A positioning method and related device

Abstract

The embodiments of the present application disclose a positioning method and related devices. The processing equipment can combine vehicle motion data and road condition image data to realize lane positioning. Since the vehicle motion data can identify the lateral displacement of the vehicle from the perspective of the vehicle itself and based on the internal data of the vehicle, the road condition image data can determine the lateral displacement of the vehicle from the perspective of simulated vehicle vision and based on the reference of external data of the vehicle. Therefore, by combining the complementarity of the simulated vehicle vision dimension and the vehicle's own motion dimension in the perspective of vehicle lateral displacement identification, it is possible to accurately outline the lane changes of the vehicle in a complex environment such as a target area, and then before the target vehicle leaves the target area, the lane where the target vehicle ends at the target area can be determined in combination with the first lane marking, thereby realizing timely positioning of the lane. The applicable scenarios of this method include but are not limited to maps, vehicle networking, autonomous driving, vehicle-road collaboration, etc.

Description

Technical Field

[0001] The present application relates to the field of vehicle driving technology, and in particular to a positioning method and related devices. Background Art

[0002] When traveling, map functions will be used, for example, planning driving routes through software or systems that include map functions, and reminding drivers whether they have any illegal driving behaviors.

[0003] In the application process, the vehicle needs to be accurately positioned. In related technologies, sensors, laser radars, high-precision maps and other methods are usually used to achieve accurate positioning of the lane where the vehicle is located.

[0004] However, these methods are costly, and some of them require complex road reconstruction of existing roads, making them difficult to put into large-scale use. Summary of the invention

[0005] In order to solve the above technical problems, the present application provides a positioning method, in which a processing device can combine vehicle motion data and road condition image data to locate the lane, thereby improving the accuracy of positioning.

[0006] The embodiments of the present application disclose the following technical solutions:

[0007] In a first aspect, an embodiment of the present application discloses a positioning method, the method comprising:

[0008] Determine a first target lane in the road where the target vehicle is located when the target vehicle reaches a first position, the first position being a starting position of a target area in the road in a driving direction of the target vehicle, a first number of lanes included in the target area at the first position being different from a second number of lanes included in the target area at a second position, and the second position being an ending position of the target area in the driving direction of the target vehicle;

[0009] Acquire vehicle motion data and road condition image data corresponding to the target vehicle in the target area;

[0010] A second target lane corresponding to the target vehicle before it leaves the second position is determined according to the vehicle motion data, the road condition image data and the first target lane.

[0011] In a second aspect, an embodiment of the present application discloses a positioning device, the device comprising a first determining unit, a first acquiring unit, and a second determining unit:

[0012] The first determination unit is used to determine a first target lane in the road where the target vehicle is located when the target vehicle reaches a first position, the first position being a starting position of a target area in the road in a driving direction of the target vehicle, a first number of lanes included in the target area at the first position being different from a second number of lanes included in the target area at the second position, and the second position being an ending position of the target area in the driving direction of the target vehicle;

[0013] The first acquisition unit is used to acquire the vehicle motion data and road condition image data corresponding to the target vehicle in the target area;

[0014] The second determination unit is used to determine a second target lane corresponding to the target vehicle before it leaves the second position based on the vehicle motion data, the road condition image data and the first target lane.

[0015] In a third aspect, an embodiment of the present application discloses a computer device, the device comprising a processor and a memory:

[0016] The memory is used to store program code and transmit the program code to the processor;

[0017] The processor is used to execute the positioning method described in the first aspect according to the instructions in the program code.

[0018] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is used for the positioning method described in the first aspect.

[0019] In one or more embodiments, by acquiring vehicle motion data and road condition image data corresponding to the target vehicle before the target vehicle leaves the target area, accurate and timely positioning of the lane can be achieved.

[0020] In one or more embodiments, vehicle motion data and road condition image data can be directly acquired through conventional vehicle-mounted equipment without incurring additional costs, thereby reducing positioning costs while ensuring lane-level real-time positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1A schematic diagram of a positioning method in an actual application scenario provided by an embodiment of the present application;

[0023] Figure 2 A flowchart of a positioning method provided in an embodiment of the present application;

[0024] Figure 3 A schematic diagram of determining a first target lane provided in an embodiment of the present application;

[0025] Figure 4 A schematic diagram of determining motion lane change parameters provided in an embodiment of the present application;

[0026] Figure 5 A schematic diagram of determining image lane change parameters provided in an embodiment of the present application;

[0027] Figure 6 A schematic diagram of determining image lane change parameters provided in an embodiment of the present application;

[0028] Figure 7 A schematic diagram of lane line disappearance provided in an embodiment of the present application;

[0029] Figure 8 A schematic diagram of road map data provided in an embodiment of the present application;

[0030] Fig. 9 A schematic diagram of updating a navigation planning path provided in an embodiment of the present application;

[0031] Fig.10 An architecture diagram of a vehicle-mounted terminal capable of lane-level real-time positioning provided in an embodiment of the present application;

[0032] Fig.11 A schematic diagram of a lane condition provided in an embodiment of the present application;

[0033] Fig.12 A schematic diagram of a lane expansion to the left provided in an embodiment of the present application;

[0034] Fig.13 A schematic diagram of a lane extending to the right provided in an embodiment of the present application;

[0035] Fig.14 A schematic diagram of lane separation provided in an embodiment of the present application;

[0036] Fig.15 A structural block diagram of a positioning device provided in an embodiment of the present application;

[0037] Fig.16 A structural diagram of a computer device provided in an embodiment of the present application;

[0038] Fig.17 A structural diagram of a server provided in an embodiment of the present application;

[0039] Fig.18 A flowchart of a positioning method in an actual application scenario provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The embodiments of the present application are described below in conjunction with the accompanying drawings.

[0041] Accurate lane positioning of vehicles is the basis for the good application of various related technologies. For example, only by being able to accurately locate the lane in which the vehicle is located can effective vehicle navigation be achieved. In the field of map navigation, lane-level real-time positioning is of great significance for the vehicle to determine its own lateral position and formulate navigation strategies. In addition, based on the results of lane-level real-time positioning, vehicle lane-level path planning and guidance can also be performed. Accurate lane-level real-time positioning is also conducive to improving the vehicle traffic rate of the existing road network to alleviate traffic congestion. On the other hand, it can also improve vehicle driving safety and reduce traffic accident rates.

[0042] Most of the technologies that can achieve accurate lane positioning in related technologies require a lot of technical costs. Among them, some lane positioning methods have lower implementation costs, such as locating the lane where the vehicle is located by collecting visual images around the vehicle.

[0043] However, this method of lane positioning through visual images usually relies on lane lines in the lane. If the number of lanes on the road where the vehicle is located changes, there may be areas on the road where some lane lines disappear. In addition, lane line information may not be collected in many situations such as a large number of vehicles parked at the same time at an intersection or lane congestion. Therefore, it may be impossible to accurately locate the lane where the vehicle is located using only visual images.

[0044] In order to solve the above technical problems, the present application provides a positioning method, in which a processing device can combine vehicle motion data and road condition image data to locate lanes, so that multi-dimensional data can complement each other and avoid the problem of low positioning accuracy based on single-dimensional data due to changes in the number of lanes; at the same time, through multi-dimensional data that is relatively easy to collect, the lane positioning cost can be reduced as much as possible while ensuring positioning accuracy, which is conducive to the implementation and promotion of the method.

[0045] It is understandable that the method can be applied to a lane positioning device, which is a processing device with a positioning function, for example, a terminal device or a server with a positioning function. The method is independently executed by a terminal device or a server, and can also be applied to a network scenario in which a terminal device and a server communicate, and the terminal device and the server cooperate to operate. Among them, the terminal device can be a mobile phone, a desktop computer, a personal digital assistant (PDA for short), a tablet computer, a vehicle-mounted device and other devices. The server can be understood as an application server or a Web server. In actual deployment, the server can be an independent physical server or a server cluster or distributed system composed of multiple physical servers. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application is not limited here.

[0046] In order to facilitate understanding of the technical solution provided in the embodiment of the present application, a positioning method provided in the embodiment of the present application will be introduced below in combination with an actual application scenario.

[0047] See also Figure 1 , Figure 1 This is a schematic diagram of a positioning method in an actual application scenario provided by an embodiment of the present application. In this actual application scenario, the processing device may be a server 101. Figure 1 In the lane scene shown in the lower left corner, there is a target area where the number of lanes has changed. As shown in the figure, the starting position of the target area includes 3 lanes and the ending position includes 6 lanes. Since the number of lanes has changed, lane positioning based solely on visual image data may result in inaccurate positioning results.

[0048] In order to improve the accuracy of lane positioning and control the cost required for lane positioning, the server 101 can realize the comprehensive positioning of the lane based on the data collected at a lower cost in multiple dimensions. First, the server 101 can determine whether the target vehicle has reached the first position, which is the starting position of the target area in the road in the direction of travel of the target vehicle. If it has arrived, it is determined that the target vehicle has begun to enter the target area. At this time, the server can determine the first target lane where the target vehicle is located in the road. As can be seen from the figure, the first target lane can be the third lane.

