Vehicle positioning method, device and electronic equipment

Abstract

The application discloses a vehicle positioning method, device and electronic equipment. The method of the application is executed by a road end, and comprises the following steps: acquiring image data collected by a roadside camera at a current road section and lane line information of the current road section, wherein the lane line information comprises image lane lines and corresponding map lane lines; acquiring a vehicle detection result of a traveling vehicle on the current road section and a target image lane line corresponding to the traveling vehicle according to the image data, wherein the vehicle detection result comprises pixel-level position information and an initial positioning result of the traveling vehicle; acquiring a lateral distance constraint value between the traveling vehicle and the target image lane line according to the pixel-level position information of the traveling vehicle; acquiring a lateral distance reference point located on a target map lane line according to the initial positioning result of the traveling vehicle; and acquiring a final positioning result of the traveling vehicle according to the lateral distance reference point and the lateral distance constraint value. The technical scheme of the application can improve the lateral positioning accuracy of the final positioning result.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a vehicle positioning method, device and electronic device. Background Technology

[0002] As intelligent transportation roadside monitoring systems become more mature, the requirements for the positioning accuracy of vehicles, the main traffic participants on the road, are becoming increasingly higher. Currently, most of the widely used vehicle positioning and detection algorithms obtain the vehicle's detection position in the image by collecting image data from roadside cameras, and then use the calibration parameters of the roadside cameras to calculate the latitude and longitude information corresponding to the vehicle's detection position in the image, thereby completing the vehicle positioning.

[0003] However, the above vehicle positioning algorithm relies heavily on the calibration accuracy of the roadside camera. In particular, when the roadside camera is put into use, it may be affected by external factors (such as strong winds) causing the roadside camera to shake, which will lead to serious errors. In this case, the accuracy of the vehicle positioning result will be poor. Summary of the Invention

[0004] This application provides a vehicle positioning method, device, and electronic device to reduce the impact of roadside camera calibration accuracy on vehicle positioning accuracy to a certain extent.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a vehicle positioning method, the method comprising:

[0007] The system acquires image data and lane line information of the current road segment collected by the roadside camera. The lane line information includes the image lane lines obtained by the roadside camera and the map lane lines corresponding to each image lane line.

[0008] The vehicle detection results and the target image lane lines corresponding to the vehicles are obtained based on the image data. The vehicle detection results include the pixel-level position information of the vehicles and the initial positioning results of the vehicles obtained based on the calibration parameters of the roadside camera.

[0009] The lateral distance constraint value between the driving vehicle and the lane line of the target image is obtained based on the pixel-level position information of the driving vehicle.

[0010] Based on the initial positioning result of the vehicle, obtain the lateral distance reference point located on the lane line of the target map, and based on the lateral distance reference point and the lateral distance constraint value, obtain the final positioning result of the vehicle.

[0011] Secondly, embodiments of this application also provide a vehicle positioning device, the device comprising:

[0012] The first acquisition unit is used to acquire image data collected by the roadside camera in the current road segment and lane line information of the current road segment. The lane line information includes the image lane lines obtained by the roadside camera and the map lane lines corresponding to each image lane line.

[0013] The second acquisition unit is used to acquire vehicle detection results of vehicles traveling on the current road segment and target image lane lines corresponding to the vehicles based on the image data. The vehicle detection results include pixel-level position information of the vehicles and initial positioning results of the vehicles obtained based on the calibration parameters of the roadside camera.

[0014] The first calculation unit is used to obtain the lateral distance constraint value between the driving vehicle and the lane line of the target image based on the pixel-level position information of the driving vehicle;

[0015] The second calculation unit is used to obtain a lateral distance reference point located on the lane line of the target map based on the initial positioning result of the vehicle, and to obtain the final positioning result of the vehicle based on the lateral distance reference point and the lateral distance constraint value.

[0016] Thirdly, embodiments of this application also provide an electronic device, including:

[0017] Processor; and

[0018] A memory is configured to store computer-executable instructions, which, when executed, cause the processor to perform a vehicle positioning method.

[0019] Fourthly, embodiments of this application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform a vehicle positioning method.

