Lane level positioning method, device, equipment and storage medium

Abstract

The embodiments of the present application relate to a lane-level positioning method, device, equipment and storage medium, which are applicable to the fields of mapping, navigation, automatic driving, Internet of Vehicles, intelligent transportation and cloud computing. The method comprises: obtaining the first lane data of the first road section where the vehicle is located at the first moment, and the second lane data of the second road section where the vehicle is located at the second moment, where the second moment is the previous moment of the first moment; obtaining the lane image in front of the vehicle at the first moment, and determining the lane line information of each lane line in the lane image; determining the actual lane where the vehicle is located at the first moment based on the first lane data, the second lane data and the lane line information of each lane line in the lane image. The embodiment of the present application can improve the positioning efficiency and applicability of lane-level positioning.

Description

Technical Field

[0001] The present application relates to the field of transportation, and in particular to a lane-level positioning method, device, equipment and storage medium. Background Art

[0002] In related technologies, lane-level positioning can be achieved based on high-precision map data through real-time kinematic (RTK) carrier phase differential technology. However, this method is highly dependent on measurement equipment, lacks stability, and consumes a lot of time in collecting and processing high-precision map data, which leads to low positioning efficiency.

[0003] In the related art, when lane-level positioning is realized, position recognition is performed by sensors, and the vehicle is tracked based on laser radar ranging and 3D cloud feature scanning to realize vehicle positioning. However, such methods are costly and have low applicability.

[0004] Therefore, it is necessary to improve the positioning efficiency and applicability of lane-level positioning. Summary of the invention

[0005] The embodiments of the present application provide a lane-level positioning method, apparatus, device, and storage medium, which can improve the positioning efficiency and applicability of lane-level positioning.

[0006] On the one hand, an embodiment of the present application provides a lane-level positioning method, the method comprising:

[0007] Acquire data of a first lane of a first road section where a vehicle is located at a first moment, and data of a second lane of a second road section where the vehicle is located at a second moment, wherein the second moment is a moment before the first moment;

[0008] Acquire a lane image in front of the vehicle at a first moment, and determine lane line information of each lane line in the lane image;

[0009] Based on the first lane data, the second lane data and lane line information of each lane line in the lane image, the actual lane in which the vehicle is located at the first moment is determined.

[0010] On the other hand, an embodiment of the present application provides a lane-level positioning device, the device comprising:

[0011] A lane data acquisition module, used to acquire first lane data of a first road section where a vehicle is located at a first moment, and second lane data of a second road section where the vehicle is located at a second moment, wherein the second moment is a moment before the first moment;

[0012] A lane image acquisition module, used to acquire a lane image in front of the vehicle at a first moment, and determine lane line information of each lane line in the lane image;

[0013] A lane positioning module is used to determine the actual lane in which the vehicle is located at the first moment based on the first lane data, the second lane data and the lane line information of each lane line in the lane image.

[0014] On the other hand, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein the processor and the memory are connected to each other;

[0015] The memory is used to store computer programs;

[0016] The above-mentioned processor is configured to execute the lane-level positioning method provided in the embodiment of the present application when calling the above-mentioned computer program.

[0017] On the other hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the lane-level positioning method provided in the embodiment of the present application.

[0018] On the other hand, an embodiment of the present application provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the lane-level positioning method provided in the embodiment of the present application.

[0019] In the embodiment of the present application, by acquiring the lane image in front of the vehicle at the first moment, the lane line information of each lane line in front of the road section at the first moment can be determined, and then based on the lane line information of each lane line in front of the road section at the first moment and the lane data of the road section at different moments, the actual lane of the first vehicle at the first moment is determined, thereby improving the positioning efficiency of lane-level positioning. In addition, based on the present application, the lane data of the vehicle in the road section and the lane image in front of the vehicle can be obtained in real time, thereby achieving real-time determination of the actual lane of the vehicle at each moment, which has high applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1is a scene schematic diagram of the lane-level positioning method provided in an embodiment of the present application;

[0022] Figure 2 is a flow chart of a lane-level positioning method provided in an embodiment of the present application;

[0023] Figure 3 is another flowchart of the lane-level positioning method provided in an embodiment of the present application;

[0024] Figure 4 is a schematic diagram of a scenario for determining a lane line combination provided in an embodiment of the present application;

[0025] Figure 5 is a schematic diagram of constructing a vehicle coordinate system provided in an embodiment of the present application;

[0026] Figure 6 is a schematic diagram of a method for determining lane line distance provided in an embodiment of the present application;

[0027] Figure 7a is a schematic diagram of a scenario for determining a transition probability matrix provided in an embodiment of the present application;

[0028] Figure 7b is another schematic diagram of a scenario for determining a transition probability matrix provided in an embodiment of the present application;

[0029] Figure 8 is a flow chart of the lane-level positioning method provided in an embodiment of the present application;

[0030] Fig. 9 is a schematic diagram of the structure of a lane-level positioning device provided in an embodiment of the present application;

[0031] Fig.10 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] The lane-level positioning method provided in the embodiments of the present application can be applied to fields such as mapping, navigation, autonomous driving, intelligent vehicle control, Internet of Vehicles, intelligent transportation, and cloud computing, such as the Intelligent Traffic System (ITS) and Intelligent Vehicle Infrastructure Cooperative Systems (IVICS) in the transportation field.

[0034] Among them, the intelligent transportation system, also known as the intelligent transportation system (Intelligent Transportation System), is to effectively and comprehensively apply advanced science and technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) to transportation, service control and vehicle manufacturing, strengthen the connection between vehicles, roads and users, and thus form a comprehensive transportation system that ensures safety, improves efficiency, improves the environment and saves energy. Based on the lane-level positioning method provided in the embodiment of this application, the lane of the lane in the road can be determined, thereby providing strong guarantees for transportation, service control and other aspects.

