; the step S130 of determining the second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera, and the first global pose includes:

[0122] Determining the intermediate global pose corresponding to the camera according to the first coordinate, the intrinsic parameter, and the first global pose; or, determining the intermediate global pose corresponding to the camera according to the second coordinate, the intrinsic parameter, and the first global pose;

[0123] Determining the second global pose corresponding to the vehicle according to the second extrinsic parameter and the intermediate global pose.

[0124] In the embodiment of the present application, after obtaining the first global pose corresponding to the traffic light, the intermediate global pose corresponding to the camera can be calculated through the camera imaging principle. Specifically, its calculation essence is through the Perspective-n-Point (PnP) algorithm, which infers the position and pose of an object in three-dimensional space from points in a two-dimensional image. It can be understood that when given points in three-dimensional space (the first global pose) and their corresponding two-dimensional image projection points (the first coordinate or the second coordinate), the PnP method can solve the pose of the camera, that is, the rotation matrix and displacement vector of the camera, which is also the intermediate global pose in the embodiment of the present application.

[0125] It should be noted that the second extrinsic parameter refers to the rotation and translation of the camera relative to the rear axle of the vehicle, that is, taking the rear axle of the vehicle as the origin of the vehicle coordinate system, and the second extrinsic parameter can be understood as the position of the camera in the vehicle coordinate system.

[0126] In the embodiment of the present application, based on the intermediate global pose and the second extrinsic parameter, the conversion between the camera coordinate system, the world coordinate system, and the vehicle coordinate system can be realized. Specifically, the conversion from the camera coordinate system to the vehicle coordinate system can be realized through the second extrinsic parameter, and the conversion from the camera coordinate system to the world coordinate system can be realized through the intermediate global pose. Therefore, by combining the intermediate global pose and the second extrinsic parameter, the second global pose corresponding to the vehicle can be obtained.

[0127] As an example, the present application can multiply the intermediate global pose by the second extrinsic parameter to obtain the second global pose.

[0128] Through the conversion between different coordinate systems, the embodiment of the present application can achieve a high-precision and highly reliable mapping from visual perception (traffic light image) to the vehicle body pose (second global pose), thereby realizing high-precision positioning of the vehicle.

[0129] In an embodiment of the present application, the type point information includes the geographical coordinates corresponding to the target point provided by the navigation in the vehicle in the world coordinate system. The step S140 of determining the relative angle of the traffic light with respect to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose includes:

[0130] Determine the perceived angle of the traffic light with respect to the vehicle according to the second extrinsic parameter and the first global pose;

[0131] Determine the geographical angle of the traffic light with respect to the vehicle according to the geographical coordinates and the second global pose;

[0132] Determine the relative angle by using the perceived angle and the geographical angle.

[0133] In the embodiment of the present application, although the position of the vehicle in the real-world space (second global pose) has been determined in step S130, there will be certain errors if lane-level positioning is directly based on the second global pose. Therefore, the embodiment of the present application also calculates the relative angle of the traffic light with respect to the vehicle to optimize the positioning result based on the relative angle subsequently, so as to improve the accuracy of the positioning result.

[0134] It should be noted that the type point information includes the accurate geographical coordinates of the traffic light provided by the navigation system in the world coordinate system.

[0135] As an example, the perceived angle specifically reflects the orientation of the traffic light under the camera's perspective and is affected by the camera installation position (second extrinsic parameter). And the first global pose is determined based on the image captured by the camera. Therefore, by combining the first global pose and the second extrinsic parameter, the angle of the traffic light with respect to the camera can be calculated, and this angle is the perceived angle zij in the embodiment of the present application.

[0136] As an example, the geographical angle specifically reflects the absolute orientation of the traffic light relative to the vehicle in the map coordinate system. Depending on the accuracy of the high-precision map, at this time, it is necessary to calculate the relative angle between the second global pose and the geographical coordinate according to the geographical coordinate in the type point information provided by the navigation, that is, the geographical angle rij(x) of the traffic light relative to the vehicle, where x is the second global pose corresponding to the vehicle.

[0137] In the embodiment of the present application, by fusing the visual perception angle (based on camera parameters and image positioning) and the geographical angle (based on the navigation coordinates of the high-precision map), a geometric constraint and data fusion mechanism is established to effectively correct the error of a single positioning source, improve the accuracy of the vehicle's global pose, and provide a more reliable spatial relationship basis for subsequent lane-level positioning.