[0020] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0021] This application embodiment first acquires image data collected by a roadside camera on the current road segment and lane line information of the current road segment, wherein the lane line information includes image lane lines and map lane lines corresponding to each image lane line; then, based on the image data, it acquires vehicle detection results of vehicles traveling on the current road segment and target image lane lines corresponding to the vehicles, wherein the vehicle detection results include pixel-level position information of the vehicles and initial positioning results of the vehicles obtained based on the calibration parameters of the roadside camera; next, it acquires lateral distance constraint values ​​between the vehicles and the target image lane lines based on the pixel-level position information of the vehicles; finally, it acquires lateral distance reference points located on the target map lane lines based on the initial positioning results of the vehicles, and acquires the final positioning results of the vehicles based on the lateral distance reference points and the lateral distance constraint values.

[0022] This application embodiment assumes that the lateral distance constraint value between the vehicle and the lane line is equal or approximately equal in the image coordinate system and the world coordinate system. First, the lateral distance constraint value between the vehicle and the lane line is calculated in the image coordinate system. Then, the final positioning result of the vehicle in the world coordinate system is solved in reverse based on the lateral distance constraint value. Since the lateral distance reference point located on the lane line of the target map is calculated using only the calibration parameters of the roadside camera during the reverse solution process, the lateral error caused by the calibration parameters can be reduced, and the lateral positioning accuracy of the final positioning result can be improved. Attached Figure Description

[0023] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0024] Figure 1 This is a flowchart illustrating a vehicle positioning method according to an embodiment of this application;

[0025] Figure 2 This is a schematic diagram illustrating the relationship between the lateral distance reference point on the target map lane line and the initial positioning result in an embodiment of this application;

[0026] Figure 3 This is a schematic diagram illustrating the geometric constraint relationship between a driving vehicle and a target lane line in an embodiment of this application;

[0027] Figure 4 This is a schematic diagram of the structure of a vehicle positioning device according to an embodiment of this application;

[0028] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0031] This application provides a vehicle positioning method, such as... Figure 1 The diagram shows a flowchart of a vehicle positioning method according to an embodiment of this application. The method includes at least the following steps S110 to S140:

[0032] Step S110: Obtain image data and lane line information of the current road segment collected by the roadside camera. The lane line information includes the image lane lines obtained by the roadside camera and the map lane lines corresponding to each image lane line.

[0033] The vehicle positioning method of this application embodiment can be executed by the roadside or the cloud. The roadside includes, for example, roadside units deployed at intersections or road sections. The ground of the intersections or road sections is paved with lane markings. Therefore, when the roadside camera deployed on the roadside unit collects image data of the current road section, the collected image data will include lane marking information.

[0034] The lane line information in this application embodiment includes at least two dimensions of lane line information: image lane lines obtained through roadside cameras, such as lane line detection performed on calibration images, historical image data or current image data collected by roadside cameras to obtain image lane lines in the image coordinate system; and map lane lines obtained through maps (e.g., high-precision maps) in the world coordinate system.

[0035] In theory, the lateral distance constraint value between a vehicle and a lane line is equal in the image coordinate system and the world coordinate system. In engineering implementation, considering various errors, the lateral distance constraint value between a vehicle and a lane line is also approximately equal in the image coordinate system and the world coordinate system. Therefore, the final positioning result of the vehicle can be calculated based on the above constraint relationship, improving vehicle positioning accuracy and reducing the adverse effects of roadside camera calibration accuracy.

[0036] Step S120: Obtain vehicle detection results and target image lane lines corresponding to the vehicles traveling on the current road segment based on the image data. The vehicle detection results include pixel-level position information of the vehicles and initial positioning results of the vehicles obtained based on the calibration parameters of the roadside camera.

[0037] This application embodiment can perform vehicle detection on image data based on deep learning technology to obtain vehicle detection results. Of course, those skilled in the art can also combine other target detection algorithms in the prior art to obtain vehicle detection results, and this application embodiment does not specifically limit this.

[0038] It should be noted that the target image lane lines in this embodiment are used to establish lateral distance constraints between the vehicle and the lane lines. These target image lane lines can be any lane line in the current road segment, such as any lane line within the vehicle's lane, or a boundary lane line of the road. Alternatively, the target image lane lines can be any two or more lane lines in the current road segment. When there are two or more target image lane lines, a final positioning result can be calculated based on each lane line. At this point, clustering multiple final positioning results yields a more accurate positioning result.

[0039] Step S130: Obtain the lateral distance constraint value between the driving vehicle and the lane line of the target image based on the pixel-level position information of the driving vehicle.