[0035] Among them, the intelligent vehicle-road cooperative system, referred to as the vehicle-road cooperative system, is a development direction of the intelligent transportation system (ITS). The vehicle-road cooperative system adopts advanced wireless communication and new generation Internet technologies to implement all-round dynamic real-time information interaction between vehicles and roads, and carries out vehicle active safety control and road cooperative management based on the collection and integration of dynamic traffic information in all time and space, fully realizing the effective coordination of people, vehicles and roads, ensuring traffic safety, and improving traffic efficiency, thus forming a safe, efficient and environmentally friendly road traffic system. Based on the lane-level positioning method provided in the embodiment of the present application, technical support can be provided for traffic safety and vehicle-road collaboration based on the lane-level positioning of the vehicle.

[0036] See also Figure 1 , Figure 1 Schematic diagram of a lane-level positioning method provided in an embodiment of the present application. Figure 1 As shown, during the driving process of the vehicle 100, the first lane data of the first road section 200 where the vehicle 100 is located at the first moment and the second lane data of the second road section 300 where the vehicle 100 is located at the second moment can be obtained, and the second moment is the previous moment of the first moment. That is, during the driving process of the vehicle 100, the first lane data of the road section where the vehicle 100 is located at any moment and the second lane data of the road section where the vehicle 100 is located at the previous moment of any moment can be obtained.

[0037] Furthermore, in the process of acquiring the first lane data and the second lane data of the vehicle 100, a lane image 400 in front of the vehicle 100 at the first moment can also be acquired. The lane image 400 in front of the vehicle 100 is a road image including lane information of the vehicle 100 in the first road section 200 and in front of the vehicle at the first moment.

[0038] Furthermore, lane line information of each lane line in the lane image 400 may be determined, and based on the first lane data, the second lane data and the lane line information, the actual lane in which the vehicle 100 is located in the first road section 200 at the first moment may be determined.

[0039] Among them, the lane-level positioning method provided in the embodiment of the present application can be implemented through an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services, etc. It can also be implemented through terminals such as smart phones, tablets, laptops, desktop computers, smart watches, vehicle-mounted terminals, smart TVs, etc., without limitation here.

[0040] See also Figure 2 , Figure 2 Schematic diagram of a process of lane-level positioning method provided by an embodiment of the present application. Figure 2 As shown, the lane-level positioning method provided in the embodiment of the present application may include the following steps:

[0041] Step S21, obtaining first lane data of a first road section where the vehicle is located at a first moment, and second lane data of a second road section where the vehicle is located at a second moment.

[0042] In some feasible implementations, when a vehicle is traveling on a road, lane data of the road section where the vehicle is located at each time can be obtained in real time, the first time is any time when the vehicle is traveling on the road, and the second time is the previous time of the first time. The time span corresponding to the first time and the second time can be determined based on the actual application scenario requirements and is not limited here.

[0043] Among them, the lane data of any road section can be obtained based on the road data corresponding to the road section, and the lane data of any road section includes but is not limited to the number of lanes, lane direction, lane topology (lane distribution), lane line color and lane line type (solid line, dotted line, etc.), etc., which are not restricted here.

[0044] The above-mentioned road data may be existing map data, Advanced Driving Assistance System (ADAS) data, Internet of Vehicles data, etc., without limitation. ADAS is an active safety technology that uses various sensors installed on the vehicle to collect environmental data inside and outside the vehicle at the first time, and performs technical processing such as identification, detection and tracking of static and dynamic objects, so that the driver can be aware of possible dangers as soon as possible to attract attention and improve safety.

[0045] Specifically, taking the first moment (current moment) as an example, when obtaining the lane data of the road section where the vehicle is located at the first moment, the positioning information of the vehicle at the first moment can be determined, and then based on the positioning information of the vehicle at the first moment, the first road section where the vehicle is located at the first moment can be determined, and then the first lane data of the first road section can be obtained.

[0046] Among them, the positioning information of the vehicle at the first moment can be determined based on satellite positioning information, or based on vehicle control information, vehicle visual perception information, and inertial measurement unit (IMU) information, and then based on the above information, the positioning information of the vehicle at the first moment is output through a certain algorithm.

[0047] After determining the first road section where the vehicle is located at the first moment, first lane data corresponding to the first road section may be acquired from road data corresponding to the first road section based on the positioning information of the vehicle at the first moment.

[0048] The above positioning information includes but is not limited to latitude and longitude information and the specific driving distance of the vehicle on each road, such as 300 meters from intersection A, etc., which is not limited here.

[0049] Furthermore, the previous road section of the vehicle on the first road section may be determined as the second road section where the vehicle is located at the second moment, and then the second lane data corresponding to the second road section may be acquired from the road data corresponding to the second road section.

[0050] Optionally, the positioning information of the vehicle at the second moment can be determined based on the positioning information of the vehicle at the first moment and the driving information of the vehicle during driving, such as vehicle control information, vehicle driving speed and other information, and then based on the positioning information of the vehicle at the second moment, the second section of the vehicle at the second moment can be determined, and then the second lane data of the second section can be obtained.

[0051] In the embodiment of the present application, the road data and lane data corresponding to each road section can be obtained from a database, a database management system or a blockchain, etc., which can be determined based on the actual application scenario requirements and is not limited here. Among them, the blockchain is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. The blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods, and each data block is used to store the road data of each road section.

[0052] Step S22: Acquire a lane image in front of the vehicle at the first moment, and determine lane line information of each lane line in the lane image.