[0049] Subsequently, the server 101 can obtain the vehicle motion data and road condition image data corresponding to the target vehicle in the target area. These data can reflect the lane changes of the target vehicle in the target area from the two data dimensions of vehicle motion and road condition image. Among them, the vehicle motion data is data that can be obtained based on the vehicle's own motion, without the need for the external environment as a reference, so it is less affected by the lane environment, but it also lacks certain reliability because there is no reference to the external environment; the road condition image data is mainly data obtained based on the lane environment. Although it is easily affected by the complex lane environment, it can also more intuitively reflect the lane changes of the target vehicle. Therefore, the complementary effect between the advantages and disadvantages of the data can be achieved through the data of these two dimensions.

[0050] For example, in the part where the lane line disappears in the target area, the road condition image data may not be able to collect relatively accurate lane line information, and thus the lane change situation determined by the road condition image data may have low accuracy; since the vehicle motion data can be collected independently of the lane line, the lane change situation determined based on the vehicle motion data may have high accuracy. At this time, the server 101 can perform data complementation on the road condition image data based on the vehicle motion data.

[0051] The server 101 can combine the vehicle motion data and the road condition image data to determine the lane change of the target vehicle in the target area. By combining the first target lane and the lane change, the second target lane corresponding to the target vehicle before leaving the second position can be determined. The second position is the end position of the target area in the driving direction of the target vehicle. Figure 1 As shown, the second target lane can be lane 4. Compared with laser radar, sensors, high-precision maps and other methods, the acquisition cost of vehicle motion data and road image data is relatively low. Therefore, this positioning method can ensure the accuracy of lane positioning while reducing the difficulty of implementation of the method, making it easy to use and promote.

[0052] Next, a positioning method provided in an embodiment of the present application will be introduced in conjunction with the accompanying drawings.

[0053] See also Figure 2 , Figure 2 A flowchart of a positioning method provided in an embodiment of the present application, the method comprising:

[0054] S201: Determine a first target lane on the road where the target vehicle is located when the target vehicle reaches a first position.

[0055] In order to reduce the cost of lane-level real-time positioning while ensuring positioning accuracy, in the embodiments of the present application, the use of high-cost technologies, such as high-precision maps, carrier measurement, lidar and other technologies, can be reduced, and instead some technologies with lower implementation difficulty and lower cost can be used for lane positioning.

[0056] However, since these low-cost technologies may have problems such as simple data collection, low positioning accuracy, and high probability of interference, it may be difficult to achieve accurate lane-level real-time positioning in some more complex driving scenarios. For example, when locating the lane of a target vehicle through image acquisition, it usually depends on the position of the lane line in the acquired image. However, if the lane line disappears on the road where the vehicle is located or the lane line cannot be photographed due to vehicle congestion, accurate positioning may not be achieved by relying solely on image acquisition technology.

[0057] In order to solve the above problems, in an embodiment of the present application, the processing device can further add data of other dimensions that can perform lane positioning independently of images on the basis of the image data dimension, thereby achieving complementarity between multi-dimensional data and improving the accuracy of lane-level real-time positioning.

[0058] First, the processing device can set a target area, which is an area where it is difficult to achieve accurate lane-level real-time positioning through visual positioning only through image data. For example, it can be an area where the road changes are more complex and vehicle congestion is prone to occur. In reality, such areas are usually accompanied by changes in the number of lanes. Due to the difference in the number of lanes before and after the change, there is a high probability that the lane lines will disappear. At the same time, changes in the number of lanes usually occur at intersections that require multi-directional vehicle traffic. At intersections, there will often be vehicle congestion caused by waiting for traffic. The above situations are likely to lead to inaccurate visual positioning problems, such as Fig.11 As shown, Fig.11 A schematic diagram of a lane situation provided in an embodiment of the present application. Since the vehicle is surrounded by multiple vehicles, it may be difficult to accurately collect lane images around the vehicle. Based on this, the embodiment of the present application can set the target area as the area where the number of lanes changes, so that accurate analysis can be performed on these more complex areas.

[0059] The processing device can determine a first target lane in a road where a target vehicle is located when the target vehicle reaches a first position, where the target vehicle can be any vehicle traveling on the road, where the first position is a starting position of a target area in the road in a direction of travel of the target vehicle, where a first lane number of lanes included in the target area at the first position is different from a second lane number of lanes included in the target area at the second position, and where the second position is an ending position of the target area in the direction of travel of the target vehicle.

[0060] For example, Figure 3 As shown, Figure 3 A schematic diagram of determining a first target lane provided in an embodiment of the present application. First, the processing device can obtain a road image in front of the target vehicle through a monocular camera installed on the target vehicle (for example, installed on a windshield, or a roof, etc.), and then perform element segmentation on the image data to identify the lane line information adjacent to the target vehicle. The processing device can perform an inverse perspective transformation on each adjacent lane line, that is, convert the coordinates corresponding to each adjacent lane line from the camera coordinate system to the world coordinate system.

[0061] The processing device can reconstruct the transformed lane line by fitting, and determine the lane where the target vehicle is located on the current road, such as the left lane or the right lane. Figure 3 , Figure 3 A 4-lane road scene is shown. The double solid lines on the left and right sides represent the road edges. For the target vehicle, Figure 3 The above shows the lane determination rule for the left lane. From the first lane on the left to the current lane, the first target lane determined is the second lane on the left. Figure 3 The lane determination rules for the right are shown below. From the 1st lane from the right to the current lane, the first target lane determined is the 3rd lane from the right.

[0062] In addition, the processing device can also use machine learning technology to input the collected road images into a neural network for learning and training to obtain a corresponding neural network model, which can output the lane where the vehicle is located, such as the lane from the left, etc. When the above method cannot determine the lane where the vehicle is located, the output result can be 0.

[0063] In order to further improve the accuracy of the first target lane, the processing device may filter the determination result of the first target lane according to certain rules or methods, such as median filtering, which can effectively reduce the jitter of the lane positioning result.

[0064] S202: Acquire vehicle motion data and road condition image data corresponding to the target vehicle in the target area.

[0065] In order to make up for the shortcomings of visual positioning, the processing device can integrate other dimensional data that does not rely on visual images for positioning to jointly perform lane-level real-time positioning. The processing device can obtain the vehicle motion data and road condition image data corresponding to the target vehicle in the target area. The vehicle motion data can reflect the displacement of the target vehicle in the target area from the perspective of the vehicle's own motion, and the road condition image data can reflect the displacement of the target vehicle in the target area from the perspective of changes in the image around the vehicle.

[0066] Since the vehicle motion data only needs to collect the vehicle's own data information and does not require the external environment as a reference, even if a more complex lane situation occurs, such as lane lines disappearing, surrounding vehicles congested, etc., which are not conducive to accurate analysis of changes in the image around the vehicle, the vehicle motion data can also reflect a more accurate vehicle displacement situation, thereby making up for the defects of lane positioning based on road condition image data to a certain extent.

[0067] S203: Determine, based on the vehicle motion data, the road condition image data and the first target lane, a second target lane corresponding to the target vehicle before it leaves the second position.

[0068] As mentioned above, through the vehicle motion data and the road condition image data, the processing device can analyze the displacement of the target vehicle in the target area based on the two angles of the vehicle's own motion and the image around the vehicle, so as to more accurately determine the lane change of the target vehicle in the target area. Furthermore, based on the first target lane and the lane change of the target vehicle in the target area identified by the vehicle motion data and the road condition image data, the processing device can more accurately determine the second target lane where the target vehicle is located when leaving the target area.

[0069] It can be seen from the above technical solution that since the vehicle motion data can identify possible lateral displacement of the vehicle based on the internal data of the vehicle from the perspective of the vehicle itself, the road condition image data can determine possible lateral displacement of the vehicle based on the reference of the external data of the vehicle from the perspective of the simulated vehicle vision. Combining the complementarity of the simulated vehicle vision dimension and the vehicle's own motion dimension in the perspective of vehicle lateral displacement identification, the lane changes of the target vehicle in the complex environment of the target area can be accurately outlined, and then the first target lane on the road where the target vehicle is located when it arrives at the first position can be combined to determine the second target lane corresponding to the target vehicle before it leaves the second position, thereby achieving timely positioning of the lane. Moreover, since the vehicle motion data and road condition image data can be directly obtained through conventional on-board equipment, no additional cost will be added, thereby reducing the positioning cost while ensuring real-time positioning at the lane level.

[0070] Specifically, in the actual lane positioning process, the processing device may analyze the vehicle motion data and road condition image data in a variety of ways. In one possible implementation, since in more complex road conditions, the road condition image data is more likely to be interfered with, while the vehicle motion data is usually only collected based on the vehicle's own motion and is less likely to be interfered with, the lane change situation reflected by the vehicle motion data may be more accurate than the road condition image data. At the same time, since the road condition image data can reflect the image conditions around the vehicle, some image features that can be used to locate the road on which the vehicle is located may be collected. Therefore, based on the road condition image data, the lane change verification effect can be achieved to a certain extent.