[0040] Because image coordinate systems and world coordinate systems have different dimensions—for example, distances are typically described in pixels in image coordinate systems, while they are typically described in meters (m) in world coordinate systems—to eliminate the influence of these different dimensions, the lateral distance constraint between the driving vehicle and the lane line in the target image in this embodiment is constructed by the ratio of the lateral distances. For example, the ratio of the lateral distance between the driving vehicle and the lane line in the target image to the pixel-level lane width corresponding to the lane line in the target image is used as the lateral distance constraint value.

[0041] Step S140: Obtain a lateral distance reference point located on the lane line of the target map based on the initial positioning result of the vehicle. Obtain the final positioning result of the vehicle based on the lateral distance reference point and the lateral distance constraint value.

[0042] As described above, since the lateral distance constraint values ​​between the vehicle and the lane line are equal or approximately equal in different coordinate systems, when the lateral distance constraint values ​​between the vehicle and the lane line are obtained, the final positioning result of the vehicle in the world coordinate system can be solved in reverse. In the reverse solution process, only the calibration parameters of the roadside camera are used to calculate the lateral distance reference point located on the lane line of the target map. This can reduce the lateral error caused by the calibration parameters and improve the lateral positioning accuracy of the final positioning result.

[0043] In some embodiments of this application, lane line information for the current road segment is obtained through the following steps:

[0044] The system acquires preset images from roadside cameras. These preset images can be calibration images, historical image data, or current image data. In some scenarios, the road segment or cloud can pre-acquire lane line information for the current road segment, in which case the lane line information can be calculated using the calibration images or historical image data acquired by the roadside cameras. Conversely, in other scenarios, the road segment or cloud can acquire lane line information for the current road segment in real time, in which case the lane line information can be calculated using the current image data acquired by the roadside cameras.

[0045] Lane line detection is performed on the preset image to obtain the image lane lines of the current road segment and the pixel information and road information of each image lane line. The road information indicates the road to which the image lane lines belong.

[0046] In some scenarios, such as instance segmentation algorithms based on deep learning technology, lane lines in a preset image are segmented into instances. Each segmented lane line is then clustered to obtain lane line instances belonging to the same road. For example, assuming the current road segment includes two roads separated by a green median strip, and each road is a two-lane road, then the above method can detect six lane lines in the image.

[0047] Obtain a local high-precision map corresponding to the current road segment.

[0048] In some implementations of this embodiment, the latitude and longitude information of pixels on any image lane line in the world coordinate system can be calculated based on the calibration parameters of the roadside camera, and a local high-precision map of the current road segment can be determined on a high-precision map based on this latitude and longitude information. Of course, in other implementations of this embodiment, the local high-precision map corresponding to the current road segment can also be determined based on the location information of the landmarks of the current road segment (landmarks such as buildings, traffic lights, trees, and other fixed obstacles, or calibration objects during the calibration phase).

[0049] Based on the calibration parameters of the roadside camera, the pixel information of each image lane line, and the road information, the map lane line corresponding to each image lane line is determined from the local high-precision map.

[0050] Specifically, in some implementation schemes of this embodiment, the map lane line corresponding to each image lane line can be determined by the following steps:

[0051] All image lane lines are classified according to the road information of each image lane line to obtain image lane lines belonging to the same road;

[0052] The boundary image lane line of each road and the positional relationship between the boundary image lane line and other image lane lines on the same road are determined based on the pixel information of each image lane line.

[0053] The boundary map lane lines corresponding to the lane lines in the boundary image are determined based on the calibration parameters of the roadside camera.

[0054] Based on the positional relationship between the lane lines in other images on each road and the lane lines in the boundary images, and the boundary map lane lines corresponding to the lane lines in the boundary images, the map lane lines corresponding to the lane lines in the boundary images are determined.

[0055] For example, suppose the current road includes a first road, which is a three-lane road. When classifying the image lane lines, the group corresponding to the first road includes four image lane lines, which are sorted from left to right according to the pixel information of the image lane lines as the first image lane line, the second image lane line, the third image lane line, and the fourth image lane line.

[0056] Then, the first image lane line (or the fourth image lane line) can be used as the boundary image lane line. At this time, according to the calibration parameters of the roadside camera, the mapping point of at least one pixel on the boundary image lane line on the local high-precision map is determined. The map lane line with the closest lateral distance to the mapping point is determined on the local high-precision map. The map lane line with the closest lateral distance to the mapping point is determined as the boundary map lane line corresponding to the boundary image lane line.