[0053] In some feasible implementations, the lane image in front of the vehicle at the first moment includes images of relevant information of all or part of the lanes in the first road section, which can be obtained through the image acquisition device of the vehicle. For example, it can be obtained through the real-time images of the vehicle's windshield, roof, and front camera, and the vehicle's driving recorder. The specific acquisition method can be determined based on the actual application scenario requirements and is not limited here.

[0054] Furthermore, the lane image in front of the vehicle at the first moment is processed by image processing, visual recognition, machine learning and other technologies to obtain lane lines in the lane image and lane line information of each lane line. The lane line information of each lane line in the lane image includes but is not limited to lane line color, lane line type, lane line distribution information, and lane line number, which are not limited here.

[0055] Specifically, after the lane lines in the lane image are identified, for each lane line, the confidence of the lane line type of the lane line can be determined as the existing lane line types, and then the lane line type with the highest confidence can be determined as the lane line type of the lane line. Similarly, for each lane line, the confidence of the lane line color of the lane line can be determined as the existing lane line colors, and then the lane line color with the highest confidence can be determined as the lane line color of the lane line.

[0056] The lane line type refers to the actual lane line presentation mode in the road, including but not limited to single solid line, single dashed line, double solid line, double dashed line, left dashed and right solid, left solid and right dashed, etc. At the same time, in the embodiment of the present application, the guardrail, curb, curb, road edge, etc. of the road in the lane image can be determined as the lane line in the lane image through image processing, visual recognition and other technologies.

[0057] The lane line color is the actual lane line color on the road, including but not limited to yellow, white, blue, green, gray, black, etc. For lane line types such as guardrails, curbstones, curbs, road edges, etc., which are not actual lane line types, their lane line colors can be determined as preset colors different from the colors of other actual lane lines, and there is no limitation here.

[0058] Step S23: determining the actual lane in which the vehicle is located at the first moment based on the first lane data, the second lane data, and the lane line information of each lane line in the lane image.

[0059] In some feasible implementations, based on the first lane data, the second lane data and the lane line information, determining the actual lane where the vehicle is located at the first moment can be implemented based on a hidden Markov model. For details, see Figure 3 . Figure 3 FIG. 2 is another flow chart of the lane-level positioning method provided in the embodiment of the present application. Figure 3 As shown, determining the actual lane where the vehicle is located at the first moment specifically includes the following steps:

[0060] Step S31: Determine a first probability that each lane of the first road section is within the field of view of the vehicle when the vehicle is on the second road section based on the first lane data and the lane line information of each lane line in the lane image.

[0061] In some feasible implementations, based on the first lane data and lane line information, a transmission probability matrix corresponding to the actual lane where the vehicle is located at the first moment can be determined based on the hidden Markov model. Among them, any element in the above transmission probability matrix represents the first probability that a lane of the first section is within the field of view of the vehicle at the second section. The above transmission probability matrix represents the first probability that each lane of the first section is within its field of view when the vehicle is traveling on the second section at the second moment.

[0062] When determining the first probability corresponding to each lane of the first road section, the lane line information of each lane line of the first road section can be determined based on the first lane data, and then based on the number of lane lines in the lane image, the lane line information of each lane line in the lane image and the lane line information of each lane line of the first road section, the first probability that each lane of the first road section is within the field of view of the vehicle when it is in the second road section is determined.

[0063] Wherein, each lane line of the first road section can also be determined based on the first lane data. The lane line information of each lane line of the first road section includes the lane line type and lane line color of each lane line of the first road section, that is, the lane line information of each lane line of the first road section is the actual lane line type and actual lane line color of each lane line of the first road section.

[0064] In some feasible implementations, when determining a first probability that each lane of a first road section is within the field of view of a vehicle on a second road section based on the number of lane lines in a lane image, lane line information of each lane line in the lane image, and lane line information, the lane line combination corresponding to each lane of the first road section may be determined first.

[0065] Each lane line combination includes lane lines corresponding to the corresponding lane, and the number of lane lines in the lane line combination is the same as the number of lane lines in the lane image. That is, for each lane in the first road section, a lane line combination having the same number of lane lines as the number of lane lines in the lane image can be formed based on the two lane lines corresponding to the lane (i.e., the two lane lines constituting the lane) and other lane lines in the first road section.

[0066] Among them, for each lane in the first road section, a lane line combination corresponding to the lane can be formed based on the two lane lines corresponding to the lane (the first lane line and the second lane line), as well as the lane line adjacent to the first lane line and / or the lane line adjacent to the second lane line, and the number of lane lines in the lane line combination is the same as the number of lane lines in the lane image.

[0067] See also Figure 4 , Figure 4 It is a schematic diagram of a scenario for determining a lane line combination provided in an embodiment of the present application. Figure 4 Five lanes in the first road section are shown, which are composed of six lane lines L1, L2, L3, R1, R2 and R3, and the number of lane lines in the lane image is 4. Based on this, for the first lane in the first road section, the lane line combination corresponding to the first lane can be formed based on the lane lines corresponding to the first lane (lane lines L1 and R1), the lane line L2 adjacent to the lane line L1, and the lane line R2 adjacent to the lane line R1.

[0068] For the second lane in the first road section, the lane line combination corresponding to the second lane can be formed based on the lane lines corresponding to the second lane (lane lines R1 and R2) and the lane line L1 adjacent to the lane line R1 and the lane line R3 adjacent to the lane line R2.

[0069] Furthermore, for each lane line combination, the matching degree of each lane line in the lane image of the lane line combination can be determined based on the lane line information of each lane line in the lane line combination and the lane line information of each lane line in the lane image, and then based on the matching degree corresponding to the lane line combination, a first probability that the lane corresponding to the lane line combination is within the field of view of the vehicle when on the second road section is determined.