[0071] At the same time, since the first target lane can be determined when the target vehicle reaches the first position, the vehicle motion data and road condition image data can be obtained when the target vehicle is in the target area. Therefore, before the target vehicle leaves the second position, the processing device can already obtain the information required for lane positioning of the target vehicle. Therefore, in order to achieve lane-level real-time positioning, the processing device can determine the second target lane corresponding to the target vehicle before the target vehicle leaves the second position based on the vehicle motion data, road condition image data and the first target lane.

[0072] In summary, the processing device can determine the lane change of the target vehicle mainly based on the vehicle motion data, and verify the lane change determined based on the vehicle motion data based on the road condition image data. The processing device can determine the motion lane change parameter based on the vehicle motion data, and the motion lane change parameter is used to identify that the target vehicle has not changed lanes or has changed the direction of lanes, or the number of lanes changed. Based on the motion lane change parameter, the road condition image data, and the first target lane identification corresponding to the first target lane, the processing device can determine the second target lane identification before the target vehicle leaves the second position, and the second target lane identification is used to identify the second target lane. Therefore, the lane change of the target vehicle can be determined by more accurate data, and the analyzed lane change can be verified by more distinct image data features, so as to determine a more accurate second target lane identification.

[0073] For example, if the processing device determines based on the vehicle motion data that the target vehicle has changed lanes to the left in the target area, but the road condition image data shows that the target vehicle has actually moved away from the road guardrail on the left side of the driving direction, it can be determined that the lane change determined based on the vehicle motion data is not accurate enough.

[0074] In order to further improve the accuracy of lane positioning, the processing device may use a variety of vehicle motion data to analyze lane changes. In a possible implementation, the vehicle motion data may include at least one of vehicle motion angle data, gyroscope data, and steering wheel rotation data. The vehicle motion angle data is used to identify the change in the driving angle of the target vehicle during driving, the gyroscope data can be used to identify the angle change of the target vehicle in each angle dimension, and the steering wheel rotation data can be used to identify the steering wheel rotation of the target vehicle during driving.

[0075] The processing device can determine the displacement parameter of the target vehicle in the target area in the lateral direction according to the vehicle motion data, and the lateral direction is perpendicular to the direction of travel indicated by the lane corresponding to the second position. Thus, according to the displacement parameter in the lateral direction, the processing device can determine the distance of displacement of the target vehicle in the direction corresponding to the lane change, and then determine the motion lane change parameter according to the displacement parameter, so that the motion lane change parameter can identify that the target vehicle has not changed lanes or has changed lanes in a certain direction and the number of lanes changed.

[0076] like Figure 4 As shown, Figure 4 A schematic diagram of determining motion lane change parameters provided in an embodiment of the present application, based on vehicle motion data, the processing device can obtain the speed V of the target vehicle, in meters per second (m / s), or it can be converted from kilometers per hour (km / h) to get m / s. The processing device can set the sampling frequency S, then the interval time Δt between two samples = 1 / S. The processing device can obtain the gyroscope data in the vehicle motion data through the inertial measurement unit (IMU) on the target vehicle, and determine the direction angle β based on the gyroscope data, which refers to the direction of travel of the vehicle; the processing device can also collect the gyroscope rotation angle φ within two sampling intervals, that is, the sampling results of the direction angles before and after Δt are β and β+φ respectively, so that the average direction angle of the target vehicle within the Δt time is like Figure 4 As shown in Figure 1, the road direction angle α and the gyroscope direction angle β are angles expressed based on the same rule. For example, the north direction is selected as 0°, the clockwise direction is positive, and the angle value range is [0,360).

[0077] The above parameters can be used to determine the displacement parameter Δy of the target vehicle in the lateral direction within the sampling interval Δt:

[0078]

[0079] By calculating the sum of Δy within a preset window time (e.g., 3s, 5s, etc.), the processing device can determine the cumulative lateral displacement value of the target vehicle within the window time. The window time can be the time during which the target vehicle can change lanes in the target area. The cumulative lateral displacement value is the displacement parameter of the target vehicle in the lateral direction within the target area. The processing device can set the displacement parameter to be negative when displacing to the left and positive when displacing to the right. By determining whether the displacement parameter is greater than a set threshold, it is determined whether the target vehicle has changed lanes to the right. By determining whether the displacement parameter is less than a set threshold, it is determined whether the target vehicle has changed lanes to the left. If it is not greater than or less than the above-mentioned set threshold, it can be determined that the target vehicle has not changed lanes. The set threshold can be set based on the lane width.

[0080] In addition, the processing device can also judge the lane change situation through the gyroscope's direction angle β and the gyroscope's rotation angle φ within two sampling intervals. For example, if the target vehicle changes lanes to the right, it needs to turn right first and then turn left, and β increases first and then decreases, that is, φ is first greater than 0 and then less than 0; if it changes lanes to the left, it needs to turn left first and then turn right, and β decreases first and then increases, that is, φ is first less than 0 and then greater than 0. It is worth noting that if the road is a curved road, the target vehicle will also deflect at an angle during normal driving. Therefore, in order to further improve the accuracy of the judgment of the lane change situation, the processing device can also combine other data, such as road data, to make judgments together.

[0081] Similarly, based on the steering wheel rotation data, the processing device can also judge the lane change situation. For example, when the target vehicle changes lanes to the left, it needs to turn the steering wheel to the left first and then turn right; when changing lanes to the right, it needs to turn the steering wheel to the right first and then turn left. This method also needs to be combined with other data to improve accuracy in situations such as curved roads.

[0082] In addition, in order to further improve the accuracy of lane-level real-time positioning, in addition to determining the lane change parameters based on vehicle motion data, the processing device can also determine the lane change parameters of the target vehicle in the target area based on the road condition image data. It is understandable that when the target vehicle changes lanes, the image around the target vehicle usually changes, for example, the distance between the target vehicle and the lane line in the lane in the image changes, the distance between the target vehicle and the guardrails on both sides of the road changes, etc. Based on these image information, the processing device can determine the parameters such as the direction and distance of the displacement of the target vehicle, and then determine the lane change of the target vehicle.

[0083] In a possible implementation, the processing device may determine an image lane change parameter based on the road condition image data, and the image lane change parameter is used to identify that the target vehicle has not changed lanes or has changed lanes in a certain direction or in a certain number of lanes. The processing device may determine a second target lane marker based on the vehicle motion data, the image lane change parameter, and a first target lane marker corresponding to the first target lane before the target vehicle leaves the second position, and the second target lane marker is used to identify the second target lane.

[0084] Among them, based on the motion lane change parameter, the processing device can reflect the lane change of the target vehicle in the target area based on the internal data of the vehicle from the perspective of the vehicle's own motion. Since the vehicle motion data is mainly collected based on the vehicle's own motion, the motion lane change parameter is less affected by the change of the lane environment. Based on the image lane change parameter, the processing device can reflect the lane change of the target vehicle in the target area from the perspective of simulating vehicle vision based on the change of the vehicle's external image. Since the road condition image data can more intuitively reflect the changes in the environment where the target vehicle is located, the image lane change parameter can more reliably reflect the actual lane change of the target vehicle. Based on this, by combining the motion lane change parameter and the image lane change parameter, the processing device can achieve the complementarity between the two dimensional data, which can not only reduce the impact of the complex lane environment on the positioning results, but also ensure the accuracy of the lane positioning results to a certain extent, thereby achieving effective lane-level real-time positioning.

[0085] like Figure 5 As shown, Figure 5 A schematic diagram of determining lane change parameters of an image provided by an embodiment of the present application. First, the processing device can transform the coordinates corresponding to the lane line from the camera coordinate system to the world coordinate system as in the above embodiment, and then determine the equation information corresponding to the lane line based on the transformation result and the vehicle coordinate system. The lane line equation can be expressed in the form of a quadratic polynomial, a cubic polynomial or other forms, for example:

[0086] y=d+a*x+b*x 2 +c*x 3

[0087] or

[0088] y=d+a*x+b*x 2

[0089] Among them, a, b, c, d are the fitting coefficients of the polynomial, d indicates the value of y when x=0, which can represent the distance from the target vehicle to the lane line in a physical sense, with the distance to the left being positive and the distance to the right being negative. By analyzing the change in the value d, the processing device can determine the change in the distance between the target vehicle and the lane line, and then determine the lane change of the target vehicle. The Vehicle Coordinate System (VCS) is as follows Figure 5 As shown, this is a special three-dimensional moving coordinate system o-xyz used to describe the motion of the vehicle. The origin o of the coordinate system is fixed relative to the vehicle position and is generally taken as the center of mass of the vehicle.

[0090] When the vehicle is stationary on a horizontal road, the x-axis is parallel to the ground and points to the front of the vehicle, the y-axis points to the left of the driver, and the z-axis passes through the center of mass of the vehicle and points upward. Figure 5 It is just a display of a coordinate system. There are many ways to establish a vehicle coordinate system, such as left-hand system, right-hand system, etc. There are also many choices for the origin of the coordinate system, such as the midpoint of the vehicle's front axle, the midpoint of the front of the vehicle, the midpoint of the rear axle, etc.