[0057] After obtaining the correspondence between the lane lines in the boundary image and the lane lines in the boundary map, the map lane lines corresponding to the other three map lane lines can be determined based on the positional relationship between the other three map lane lines on the first road and the lane lines in the boundary map.

[0058] It should be noted that the positioning error caused by the calibration parameters of roadside cameras is generally between tens of centimeters and one or two meters, while the lane width is generally around three meters. Therefore, when calculating the correspondence between image lane lines and map lane lines using the calibration parameters of roadside cameras, the accuracy of this correspondence will not be affected by the calibration error. In practical applications, to facilitate the description of the above correspondence, an index can be set for the image lane lines. This allows the creation of a correspondence table between the index of image lane lines and the lane line numbers on the map. This correspondence table facilitates the retrieval of the correspondence and also facilitates the management and maintenance of the correspondence.

[0059] In some other implementations of this embodiment, after obtaining the local high-precision map corresponding to the current road segment, the method further includes:

[0060] Detect whether the number of lane lines in the current road segment's image is consistent with the number of lane lines in the local high-precision map image;

[0061] When the number of both is the same, the map lane line corresponding to each image lane line is determined from the local high-precision map based on the calibration parameters of the roadside camera, the pixel information of each image lane line, and the road information. This ensures a correct correspondence between the image lane lines and the map lane lines.

[0062] It should be noted that the embodiments of this application illustrate one implementation scheme for determining the map lane line corresponding to each image lane line. In other embodiments of this application, the position of at least one pixel on each image lane line on the local high-precision map can be calculated according to the calibration parameters of the roadside camera, and the map lane line closest to that position can be taken as the corresponding map lane line of the image lane line.

[0063] In some embodiments of this application, the step S130 above, which obtains the lateral distance constraint value between the driving vehicle and the lane line of the target image based on the pixel-level position information of the driving vehicle, specifically includes:

[0064] The lateral pixel distance between the driving vehicle and the lane line of the target image is obtained based on the pixel-level position information of the driving vehicle.

[0065] Obtain the pixel-level lane width of the lane where the lane line of the target image is located;

[0066] The lateral distance constraint value between the driving vehicle and the lane line of the target image is obtained based on the ratio of the lateral pixel distance to the pixel-level lane width.

[0067] It should be noted that the lateral distance in this embodiment is the vertical distance from a point (the pixel-level position of a driving vehicle can be represented by a single pixel) to a line (the image lane line can be represented by a curve). Assuming the pixel-level position information of the driving vehicle is pixel position a, and the pixel position b on the target image lane line has the minimum pixel distance to pixel position a, the lateral pixel distance Dis1 between the driving vehicle and the target image lane line can be calculated using pixel position a and pixel position b. Pixel Assuming the target image lane line is one of two image lane lines corresponding to the lane where the vehicle is located, the pixel-level lane width Dis2 can be calculated based on the relative pixel distance between the two image lane lines. Pixel The horizontal pixel distance from Dis1 Pixel With pixel-level lane width Dis2 Pixel The ratio of Dis1 Pixel / Dis2 Pixel This serves as a lateral distance constraint value between the driving vehicle and the lane lines in the target image.

[0068] In some embodiments of this application, the step S140 above, which obtains a lateral distance reference point located on the target map lane line based on the initial positioning result of the driving vehicle, specifically includes:

[0069] The point on the target map lane line that has the minimum distance from the initial positioning result is used as the lateral distance reference point. Those skilled in the art can calculate the point on the target map lane line that has the minimum distance from the initial positioning result using existing techniques; this embodiment will not be described in detail here.

[0070] like Figure 2 As shown, assuming the actual location of the vehicle is Figure 2 Point A0 in the map, while the initial positioning result calculated based on the calibration parameters of the roadside camera is... Figure 2 Point A1 in the target map shows that the lateral distance reference point for points A1 and A2 on the lane line is the same point B0. This demonstrates that using the lateral distance reference point and lateral distance constraint value to inversely solve for the final positioning result of the vehicle can reduce the lateral positioning error of the vehicle within the lane to a certain extent.