[0070] Specifically, for each lane line combination, when determining the overall matching degree between the lane line combination and each lane line in the lane image, a lane line combination image can be constructed based on the lane line combination and the lane line information of each lane line in the lane line combination, and then the image similarity between the lane line combination image and the lane image is determined, and then the image similarity is determined as the overall matching degree between the lane line combination and each lane line in the lane image. As an example, the matching degree corresponding to the lane line combination can be determined as the first probability corresponding to the lane corresponding to the lane line combination.

[0071] Optionally, for each lane line combination, when determining the overall matching degree between the lane line combination and each lane line in the lane image, if the lane line information of each lane line in the first road section includes a lane line type, lane lines having the same lane line type in the lane line combination and the corresponding lane line in the lane image may be determined, and then the overall type matching degree between the lane line combination and each lane line in the lane image is determined based on the lane lines having the same lane line type. As an example, the overall type matching degree between the lane line combination and each lane line in the lane image may be determined as the first probability corresponding to the lane corresponding to the lane line combination.

[0072] If the lane line type of each lane line in the lane line combination is the same as the lane line type of the corresponding lane line in the lane image, then the overall type matching degree between the lane line combination and each lane line in the lane image can be determined to be 1, and then the overall matching degree between the lane line combination and each lane line in the lane image can be determined based on the overall type matching degree. As an example, the overall type matching degree or the product of the overall type matching degree and the overall type weight can be determined as the overall matching degree between the lane line combination and each lane line in the lane image.

[0073] If the lane line type of some lane lines in the lane line combination is the same as the lane line type of the corresponding lane lines in the lane image, then the overall type matching degree of the lane line combination and each lane line in the lane image is determined based on the corresponding relationship between the number of lane lines with the same lane line type and the overall type matching degree. As an example, if the lane line type of half of the lane lines in the lane line combination is the same as the lane line type of the corresponding lane lines in the lane image, then the overall type matching degree of the lane line combination and each lane line in the lane image is determined to be 0.5 based on the corresponding relationship between the number of lane lines with the same lane line type and the overall type matching degree, and then the overall type matching degree of 0.5 or the product of the overall type matching degree of 0.5 and the overall type weight can be determined as the overall matching degree of the lane line combination and each lane line in the lane image.

[0074] Optionally, for each lane line combination, when determining the overall matching degree between the lane line combination and each lane line in the lane image, if the lane line information of each lane line in the first road section includes lane line color, a lane line having the same lane line color as the corresponding lane line in the lane image may be determined, and then the overall color matching degree between the lane line combination and each lane line in the lane image is determined based on the lane lines having the same lane line color. As an example, the overall color matching degree between the lane line combination and each lane line in the lane image may be determined as the first probability corresponding to the lane corresponding to the lane line combination.

[0075] If the lane line color of each lane line in the lane line combination is the same as the lane line color of the corresponding lane line in the lane image, then the overall color matching degree between the lane line combination and each lane line in the lane image can be determined to be 1, and then the overall matching degree between the lane line combination and each lane line in the lane image can be determined based on the overall color matching degree. As an example, the overall color matching degree or the product of the overall color matching degree and the overall color weight can be determined as the overall matching degree between the lane line combination and each lane line in the lane image.

[0076] If the lane line colors of some lane lines in the lane line combination are the same as the lane line colors of the corresponding lane lines in the lane image, then the overall color matching degree of the lane line combination and each lane line in the lane image is determined based on the corresponding relationship between the number of lane lines with the same lane line color and the overall color matching degree. As an example, if the lane line colors of half of the lane lines in the lane line combination are the same as the lane line colors of the corresponding lane lines in the lane image, then the overall color matching degree of the lane line combination and each lane line in the lane image is determined to be 0.5 based on the corresponding relationship between the number of lane lines with the same lane line color and the overall color matching degree, and then the overall color matching degree of 0.5 or the product of the overall color matching degree of 0.5 and the overall color weight can be determined as the overall matching degree of the lane line combination and each lane line in the lane image.

[0077] Optionally, for each lane line combination, when determining the overall matching degree between the lane line combination and each lane line in the lane image, if the lane line information of each lane line in the first road section includes lane line color and lane line type, the overall color matching degree and overall type matching degree between the lane line combination and each lane line in the lane image can be determined based on the above implementation method. Further based on the overall color matching degree and overall type matching degree between the lane line combination and each lane line in the lane image, the overall matching degree between the lane group combination and each lane line in the lane image is determined. As an example, the product of the overall color matching degree and the overall type matching degree can be determined as the overall matching degree between the lane line combination and each lane line in the lane image, and then the overall matching degree between the lane line combination and each lane line in the lane image is determined as the first probability of the corresponding lane.

[0078] As an example, the calculation process of the overall matching degree between the lane line combination corresponding to lane s and each lane line in the lane image is:

[0079] calcMatchProb(line_type_obs,line_type_real,line_color_obs,line_color_real);

[0080] Among them, calcMatchProb() is a function of the overall matching degree between the lane line combination and each lane line in the lane image, line_type_obs represents the lane line type of the lane line in the lane image, line_type_real represents the lane line type of the lane line in the lane group, line_color_obs represents the lane line color of the lane line in the lane image, and line_color_real represents the lane line color of the lane line in the lane group.

[0081] Among them, the specific calculation process of the above function can be implemented as described above by determining the overall matching degree between the lane line combination and each lane line in the lane image through the overall color matching degree and the overall type matching degree, which is not limited here.