[0138] In an embodiment of the present application, the step S150 of determining the positioning information for characterizing the lane in which the vehicle is located on the road according to the second global pose, the relative angle, and the lane information includes:

[0139] Adjust the second global pose according to the relative angle to obtain the target global pose corresponding to the vehicle;

[0140] Determine the positioning information for characterizing the lane in which the vehicle is located on the road according to the target global pose and the lane information.

[0141] In the embodiment of the present application, lane-level three-dimensional positioning of the vehicle is realized based on the relative angle. Specifically, it is necessary to continuously adjust the second global pose based on the relative angle until the requirements are met. At this time, the second global pose is the target global pose.

[0142] The target global pose is the final position of the vehicle calculated in the real-world space in the embodiment of the present application. Based on this, combined with the lane information of the current road on which the vehicle is traveling, the positioning information of which lane the vehicle is located on the current road can be determined.

[0143] In the embodiment of the present application, the global pose (second global pose) of the vehicle is dynamically optimized through the relative angle, and combined with the lane geometric information (such as the center line coordinates), the positioning result is refined to the lane level to achieve high-precision three-dimensional positioning, meeting the real-time and accuracy requirements of autonomous driving for lane-level position judgment.

[0144] In an embodiment of the present application, the adjusting the second global pose according to the relative angle to obtain the target global pose corresponding to the vehicle includes:

[0145] Calculate the angle difference between the perception angle and the geographical angle;

[0146] Construct a factor graph based on the angle difference and the second global pose; wherein, the factor nodes of the factor graph are residual functions constructed based on the angle difference, and the variable nodes of the factor graph are the second global pose;

[0147] Update the second global pose in the factor graph according to the sum of the residual functions in the factor graph to obtain an intermediate factor graph;

[0148] Determine a sliding window;

[0149] Based on the data within the sliding window, perform local optimization on the intermediate factor graph to obtain a target factor graph;

[0150] Extract the optimized second global pose from the target factor graph as the target global pose corresponding to the vehicle.

[0151] In the embodiments of the present application, it is necessary to calculate the angle difference between the perceived angle and the geographical angle, and construct a factor graph based on this angle difference and the second global pose. A factor graph is a probabilistic graphical model composed of variable nodes (parameters to be optimized) and factor nodes (observation constraints). In the embodiments of the present application, the second global pose is the parameter to be optimized, and the residual function constructed by the angle difference is the observation constraint. Therefore, the factor nodes in the factor graph in the embodiments of the present application are residual functions, and the variable nodes are the second global pose. Specifically, the residual function eij(x) = zij - rij(x).

[0152] As an example, the global positioning problem of the vehicle in the embodiments of the present application can be transformed into minimizing the sum or weighted sum of the residuals generated by all factors: minx∑ ij ρ(eij(x)), where ρ is a robust loss function used to handle noise and outliers. Subsequently, a non-linear optimization algorithm (such as Levenberg-Marquardt) can be used to iteratively update the variable nodes (the second global pose) in the factor graph to obtain an intermediate factor graph. The intermediate factor graph contains the preliminarily optimized second global pose but has not been locally optimized by the sliding window.

[0153] In the embodiments of the present application, it is necessary to set a sliding window according to the computing resources and real-time requirements to dynamically update and optimize the variables, avoiding the accumulation of historical errors. Specifically, if the window is too large, it will lead to high computational overhead and poor real-time performance; if the window is too small, it will lead to unstable optimization results and be easily affected by noise.

[0154] It should be noted that in the embodiments of the present application, only the data within the sliding window is locally optimized, and the variable nodes (the second global pose after preliminary optimization) are updated. The gradient descent method can be used for the iterative optimization algorithm. Only the variable nodes and factor nodes that change within the window are updated, and the historical data outside the window is retained as a priori constraints to avoid pose jumps, so as to obtain the final target factor graph. The target factor graph contains the second global pose after final optimization, that is, the target global pose in the present application. The target global pose in the present application is a high-precision pose that has been verified by the angle difference and optimized by the sliding window, and can be directly used for lane-level positioning.

[0155] In the embodiments of the present application, a residual function is constructed using the angle difference to realize the iterative correction of the vehicle pose. The optimization result is dynamically updated through the sliding window mechanism to suppress the cumulative error and instantaneous noise. Moreover, the local optimization can retain the historical data as a priori constraints to avoid pose jumps and improve the system stability. In addition, the angle difference verification realizes the closed-loop fusion of visual positioning and map data to ensure the accuracy of long-term vehicle positioning.

