A vehicle positioning method, vehicle and positioning system based on ground marking grids

Abstract

The present invention provides a vehicle positioning method, a vehicle and a positioning system based on ground identification grids, which relates to the technical field of vehicle information management. The vehicle positioning method based on ground identification grids of the present invention includes: identifying the first relative position information of a target vehicle, where the first relative position information is the position information of the target vehicle automatically identified relative to the meta coordinates of the identification grid pre-drawn at the position where the target vehicle is located. Fusing and determining the first relative position information with the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle. Combining the final relative position information with the actual position information of the meta coordinates to obtain the final actual position information of the target vehicle. The positioning method, vehicle and positioning system of the present invention mutually redundantly identify through the first relative position information and the second relative position information, so that the position of the target vehicle can be quickly identified, the positioning accuracy of the target vehicle is high, and the overall functional safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle information management, and particularly to a vehicle positioning method, a vehicle and a positioning system based on ground identification grids. Background Art

[0002] Currently, vehicle positioning technologies mainly include the following categories: vehicle positioning technologies based on satellite and ground base station positioning technologies, such as using satellite systems like Beidou, GPS, GLONASS, Galileo, and Qianxun Positioning. 2. Vehicle positioning technologies based on near-field wireless communication, using systems such as Bluetooth beacons, Wi-Fi hotspots, ZigBee, and UWB for positioning; 3. Auxiliary vehicle positioning technologies using vehicle inertial navigation, using gyroscopes, vehicle speed sensors, etc. installed in the vehicle to estimate the position of the vehicle after traveling for a period of time based on the original vehicle position; 4. Vehicle positioning technologies based on mobile operation network base stations; 5. Vehicle positioning technologies based on high-precision sensors and video recognition landmarks installed in the vehicle; 6. Vehicle positioning technologies integrating multiple positioning technologies.

[0003] For these existing positioning technologies, for example, for vehicle positioning technologies based on satellite and ground base station positioning technologies, generally the positioning accuracy is 5 - 10m, and the traditional positioning delay is 30 - 50s. Even for the new Qianxun Positioning system based on the integration of multiple satellites and multiple base stations, the positioning accuracy at the vehicle level is about 5cm, and the positioning delay is 3 - 5s (the positioning delay is still too long in the control scenario of high-speed vehicles). In addition, the Qianxun Positioning system needs to build more ground base stations, with huge upfront investment, relatively high usage costs, and inability to position in areas with obstructions or basements. For vehicle positioning technologies based on near-field wireless communication, this technology requires specially building positioning landmarks in advance, and multiple landmarks need to cooperate for positioning to improve the positioning accuracy, and a professional high-definition map with landmark position data is required. For auxiliary vehicle positioning technologies using vehicle inertial navigation, using gyroscopes, vehicle speed sensors, etc. installed in the vehicle to estimate the position of the vehicle after traveling for a period of time based on the original vehicle position; for auxiliary vehicle positioning technologies using vehicle inertial navigation, an initial positioning position is required, and deviations in the driving direction and frequent lane changes will bring more errors, and the positioning accuracy will become lower and lower over time. For vehicle positioning technologies based on mobile operation network base stations; even in the future 5G stage, the positioning accuracy requirement for this technology is 1m. For vehicle positioning technologies based on high-precision sensors and video recognition landmarks installed in the vehicle, high-position detection accuracy sensors such as lidar, millimeter-wave radar, and binocular cameras are relatively costly. A high-precision map based on the corresponding sensor information at the landmark is required, and the map needs to be updated as real-time as possible. For vehicle positioning technologies integrating multiple positioning technologies, the integration requires complex control logic and higher costs. Summary of the Invention

[0004] An object of the present invention is to provide a vehicle positioning method based on ground identification grids, so as to solve the problems of low positioning accuracy and long positioning delay time in existing positioning technologies.

[0005] Another object of the present invention is to solve the problems of high technical requirements and high costs in existing positioning technologies.

[0006] Another object of the present invention is to provide a vehicle, so as to solve the problems of low positioning accuracy, long positioning delay time and high costs in existing vehicles.

[0007] Another object of the present invention is to provide an identification grid-based vehicle positioning system including the above-mentioned vehicle.

[0008] In particular, the present invention provides a vehicle positioning method based on ground identification grids, including:

[0009] Identifying the first relative position information of a target vehicle, where the first relative position information is the position information of the target vehicle automatically identified relative to the meta-coordinates of the identification grid pre-drawn at the position where the target vehicle is located; where different regions include multiple different identification grids, and each identification grid corresponds to a meta-coordinate;

[0010] Fusing and determining the first relative position information with the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle, where the second relative position information is the position information of the target vehicle identified by a landmark camera system relative to the meta-coordinates of the identification grid at the position where the target vehicle is located;

[0011] Combining the final relative position information with the actual position information of the meta-coordinates obtained and stored in advance to obtain the final actual position information of the target vehicle.

[0012] Optionally, the identification grids include multiple identification grids drawn on the road surfaces in different regions; a landmark camera system is provided at each identification grid, and the second relative position information of the target vehicle at the corresponding identification grid is identified through the landmark camera system;

[0013] Optionally, the identification grid is an intersection grid formed by a first identification line and a second identification line, where the first identification line is multiple identification lines drawn along a direction parallel to the road edge and having a preset width and a preset spacing, and the second identification line is multiple identification lines drawn along a direction perpendicular to the road edge and having the preset width and the preset spacing.