[0091] like Figure 6 As shown, Figure 6 A schematic diagram of determining image lane change parameters provided in an embodiment of the present application, L1 and L2 respectively represent the first lane line and the second lane line closest to the left side of the target vehicle, R1 and R2 respectively represent the first lane line and the second lane line closest to the right side of the vehicle, and according to the fitting result of the lane line equation, the intercept distance parameter d between the target vehicle and each lane line can be obtained. L1 , d L2 , d R1 , d R2 .

[0092] Based on the intercept distance parameter, the processing device can determine the lateral displacement of the target vehicle on the road, and then determine whether the target vehicle has changed lanes. The processing device can determine an image lane change parameter VisionTrend, which can be any of the following three results: no lane change (0), left lane change (-1), and right lane change (+1). In addition, when the target vehicle changes lanes in multiple lanes in the target area, the image lane change parameter can use a numerical value to identify the number of lane changes made by the target vehicle, such as -2 for changing 2 lanes to the left, +3 for changing 3 lanes to the right, etc.

[0093] It is understandable that in some special lane environments, there may be no image features around the vehicle that can be used as a basis for determining the image lane change parameters. Figure 7 As shown, Figure 7A schematic diagram of lane line disappearance provided in an embodiment of the present application, where a road expansion has occurred may have an area where some lane lines disappear. In order to enable the target vehicle to more accurately determine the image lane change parameters in this special area and improve the flexibility and applicability of the method, in a possible implementation, there is a lane line disappearance area in the target area. When the target vehicle is in the lane line disappearance area, the processing device can first determine the target lane line of the lane included in the second position based on the road condition image data. The target lane line refers to a lane line that can be used to analyze the lane change situation of the target vehicle.

[0094] Although the target lane line may not be located on both sides of the current target vehicle position, the processing device can fit the target vehicle and the target lane line to the same position dimension for analysis by simulating the lane line position or simulating the vehicle position, thereby determining the distance between the target vehicle and the target lane line. The processing device can determine the intercept distance parameter between the target vehicle and the target lane line. Based on the intercept distance parameter, the processing device can analyze the lateral displacement change of the target vehicle on the road, thereby determining the image lane change parameter based on the intercept distance parameter, so that the image lane change parameter can reflect the lane change of the target vehicle.

[0095] Among them, there are multiple ways to fit the target vehicle and the target lane line to the same position dimension. For example, in the first method, the processing device can extend based on the target lane line to obtain a simulated lane line, and the simulated lane line can be extended to the vehicle position where the target vehicle is located. The processing device determines the intercept distance parameter between the target vehicle and the target lane line based on the intercept distance between the target vehicle and the simulated lane line; in the second method, the processing device can extend based on the position of the target vehicle to obtain the simulated vehicle position of the target vehicle near the target lane line, and determine the intercept distance parameter between the target vehicle and the target lane line based on the intercept distance between the simulated vehicle position and the target lane line. Thus, in the case where there is no lane line around the vehicle body, the processing device can also more accurately analyze the lane change of the target vehicle based on the lane line in the distance, thereby improving the practicality of the method.

[0096] In addition to analyzing the lane change of the target vehicle itself, the number of lane changes is also an important factor in lane-level real-time positioning technology. For example, the increase in the number of lanes, that is, lane expansion, may include two situations: lane expansion to the left and lane expansion to the right. Fig.12 and Fig.13 As shown, Fig.12 A schematic diagram showing a lane expansion to the left is shown. Fig.13A schematic diagram of lane expansion to the right is shown. When the lane positioning is based on the left number rule, if the lane expands to the left, the processing device can determine the target vehicle's final left lane based on the number of lane expansions to the left, thereby avoiding the problem of inaccurate second lane identification due to lack of calculation of the number of added lanes. In addition, lane expansion may also result in lane separation scenarios, such as Fig.14 As shown, Fig.14 A schematic diagram of lane separation is shown. The processing device can determine the lane by any left or right number rule, which is not limited here.

[0097] Based on this, in a possible implementation, the processing device can determine the second target lane in combination with the lane topology relationship, so that the lane where the target vehicle is located can be more accurately located based on the change in the number of lanes. First, in order to know which road the target vehicle is located on, the processing device can obtain the vehicle position information corresponding to the target vehicle, and the vehicle position information is used to identify the location of the target vehicle. For example, the processing device can obtain the vehicle position information collected by the target vehicle in a historical period, and the vehicle position information may include but is not limited to global positioning system GPS information, vehicle control information, vehicle visual perception information, and IMU information. The processing device can determine the positioning point information of the target vehicle at the current moment based on analyzing this information. The positioning point information is the current geographical location of the target vehicle, for example, it can be the latitude and longitude coordinates corresponding to the target vehicle.

[0098] The processing device may obtain the road map data corresponding to the target area according to the vehicle position information, and the road map data is used to identify the relevant information of the roads included in the target area. In an embodiment of the present application, the processing device may determine the lane topology relationship corresponding to the target area according to the road map data, and the lane topology relationship may include the topology relationship between the first lane and the second lane, and the topology relationship is used to reflect the quantity change and quantity change method between the first lane and the second lane, the first lane is the lane corresponding to the starting position, and the second lane is the lane corresponding to the ending position.

[0099] For example, the topological relationship can identify the number of first lanes, the number of second lanes, and the lane topology between the lanes included in the first position and the lanes included in the second position. The lane topology refers to the specific way in which the number of lanes changes from the first number of lanes to the second number of lanes. It can be understood that the information contained in the lane topological relationship is the basic data of the road. Therefore, the processing device does not need to obtain high-precision road map data to implement the technical solution of the embodiment of the present application, and the implementation difficulty is relatively low. For example, the processing device can obtain the positioning point information based on the target vehicle, match it to the corresponding road position, and then obtain the traditional road map data of the road position, such as Standard Definition (SD) data. The traditional road map data is used to record the basic attributes of the road, such as road length, number of lanes, road direction, lane topological relationship and other basic information. The production cost of the traditional road map data is low and the acquisition difficulty is relatively low.

[0100] The processing device can determine a second target lane marker before the target vehicle leaves the second position based on the vehicle motion data, road condition image data, lane topology relationship and the first target lane marker corresponding to the first target lane. The second target lane marker is used to identify the second target lane, so that the second target lane marker can more accurately identify the lane where the target vehicle was before leaving the second position when the number of lanes changes.

[0101] In addition to obtaining lane topology relationships based on road map data, in order to further improve the accuracy of lane-level real-time positioning, the processing device can also determine a more accurate starting point of the target area based on the road map data, and locate the lane in which the target vehicle is located based on the starting point of the target area, so that the determined second lane marking can effectively identify the lane in which the target vehicle is located when it leaves the target area.

[0102] For example, when the processing device acquires road map data, the road map data may include Advanced Driving Assistance System (ADAS) data. ADAS data is a transitional form of data between SD data and High Definition (HD) data. The richness and accuracy of its information are between SD data and HD data. Compared with SD data, it mainly adds information such as lane line type, color, lane attributes, lane number change points, lane virtual and real line change points, etc. Based on some feature point information included in the ADAS data, the processing device can determine the first position and the second position corresponding to the target area.

[0103] like Figure 8 As shown, Figure 8 A schematic diagram of a road map data provided by an embodiment of the present application. Based on the traditional SD data, ADAS data can add multiple feature points Fearture Point to the data, and divide the road into more detailed sections through the feature points. Each section has the number of lanes and the associated information of the lanes themselves. For example, through the ADAS data, the processing device can determine Figure 8 The lane extension starting point and stop line feature point of the intersection are used to identify the first position, and the stop line feature point is used to identify the second position. The area between the lane extension starting point and the stop line feature point of the intersection is the target area. The target area is the intersection area where the lane extension has occurred, which is composed of area 2 and area 3. The lanes in the road are extended from the lane extension starting point to the stop line feature point from 3 lanes to 6 lanes. The processing device can determine the first target lane corresponding to the target vehicle when the target vehicle reaches the lane extension starting point, and then obtain the road condition image data and vehicle motion data of the target vehicle in the area 2 and area 3. Based on the data, the lane topology relationship and the first target lane identification corresponding to the first target lane, the second target lane identification corresponding to the target vehicle is determined before the target vehicle reaches the stop line feature point.

[0104] In addition, through ADAS data, the processing device can also obtain lane-level topology information, for example, lanes 1, 2, and 3 after expansion correspond to lane 1 before expansion, and lanes 5 and 6 after expansion correspond to lane 3 before expansion. Through this lane-level topology information, the processing device can further verify the determined second target lane identification. For example, if the first target lane is lane 1, in most cases the target vehicle will enter the expanded lanes 1, 2, and 3. If the second target lane identified by the second target lane identification is lane 6 after expansion, it means that the accuracy of the lane positioning result may be low.

[0105] It is understandable that certain conditions are also required for a vehicle to change lanes on the road, such as the need to comply with traffic rules and change lanes at the location where the dotted line or lane line disappears. Therefore, not all parts of the target area may allow the target vehicle to change lanes. In order to further improve the timeliness of lane-level real-time positioning, the processing device can pay attention to the lane changes of the target vehicle in the variable lane area in the target area. The variable lane area refers to the area where the vehicle is allowed to change lanes. Since the target vehicle is unlikely to change lanes again after leaving the variable lane area, the processing device can obtain all the data for analyzing the lane changes during the target vehicle's driving in the variable lane area, and can determine the second lane marking before the target vehicle leaves the variable lane area, so there is no need to wait for the target vehicle to complete the target area, and further determine the time of the second lane marking in advance.