[0156] In an embodiment of the present application, the lane information includes the coordinates corresponding to the center lines of each lane in the world coordinate system. Determining the positioning information for characterizing the lane in which the vehicle is located on the road according to the target global pose and the lane information includes:

[0157] Determine the horizontal distance between the vehicle and the center lines of each lane according to the target global pose and the coordinates corresponding to the center lines;

[0158] Determine the target lane in which the vehicle is located on the road according to the horizontal distance;

[0159] Generate positioning information for characterizing that the vehicle is located in the target lane.

[0160] It should be noted that the lane information not only includes the center lines of the lanes and their corresponding coordinates in the world coordinate system, but also includes information related to the lanes such as the number of lanes and the lane width. The target global pose is the coordinates corresponding to the vehicle in the world coordinate system.

[0161] As an example, project the target global pose onto the road plane, and then find a point on the center line of each lane that is closest to the vehicle. The Euclidean distance can be used to calculate the distance between the vehicle and this point, that is, the horizontal distance between the vehicle and the center lines of each lane.

[0162] Specifically, among the multiple horizontal distances, find the lane corresponding to the minimum horizontal distance, and this lane can be determined as the target lane in which the vehicle is currently located. Therefore, positioning information for characterizing that the vehicle is located in the target lane can be generated.

[0163] As an example, assume that there are five lanes in the current road, namely lane A, lane B, lane C, lane D, and lane E. Calculate the horizontal distances between the target global pose and the five lanes respectively, which are horizontal distance d1, horizontal distance d2, horizontal distance d3, horizontal distance d4, and horizontal distance d5. Sort the horizontal distances in ascending order, and we can get d3 < d2 < d4 < d1 < d5. Therefore, lane C corresponding to d3 can be determined as the target lane, that is, the vehicle is currently located in lane C of the current road.

[0164] Based on the geometric relationship between the optimized target global pose and the lane centerline coordinates in the embodiments of the present application, centimeter-level lane positioning is achieved. Moreover, the calculation complexity of the horizontal distance is low, and the single calculation time consumption is small, which can quickly match the lane to which the vehicle belongs. This not only improves the accuracy of vehicle positioning but also improves the efficiency of vehicle positioning, can meet the real-time requirements of autonomous driving, and provides reliable lane-level position information for autonomous driving decision-making.

[0165] It should be noted that the embodiments of the present application can be used as part of ADAS, and can provide functions such as real-time lane departure warning and lane keeping assistance for drivers. Through accurate lane positioning information, ADAS can monitor in real time whether the vehicle deviates from the lane and issue warnings to the driver or automatically adjust the vehicle driving trajectory when necessary.

[0166] The embodiments of the present application can achieve high-precision three-dimensional positioning of the vehicle's lane by combining the triangulation and feature extraction technologies of traffic lights. As road infrastructure, the position of traffic lights is relatively fixed and accurate. Using them as reference points for triangulation can significantly improve the positioning accuracy. At the same time, by calculating the angular residuals using the reciprocity of traffic light features, multiple verification and error correction can be realized, further improving the reliability of positioning. This high-precision lane positioning is crucial for applications such as autonomous driving and vehicle navigation, and can ensure that the vehicle maintains the correct driving path in a complex and changing road environment.

[0167] Since traditional lane positioning methods often have a high dependence on the external environment, for example, GPS signals are vulnerable to occlusion, and the performance of sensors such as radar or lidar may decline under adverse weather conditions. However, in the embodiments of the present application, by using traffic lights, which are road infrastructure, the dependence of vehicle positioning on the external environment is reduced. Even in complex and changing road environments, such as situations with high-rise building occlusion and tunnels, reliable lane positioning can be achieved, which greatly reduces the impact of environmental factors on the positioning accuracy and improves the stability and reliability of positioning.

[0168] Moreover, high-precision lane positioning is the foundation for achieving the safety of autonomous driving and vehicle navigation. By improving the positioning accuracy and stability, the embodiments of the present application can provide more accurate driving path and obstacle information for autonomous vehicles, thereby effectively avoiding the risk of vehicles deviating from the lane or colliding with other vehicles and pedestrians. At the same time, for vehicle navigation systems, high-precision lane positioning can also provide more accurate navigation information, helping drivers better plan driving routes and reduce misjudgments and misoperations during driving.