[0014] Optionally, the meta-coordinates include:

[0015] On a straight road, the original coordinate is selected as any intersection point in the road identification grid, and the identification grid at the original coordinate position is marked with a diagonal line; or

[0016] At a turning or intersection, the original coordinate is the intersection point of two identification lines parallel to the road edges of the corresponding roads on two directions of the road.

[0017] Optionally, the process of the target vehicle automatically identifying the first relative position information includes:

[0018] Using the vehicle camera system installed on the target vehicle to obtain an image of the target vehicle at the identification grid at the corresponding position, and identifying the first relative position information;

[0019] Optionally, the process of the landmark camera system identifying the second relative position of the target vehicle includes:

[0020] Using the landmark camera system to capture an image of the target vehicle at the identification grid at the corresponding position, and identifying the second relative position information.

[0021] Optionally, the process of fusing and determining the first relative position information and the second relative position information to obtain the final relative position information of the target vehicle includes:

[0022] When the first relative position information is consistent with the second relative position information, then at this time both the first relative position information and the second relative position information are the final relative position information of the target vehicle; or

[0023] When the first relative position information is inconsistent with the second relative position information, then first take the second relative position information as the accurate relative position information and the first relative position information as untrustworthy information. When the proportion of the first relative position information of the vehicles passing by within a preset time becoming untrustworthy information is not greater than a preset proportion, then determine the second relative position information as the final relative position information of the target vehicle; or

[0024] When the first relative position information is inconsistent with the second relative position information, and the proportion of the first relative position information of the vehicles passing by within the preset time becoming untrustworthy information is greater than the preset proportion, then determine the second relative position information as untrustworthy information. At this time, the first relative position information is the final relative position information of the target vehicle;

[0025] Optionally, when it is determined that the first relative position information is inconsistent with the second relative position information and the second relative position information is untrustworthy information, the landmark camera system is adjusted to update the second relative position information until the second relative position information is consistent with the first relative position information;

[0026] When it is determined that the first relative position information is inconsistent with the second relative position information and the first relative position information is untrustworthy information, the vehicle camera system is adjusted to update the first relative position information until the first relative position information is consistent with the second relative position information.

[0027] Specifically, the present invention further provides a vehicle, including a vehicle camera system, the vehicle camera system includes a vehicle controller, and the vehicle controller includes:

[0028] An identification module for identifying the first relative position information of the target vehicle; wherein, the first relative position information is the position information of the target vehicle automatically identified relative to the meta-coordinates of the identification grid pre-drawn at the position of the target vehicle; at least one different identification grid is drawn on the road surfaces of different regions, and each identification grid corresponds to a meta-coordinate;

[0029] A final relative position information determination module for fusing and determining the first relative position information and the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle, wherein the second relative position information is the position information of the target vehicle relative to the meta-coordinates of the identification grid at the position of the target vehicle identified by the landmark camera system; and

[0030] An actual position information acquisition module for obtaining the final actual position information of the target vehicle by combining the final relative position information with the actual position information of the pre-acquired and stored meta-coordinates.

[0031] Optionally, the vehicle camera system further includes a vehicle camera, and the vehicle camera is used to obtain an image frame of the target vehicle at the corresponding identification grid at the position of the target vehicle; the identification module identifies the first relative position information according to the image frame obtained by the vehicle camera;

[0032] Optionally, the vehicle controller is configured to determine according to the first relative position information and the second relative position information. When the determination result is that the first relative position information is the final relative position information of the target vehicle, the final actual position information of the target vehicle is obtained according to the actual position information of the meta-coordinates;

[0033] Optionally, the vehicle camera system further includes a first relative position updating module, configured to adjust the position of the vehicle camera to update the first relative position information until it is consistent with the second relative position information when the first relative position information is inconsistent with the second relative position information and it is determined that the second relative position information is the final relative position information of the target vehicle.

[0034] Specifically, the present invention further provides a vehicle positioning system based on ground marking grids, including a landmark system and the vehicle described above. The vehicle is used to identify the first relative position information of the target vehicle, and the landmark system is used to identify the second relative position information of the target vehicle. The vehicle and the landmark system perform information interaction, so that both the vehicle and the landmark system can determine the final relative position information of the target vehicle according to the first relative position information and the second relative position information, and combine the final relative position information with the actual position information of the meta-coordinates to obtain the final actual position information of the target vehicle.

[0035] Optionally, the road surfaces in different regions correspond to different landmark systems, and each landmark system includes:

[0036] Marking grids, including at least one set of marking grids pre-drawn on the road surface. The marking grids are cross grids formed by a first marking line and a second marking line. The first marking line is a plurality of marking lines drawn along a direction parallel to the road edge with a preset width and a preset spacing, and the second marking line is a plurality of marking lines drawn along a direction perpendicular to the road edge with the preset width and the preset spacing; and

[0037] Landmark camera systems, and a corresponding landmark camera system is established at each marking grid to identify the second relative position information of the target vehicle within the corresponding marking grid through the landmark camera system.