[0082] In some feasible implementations, for each lane line combination, the matching degree between the lane line combination and each lane line in the lane image includes the matching degree between each lane line in the lane line combination and the corresponding lane line in the lane image, and then based on the lane line information of each lane line in the lane image, the lane line weight corresponding to each lane line in the lane image is determined. Based on this, the first probability that the lane corresponding to the lane line combination is within the field of view of the vehicle at the second road section can be determined based on the matching degree between each lane line in the lane line combination and the corresponding lane line in the lane image, and the lane line weight corresponding to each lane line in the lane image.

[0083] As an example, if the emission matrix corresponding to each lane in the first section is emmisionProb, the matrix is ​​a 1-row N-column matrix, N represents the number of lanes in the first section, and one element in the matrix represents the first probability corresponding to a lane in the first section. When the number of lane lines in the lane image is 4, the lane line weight corresponding to each lane line in the lane image is a 1-row 4-column matrix, one element in the weight matrix represents the weight of a lane line in the lane image when calculating the emission probability, and the sum of the weights in the weight matrix is ​​1. Based on this, for lane s in the first section, the first probability corresponding to the lane is:

[0084] emmisionProb[s]=H L1 *leftQ2+H L2 *leftQ1+H R1 *rightQ1+H R2 *rightQ2.

[0085] Among them, leftQ1, leftQ2, rightQ1, rightQ2 respectively represent the matching degree between the lane lines L1, L2, R1, R2 corresponding to lane s and the corresponding lane lines in the lane image. Lane lines L1 and R1 are the two lane lines corresponding to lane s. H L1 represents the lane line weight corresponding to lane line L1 in the weight matrix, H L2 represents the lane line weight corresponding to lane line L2 in the weight matrix, H R1 represents the lane line weight corresponding to lane line R1 in the weight matrix, H R2 Represents the lane line weight corresponding to lane line R2 in the weight matrix probTable.

[0086] Specifically, when the lane line information of each lane line in the first road section includes a lane line type and a lane line color, for each lane line combination, based on the lane line information of each lane line in the lane line combination and the lane line information of each lane line in the lane image, determining a matching degree between each lane line in the lane line combination and a corresponding lane line in the lane image includes:

[0087] Determine a type matching degree between a lane line type of each lane line in the lane line combination and a lane line type of a corresponding lane line in the lane image;

[0088] Determine a color match between a lane line color of each lane line in the lane line combination and a lane line color of a corresponding lane line in the lane image;

[0089] Based on the type matching degree and the color matching degree corresponding to each lane line in the lane line combination, the matching degree of each lane line in the lane line combination and the corresponding lane line in the lane image is determined.

[0090] As an example, for each lane line in each lane line combination, the product of the type matching degree and the color matching degree corresponding to the lane line may be determined as the matching degree between the lane line and the corresponding lane line in the lane image.

[0091] For lane lines in the first road section, the positions of the lane lines in the first road section are different, and the probability of them appearing in the field of vision of the vehicle in the second road section is different. Therefore, based on the number of lane lines of the leftmost and rightmost lane lines in the lane image, the first distance between the leftmost two lane lines, and the second distance between the rightmost two lane lines, the relative distribution position of each lane line in the lane image relative to the first road section can be determined, so as to determine the lane line weight corresponding to each lane line based on the relative distribution position.

[0092] Specifically, a first distance between the two leftmost lane lines and a second distance between the two rightmost lane lines in the lane image are determined, and a road edge line in the lane image is determined based on lane line information of each lane line in the lane image. Determining the first distance between the two leftmost lane lines and the second distance between the two rightmost lane lines in the lane image can further determine the relative distribution position of each lane line in the lane image.

[0093] When determining whether there is a road edge line in the lane image, it can be determined based on the lane line type and / or lane line color of each lane line in the lane image. For example, when the lane image includes a lane line of a preset lane line type, the lane line can be determined as a road edge line, and / or, when the lane image includes a lane line of a preset lane line color, the lane line can be determined as a road edge line. Alternatively, it can be identified based on image recognition and other technologies whether there is a guardrail, curb, curb, etc. in the lane image. If so, it can be determined that there is a road edge line in the lane image.

[0094] Further, if the leftmost lane line and the rightmost lane line in the lane image are both road edge lines, or the left lane line and the rightmost lane line are not road edge lines, then each preset weight in the first weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0095] If the first distance is less than the first threshold, and the leftmost lane line is a road edge line and the rightmost lane line is a non-road edge line, then each preset weight in the second weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0096] If the first distance is greater than or equal to the first threshold, and the leftmost lane line is a road edge line and the rightmost lane line is a non-road edge line, then each preset weight in the third weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0097] If the second distance is less than the second threshold, and the rightmost lane line is a road edge line and the leftmost lane line is a non-road edge line, then each preset weight in the fourth weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0098] If the second distance is greater than or equal to the second threshold, and the rightmost lane line is a road edge line and the leftmost lane line is a non-road edge line, then the preset weights in the fifth weight combination are determined as the lane line weights corresponding to each lane line in the lane image.

[0099] The number of preset weights in any weight combination is consistent with the number of lane lines in the lane image, and one preset weight in any weight combination corresponds to one lane line in the lane image. Furthermore, the sum of the preset weights in any weight combination is 1.