[0169] Embodiment 2

[0170] The embodiments of the present application also provide a positioning method for a vehicle. Please refer to Figure 2 , including the following steps:

[0171] S210. Obtain the traffic light image captured by the camera in the vehicle and the lane information corresponding to the vehicle; there is a traffic light in the traffic light image, and the traffic light image includes at least a first image and a second image;

[0172] S220. Preprocess the first image and the second image to confirm whether the first image and the second image meet the requirements;

[0173] In step S220, that is, determine whether there is a parallax between the first image and the second image. If the requirements are not met, return to step S210 to re-obtain the traffic light image; if the requirements are met, step S230 can be continued.

[0174] S230. Extract and match the feature points in the first image and the second image, and perform triangulation calculation based on the feature points to obtain the first global pose corresponding to the traffic light;

[0175] S240. Obtain the second global pose corresponding to the vehicle according to the internal parameters and external parameters of the camera;

[0176] S250. Calculate the perception angle and the geographical angle according to the type point information corresponding to the traffic light provided by the map;

[0177] S260. Construct a factor graph corresponding to the global positioning of the vehicle through the perception angle and the geographical angle;

[0178] S270. Iteratively optimize the factor graph to obtain an optimized target factor graph, and then determine the target global pose corresponding to the vehicle from the target factor graph.

[0179] In the embodiments of the present application, the method descriptions of the above steps S210 to S270 are the same as those in Embodiment 1. For detailed descriptions, please refer to Embodiment 1 and will not be elaborated here.

[0180] The embodiments of the present application also provide a positioning device 30 for a vehicle. Please refer to Figure 3, including the following modules:

[0181] An acquisition module 310, configured to acquire a traffic light image captured by a camera in the vehicle and lane information corresponding to the vehicle; there is a traffic light in the traffic light image, the traffic light has corresponding type point information, the camera has corresponding parameters, and the lane information is used to characterize information of each lane on the road where the vehicle travels;

[0182] A first global pose module 320, configured to determine a first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera;

[0183] A second global pose module 330, configured to determine a second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera, and the first global pose;

[0184] A relative angle determination module 340, configured to determine a relative angle of the traffic light with respect to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose;

[0185] A positioning module 350, configured to determine positioning information for characterizing the lane in which the vehicle is located on the road according to the second global pose, the relative angle, and the lane information.

[0186] An embodiment of the present application further provides an electronic device 40, please refer to Figure 4 , including a processor 410 and a memory 420, wherein the memory 410 is used to store a computer program; the processor 420 is configured to execute the program stored on the memory 410 to implement the vehicle positioning method introduced in any embodiment of the present application.

[0187] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the vehicle positioning method introduced in any embodiment of the present application is implemented.

[0188] In the present application, "a plurality of" means two or more.

[0189] In the present application, unless otherwise clearly defined, the terms "installation", "connection", and "coupling" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations.

[0190] The terms "first", "second", "third", "fourth", etc. (if any) in this application are used to distinguish similar objects and do not necessarily describe a specific order or sequence.

[0191] The term "and / or" in this application is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, the character " / " in this application generally indicates that the related objects before and after are in an "or" relationship.

[0192] If there is no special instruction, all steps of this application can be carried out sequentially or randomly. For example, the method includes steps A and B, indicating that the method can include steps A and B carried out sequentially, or steps B and A carried out sequentially. For example, it is mentioned that the method may further include step C, indicating that step C can be added to the method in any order. For example, the method can include steps A, B, and C, or steps A, C, and B, or steps C, A, and B, etc.

[0193] The above are only the preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims

1. A vehicle positioning method, characterized in that: include: Obtaining a traffic light image captured by a camera in a vehicle and lane information corresponding to the vehicle; There is a traffic light in the traffic light image, the traffic light has corresponding type point information, the camera has corresponding parameters, and the lane information is used to represent information of each lane on the road where the vehicle is traveling; Determine a first global pose corresponding to the traffic light according to the traffic light image and parameters corresponding to the camera; Determine a second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera and the first global pose; Determine a relative angle of the traffic light with respect to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose, and the second global pose; According to the second global posture, the relative angle and the lane information, positioning information for characterizing the lane in which the vehicle is located on the road is determined.