[0038] Optionally, each landmark camera system includes:

[0039] At least one landmark camera, configured to capture image information of the target vehicle within the range of the corresponding marking grid; and

[0040] A landmark controller, configured to receive the image frame of the target vehicle obtained by the landmark camera, analyze and obtain the second relative position information, and pre-acquire and store the actual position information of the meta-coordinates;

[0041] Optionally, the landmark controller is further configured to determine based on the second relative position information and the first relative position information. When the determination result is that the second relative position information is the final relative position information of the target vehicle, obtain the actual position information of the target vehicle according to the actually acquired and stored actual position information of the meta coordinates;

[0042] Optionally, the landmark camera system further includes a second relative position update module. The second relative position update module is configured to adjust the position of the landmark camera to update the second relative position information until it is consistent with the first relative position information when the first relative position information is inconsistent with the second relative position information and it is determined that the first relative position information is the final relative position information of the target vehicle.

[0043] The positioning method and system of the present invention only need to preset identification grids in advance at some positions where positioning is required. The target vehicle redundantly identifies through the first relative position information and the second relative position information at the position of the identification grid, so that the position identification of the target vehicle is fast, the positioning accuracy of the target vehicle is high, and the overall functional safety is improved.

[0044] Furthermore, each road surface with an identification grid is an independent position confirmation location, without the need for a dedicated map and map updates. Moreover, regardless of the first relative position information and the second relative position information, they are both used to identify the same target vehicle. Therefore, the signal consistency is relatively good.

[0045] The vehicle positioning system of the present invention mainly includes identification grids, a landmark camera system, and a vehicle camera system. Among them, the landmark controller in the landmark camera system also interacts with the vehicle. The positioning system has a simple composition and relatively low cost.

[0046] From the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more clear about the above and other objects, advantages, and features of the present invention. Description of the Drawings

[0047] Some specific embodiments of the present invention will be described in detail hereinafter with reference to the accompanying drawings in an exemplary but not restrictive manner. The same reference numerals in the drawings denote the same or similar components or parts. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0048] Figure 1 is a schematic flowchart of a vehicle positioning method based on ground identification grids according to an embodiment of the present invention;

[0049] Figure 2 [[ID=******]] ​

[0050] Figure 3 is a schematic diagram of a marking grid at a right-angle turn or intersection according to an embodiment of the present invention;

[0051] Figure 4 is a schematic diagram of a marking grid at a non-right-angle turn or intersection according to an embodiment of the present invention;

[0052] Figure 5 is a schematic diagram of coordinate selection of a target vehicle relative to a meta-coordinate on a straight road according to an embodiment of the present invention;

[0053] Figure 6 is a schematic diagram of coordinate selection of a target vehicle relative to a meta-coordinate on a turning or intersecting road according to an embodiment of the present invention;

[0054] Figure 7 is a schematic block diagram of a vehicle according to an embodiment of the present invention;

[0055] Figure 8 is a schematic block diagram of a vehicle according to another embodiment of the present invention; Figure 9 is a schematic block diagram of a vehicle positioning system based on a ground marking grid according to an embodiment of the present invention;

[0056] Figure 10 is a schematic block diagram of a vehicle positioning system based on a ground marking grid according to an embodiment of the present invention;

[0057] Figure 11 is a schematic block diagram of a landmark system according to an embodiment of the present invention;

[0058] Figure 12 is a schematic block diagram of a vehicle positioning system based on a ground marking grid according to another embodiment of the present invention;

[0059] Figure 13 is a schematic flowchart of the interaction between a vehicle and a positioning system of a vehicle positioning system according to an embodiment of the present invention. Detailed implementation manners

[0060] Figure 1 is a schematic flowchart of a vehicle positioning method based on a ground marking grid according to an embodiment of the present invention. As Figure 1 shown, the vehicle positioning method based on a ground marking grid in this embodiment may include:

[0061] S10 Identify the first relative position information of the target vehicle, where the first relative position information is the position information of the target vehicle automatically identified relative to the meta-coordinate of the marking grid pre-drawn at the position of the target vehicle; wherein, different regions include multiple groups of different marking grids, and each marking grid corresponds to a meta-coordinate;

[0062] S20 fuses and determines the first relative position information with the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle, wherein the second relative position information is the position information of the meta-coordinates of the target vehicle relative to the identification grid where the target vehicle is located recognized by the landmark camera system;

[0063] S30 combines the final relative position information with the actual position information of the pre-acquired and stored meta-coordinates to obtain the final actual position information of the target vehicle.

[0064] The positioning method of this embodiment only needs to set identification grids at some positions where positioning is required. The target vehicle redundantly identifies each other through the first relative position information and the second relative position information at the position of the identification grid, so that the position identification of the target vehicle is fast, the positioning accuracy of the target vehicle is high, and the overall functional safety is improved.

[0065] In addition, each road surface with an identification grid is an independent position confirmation point, and no dedicated map and map update are required. Moreover, regardless of the first relative position information and the second relative position information, they are both used to identify the same target vehicle. Therefore, the signal consistency is relatively good.

[0066] As a specific embodiment of the present invention, the identification grid includes a plurality of identification grids drawn on the road surfaces in different regions. A landmark camera system is provided at each identification grid, and the first relative position information of the target vehicle at the corresponding identification grid is recognized through the landmark camera system.

[0067] Before implementing this method, it is necessary to first draw identification grids on the road surface at the positions where vehicle positioning is required. One or more groups of identification grids can be drawn for each road section. However, each group of identification grids corresponds to only one meta-coordinate. In addition, a landmark camera system can be established for one group of identification grids or adjacent multiple groups of identification grids. The landmark camera system can capture the image frames of all the identification grids in this area and further analyze the image frames to obtain the first relative position information of the target vehicle.