[0100] As an example, when the number of lane lines in the lane image is 4 (L2, L1, R1, R2), each weight combination can be represented by a 5-row and 4-column matrix probTable[5][4], where each row represents a weight combination and each column represents the lane line weights corresponding to lane lines L2, L1, R1, and R2 from left to right. Then:

[0101] probTable[5][4] = {

[0102] {0.24,0.26,0.26,0.24}, / / The leftmost lane line and the rightmost lane line are both road edge lines, or the leftmost lane line and the rightmost lane line are not road edge lines;

[0103] {0.50,0.20,0.20,0.10}, / / The first distance is less than the first threshold, and the leftmost lane line is the road edge line, and the rightmost lane line is not the road edge line;

[0104] {0.27, 0.28, 0.24, 0.21}, / / The first distance is greater than or equal to the first threshold, and the leftmost lane line is the road edge line, and the rightmost lane line is not the road edge line;

[0105] {0.10,0.20,0.20,0.50}, / / The second distance is less than the second threshold, and the rightmost lane line is the road edge line, and the leftmost lane line is not the road edge line;

[0106] {0.21, 0.24, 0.28, 0.27}, / / The second distance is greater than or equal to the second threshold, and the rightmost lane line is the road edge line, and the leftmost lane line is not the road edge line;

[0107] }.

[0108] In some feasible implementations, the first distance between the two leftmost lane lines in the lane image and the second distance between the two rightmost lane lines can be determined by constructing a coordinate system. Taking the determination of the first distance between the two leftmost lane lines in the lane image as an example, a vehicle coordinate system (VCS) can be constructed based on the positioning information of the vehicle at the first moment. The vehicle coordinate system is a special three-dimensional moving coordinate system O-XYZ used to describe the movement of the vehicle. The vehicle coordinate system can be constructed based on a left-hand system, a right-hand system, etc., and the origin of the coordinate system can be the midpoint of the vehicle head, the midpoint of the front axle, or the midpoint of the rear axle, etc., without limitation here.

[0109] As an example, see Figure 5 , Figure 5 Schematic diagram of the vehicle coordinate system provided in the embodiment of the present application. Figure 5 As shown, the origin O of the vehicle coordinate system is fixed relative to the vehicle position. The center of mass of the vehicle is taken. When the vehicle is stationary on a horizontal road, the X-axis is parallel to the ground and points to the front of the vehicle, the Y-axis points to the left side of the vehicle, and the Z-axis passes through the center of mass of the vehicle and points to the top of the vehicle.

[0110] Furthermore, the two lane lines on the left can be subjected to an inverse perspective transformation, converted from image coordinates to world coordinates, and then the transformed lane lines can be fitted and reconstructed to obtain the lane line equations of the two lane lines on the left corresponding to the vehicle coordinate system (hereinafter referred to as the first coordinate system for the convenience of description). The lane line equations of the two lane lines on the left corresponding to the first coordinate system can be quadratic polynomials, cubic polynomials, or other forms of expression, which are not limited here. As an example, the lane line equations of the two lane lines on the left corresponding to the first coordinate system can be y=d+a*x+b*x 2 +c*x 3 , or y = d + a*x + b*x 2 Among them, a, b, c, and d are constants, which can be determined based on the actual lane line and are not limited here.

[0111] Furthermore, based on the lane line equations of the two leftmost lane lines corresponding to the first coordinate system, the first distance between the two leftmost lane lines can be determined. For example, the intercepts of the lane line equations on a certain coordinate axis can be determined respectively, and then the first distance can be determined based on the two intercepts. Figure 6 , Figure 6Schematic diagram of the method for determining lane line distance provided by the embodiment of the present application. The x-axis and y-axis of the first coordinate system are as follows: Figure 6 As shown, the lane line equations corresponding to the two leftmost lane lines are y1 and y2 respectively. Taking the intercepts of the lane line equations y1 and y2 on the y-axis as D1 and D2 respectively, |D1-D2| can be determined as the first distance between the two leftmost lane lines.

[0112] Step S32: Based on the first lane data and the second lane data, determine a second probability that the vehicle is in each lane of the first road section at the first moment when the vehicle is in each lane of the second road section at the second moment.

[0113] In some feasible implementations, based on the first lane data corresponding to the first road section and the second lane data corresponding to the second road section, a transition probability matrix corresponding to the actual lane where the vehicle is located at the first moment can be determined based on the hidden Markov model. Wherein, any element in the above transition probability matrix represents the second probability that the vehicle is in a lane of the first road section at the first moment when it is in a lane of the second road section at the second moment. The above transition probability matrix represents the second probability that the vehicle is in each lane of the second road section at the first moment when it is in each lane of the first road section at the second moment.

[0114] Specifically, based on the first lane data, lane line information of each lane line of the first road section and lane distribution information of each lane of the first road section can be determined, and based on the second lane data, lane line information of each lane line of the second road section and lane distribution information of each lane of the second road section can be determined. Among them, the lane distribution information can be used to illustrate the number of lanes in the corresponding road section, the distribution (topology) of each lane, etc., and the lane line information includes but is not limited to the actual color and actual type of the lane line, etc.

[0115] Further, based on the lane line information of each lane line of the first section and the second section, and the lane line distribution information of each lane, the target lane can be determined. The target lane is the same lane in the first section and the second section, that is, the target lane runs through the first section and the second section.

[0116] When the vehicle is in the target lane of the second section at the second moment, since the target lane is the same lane in the first section and the second section, the probability that the vehicle is in the target lane of the first section at the first moment is relatively high. Based on this, the preset probability can be determined as the second probability that the vehicle is in the target lane of the first section at the first moment when the vehicle is in the target lane of the second section at the second moment. The preset probability is the maximum probability in the transition probability matrix, such as 1.

[0117] As an example, when the vehicle is in the target lane of the second road section at the second moment, the second probability that the vehicle is in the target lane of the first road section at the first moment may be determined as the preset probability 1.

[0118] Furthermore, for a vehicle, most of the time the vehicle will travel along the same lane. Therefore, for any lane in the second section (hereinafter referred to as the third lane for the convenience of description) and the fourth lane in the first section that is different from the third lane, the relative position of the fourth lane in the first section to the relative position of the third lane in the second section, and the lane line types corresponding to the fourth lane and the third lane (such as the lane line type that prohibits lane changes) can determine the difficulty of the vehicle moving to the fourth lane corresponding to the first moment when the vehicle is in the third lane at the second moment.