[0106] In a possible implementation, the road map data also includes a third position, which is the end position of the lane-changing area in the target area in the driving direction of the target vehicle, and the third position is located between the first position and the second position. The processing device can obtain the vehicle motion data and road condition image data corresponding to the target vehicle between the first position and the third position. Since the target vehicle enters the area of ​​the road where lane change is not allowed after passing the third position, that is, it is highly likely that no lane change will be performed, the lane change of the target vehicle in the target area can be more accurately and comprehensively reflected through the vehicle motion data and road condition image data. The processing device can determine the second target lane identification before the target vehicle leaves the third position based on the vehicle motion data, the road condition image data and the first target lane identification corresponding to the first target lane. The second target lane identification is used to identify the second target lane, thereby further shortening the time required for lane positioning.

[0107] like Figure 8 As shown, based on the ADAS data, the processing device can also determine a virtual-real line change point between the stop line feature point and the starting point of the lane expansion at the intersection as the third position. The virtual-real line change point refers to the point where the lane line disappears and becomes a solid line. Since the lane line disappears between the starting point of the lane at the intersection and the virtual-real line change point, the target vehicle can change lanes; after passing the virtual-real line change point, since the lane line is a solid line, the target vehicle cannot change lanes according to traffic rules. Based on this, the processing device can obtain the vehicle motion data and road condition image data of the target vehicle between the starting point of the road condition lane expansion and the virtual-real line change point, and determine the second target lane identification before the target vehicle reaches the virtual-real line change point or when it reaches the virtual-real line change point.

[0108] As mentioned above, the road condition image data can more intuitively reflect the changes in the image around the target vehicle. For example, it can collect some image features that can be used for lane positioning. The image features have strong objectivity and credibility. Therefore, the processing device can further verify the determined lane positioning results based on the image features.

[0109] In a possible implementation, the processing device can determine the pending lane mark of the lane where the target vehicle is located at the second position based on the road condition image data, and the pending lane mark can more intuitively reflect the lane where the target vehicle is located from the perspective of the image around the vehicle. It can be understood that the edge lane in the road usually has a more obvious image feature. The edge lane refers to the outermost lane in the road. For example, Figure 8 In the figure, lanes 1 and 3 before expansion are edge lanes on the road. Edge lanes usually have edge guardrails and curbs to prevent vehicles from leaving the lanes. If such image features appear in the road condition image data, it means that the target vehicle is likely to be located on the edge lane. It can be seen that if the lane identified by the pending lane sign determined based on the road condition image data is such a special lane, the pending lane sign usually has a high reliability.

[0110] Based on this, if the lane identified by the pending lane marker is an edge lane among the lanes included in the second position, the processing device can determine the pending lane marker as the second target lane marker, thereby further improving the accuracy of the second target lane marker based on the intuitive image characteristics reflected by the road condition image data.

[0111] Similarly, if it is determined that the lane identified by the pending lane marker is not an edge lane in the lanes included in the second position, it means that the image features that can be used to reflect the edge lane may not be collected in the road condition image data, that is, the target vehicle is most likely not located on the edge lane. At this time, if the lane identified by the second target lane marker determined by the processing device based on the vehicle motion data and the road condition image data is the edge lane, then the second target lane marker is most likely an erroneous lane marker. Therefore, the processing device can correct the second target lane marker to improve the accuracy of the second target lane marker.

[0112] In a possible implementation, in response to the second target lane being an edge lane in the lanes included in the second position, the processing device may update the second target lane identifier to a lane identifier of an adjacent lane of the second target lane. It is understandable that, since the second target lane identifier is determined by integrating vehicle motion data and road condition image data, the second target lane identifier itself also has a certain degree of accuracy. Even if there is a certain error between the lane identified by the second target lane identifier and the actual lane, the error is usually within a smaller error range. Therefore, by changing to an adjacent lane of the second target lane, the accuracy and rationality of the second target lane identifier can be guaranteed while correcting the second target lane identifier based on the road condition image data.

[0113] In the above manner, the processing device can determine a second target lane with high accuracy, so that some effective practical applications can be performed based on the second target lane. For example, a lane usually has a corresponding lane driving mark, and the lane driving mark is used to identify the drivable direction of the corresponding lane. Figure 8 As shown in the figure, among the six lanes after the expansion, the lane driving signs of the 1st and 2nd lanes are left turn signs, indicating that the vehicle can turn left through the lane; the lane driving signs of the 3rd, 4th and 5th lanes are straight ahead signs, indicating that the vehicle can go straight through the lane; the lane driving sign of the 6th lane is a right turn sign, indicating that the vehicle can turn right through the lane. Therefore, after determining the second target lane, the processing device can obtain the possible driving direction of the target vehicle in the subsequent driving process through the lane driving sign corresponding to the second target lane.

[0114] Among them, the drivable direction of the vehicle is an important reference factor in vehicle navigation technology. If the driving direction indicated by the driving route corresponding to the vehicle at the target area does not match the drivable direction corresponding to the second target lane, the target vehicle will not be able to continue driving along the driving route. In related technologies, since it is impossible to locate the lane in a complex road area with lane expansion in a timely manner through low-cost technology, the lane in which the vehicle is located can only be determined after the vehicle leaves the area and performs corresponding straight or turning actions. At this time, it is too late to plan the vehicle's driving path, making it difficult to provide users with a good navigation experience.

[0115] In an embodiment of the present application, since the processing device can determine the lane in which the target vehicle is located before the target vehicle leaves the target area, the processing device can plan the driving route of the target vehicle according to the drivable direction corresponding to the second target lane before leaving the target area, so that the user can obtain more accurate driving route navigation when leaving the target area, further improving the user's navigation experience. In one possible implementation, the processing device can determine the lane driving mark corresponding to the second target lane, and the lane driving mark is used to identify the drivable direction of the second target lane. In order to determine whether the lane in which the target vehicle is located is suitable for the current navigation plan, the processing device can obtain the navigation planning path corresponding to the target vehicle, and the navigation planning path is used to indicate how the target vehicle drives to the destination.

[0116] The processing device can obtain the driving guidance direction related to the target area in the navigation planning path, and determine whether the driving guidance direction matches the lane driving mark, that is, whether the driving guidance direction is included in the drivable direction marked by the lane driving mark. The driving guidance direction refers to the direction that the target vehicle needs to travel in order to reach the destination. If the driving guidance direction related to the target area in the navigation planning path does not match the lane driving mark, it means that the target vehicle can no longer travel according to the navigation planning path. At this time, the processing device can re-determine the navigation planning path according to the lane driving mark before the target vehicle leaves the second position, so that the navigation planning path can be updated in time, so that the user can know the next driving route before leaving the target area, further improving the user's navigation experience. At the same time, since the navigation update can be performed in advance, the user can avoid driving the vehicle for invalid driving, saving energy, reducing environmental pollution and resource consumption.

[0117] like Fig. 9 As shown, Fig. 9 A schematic diagram of an updated navigation planning path provided for the present application, wherein the dotted line is the navigation planning path before the update, the solid line is the navigation planning path after the update, and the target area is an intersection area. As can be seen from the figure, in the navigation planning path before the update, the processing device should drive in a straight line after leaving the intersection. However, since the target vehicle is in the left turn lane at the intersection, it can only turn left. In the related art, it is necessary to wait for the target vehicle to arrive at point B before determining that the target vehicle has entered the wrong lane, and then the navigation planning path can be re-determined, and the update speed is slow. In an embodiment of the present application, the processing device can obtain the lane driving identification corresponding to the second target lane identified by the second target lane identification from the ADAS data, and then Figure 8In the figure, there is a left turn sign. After determining that the left turn sign does not match the straight direction related to the target area in the navigation planning path, the processing device can complete the update of the navigation planning path based on the left turn sign, the current position of the target vehicle and the destination of the target vehicle when the target vehicle arrives near point A, thereby further improving the speed and efficiency of navigation planning and improving the user's navigation experience.

[0118] In order to facilitate understanding of the technical solution provided by the embodiment of the present application, a positioning method provided by the embodiment of the present application will be introduced below in combination with an actual application scenario.

[0119] In this practical application scenario, the target area is as follows Figure 8 The intersection area where lane expansion occurs is shown, and the processing device is a vehicle-mounted terminal with lane-level real-time positioning function. Fig.10 , Fig.10 An architecture diagram of a vehicle-mounted terminal capable of lane-level real-time positioning is provided for an embodiment of the present application, and the following description will be based on the architecture diagram of the vehicle-mounted terminal.

[0120] Combination Fig.18 , Fig.18 A flowchart of a positioning method in an actual application scenario provided in an embodiment of the present application, the method comprising:

[0121] S1801: Determine a first target lane when the target lane reaches the intersection area.