[0068] Figure 2It is a schematic diagram of the identification grid on a straight road according to an embodiment of the present invention. Specifically, the identification grid 20 is an intersection grid formed by the first identification line 21 and the second identification line 22 together. Among them, the first identification line 21 is a plurality of identification lines drawn along a direction parallel to the road edge 70 with a preset width and a preset spacing. And the second identification line 22 is a plurality of identification lines drawn perpendicular to the road edge 70 with a preset width and a preset spacing. Specifically, in this embodiment, the preset width of the identification line is about 10 cm, and the preset distance is about 40 cm. In addition, in one embodiment, additional identification lines can be added at the edge of the identification grid 20 to ensure that the inner identification grid 20 is clear and complete. The parallel spacing between the identification line and the road edge 70 for safe driving is about 10 cm. In this embodiment, based on the image recognition of the square identification grid 20 with a side length of 50 cm, the positioning accuracy is high, which can reach the 5 cm level. With the identification grid 20 as the reference for image recognition, the recognition speed is fast, and the positioning delay is within 50 ms.

[0069] As a specific embodiment of the present invention, as Figure 2 shown, the selection of the meta coordinate can specifically include two types. First, the selection of the meta coordinate 60 on the straight road is any intersection point in the identification grid 20 of this section, and a diagonal line 23 is marked at the identification grid 20 at the position of the meta coordinate 60. Specifically, in the actual operation process, due to the technical limitations of the landmark camera system, when it shoots the identification grid 20, a deformation area will appear at the edge position, and the deformation of the shooting picture will directly lead to inaccurate positioning. Therefore, in order to improve the positioning accuracy, the meta coordinate 60 is preferably selected in the non-deformed area of the picture that the landmark camera system can shoot. And it is preferably at a position relatively close to the landmark camera system. The specific selection of the meta coordinate 60 can be made according to actual needs. After selecting the meta coordinate 60, in order to facilitate the identification of the meta coordinate 60, generally an additional diagonal line 23 will be added as a mark at the grid at the position of the meta coordinate 60, and the meta coordinate 60 is selected at the outer right-angled vertex of the right-angled triangle.

[0070] As other embodiments, Figure 3 It is a schematic diagram of the identification grid 20 at a right-angle turn or an intersection according to an embodiment of the present invention; Figure 4 It is a schematic diagram of the identification grid 20 at a non-right-angle turn or an intersection according to an embodiment of the present invention. As Figure 3 and Figure 4As shown, the selection of the meta coordinates may further include the following. Second, at a turning point or an intersection, the meta coordinate 60 is the intersection point of two marking lines respectively parallel to the corresponding road edges 70 on the roads in two directions. And at the position of the meta coordinate 60, an oblique line 23 is added to form an isosceles triangle as a mark, and the meta coordinate 60 is the vertex position of the isosceles triangle. In the actual operation process, for the determination method of the marking lines in each direction, the marking line parallel to the road passing through the first superelevation of 2 m after the turning point is preferentially drawn. For a special sharp turning section with an angle greater than or equal to 180° or a special continuous turning section, one or more marking lines tangent to the road arc are added between the included angles of the two road directions, and the section is divided into two marking cells 20 that share a part of the marking cells 20. After the drawing is determined, use high-precision positioning means to measure and record its actual geographical location, and obtain the actual position information of the meta coordinate. Generally, the recorded actual geographical location includes longitude and latitude and the included angle between the road direction and longitude. When the meta coordinate is at a turning point or an intersection, record all the included angles between the road directions and longitude. The turning point is regarded as two roads, and each road is defined with a label. In addition, at a non-90° turning point, leave a 1 m extension line after the intersection of the marking lines.

[0071] As a specific embodiment, the specific process of identifying the second relative position of the target vehicle by the landmark camera system includes:

[0072] Use the landmark camera system to capture an image of the target vehicle at the marking cell 20 at the corresponding position, and analyze and obtain the second relative position information.

[0073] As a specific embodiment, the process of automatically identifying the first relative position information of the target vehicle includes:

[0074] Use the vehicle camera system installed on the target vehicle to capture an image of the target vehicle at the marking cell 20 at the corresponding position, and analyze and obtain the first relative position information.

[0075] The principles of obtaining the first relative position information and the second relative position information are basically the same. Both use the camera to first obtain the image of the target vehicle and the marking cell 20, and then analyze and calculate to identify the relative position information of the target vehicle and the meta coordinate.

[0076] Figure 5 It is a schematic diagram of the coordinate selection of the target vehicle relative to the meta coordinate 60 on a straight road according to an embodiment of the present invention; Figure 6It is a schematic diagram of coordinate selection of a target vehicle relative to the original coordinate 60 on a turning or intersection road according to an embodiment of the present invention. In this embodiment, when analyzing the screen information, first, the target vehicle in the captured screen is replaced by a rectangle with sides parallel or perpendicular to the road marking grid 20 as the vehicle position, and the vehicle edge is tangent to the rectangle (that is, the vehicle edge is completely contained within the rectangle and there are tangent points at the edges). The position coordinates of the landmark rectangle are represented as follows: the coordinate system takes the original coordinate 60 as the origin, the direction along the road edge 70 as the X-axis direction, and the direction perpendicular to the road edge 70 as the Y-axis direction, which is an orthogonal coordinate system. X1 is the X-axis coordinate of the rectangle near the landmark camera, X2 is the X-axis coordinate of the rectangle far from the landmark camera, YI is the Y-axis coordinate of the rectangle near the landmark camera, and Y2 is the Y-axis coordinate of the rectangle far from the landmark camera.