[0071] It should be noted that this embodiment is provided for the purpose of conveniently and intuitively describing the improvement of lateral positioning error in this application. Figure 2 The example shows that the initial positioning result A1 calculated based on the calibration parameters of the roadside camera has only a lateral positioning error with the actual positioning result A0. More generally, when there is also a longitudinal positioning error between the two, the solution of this application embodiment can still reduce the lateral positioning error of the vehicle in the lane.

[0072] After obtaining the lateral distance constraint value between the driving vehicle and the lane lines of the target image, and the lateral distance reference point on the lane lines of the target map, the final positioning result of the driving vehicle can be calculated. Specifically, in some embodiments of this application, the final positioning result of the driving vehicle can be calculated through the following steps:

[0073] Obtain the lane width of the lane containing the target map lane line. For example, if the target map lane line is one of two map lane lines in the lane where the vehicle is located, the lane width Dis2 can be obtained by calculating the relative distance between the lateral distance reference point and the other map lane in the lane where the vehicle is located. Position Of course, those skilled in the art can also obtain lane width by combining existing technologies. For example, when a high-precision map carries lane information, the lane width information can be obtained directly from the high-precision map.

[0074] Establish the coordinate points of the parameters to be solved corresponding to the final positioning result, and obtain the lateral positioning distance between the driving vehicle and the lane line of the target map based on the coordinate points of the parameters to be solved corresponding to the final positioning result and the lateral distance reference point;

[0075] Based on the lateral positioning distance, the lane width, and the lateral distance constraint value, a first equation is established regarding the coordinate points of the parameters to be solved;

[0076] A second equation is established based on the lateral distance reference point and the coordinate points of the parameter to be solved.

[0077] Based on the first equation and the second equation, the values ​​of the coordinate points of the parameter to be solved are obtained.

[0078] like Figure 3 As shown, assume the coordinates of the parameter to be solved corresponding to the final positioning result are A(x). A y A Given that the lateral distance reference point is B (the coordinates of point B are known), and based on the coordinates of the parameter to be solved (point A) and the lateral distance reference point B, the lateral positioning distance Dis1 between the driving vehicle and the lane line of the target map can be obtained. Position According to Dis1 Position / Dis2 Position =Dis1 Pixel / Dis2 Pixel The first equation can be obtained, since the first equation includes (x) A y A Since there are two parameters to be solved, an auxiliary equation needs to be constructed.

[0079] In some implementation schemes of this embodiment, establishing a second equation based on the lateral distance reference point and the coordinate points of the parameter to be solved specifically includes:

[0080] Construct auxiliary points, wherein the first vector formed by the auxiliary points and the lateral distance reference points and the second vector formed by the coordinate points of the parameters to be solved and the lateral distance reference points have a 90-degree angle;

[0081] The second equation is established based on the formula for the angle between planar vectors.

[0082] In this context, the auxiliary point can be selected on the lane line of the target map, which is close to the lateral distance reference point. In this way, the position of the auxiliary point in the world coordinate system is known.

[0083] like Figure 3 As shown, point C is an auxiliary point. Even if the lane lines on the target map have a large curvature at the lateral distance from the reference point, since the auxiliary point C is closer to the lateral distance reference point B, the vector... and adjacent The included angle between them is also approximately 90 degrees, according to the included angle formula.

[0084] Then, based on the first and second equations, the coordinates of the parameter point A to be solved can be calculated, and thus the final positioning result of the vehicle can be obtained.

[0085] It should be noted that this embodiment shows an implementation scheme for establishing the second equation based on the formula for the angle between planar vectors. In other implementation schemes, the second equation can also be established based on the relevant formula obtained from the triangle rule.

[0086] This application also provides a vehicle positioning device 400, such as... Figure 4 The diagram shows a structural schematic of a vehicle positioning device according to an embodiment of this application. The vehicle positioning device 400 is applied at the roadside or in the cloud. The device 400 includes: a first acquisition unit 410, a second acquisition unit 420, a first calculation unit 430, and a second calculation unit 440, wherein:

[0087] The first acquisition unit 410 is used to acquire image data collected by the roadside camera in the current road segment and lane line information of the current road segment. The lane line information includes the image lane lines obtained by the roadside camera and the map lane lines corresponding to each image lane line.