2. The method according to claim 1, characterized in that The traffic light image includes at least a first image and a second image with a time difference, and the parameters corresponding to the camera include an intrinsic parameter and a first extrinsic parameter, wherein the first extrinsic parameter is used to characterize the rotation and translation of the camera in the world coordinate system; The determining a first global pose corresponding to the traffic light according to the traffic light image and the parameters corresponding to the camera includes: Extracting a first feature point from the first image and extracting a second feature point from the second image; both the first feature point and the second feature point correspond to a target point of the traffic light; Determine a first coordinate of the first feature point in the first image and a second coordinate of the second feature point in the second image; Determine the measurement coordinates corresponding to the target point in the world coordinate system according to the first coordinates, the second coordinates, the internal parameters and the first external parameters; The measured coordinates are determined as a first global pose corresponding to the traffic light.

3. The method according to claim 2, characterized in that The parameters corresponding to the camera also include a second extrinsic parameter, which is used to characterize the rotation and translation of the camera relative to the rear axle of the vehicle; The determining, according to the traffic light image, the parameters corresponding to the camera and the first global pose, a second global pose corresponding to the vehicle comprises: Determine the intermediate global pose corresponding to the camera according to the first coordinate, the internal parameter and the first global pose; or determine the intermediate global pose corresponding to the camera according to the second coordinate, the internal parameter and the first global pose; A second global pose corresponding to the vehicle is determined according to the second extrinsic parameter and the intermediate global pose.

4. The method according to claim 3, characterized in that The point information includes the geographic coordinates of the target point provided by the navigation in the vehicle in the world coordinate system, and determining the relative angle of the traffic light with respect to the vehicle according to the point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose and the second global pose, comprises: Determining a perception angle of the traffic light relative to the vehicle according to the second external parameter and the first global pose; Determining a geographic angle of the traffic light relative to the vehicle based on the geographic coordinates and the second global pose; The perception angle and the geographic angle are determined as the relative angle.

5. The method according to claim 4, characterized in that The determining, according to the second global posture, the relative angle and the lane information, positioning information for characterizing the lane in which the vehicle is located on the road comprises: Adjusting the second global pose according to the relative angle to obtain a target global pose corresponding to the vehicle; According to the target global position and the lane information, positioning information for characterizing the lane in which the vehicle is located on the road is determined.

6. The method according to claim 5, characterized in that: The step of adjusting the second global pose according to the relative angle to obtain a target global pose corresponding to the vehicle includes: calculating an angular difference between the perceived angle and the geographic angle; Constructing a factor graph according to the angle difference and the second global pose; wherein the factor node of the factor graph is a residual function constructed based on the angle difference, and the variable node of the factor graph is the second global pose; According to the sum of the residual functions in the factor graph, updating the second global pose in the factor graph to obtain an intermediate factor graph; Determine the sliding window; Based on the data in the sliding window, the intermediate factor graph is locally optimized to obtain the target factor graph; An optimized second global pose is extracted from the target factor graph as a target global pose corresponding to the vehicle.

7. The method according to claim 5, characterized in that: The lane information includes coordinates corresponding to the center line of each lane in the world coordinate system, and the determining, based on the target global pose and the lane information, positioning information for characterizing the lane in which the vehicle is located on the road includes: Determining the horizontal distance between the vehicle and the center line of each lane according to the target global pose and the coordinates corresponding to the center line; Determining a target lane where the vehicle is located on the road according to the horizontal distance; Generate positioning information for indicating that the vehicle is located in the target lane.

8. A vehicle positioning device, characterized in that: include: An acquisition module, used to acquire a traffic light image captured by a camera in a vehicle and lane information corresponding to the vehicle; There is a traffic light in the traffic light image, the traffic light has corresponding type point information, the camera has corresponding parameters, and the lane information is used to represent information of each lane on the road where the vehicle is traveling; A first global pose module, used for determining a first global pose corresponding to the traffic light according to the traffic light image and parameters corresponding to the camera; A second global pose module, used for determining a second global pose corresponding to the vehicle according to the traffic light image, the parameters corresponding to the camera and the first global pose; A relative angle determination module, configured to determine a relative angle of the traffic light relative to the vehicle according to the type point information corresponding to the traffic light, the parameters corresponding to the camera, the first global pose and the second global pose; A positioning module is used to determine positioning information for characterizing a lane in which the vehicle is located on the road based on the second global posture, the relative angle and the lane information.

9. An electronic device, characterized in that: comprising a processor and a memory, wherein Memory, used to store computer programs; A processor, used to execute a program stored in a memory to implement the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images