[0119] Based on this, different lanes in the first section and the second section can be determined based on the lane line information of the first section and the second section and the lane distribution information of each lane. And further based on the lane line information of each lane line in the first section and the second section and the lane distribution information of each lane, the second probability of the vehicle being in each lane other than the target lane of the first section at the first moment when the vehicle is in the target lane of the second section at the second moment, and the second probability of the vehicle being in each lane of the first section at the first moment when the vehicle is in each lane other than the target lane of the second section at the second moment are determined.

[0120] Among them, when the vehicle is in the third lane at the second moment, it is easier to move to the fourth lane corresponding to the first moment. For example, the smaller the lane interval between the third lane and the fourth lane, the greater the second probability that the vehicle is in the fourth lane at the first moment when it is in the third lane at the second moment. When the vehicle is in the third lane at the second moment, it cannot move to the fourth lane corresponding to the first moment. If the vehicle cannot change lanes from the third lane to the fourth lane, the second probability that the vehicle is in the fourth lane at the first moment when it is in the third lane at the second moment is almost 0.

[0121] See also Figure 7a , Figure 7a Schematic diagram of a scenario for determining a transition probability matrix provided by an embodiment of the present application. Figure 7aAs shown, the second section of the vehicle at the second moment includes lanes B1, B2 and B3, and the first section of the vehicle at the first moment includes lanes A1, A2 and A3. If the vehicle can travel to other adjacent lanes in the first section in any lane of the second section, and lanes B1 and A1, lanes B2 and A2, lanes B3 and A3 are the same lanes, then if the vehicle is in any lane of the second section at the second moment, the second probability of being in the target lane of the first section at the first moment is 1 / (|mn|+1). Where m is the row index corresponding to each lane in the second section in the probability matrix, and n is the column index corresponding to each lane in the first section in the probability matrix.

[0122] like Figure 7a The vehicle is in lane B1 at the second moment, and the second probability of being in lane A1 at the first moment is 1, the second probability of being in lane A2 at the first moment is 1 / 2, and the second probability of being in lane A3 at the first moment is 1 / 3; the vehicle is in lane B2 at the second moment, and the second probability of being in lane A1 at the first moment is 1 / 2, the second probability of being in lane A2 at the first moment is 1, and the second probability of being in lane A3 at the first moment is 1 / 2; the vehicle is in lane B3 at the second moment, and the second probability of being in lane A1 at the first moment is 1 / 3, the second probability of being in lane A2 at the first moment is 1 / 2, and the second probability of being in lane A3 at the first moment is 1.

[0123] See also Figure 7b , Figure 7b is another schematic diagram of a scenario for determining a transition probability matrix provided by an embodiment of the present application. Figure 7a As shown, the second section of the vehicle at the second moment includes lanes B1, B2 and B3, and the first section of the vehicle at the first moment includes lanes A1, A2, A3 and A4. If the vehicle in any lane of the second section can travel to other adjacent lanes in the first section, and lanes B1 and A2, lanes B2 and A3, lanes B3 and A4 are the same lanes.

[0124] If lane B1 and lane A1, as well as lane B1 and lane A2 are the same lanes, that is, lane B1 is connected with lane A1, and lane B1 is connected with lane A2, then the preset probability 1 can be determined as the second probability that the vehicle is in lane A1 and lane A2 at the first moment when it is in lane B1 at the second moment, and the other probability value 0 (or other probability value less than 1) can be determined as the second probability that the vehicle is in lane A3 and lane A4 at the first moment.

[0125] If lane B2 is connected with lane A3, when the vehicle is in lane B2 at the second moment, the second probability of being in lane A3 at the first moment is 1, and the second probability of being in other lanes in the first road section at the first moment is 0; if lane B3 is connected with lane A4, when the vehicle is in lane B3 at the second moment, the second probability of being in lane A4 at the first moment is 1, and the second probability of being in other lanes in the first road section at the first moment is 0.

[0126] Based on the case where the vehicle is in each lane in the second road section at the second moment, the second probability of being in each lane in the first road section at the first moment can be determined as follows: Figure 7b The transition probability matrix is ​​shown.

[0127] Step S33: determine a third probability that the vehicle is in each lane of the second road section at the second moment, and determine the actual lane where the vehicle is located at the first moment based on the first probability, the second probability and the third probability.

[0128] In some feasible embodiments, after determining the third probability that the vehicle is in each lane of the second road section at the second moment, as well as the above-mentioned emission probability matrix and transition probability matrix, the fourth probability that the vehicle travels from each lane of the second road section to each lane of the first road section can be determined based on the above-mentioned third probability, the above-mentioned emission probability and the transition probability matrix.

[0129] For each lane of the first road section, the maximum probability among the sixth probabilities of the vehicle traveling from each lane of the second road section to the lane is determined as the fifth probability that the vehicle is in the lane of the first road section at the first moment. Specifically, the determination can be made by the Viterbi algorithm:

[0130] W(j)=max i＝1…N′ {prevW(i)*transMatrix(i,j)}*emissionProb[j];

[0131] Wherein, prevW(i) is the third probability matrix, an element of which represents the third probability that the vehicle is in a lane of the second section at the second moment, and i is the index of each lane in the second section. transMatrix(i,j) represents the transition probability matrix, an element of which represents the second probability that the vehicle is in lane j of the first section at the first moment when the vehicle is in lane i of the second section at the second moment, and j is the index of each lane in the first section. emissionProb[j] represents the emission probability matrix, an element of which represents the first probability that lane j of the first section is within the field of view of the vehicle when it is in the second section.