[0088] The second acquisition unit 420 is used to acquire vehicle detection results of vehicles traveling on the current road segment and target image lane lines corresponding to the vehicles based on the image data. The vehicle detection results include pixel-level position information of the vehicles and initial positioning results of the vehicles obtained based on the calibration parameters of the roadside camera.

[0089] The first calculation unit 430 is used to obtain the lateral distance constraint value between the driving vehicle and the lane line of the target image based on the pixel-level position information of the driving vehicle.

[0090] The second calculation unit 440 is used to obtain a lateral distance reference point located on the lane line of the target map based on the initial positioning result of the vehicle, and to obtain the final positioning result of the vehicle based on the lateral distance reference point and the lateral distance constraint value.

[0091] In some embodiments of this application, the first acquisition unit 410 is specifically used to acquire a preset image captured by a roadside camera, and to perform lane line detection on the preset image to obtain the image lane lines of the current road segment and the pixel information and road information of each image lane line; to acquire a local high-precision map corresponding to the current road segment; and to determine the map lane line corresponding to each image lane line from the local high-precision map based on the calibration parameters of the roadside camera, the pixel information and road information of each image lane line.

[0092] In some embodiments of this application, the first acquisition unit 410 is specifically used to classify all image lane lines according to the road information of each image lane line to obtain image lane lines belonging to the same road; determine the boundary image lane line of each road and the positional relationship between the boundary image lane line and other image lane lines on the road according to the pixel information of each image lane line; determine the boundary map lane line corresponding to the boundary image lane line according to the calibration parameters of the roadside camera; and determine the map lane line corresponding to other image lane lines on each road according to the positional relationship between the boundary image lane line and other image lane lines on each road and the boundary map lane line corresponding to the boundary image lane line.

[0093] In some embodiments of this application, the first acquisition unit 410 is specifically used to determine, based on the calibration parameters of the roadside camera, the mapping point of at least one pixel on the boundary image lane line on the local high-precision map; determine the map lane line on the local high-precision map that is laterally closest to the mapping point; and determine the map lane line that is laterally closest to the mapping point as the boundary map lane line corresponding to the boundary image lane line.

[0094] In some embodiments of this application, the first acquisition unit 410 is specifically used to detect whether the number of image lane lines of the current road segment is consistent with the number of image lane lines of the local high-precision map after acquiring the local high-precision map corresponding to the current road segment; when the two numbers are consistent, the map lane line corresponding to each image lane line is determined from the local high-precision map according to the calibration parameters of the roadside camera, the pixel information of each image lane line and the road information.

[0095] In some embodiments of this application, the first calculation unit 430 is specifically used to obtain the lateral pixel distance between the driving vehicle and the lane line of the target image based on the pixel-level position information of the driving vehicle; obtain the pixel-level lane width of the lane where the lane line of the target image is located; and obtain the lateral distance constraint value between the driving vehicle and the lane line of the target image based on the ratio of the lateral pixel distance to the pixel-level lane width.

[0096] In some embodiments of this application, the second calculation unit 440 is specifically used to obtain the lane width of the lane where the target map lane line is located; establish the coordinate points of the parameter to be solved corresponding to the final positioning result; obtain the lateral positioning distance between the driving vehicle and the target map lane line based on the coordinate points of the parameter to be solved corresponding to the final positioning result and the lateral distance reference point; establish a first equation about the coordinate points of the parameter to be solved based on the lateral positioning distance, the lane width and the lateral distance constraint value; establish a second equation based on the lateral distance reference point and the coordinate points of the parameter to be solved; and obtain the value of the coordinate points of the parameter to be solved based on the first equation and the second equation.

[0097] In some embodiments of this application, the second calculation unit 440 is specifically used to construct an auxiliary point, wherein the first vector formed by the auxiliary point and the lateral distance reference point and the second vector formed by the coordinate point of the parameter to be solved and the lateral distance reference point have a 90-degree angle; and the second equation is established according to the formula for the angle between planar vectors.

[0098] It is understood that the vehicle positioning device described above can realize all the steps of the vehicle positioning method provided in the foregoing embodiments. The relevant explanations of the vehicle positioning method are applicable to the vehicle positioning device and will not be repeated here.

[0099] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 5At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0100] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0101] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0102] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a vehicle positioning device at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0103] The system acquires image data and lane line information of the current road segment collected by the roadside camera. The lane line information includes the image lane lines obtained by the roadside camera and the map lane lines corresponding to each image lane line.