[0077] When the target vehicle is on a straight road, a set of coordinate information can be obtained. When the target vehicle is in a turning transition area, the vehicle body is located in different groups of marking grids 20, and two sets of coordinate position information can be obtained. Specifically, as Figure 5 and Figure 6 shown. Figure 5 On a straight road, the vehicle has only one set of coordinates, which are (X1, X2, Y1, Y2) respectively. When the vehicle is at a turning or intersection, as Figure 6 shown, the vehicle may have at least two sets of coordinates. Taking two sets of coordinates as an example, (X1, X2, Y1, Y2) and (X1’, X2’, Y1’, Y2’) are obtained respectively. According to this method, the first relative position information and the second relative position information are obtained. When comparing the first relative position information and the second relative position information, the coordinates obtained in the unified coordinate system need to be compared and analyzed.

[0078] As a specific embodiment, the process of fusing and determining the first relative position information and the second relative position information to obtain the final relative position information of the target vehicle includes:

[0079] When the first relative position information is consistent with the second relative position information, then at this time, both the first relative position information and the second relative position information are the final relative position information of the target vehicle; or

[0080] When the first relative position information is inconsistent with the second relative position information, first, the second relative position information is regarded as the accurate relative position information, and the first relative position information is regarded as untrustworthy information. When the proportion of the first relative position information of the vehicles passing by within the preset time becoming untrustworthy information is not greater than the preset proportion, it is determined that the second relative position information is the final relative position information of the target vehicle; or

[0081] When the first relative position information and the second relative position information are inconsistent, and the proportion of the first relative position information of the vehicles passing by within the preset time becoming untrustworthy information is greater than the preset proportion, it is determined that the second relative position information is untrustworthy information. At this time, the first relative position information is the final relative position information of the target vehicle.

[0082] The above preset time and preset proportion can be set such that within one hour, when 2 / 3 of the vehicles pass by a certain identification grid 20, the first relative position information and the second relative position information of the vehicles are inconsistent, indicating that the second relative position information at this position is untrustworthy. Of course, this proportion can also be freely designed according to actual requirements and accuracy requirements.

[0083] As a specific embodiment, when it is determined that the first relative position information and the second relative position information are inconsistent, and the second relative position information is untrustworthy information, the landmark camera system is adjusted to update the second relative position information until the second relative position information is consistent with the first relative position information. In this embodiment, it is shown that there may be a deviation in the landmark camera system, resulting in all the second relative position information obtained by the landmark camera system being incorrect. After this situation occurs, it can be promptly reported for repair to the maintenance personnel of the system. After the maintenance personnel adjust the landmark camera system, accurate second relative position information can be obtained.

[0084] As another specific embodiment, when it is determined that the first relative position information and the second relative position information are inconsistent, and the first relative position information is untrustworthy information, the vehicle camera system is adjusted to update the first relative position information until the first relative position information is consistent with the second relative position information. This situation occurs when there is a deviation in the vehicle camera system of a certain vehicle. Since the vehicle may jitter or have other situations during driving, the possibility of the vehicle camera system deviating is relatively high. When the landmark camera system is confirmed to be accurate, the vehicle camera system can be adjusted so that the first relative position information obtained by the camera system is also accurate, thereby ensuring the accuracy of the positioning of the target vehicle.

[0085] In this embodiment, both the vehicle internal system and the landmark camera system will independently determine the first relative position information and the second relative position information, and independently update their respective systems according to the determination results to improve the accuracy of the positioning method for the target vehicle.

[0086] Figure 7It is a schematic block diagram of a vehicle according to an embodiment of the present invention. As a specific embodiment of the present invention, this embodiment further provides a vehicle, which may include a vehicle controller 42. The vehicle controller 42 may include an identification module 11, a final relative position information determination unit 12, and an actual position information acquisition unit 13. Among them, the identification module 11 is used to identify the first relative position information of the target vehicle. The first relative position information is the position information of the target vehicle automatically identified relative to the meta-coordinate 60 of the identification grid 20 pre-drawn at the position where the target vehicle is located. At least one different identification grid is drawn on the road surfaces of different regions, and each identification grid corresponds to a meta-coordinate 60. The final relative position information determination module 12 is used to fuse and determine the first relative position information with the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle. The second relative position information is the position information of the target vehicle relative to the meta-coordinate 60 of the identification grid at the position where the target vehicle is located identified by the landmark camera system. The actual position information acquisition module 13 combines the final relative position information with the actual position information of the pre-acquired and stored meta-coordinate 60 to obtain the final actual position information of the target vehicle.

[0087] The positioning system 100 of this embodiment only needs to set identification grids at some positions where positioning is required. The target vehicle redundantly identifies each other through the first relative position information and the second relative position information at the position of the identification grid, so that the position identification of the target vehicle is fast, the positioning accuracy of the target vehicle is high, and the overall functional safety is improved.

[0088] In addition, each road surface with an identification grid is an independent position confirmation place, and no special map and map update are required. And regardless of the first relative position information and the second relative position information, they are both used to identify the same target vehicle. Therefore, the signal consistency is relatively good.