[0122] First, when the target vehicle arrives at the intersection area, the lane-level positioning module can locate the lane where the target vehicle is located and obtain the first target lane identifier LaneIndex corresponding to the first target lane. There are many methods for determining whether the target vehicle has arrived at the intersection area. For example, the road map data obtained by the map data module can be used to determine whether there is an intersection in the nearby area. If there is an intersection, the distance between the target vehicle and the lane expansion change point of the intersection is calculated. When the distance is less than a certain threshold (for example, 5m, 10m), it is confirmed that the vehicle has arrived at the intersection area.

[0123] S1802: Determine the positioning point information corresponding to the target vehicle.

[0124] Subsequently, the vehicle positioning module can be used to determine the positioning point information corresponding to the target vehicle, where the positioning point information is the vehicle position information corresponding to the target vehicle.

[0125] S1803: Obtain road map data corresponding to the target area.

[0126] Based on the positioning point information, the map data module can obtain the road map data corresponding to the target area, which includes information such as the intersection lane expansion starting point, the virtual and real line change point, the stop line feature point, the lane topology relationship and the lane driving signs on the lane in the intersection area.

[0127] S1804: Determine whether lane expansion occurs based on the road map data.

[0128] Based on the lane topology relationship in the road map data, the processing device can determine whether lane expansion has occurred in the intersection area, that is, whether the number of lanes at the starting position and the ending position of the intersection area are consistent. If they are consistent, it means that there is no lane expansion and the process can proceed to S1805; if they are inconsistent, it means that there is a lane expansion and the process can proceed to S1806.

[0129] Among them, the following methods may be used to determine whether lane expansion occurs in the intersection area:

[0130] Method 1: It is possible to determine whether the total number of lanes LaneCntCur at the end position of the intersection area is equal to the total number of lanes LaneCntPre at the start position through the local ADAS data in the road map data;

[0131] Method 2: It is possible to determine whether the ADAS data contains lane expansion starting point information. If so, it means that lane expansion has occurred.

[0132] Method three can be judged by the lane topology relationship in the ADAS data, for example Figure 8 In the area shown, lane 1 at the starting position connects lanes 1, 2, and 3 at the ending position, indicating that the area has been expanded to the left by 2 lanes; lane 3 at the starting position connects lanes 4 and 6 at the intersection, indicating that the area has been expanded to the right by 1 lane.

[0133] S1805: If there is no lane expansion, determine the second target lane according to the lane-level positioning module.

[0134] Among them, if it is judged based on the lane topology relationship that there is no lane expansion at the intersection, the vehicle terminal can consider that this scenario is easier to perform lane-level positioning, and directly use the positioning result of the lane-level positioning module as the second target lane identification, that is, LaneIndexCrossing=LaneIndex.

[0135] S1806: If lane expansion exists, determine the number and direction of lane expansion.

[0136] If lane expansion exists, the vehicle terminal can calculate the number of left and right lane expansions based on the lane topology relationship. The specific method is as follows:

[0137] According to the lane connection relationship from the left lane 1 at the starting position to the lane connection relationship at the ending position (assuming that the left lane 1 connects m lanes at the ending position), the left expansion information is determined, and the number of left expansions is Left_expand=m-1;

[0138] According to the lane connection relationship from the right lane 1 at the starting position to the lane at the ending position (assuming that the right lane 1 connects n lanes at the ending position), the right expansion information is determined, and the number of right expansions is right_expand=n-1;

[0139] It is worth noting that this value can also be obtained directly through ADAS data.

[0140] S1807: Obtain the corresponding vehicle motion data and road condition image data in the variable lane area.

[0141] The vehicle terminal can acquire data based on multiple feature points determined by the map data module. In this actual application scenario, the vehicle terminal can obtain the vehicle motion data and road condition image data of the target vehicle between the lane expansion starting point and the virtual and real line change point at the intersection through the motion data acquisition module and the image acquisition unit in the vision module. The vehicle motion data includes the vehicle speed data collected by the vehicle speed acquisition unit, the steering wheel rotation data collected by the steering wheel angle acquisition unit, and the IMU data collected by the IMU acquisition unit. The vehicle speed data and steering wheel rotation data can be obtained from the vehicle controller area network (Controller Area Network, referred to as CAN) bus, the IMU data can be obtained from the sensor built into the vehicle computer, and the GPS signal can be obtained through the vehicle computer telematics BOX (T-BOX).

[0142] S1808: Determine motion lane change parameters and image lane change parameters based on vehicle motion data and road condition image data.

[0143] Based on the road condition image data, the image processing unit in the vision module can determine the image lane change parameter VisionTrend, which can use a numerical value to indicate whether the target vehicle has not changed lanes or the number of lane changes, and use positive and negative numbers to indicate the direction of the target vehicle's lane change, with a negative number for changing lanes to the left and a positive number for changing lanes to the right. For example, changing lanes to the left by 2 lanes can be -2. In addition, based on the image features corresponding to special lanes in the road condition image, the vehicle-mounted terminal can also determine a pending road identification VisionLaneIndex, which can identify whether the target vehicle is in the edge lane at the end position of the intersection area.

[0144] The lane-level positioning module at the intersection can determine the motion lane change parameter DrTrend based on the vehicle motion data, and the motion lane change parameter is consistent with the numerical rule of the image lane change parameter.

[0145] S1809: Determine a second target lane identifier before the target vehicle leaves the lane change area according to the first target lane identifier corresponding to the first target lane, the image lane change parameter, the motion lane change parameter, and the lane topology relationship.

[0146] The lane-level positioning module at the intersection can determine the second target lane marker based on the first target lane marker, motion lane change parameters, image lane change parameters, and the direction and amount of lane expansion in the lane topology relationship.

[0147] Among them, the intersection lane-level positioning module can first determine whether the pending road sign VisionLaneIndex is the left lane 1 or the right lane 1, that is, whether VisionLaneIndex is equal to 1 or LaneCntCur. If so, the VisionLaneIndex can be determined as the second target lane sign LaneIndexCrossing.

[0148] If it is not an edge lane, a more accurate comprehensive lane change parameter FusionTrend can be determined based on the image lane change parameter and motion lane change parameter. The determination method is as follows:

[0149] When both the image lane change parameter and the motion lane change parameter indicate that the target vehicle is changing lanes left / right, the output comprehensive lane change parameter is left / right lane change, otherwise the output result is no lane change, FusionTrend=0, and a lane change parameter with a higher confidence level can also be selected for output;

[0150] When any one of the image lane change parameter and the motion lane change parameter is a left / right lane change and the other is no lane change, output the left / right lane change result;

[0151] In other cases, the output is no lane change.

[0152] The intersection lane-level positioning module can determine the second target lane marker using the following formula:

[0153] LaneIndexCrossing=LaneIndex+Left_expand+FusionTrend

[0154] It is understandable that when the lane change parameters are set to negative for left lane change and positive for right lane change, the lane right expansion value will not affect the second target lane mark, so you only need to pay attention to the left lane change. For example, when LaneIndex=1, Left_expand=2, FusionTrend=-2, that is, the lane marked by the first target lane mark is lane 1, the lane expands 2 lanes to the left, and the target vehicle changes lanes to the left by 2 lanes. The final second target lane mark LaneIndexCrossing=1+2-2=1, that is, the target vehicle is in lane 1 at the second position.

[0155] Since the data required for the determination process of the second target lane identification can be fully acquired before the target vehicle reaches the point where the virtual and solid lines change, the vehicle-mounted terminal can complete the above process before the target vehicle leaves the variable lane area.

[0156] S1810: Verify the second target lane marker.

[0157] The vehicle terminal can further verify the second target lane mark in the following way:

[0158] Method 1: Since the minimum lane identification is 1, if LaneIndexCrossing<1, LaneIndexCrossing=1 can be set;

[0159] Method 2: Since the maximum lane marker is LaneCntCur, if LaneIndexCrossing>LaneCntCur, LaneIndexCrossing=LaneCntCur can be set;

[0160] Method three, since the lane marked by the lane sign to be identified is not an edge lane, if LaneInd-exCrossing=1, set LaneIndexCrossing=2; if LaneIndexCrossing=LaneCntCur, set LaneIndexCrossing=LaneCntCur-1.

[0161] Finally, it can be determined whether the second target lane marker conforms to the connection relationship between lanes based on the lane topology relationship. Figure 8 In the area shown, lane 3 at the starting position is connected to lane [5,6] at the ending position. If LaneIndex=3, the LaneIndexCrossing value should usually be in the set [5,6]. If LaneIndexCrossing is not in the set, a closer result can be selected from the set for output.

[0162] Based on the positioning method provided in the above embodiment, the present application also provides a positioning device, see Fig.15 , Fig.15 This is a structural block diagram of a positioning device 1500 provided in an embodiment of the present application. The device 1500 includes a first determining unit 1501, a first acquiring unit 1502, and a second determining unit 1503:

[0163] A first determining unit 1501 is used to determine a first target lane in a road where a target vehicle is located when the target vehicle reaches a first position, wherein the first position is a starting position of a target area in the road in a driving direction of the target vehicle, a first number of lanes included in the target area at the first position is different from a second number of lanes included in the target area at a second position, and the second position is an ending position of the target area in the driving direction of the target vehicle;

[0164] The first acquisition unit 1502 is used to acquire the vehicle motion data and road condition image data corresponding to the target vehicle in the target area;

[0165] The second determining unit 1503 is used to determine a second target lane corresponding to the target vehicle before it leaves the second position according to the vehicle motion data, the road condition image data and the first target lane.