[0104] The vehicle detection results and the target image lane lines corresponding to the vehicles are obtained based on the image data. The vehicle detection results include the pixel-level position information of the vehicles and the initial positioning results of the vehicles obtained based on the calibration parameters of the roadside camera.

[0105] The lateral distance constraint value between the driving vehicle and the lane line of the target image is obtained based on the pixel-level position information of the driving vehicle.

[0106] Based on the initial positioning result of the vehicle, obtain the lateral distance reference point located on the lane line of the target map, and based on the lateral distance reference point and the lateral distance constraint value, obtain the final positioning result of the vehicle.

[0107] The above is as stated in this application. Figure 1 The method executed by the vehicle positioning device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads the information from the memory and, in conjunction with its hardware, completes the steps of the vehicle positioning method described above.

[0108] The electronic device can also perform Figure 1 The method for executing the vehicle positioning device, and realizing the vehicle positioning device in Figure 1 The functions of the embodiments shown are not described in detail here.

[0109] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the vehicle positioning device in the illustrated embodiment is specifically used to perform the following:

[0110] The system acquires image data and lane line information of the current road segment collected by the roadside camera. The lane line information includes the image lane lines obtained by the roadside camera and the map lane lines corresponding to each image lane line.

[0111] Based on the image data, the vehicle detection results of the vehicles traveling on the current road segment and the target image lane lines corresponding to the vehicles are obtained. The vehicle detection results include the pixel-level position information of the vehicles and the initial positioning results of the vehicles obtained according to the calibration parameters of the roadside camera.

[0112] The lateral distance constraint value between the driving vehicle and the lane line of the target image is obtained based on the pixel-level position information of the driving vehicle.

[0113] Based on the initial positioning result of the vehicle, obtain the lateral distance reference point located on the lane line of the target map, and based on the lateral distance reference point and the lateral distance constraint value, obtain the final positioning result of the vehicle.

[0114] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0119] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0120] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0122] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A vehicle positioning method, characterized in that, The method includes: The system acquires image data and lane line information of the current road segment collected by the roadside camera. The lane line information includes the image lane lines obtained by the roadside camera and the map lane lines corresponding to each image lane line. The vehicle detection results and the target image lane lines corresponding to the vehicles are obtained based on the image data. The vehicle detection results include the pixel-level position information of the vehicles and the initial positioning results of the vehicles obtained based on the calibration parameters of the roadside camera. The lateral distance constraint value between the driving vehicle and the lane line of the target image is obtained based on the pixel-level position information of the driving vehicle. Based on the initial positioning result of the vehicle, obtain the lateral distance reference point located on the lane line of the target map, and based on the lateral distance reference point and the lateral distance constraint value, obtain the final positioning result of the vehicle. The step of obtaining the final positioning result of the driving vehicle based on the lateral distance reference point and the lateral distance constraint value includes: Obtain the lane width of the lane where the target map lane line is located; Establish the coordinate points of the parameters to be solved corresponding to the final positioning result, and obtain the lateral positioning distance between the driving vehicle and the lane line of the target map based on the coordinate points of the parameters to be solved corresponding to the final positioning result and the lateral distance reference point; Based on the lateral positioning distance, the lane width, and the lateral distance constraint value, a first equation is established regarding the coordinate points of the parameters to be solved; A second equation is established based on the lateral distance reference point and the coordinate points of the parameter to be solved. Based on the first equation and the second equation, the values ​​of the coordinate points of the parameter to be solved are obtained; The target image lane line is one or more of the lane lines in the image obtained by the roadside camera; The lateral distance reference point refers to the point on the target map lane line that has the minimum distance from the initial positioning result.

2. The vehicle positioning method as described in claim 1, characterized in that, The lane line information of the current road segment is obtained through the following steps: Acquire a preset image captured by a roadside camera, and perform lane line detection on the preset image to obtain the image lane lines of the current road segment and the pixel information and road information of each image lane line; Obtain a local high-precision map corresponding to the current road segment; Based on the calibration parameters of the roadside camera, the pixel information of each image lane line, and the road information, the map lane line corresponding to each image lane line is determined from the local high-precision map.