[0089] Specifically, as Figure 7 shown, the vehicle camera system 40 may further include a vehicle camera 41. The vehicle camera 41 is used to obtain an image of the target vehicle at the identification grid 20 at the corresponding position where the target vehicle is located. The identification module 11 identifies the first relative position information according to the image obtained by the vehicle camera 41.

[0090] Specifically, the vehicle controller 42 is configured to determine according to the first relative position information and the second relative position information. When the determination result is that the first relative position information is the final relative position information of the target vehicle, the final actual position information of the target vehicle is obtained according to the actual position information of the meta-coordinate.

[0091] Figure 8 It is a schematic block diagram of a vehicle according to another embodiment of the present invention. Specifically, as Figure 8As shown, the vehicle camera system further includes a first relative position update module 14, which is configured to adjust the position of the vehicle camera 41 to update the first relative position information until it is consistent with the second relative position information when the first relative position information is inconsistent with the second relative position information and it is determined that the second relative position information is the final relative position information of the target vehicle. The continuously updated vehicle camera system 40 can ensure the accuracy of the vehicle camera system 40 for vehicle positioning, thereby improving the accuracy of vehicle positioning.

[0092] Figure 9 is a schematic block diagram of a vehicle positioning system 100 based on ground identification grids according to an embodiment of the present invention; Figure 10 is a schematic block diagram of a vehicle positioning system 100 based on ground identification grids according to an embodiment of the present invention. As a specific embodiment, the vehicle positioning system 100 of this embodiment may include a vehicle 200 and a landmark system 10. Among them, the vehicle 200 is used to identify the first relative position information of the target vehicle, and the landmark system 10 is used to identify the second relative position information of the target vehicle. The vehicle 200 and the landmark system 10 perform information interaction, so that both the vehicle 200 and the landmark system 10 can determine the final relative position information of the target vehicle based on the first relative position information and the second relative position information, and combine the final relative position information with the actual position information of the meta-coordinates to obtain the final actual position information of the target vehicle. In this embodiment, the actual position information of the meta-coordinates has been stored in the landmark system when the landmark system 10 is established. The actual position information of the meta-coordinates in the vehicle 200 is obtained and stored from the landmark system 10 through interaction with the landmark system 10.

[0093] In this embodiment, the vehicle positioning system 100 includes a vehicle 200 and a landmark system 10. The dual recognition and interaction of the vehicle position by the vehicle 200 and the landmark system 10 make the structure of the vehicle positioning system 100 of this embodiment simple and ensure the accuracy of the vehicle positioning system 100.

[0094] Figure 11Schematic block diagram of a landmark system according to an embodiment of the present invention. In this embodiment, the road surfaces of different regions correspond to different landmark systems 10, and each landmark system 10 may include identification grids 20 and landmark camera systems 30. Among them, one or more groups of identification grids 20 may be drawn on each road section. However, each group of identification grids 20 corresponds to only one meta coordinate 60. A corresponding landmark camera system 30 is established at each identification grid 20 to identify the first relative position information of the target vehicle within the corresponding identification grid 20. A landmark camera system 30 may be established for one group of identification grids 20 or multiple adjacent groups of identification grids 20. The landmark camera system 30 may capture image frames of all the identification grids 20 in this area.

[0095] Specifically, in this embodiment, the identification grid 20 is an intersection grid formed by the first identification line 21 and the second identification line 22. Among them, the first identification line 21 is a plurality of identification lines drawn along a direction parallel to the road edge 70 with a preset width and a preset spacing. The second identification line 22 is a plurality of identification lines drawn perpendicular to the road edge 70 with a preset width and a preset spacing. Specifically, in this embodiment, the preset width of the identification line is about 10 cm, and the preset distance is about 40 cm. In addition, in one embodiment, additional identification lines may be added at the edge of the identification grid 20 to ensure that the inner identification grid 20 is clear and complete. The parallel spacing between the identification line and the road edge 70 available for safe driving is about 10 cm. In this embodiment, based on the image recognition of a square identification grid 20 with a side length of 50 cm, the positioning accuracy is high, reaching the 5 cm level. With the identification grid 20 as the reference for image recognition, the recognition speed is fast, and the positioning delay is within 50 ms.

[0096] As a specific embodiment, as Figure 10 and Figure 11 shown, each landmark camera system 30 of this embodiment may include at least one landmark camera 31 and a landmark controller 32. Among them, at least one landmark camera 31 is used to capture the image information of the target vehicle within the range of the corresponding identification grid 20. The landmark controller 32 is used to receive the image frame of the target vehicle obtained by the landmark camera 31, analyze and obtain the second relative position information, and pre-acquire and store the actual position information of the meta coordinate 60.

[0097] As a specific embodiment, the landmark controller 32 is further configured to determine according to the first relative position information and the second relative position information. When the determination result is that the second relative position information is the final relative position information of the target vehicle, the actual position information of the target vehicle is obtained according to the pre-acquired and stored actual position information of the meta coordinate 60.

[0098] As a specific embodiment, when the first relative position information is inconsistent with the second relative position information and it is determined that the first relative position information is the final relative position information of the target vehicle, the position of the landmark camera 31 is adjusted to update the second relative position information until it is consistent with the first relative position information. By continuously adjusting the position of the landmark camera 31, the accuracy of the landmark camera 31 for the position of the target vehicle is ensured, and the accuracy of vehicle positioning is improved.