[0166] In a possible implementation manner, the second determining unit 1503 is specifically configured to:

[0167] Determine a motion lane change parameter according to the vehicle motion data, wherein the motion lane change parameter is used to indicate that the target vehicle does not change lanes or changes the direction of lanes or the number of lanes changed;

[0168] According to the motion lane change parameter, the road condition image data and a first target lane marker corresponding to the first target lane, a second target lane marker is determined before the target vehicle leaves the second position, and the second target lane marker is used to identify the second target lane.

[0169] In a possible implementation, the vehicle motion data includes at least one of vehicle motion angle data, gyroscope data, and steering wheel rotation data, and the second determining unit 1503 is specifically configured to:

[0170] Determining a displacement parameter of the target vehicle in a lateral direction within the target area according to the vehicle motion data, wherein the lateral direction is perpendicular to a direction of travel indicated by a lane corresponding to the second position;

[0171] The motion lane change parameter is determined according to the displacement parameter.

[0172] In a possible implementation manner, the second determining unit 1503 is specifically configured to:

[0173] Determine an image lane change parameter according to the road condition image data, wherein the image lane change parameter is used to indicate that the target vehicle does not change lanes or changes the direction of lanes or the number of lanes changed;

[0174] A second target lane marker is determined before the target vehicle leaves the second position based on the vehicle motion data, the image lane change parameter and a first target lane marker corresponding to the first target lane, wherein the second target lane marker is used to identify the second target lane.

[0175] In a possible implementation manner, there is a lane line disappearing area in the target area, and the second determining unit 1503 is specifically configured to:

[0176] When the target vehicle is in the lane line disappearing area, determining a target lane line of the lane included in the second position according to the road condition image data;

[0177] Determining an intercept distance parameter between the target vehicle and the target lane line;

[0178] The image lane change parameter is determined according to the intercept distance parameter.

[0179] In a possible implementation, the apparatus 1500 further includes a second acquiring unit, a third acquiring unit, and a third determining unit:

[0180] A second acquisition unit, used to acquire vehicle position information corresponding to the target vehicle;

[0181] A third acquisition unit, configured to acquire road map data corresponding to the target area according to the vehicle position information;

[0182] a third determining unit, configured to determine a lane topology relationship corresponding to the target area according to the road map data, wherein the lane topology relationship includes a topology relationship between a first lane and a second lane, wherein the first lane is a lane corresponding to the starting position, and the second lane is a lane corresponding to the ending position;

[0183] The second determining unit 1503 is specifically configured to:

[0184] Based on the vehicle motion data, the road condition image data, the lane topology relationship and the first target lane identifier corresponding to the first target lane, a second target lane identifier is determined before the target vehicle leaves the second position, and the second target lane identifier is used to identify the second target lane.

[0185] In a possible implementation, the road map data further includes a third position, the third position being an end position of the variable lane area in the target area in the driving direction of the target vehicle, and the third position being located between the first position and the second position;

[0186] The first acquisition unit 1502 is specifically used for:

[0187] Acquire vehicle motion data and road condition image data corresponding to the target vehicle between the first position and the third position;

[0188] The second determining unit 1503 is specifically configured to:

[0189] Based on the vehicle motion data, the road condition image data and a first target lane marker corresponding to the first target lane, a second target lane marker is determined before the target vehicle leaves the third position, and the second target lane marker is used to identify the second target lane.

[0190] In a possible implementation manner, the apparatus 1500 further includes a fourth determining unit, a fourth acquiring unit, and a fifth determining unit:

[0191] a fourth determining unit, configured to determine a lane driving mark corresponding to the second target lane, wherein the lane driving mark is used to identify a drivable direction of the second target lane;

[0192] A fourth acquisition unit, used to acquire a navigation planning path corresponding to the target vehicle;

[0193] A fifth determination unit is used to redetermine the navigation planned path according to the lane driving sign before the target vehicle leaves the second position if the driving guidance direction related to the target area in the navigation planned path does not match the lane driving sign.

[0194] In a possible implementation manner, the apparatus 1500 further includes a sixth determining unit and a seventh determining unit:

[0195] a sixth determining unit, configured to determine, based on the road condition image data, a pending lane marker of the lane where the target vehicle is located at the second position;

[0196] A seventh determining unit is configured to determine the pending lane marker as a second target lane marker if the lane identified by the pending lane marker is an edge lane among the lanes included in the second position, wherein the second target lane marker is used to identify the second target lane.

[0197] In a possible implementation, if it is determined that the lane identified by the pending lane marker is not an edge lane among the lanes included in the second position, the device 1500 further includes an updating unit:

[0198] An updating unit is configured to update the second target lane identifier to a lane identifier of an adjacent lane of the second target lane in response to the second target lane being an edge lane in the lanes included in the second position.

[0199] The present application also provides a computer device, which is described below in conjunction with the accompanying drawings. Fig.16 As shown, the embodiment of the present application provides a device, which may also be a terminal device. The terminal device may be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a point of sales (POS), a vehicle-mounted computer, etc., and the terminal device is a mobile phone as an example:

[0200] Fig.16 FIG. 1 is a block diagram showing a partial structure of a mobile phone related to a terminal device provided in an embodiment of the present application. Fig.16 The mobile phone includes: a radio frequency (RF) circuit 710, a memory 720, an input unit 730, a display unit 740, a sensor 750, an audio circuit 760, a wireless fidelity (WiFi) module 770, a processor 780, and a power supply 790. Those skilled in the art will understand that Fig.16 The mobile phone structure shown in the figure does not constitute a limitation on the mobile phone, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0201] Combine the following Fig.16 A detailed introduction to the various components of the mobile phone:

[0202] The RF circuit 710 can be used for receiving and sending signals during the process of sending and receiving information or making calls. In particular, after receiving the downlink information of the base station, it is sent to the processor 780 for processing; in addition, the designed uplink data is sent to the base station. Usually, the RF circuit 710 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, referred to as LNA), a duplexer, etc. In addition, the RF circuit 710 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to the Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0203] The memory 720 can be used to store software programs and modules. The processor 780 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 720. The memory 720 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 720 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0204] The input unit 730 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone. Specifically, the input unit 730 may include a touch panel 731 and other input devices 732. The touch panel 731, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 731 or near the touch panel 731 using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 731 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 780, and can receive and execute commands sent by the processor 780. In addition, the touch panel 731 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 731, the input unit 730 may further include other input devices 732. Specifically, the other input devices 732 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

[0205] The display unit 740 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 740 may include a display panel 741. Optionally, the display panel 741 may be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), etc. Further, the touch panel 731 may cover the display panel 741. When the touch panel 731 detects a touch operation on or near it, it is transmitted to the processor 780 to determine the type of touch event. Subsequently, the processor 780 provides a corresponding visual output on the display panel 741 according to the type of touch event. Although in Fig.16 In the embodiment, the touch panel 731 and the display panel 741 are used as two independent components to realize the input and output functions of the mobile phone, but in some embodiments, the touch panel 731 and the display panel 741 can be integrated to realize the input and output functions of the mobile phone.

[0206] The mobile phone may also include at least one sensor 750, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 741 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 741 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0207] The audio circuit 760, the speaker 761, and the microphone 762 can provide an audio interface between the user and the mobile phone. The audio circuit 760 can transmit the received audio data to the speaker 761 after converting the received audio data into an electrical signal, which is converted into a sound signal for output; on the other hand, the microphone 762 converts the collected sound signal into an electrical signal, which is received by the audio circuit 760 and converted into audio data, and then the audio data is output to the processor 780 for processing, and then sent to another mobile phone through the RF circuit 710, or the audio data is output to the memory 720 for further processing.

[0208] WiFi is a short-range wireless transmission technology. The mobile phone can help users send and receive emails, browse web pages and access streaming media through the WiFi module 770. It provides users with wireless broadband Internet access. Fig.16 A WiFi module 770 is shown, but it is understandable that it is not an essential component of the mobile phone and can be omitted as needed without changing the essence of the invention.

[0209] The processor 780 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. It executes various functions of the mobile phone and processes data by running or executing software programs and / or modules stored in the memory 720, and calling data stored in the memory 720. Optionally, the processor 780 may include one or more processing units; preferably, the processor 780 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 780.

[0210] The mobile phone also includes a power supply 790 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 780 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions.

[0211] Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0212] In this embodiment, the processor 780 included in the terminal device also has the following functions:

[0213] Determine a first target lane in the road where the target vehicle is located when the target vehicle reaches a first position, the first position being a starting position of a target area in the road in a driving direction of the target vehicle, a first number of lanes included in the target area at the first position being different from a second number of lanes included in the target area at a second position, and the second position being an ending position of the target area in the driving direction of the target vehicle;

[0214] Acquire vehicle motion data and road condition image data corresponding to the target vehicle in the target area;

[0215] A second target lane corresponding to the target vehicle before it leaves the second position is determined according to the vehicle motion data, the road condition image data and the first target lane.