3. The vehicle positioning method as described in claim 2, characterized in that, The step of determining the map lane line corresponding to each image lane line from the local high-precision map based on the calibration parameters of the roadside camera, the pixel information of each image lane line, and road information includes: All image lane lines are classified according to the road information of each image lane line to obtain image lane lines belonging to the same road; The boundary image lane line of each road and the positional relationship between the boundary image lane line and other image lane lines on the road are determined based on the pixel information of each image lane line. The boundary map lane lines corresponding to the lane lines in the boundary image are determined based on the calibration parameters of the roadside camera. Based on the positional relationship between the lane lines in other images on each road and the lane lines in the boundary images, and the boundary map lane lines corresponding to the lane lines in the boundary images, the map lane lines corresponding to the lane lines in the boundary images are determined.

4. The vehicle positioning method as described in claim 3, characterized in that, Determining the boundary map lane lines corresponding to the boundary image lane lines based on the calibration parameters of the roadside camera includes: Based on the calibration parameters of the roadside camera, determine the mapping point of at least one pixel on the lane line of the boundary image on the local high-precision map; On the local high-precision map, determine the map lane line that is laterally closest to the mapping point, and define the map lane line that is laterally closest to the mapping point as the boundary map lane line corresponding to the boundary image lane line.

5. The vehicle positioning method as described in claim 2, characterized in that, After obtaining the local high-precision map corresponding to the current road segment, the method further includes: Detect whether the number of lane lines in the current road segment's image is consistent with the number of lane lines in the local high-precision map image; When the number of both is the same, the map lane line corresponding to each image lane line is determined from the local high-precision map based on the calibration parameters of the roadside camera, the pixel information of each image lane line, and the road information.

6. The vehicle positioning method as described in claim 1, characterized in that, The step of obtaining the lateral distance constraint value between the driving vehicle and the lane line of the target image based on the pixel-level position information of the driving vehicle includes: The lateral pixel distance between the driving vehicle and the lane line of the target image is obtained based on the pixel-level position information of the driving vehicle. Obtain the pixel-level lane width of the lane where the lane line of the target image is located; The lateral distance constraint value between the driving vehicle and the lane line of the target image is obtained based on the ratio of the lateral pixel distance to the pixel-level lane width.

7. The vehicle positioning method as described in claim 1, characterized in that, The step of establishing the second equation based on the lateral distance reference point and the coordinate points of the parameters to be solved includes: Construct auxiliary points, wherein the first vector formed by the auxiliary points and the lateral distance reference points and the second vector formed by the coordinate points of the parameters to be solved and the lateral distance reference points have a 90-degree angle; The second equation is established based on the formula for the angle between planar vectors.

8. A vehicle positioning device, characterized in that, The device includes: The first acquisition unit is used to acquire image data collected by the roadside camera in the current road segment and lane line information of the current road segment. The lane line information includes the image lane lines obtained by the roadside camera and the map lane lines corresponding to each image lane line. The second acquisition unit is used to acquire vehicle detection results of vehicles traveling on the current road segment and target image lane lines corresponding to the vehicles based on the image data. The vehicle detection results include pixel-level position information of the vehicles and initial positioning results of the vehicles obtained based on the calibration parameters of the roadside camera. The first calculation unit is used to obtain the lateral distance constraint value between the driving vehicle and the lane line of the target image based on the pixel-level position information of the driving vehicle; The second calculation unit is used to obtain a lateral distance reference point located on the lane line of the target map based on the initial positioning result of the vehicle, and to obtain the final positioning result of the vehicle based on the lateral distance reference point and the lateral distance constraint value. The second computing unit is specifically used for: Obtain the lane width of the lane where the target map lane line is located; Establish the coordinate points of the parameters to be solved corresponding to the final positioning result, and obtain the lateral positioning distance between the driving vehicle and the lane line of the target map based on the coordinate points of the parameters to be solved corresponding to the final positioning result and the lateral distance reference point; Based on the lateral positioning distance, the lane width, and the lateral distance constraint value, a first equation is established regarding the coordinate points of the parameters to be solved; A second equation is established based on the lateral distance reference point and the coordinate points of the parameter to be solved. Based on the first equation and the second equation, the values ​​of the coordinate points of the parameter to be solved are obtained; The target image lane line is one or more of the lane lines in the image obtained by the roadside camera; The lateral distance reference point refers to the point on the target map lane line that has the minimum distance from the initial positioning result.

9. An electronic device, characterized in that, include: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the vehicle positioning method as described in any one of claims 1 to 7.

Images