[0099] Specifically, the vehicle camera system 40 and the landmark controller 32 can communicate with each other (hardwired communication or wireless communication). When the vehicle camera system 40 obtains the first relative position information and receives the actual position information of the meta-coordinates transmitted by the landmark controller 32, the first relative position information can be converted into the actual position information, so as to obtain the actual positioning information of the target vehicle. Since only the meta-coordinate information, the first relative position information, and the second relative position information are exchanged between the vehicle and the landmark camera 31, the exchanged information is small, and with dual positioning, mutual verification and redundancy, the overall functional safety is good.

[0100] Figure 12 It is a schematic block diagram of a vehicle positioning system according to another embodiment of the present invention. As a specific embodiment, the landmark camera system further includes a second relative position update module 33, and the second relative position update module 33 is configured to adjust the position of the vehicle camera 41 to update the first relative position information until it is consistent with the second relative position information when the first relative position information is inconsistent with the second relative position information and it is determined that the first relative position information is the final relative position information of the target vehicle.

[0101] The vehicle positioning system 100 of this embodiment mainly includes the vehicle 200 and the landmark system 10. The vehicle 200 only includes the vehicle camera system 40, and the landmark system 10 only includes the identification grid 20 and the landmark camera system 30. Among them, the landmark controller 32 in the landmark camera system 30 also interacts with the vehicle 200. The positioning system 100 has a simple composition and relatively low cost.

[0102] Figure 13 It is a schematic flowchart of the interaction between the vehicle and the positioning system of the vehicle positioning system according to an embodiment of the present invention. As Figure 13 shown, in the vehicle positioning system 100 of this embodiment, the interaction process between the vehicle 200 and the landmark system 10 is as shown in the figure, specifically including,

[0103] First, a network connection is established between the vehicle 200 and the landmark system 10, specifically, a network connection is established between the vehicle camera system 40 of the vehicle 200 and the landmark camera system 30.

[0104] Secondly, when the target vehicle has not entered the identification grid, the vehicle camera 41 of vehicle 200 starts to search for the identification grid 20 on the ground. If the identification grid 20 is recognized, the meta-coordinate position of the target vehicle relative to the identification grid 20 is identified and the position is published.

[0105] Thirdly, when the target vehicle enters the area of the identification grid 20, the vehicle camera system 40 identifies the meta-coordinate position of the target vehicle relative to the identification grid 20 (i.e., the first relative position information) and publishes the position. At the same time, the landmark camera system 30 also starts to identify the meta-coordinate position of the target vehicle relative to the identification grid 20 (i.e., the second relative position information) and publishes the position information.

[0106] Thirdly, the vehicle camera system 40 obtains the information of the landmark camera system 30, fuses and determines the first relative position information and the second relative position information of the target vehicle. At the same time, the landmark camera system 30 receives the first relative position information of the vehicle camera system 40 for fusion determination, confirms the final relative position information, and updates the status of the vehicle or the landmark system according to the determination result.

[0107] Finally, when the target vehicle leaves the area of the identification grid 20, the vehicle exits the positioning state at this time. Vehicles not within the identification grid 20 are not applicable to the positioning of this method and system.

[0108] At this point, those skilled in the art should recognize that although multiple exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications that conform to the principles of the present invention can still be directly determined or derived from the disclosed content of the present invention without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention should be understood and recognized as covering all these other variations or modifications.

Claims

1. A vehicle positioning method based on a ground grid, characterized in that: include: Identifying first relative position information of a target vehicle, wherein the first relative position information is position information of the target vehicle automatically identified by the target vehicle relative to a meta-coordinate of a marking grid pre-drawn at the location of the target vehicle; wherein different areas include a plurality of different marking grids, each of the marking grids corresponding to a meta-coordinate; The first relative position information is combined with the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle, wherein the second relative position information is the position information of the target vehicle relative to the meta-coordinates of the identification grid of the target vehicle's location as identified by the landmark camera system; The final relative position information is combined with the actual position information of the meta-coordinates acquired and stored in advance to obtain the final actual position information of the target vehicle; The process of fusing the first relative position information with the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle includes: When the first relative position information is consistent with the second relative position information, then the first relative position information and the second relative position information are both the final relative position information of the target vehicle; or When the first relative position information is inconsistent with the second relative position information, the second relative position information is first regarded as accurate relative position information and the first relative position information is regarded as unreliable information. When the proportion of vehicles whose first relative position information has become unreliable within a preset time is not greater than a preset proportion, the second relative position information is determined to be the final relative position information of the target vehicle; or When the first relative position information is inconsistent with the second relative position information, and the proportion of the first relative position information of vehicles passing within the preset time that becomes unreliable information is greater than the preset proportion, the second relative position information is determined to be unreliable information. At this time, the first relative position information is the final relative position information of the target vehicle.

2. The vehicle positioning method based on ground marking grid according to claim 1, characterized in that: The identification grid includes a plurality of identification grids drawn on the road surface in different areas; a landmark camera system is provided at each identification grid, and the second relative position information of the target vehicle at the corresponding identification grid is identified by the landmark camera system; The identification grid is a cross grid formed by first identification lines and second identification lines, wherein the first identification lines are multiple identification lines with a preset width and a preset spacing drawn in a direction parallel to the road edge, and the second identification lines are multiple identification lines with the preset width and the preset spacing drawn in a direction perpendicular to the road edge.