[0216] The present application also provides a server. Fig.17 As shown, Fig.17 The structural diagram of the server 800 provided in the embodiment of the present application, the server 800 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 822 (for example, one or more processors) and a memory 832, and one or more storage media 830 (for example, one or more mass storage devices) storing application programs 842 or data 844. Among them, the memory 832 and the storage medium 830 can be temporary storage or permanent storage. The program stored in the storage medium 830 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processing unit 822 can be configured to communicate with the storage medium 830 and execute a series of instruction operations in the storage medium 830 on the server 800.

[0217] The server 800 may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input and output interfaces 858, and / or one or more operating systems 841, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0218] The steps performed by the server in the above embodiment can be based on Fig.17 The server structure shown.

[0219] The embodiment of the present application further provides a computer-readable storage medium for storing a computer program, wherein the computer program is used to execute any one of the implementations of the positioning methods described in the aforementioned embodiments.

[0220] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the above-mentioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the above-mentioned storage medium can be at least one of the following media: read-only memory (English: read-only memory, abbreviated: ROM), RAM, magnetic disk or optical disk, etc. Various media that can store program codes.

[0221] It should be noted that each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments. The device and system embodiments described above are merely schematic, in which the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0222] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A positioning method, characterized in that: The method comprises: Determine a first target lane in the road where the target vehicle is located when the target vehicle reaches a first position, the first position being a starting position of a target area in the road in a driving direction of the target vehicle, a first number of lanes included in the target area at the first position being different from a second number of lanes included in the target area at a second position, and the second position being an ending position of the target area in the driving direction of the target vehicle; Acquire vehicle motion data and road condition image data corresponding to the target vehicle in the target area; the target area is an intersection area where lane expansion occurs and is located between a lane expansion starting point and a stop line feature point; the lane expansion starting point is used to identify the first position; the stop line feature point is used to identify the second position; there is a lane line disappearance area in the target area; Determining the second target lane corresponding to the target vehicle before it leaves the second position according to the vehicle motion data, the road condition image data and the first target lane, specifically comprising: when the target vehicle is in the lane line disappearing area, determining the target lane line of the lane included in the second position according to the road condition image data; determining the intercept distance parameter between the target vehicle and the target lane line; determining an image lane change parameter according to the intercept distance parameter, the image lane change parameter being used to indicate that the target vehicle has not changed lanes, or the direction and number of lane changes; determining a second target lane identifier before the target vehicle leaves the second position according to the vehicle motion data, the image lane change parameter and the first target lane identifier corresponding to the first target lane, the second target lane identifier being used to identify the second target lane; Determine a lane driving mark corresponding to the second target lane, where the lane driving mark is used to identify a drivable direction of the second target lane; Obtaining a navigation planning path corresponding to the target vehicle; If the driving guidance direction associated with the target area in the navigation planning path does not match the lane driving mark, the navigation planning path is re-determined according to the lane driving mark before the target vehicle leaves the second position.

2. The method according to claim 1, characterized in that The determining, based on the vehicle motion data, the road condition image data and the first target lane, a second target lane corresponding to the target vehicle before it leaves the second position comprises: Determine a motion lane change parameter according to the vehicle motion data, wherein the motion lane change parameter is used to indicate that the target vehicle does not change lanes, or changes the direction and amount of lanes; According to the motion lane change parameter, the road condition image data and a first target lane marker corresponding to the first target lane, a second target lane marker is determined before the target vehicle leaves the second position, and the second target lane marker is used to identify the second target lane.

3. The method according to claim 2, characterized in that The vehicle motion data includes at least one of vehicle motion angle data, gyroscope data, and steering wheel rotation data, and determining the motion lane change parameter according to the vehicle motion data includes: Determining a displacement parameter of the target vehicle in a lateral direction within the target area according to the vehicle motion data, wherein the lateral direction is perpendicular to a direction of travel indicated by a lane corresponding to the second position; The motion lane change parameter is determined according to the displacement parameter.

4. The method according to claim 1, characterized in that: The method further comprises: Obtaining vehicle position information corresponding to the target vehicle; Acquiring road map data corresponding to the target area according to the vehicle position information; Determining a lane topology relationship corresponding to the target area according to the road map data, the lane topology relationship including a topology relationship between a first lane and a second lane, the first lane being a lane corresponding to the starting position, and the second lane being a lane corresponding to the ending position; The determining, based on the vehicle motion data, the road condition image data and the first target lane, a second target lane corresponding to the target vehicle before it leaves the second position comprises: Based on the vehicle motion data, the road condition image data, the lane topology relationship and the first target lane identifier corresponding to the first target lane, a second target lane identifier is determined before the target vehicle leaves the second position, and the second target lane identifier is used to identify the second target lane.

5. The method according to claim 4, characterized in that The road map data further includes a third position, the third position being an end position of the variable lane area in the target area in the driving direction of the target vehicle, and the third position being located between the first position and the second position; The obtaining of the vehicle motion data and road condition image data corresponding to the target vehicle in the target area includes: Acquire vehicle motion data and road condition image data corresponding to the target vehicle between the first position and the third position; The determining, based on the vehicle motion data, the road condition image data and the first target lane, a second target lane corresponding to the target vehicle before it leaves the second position comprises: Based on the vehicle motion data, the road condition image data and a first target lane marker corresponding to the first target lane, a second target lane marker is determined before the target vehicle leaves the third position, and the second target lane marker is used to identify the second target lane.

6. The method according to claim 1, characterized in that The method further comprises: Determine, according to the road condition image data, a pending lane marker of the lane where the target vehicle is located at the second position; If the lane identified by the pending lane marker is an edge lane among the lanes included in the second position, the pending lane marker is determined as a second target lane marker, and the second target lane marker is used to identify the second target lane.

7. The method according to claim 6, characterized in that If it is determined that the lane identified by the pending lane marker is not an edge lane among the lanes included in the second position, the method further includes: In response to the second target lane being an edge lane among lanes included in the second position, the second target lane identifier is updated to a lane identifier of a lane adjacent to the second target lane.

8. A positioning device, characterized in that: The device comprises a first determining unit, a first acquiring unit, a second determining unit, a fourth determining unit, a fourth acquiring unit and a fifth determining unit: The first determination unit is used to determine a first target lane in the road where the target vehicle is located when the target vehicle reaches a first position, the first position being a starting position of a target area in the road in a driving direction of the target vehicle, a first number of lanes included in the target area at the first position being different from a second number of lanes included in the target area at the second position, and the second position being an ending position of the target area in the driving direction of the target vehicle; The first acquisition unit is used to acquire the vehicle motion data and road condition image data corresponding to the target vehicle in the target area; The target area is an intersection area where lane expansion occurs and is located between a lane expansion starting point at the intersection and a stop line feature point; the lane expansion starting point at the intersection is used to identify the first position; The stop line feature point is used to identify the second position; there is a lane line disappearing area in the target area; The second determining unit is used to determine a second target lane corresponding to the target vehicle before it leaves the second position according to the vehicle motion data, the road condition image data and the first target lane; The second determination unit is specifically used to determine the target lane line of the lane included in the second position according to the road condition image data when the target vehicle is in the lane line disappearing area; determine the intercept distance parameter between the target vehicle and the target lane line; determine the image lane change parameter according to the intercept distance parameter, and the image lane change parameter is used to indicate that the target vehicle has not changed lanes, or the direction and number of lane changes; determine the second target lane marker before the target vehicle leaves the second position according to the vehicle motion data, the image lane change parameter and the first target lane marker corresponding to the first target lane, and the second target lane marker is used to identify the second target lane; The fourth determining unit is used to determine a lane driving mark corresponding to the second target lane, where the lane driving mark is used to identify a drivable direction of the second target lane; The fourth acquisition unit is used to acquire the navigation planning path corresponding to the target vehicle; The fifth determination unit is used to redetermine the navigation planned path according to the lane driving sign before the target vehicle leaves the second position if the driving guidance direction related to the target area in the navigation planned path does not match the lane driving sign.

9. The device according to claim 8, characterized in that The second determining unit is specifically configured to: Determine a motion lane change parameter according to the vehicle motion data, wherein the motion lane change parameter is used to indicate that the target vehicle does not change lanes, or changes the direction and amount of lanes; According to the motion lane change parameter, the road condition image data and a first target lane marker corresponding to the first target lane, a second target lane marker is determined before the target vehicle leaves the second position, and the second target lane marker is used to identify the second target lane.

10. The device according to claim 9, characterized in that The vehicle motion data includes at least one of vehicle motion angle data, gyroscope data, and steering wheel rotation data, and the second determination unit is specifically used for: Determining a displacement parameter of the target vehicle in a lateral direction within the target area according to the vehicle motion data, wherein the lateral direction is perpendicular to a direction of travel indicated by a lane corresponding to the second position; determining the motion lane change parameter according to the displacement parameter; A second lane marker is determined before the target vehicle leaves the target area according to the motion lane change parameter, the road condition image data and the first lane marker.

11. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the positioning method described in any one of claims 1 to 7 according to the instructions in the program code.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the positioning method according to any one of claims 1 to 7.

Images