3. The vehicle positioning method based on ground marking grid according to claim 2, characterized in that: The meta-coordinates include: On a straight road, the meta-coordinate is selected as any intersection in the road identification grid, and the identification grid at the meta-coordinate position is marked with a slash; or At a turn or intersection, the meta-coordinate is an intersection of two marking lines on the road in two directions, which are respectively parallel to the road edges of the corresponding road.

4. The vehicle positioning method based on ground grid according to claim 2, characterized in that: The process of automatically identifying the first relative position information of the target vehicle includes: Using a vehicle camera system provided on the target vehicle, an image of the target vehicle at the identification grid at the corresponding position is acquired to identify and obtain the first relative position information; The process of identifying the second relative position of the target vehicle by the landmark camera system includes: The landmark camera system is used to capture an image of the target vehicle at the identification grid at the corresponding position, and the second relative position information is obtained by identification.

5. A vehicle, characterized in that: A vehicle camera system is included, the vehicle camera system including a vehicle controller, the vehicle controller including: an identification module configured to identify first relative position information of a target vehicle; wherein the first relative position information is position information of the target vehicle automatically identified by the target vehicle relative to a meta-coordinate of a pre-drawn identification grid at the target vehicle's location; at least one different identification grid is drawn on the road surface in different areas, and each identification grid corresponds to a meta-coordinate; a final relative position information determination module, configured to fuse the first relative position information with the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle, wherein the second relative position information is the position information of the target vehicle relative to the meta-coordinates of the identification grid at the location of the target vehicle as identified by the landmark camera system; and an actual position information acquisition module, combining the final relative position information with the actual position information of the meta-coordinates acquired and stored in advance to obtain the final actual position information of the target vehicle; The process of fusing the first relative position information with the second relative position information of the target vehicle to obtain the final relative position information of the target vehicle includes: When the first relative position information is consistent with the second relative position information, then the first relative position information and the second relative position information are both the final relative position information of the target vehicle; or When the first relative position information is inconsistent with the second relative position information, the second relative position information is first regarded as accurate relative position information and the first relative position information is regarded as unreliable information. When the proportion of vehicles whose first relative position information has become unreliable within a preset time is not greater than a preset proportion, the second relative position information is determined to be the final relative position information of the target vehicle; or When the first relative position information is inconsistent with the second relative position information, and the proportion of the first relative position information of vehicles passing within the preset time that becomes unreliable information is greater than the preset proportion, the second relative position information is determined to be unreliable information. At this time, the first relative position information is the final relative position information of the target vehicle.

6. The vehicle according to claim 5, characterized in that The vehicle camera system further includes a vehicle camera, which is used to obtain an image of the target vehicle at the identification grid corresponding to the location of the target vehicle; The recognition module recognizes the first relative position information according to the image acquired by the vehicle camera; The vehicle controller is configured to make a determination based on the first relative position information and the second relative position information, and when a determination result shows that the first relative position information is the final relative position information of the target vehicle, obtain the final actual position information of the target vehicle based on the actual position information of the meta-coordinates; The vehicle camera system also includes a first relative position update module, which is configured to adjust the position of the vehicle camera to update the first relative position information until it is consistent with the second relative position information when the first relative position information is inconsistent with the second relative position information and the second relative position information is determined to be the final relative position information of the target vehicle.

7. A vehicle positioning system based on a ground grid, characterized in that: It includes a landmark system and the vehicle described in claim 5 or 6, the vehicle is used to identify the first relative position information of the target vehicle, the landmark system is used to identify the second relative position information of the target vehicle, and the vehicle and the landmark system interact with each other so that both the vehicle and the landmark system can determine the final relative position information of the target vehicle based on the first relative position information and the second relative position information, and combine the final relative position information with the actual position information of the meta-coordinate to obtain the final actual position information of the target vehicle.

8. The vehicle positioning system based on ground marking grid according to claim 7, characterized in that: Road surfaces in different areas correspond to different landmark systems, and each landmark system includes: A marking grid, comprising at least one set of marking grids pre-drawn on a road surface, wherein the marking grid is a cross grid formed by first marking lines and second marking lines, wherein the first marking lines are a plurality of marking lines drawn in a direction parallel to a road edge and having a preset width and a preset spacing, and the second marking lines are a plurality of marking lines drawn in a direction perpendicular to the road edge and having the preset width and the preset spacing; and A landmark camera system is provided at each identification grid, and the second relative position information of the target vehicle in the corresponding identification grid is identified by the landmark camera system.

9. The vehicle positioning system based on ground marking grid according to claim 8, characterized in that: Each of the landmark camera systems comprises: At least one landmark camera, configured to capture image information of the target vehicle within the corresponding identification grid; and a landmark controller, configured to receive an image of the target vehicle obtained by the landmark camera, analyze and obtain the second relative position information, and pre-acquire and store the actual position information of the meta-coordinates; The landmark controller is further configured to make a determination based on the second relative position information and the first relative position information, and when the determination result is that the second relative position information is the final relative position information of the target vehicle, obtain the actual position information of the target vehicle based on the actual position information of the meta-coordinates acquired and stored in advance; The landmark camera system also includes a second relative position update module, which is configured to adjust the position of the landmark camera to update the second relative position information until it is consistent with the first relative position information when the first relative position information is inconsistent with the second relative position information and the first relative position information is determined to be the final relative position information of the target vehicle.

Images