[0132] Wherein, N′ represents the number of lanes in the second road section. Based on the above formula, it can be known that an element in W(j) represents the fifth probability that the vehicle is in lane j in the first road section at the first moment.

[0133] Further, after obtaining the fifth probability that the vehicle is in each lane in the first road section at the first moment, by argmax j＝1…N {W(j)} determines the lane corresponding to the maximum probability among the fifth probabilities that the vehicle is in each lane in the first road section at the first moment as the actual lane in which the vehicle is located in the first road section at the first moment, wherein N is the number of lanes in the first road section.

[0134] If the first moment is the initial moment of lane-level positioning, the third probability of the vehicle being in each lane of the second section at the second moment is the initial probability distribution corresponding to the hidden Markov model. The third probability of the vehicle being in each lane of the second section at the second moment is the same, which can be determined based on the number of lanes in each lane in the first section. For example, the third probability of the vehicle being in each lane of the second section at the second moment is 1 / N.

[0135] Wherein, if the first moment is any other moment in the lane-level positioning process except the initial moment, the third probability W(i) of the vehicle being in each lane of the second road section at the second moment can be determined based on the above Viterbi algorithm. For example, after determining the actual lane of the vehicle in the first road section at the first moment, when determining the actual lane of the vehicle in the third road section at the third moment (the next moment after the first moment), the probability W(k)=max i＝1…N {prevW(j)*transMatrix(j,k)}*emissionProb[k] determines the sixth probability W(k) that the vehicle is in each lane in the third road section at the third moment, and then determines the lane corresponding to the maximum probability in the sixth probability W(k) as the actual lane where the vehicle is in the third road section at the third moment. Wherein, W(j) is the fifth probability that the vehicle is in each lane in the first road section at the first moment, and N is the number of lanes in the first road section.

[0136] Based on the above implementation, the actual lane in which the vehicle is located at any time can be determined.

[0137] It should be particularly noted that if the first moment is the initial moment of lane-level positioning, the first road section of the vehicle at the first moment can be determined as the second road section of the vehicle at the second moment, and then the first lane data of the vehicle in the first road section at the first moment can be determined as the second lane data of the vehicle in the second road section at the second moment, that is, when the first moment is the initial moment of lane-level positioning, the vehicle is considered to be in the same road section at the first moment and the second moment.

[0138] Among them, if the second lane data of the second road section where the vehicle is located at the second moment is not obtained, the first moment is determined to be the initial moment of lane-level positioning. For example, the lane data of any road section can be obtained from the ADAS data, and the second road section of the vehicle at the second moment is outside the ADAS data coverage area, such as the vehicle first enters the ADAS data coverage area at the first moment, leaves the ADAS data coverage area midway and re-enters at the first moment, etc., the first moment can be determined as the initial moment of lane-level positioning. Alternatively, if based on the first lane data of the first road section of the vehicle at the first moment, it is determined that the vehicle enters a new intersection, ramp, etc. at the first moment, the first moment can also be determined as the initial moment of lane-level positioning, and then the actual lane where the vehicle is located in the first road section at the first moment is determined based on the above implementation method.

[0139] Combine the following Figure 8 The lane-level positioning method provided in the embodiment of the present application is further explained. Figure 8 is a flow chart of the lane-level positioning method provided in the embodiment of the present application. Figure 8 As shown, based on the positioning information of the vehicle at the first section at the first moment, the first lane data of the vehicle at the first section at the first moment can be obtained. If the first lane data of the first section is not obtained, such as the first section is not covered by ADAS data, then continue to wait until the measured lane data corresponding to the section at a certain moment is obtained.

[0140] Further, it is determined whether there is second lane data for the second road section where the vehicle is located at the second moment, and if there is second lane data, the emission probability and the transition probability are determined based on the acquired lane image, the first lane data, and the second lane data. And based on the emission probability, the transition probability, and the third probability that the vehicle is in each lane of the second road section at the second moment, the actual lane where the vehicle is located at the first moment is determined.

[0141] If the second lane data does not exist, the first lane data is determined as the second lane data, the first road section is determined as the second road section, and the first moment is determined as the initial moment of lane-level positioning. Then, based on the first lane data, the second lane data (first lane data) and the lane image, the emission probability and the transition probability are determined, and the initial probability distribution is determined based on the number of lanes in the first road section, so as to determine the actual lane where the vehicle is located at the first moment based on the emission probability, the transition probability and the initial probability distribution.

[0142] The data processing and calculation processes involved in the embodiments of the present application can be performed based on computer technology and cloud computing. Among them, cloud computing is the product of the development and integration of traditional computer and network technologies such as grid computing, distributed computing, parallel computing, utility computing, network storage technologies, virtualization, and load balancing. Cloud computing can improve the data processing and calculation efficiency in the embodiments of the present application.

[0143] In the embodiment of the present application, the lane data of each road section is basic road data including lane line type, lane line color and lane line distribution information, so that lane data acquisition is convenient, data processing is simple, and the lane image acquisition method is simple, with low equipment dependence, thereby improving the positioning efficiency of lane-level positioning. And based on the lane data of the road section where the vehicle is at any time, the lane data of the road section of the vehicle at the previous time, and the lane image in front of the vehicle at any of the aforementioned times, the actual lane where the vehicle is at any of the aforementioned times can be determined, thereby realizing real-time lane-level positioning of the vehicle, which can be applied to vehicle positioning in different road scenarios and has high applicability.

[0144] See also Fig. 9 , Fig. 9 : is a schematic diagram of the structure of the lane level positioning device provided in the embodiment of the present application. The lane level positioning device provided in the embodiment of the present application includes:

[0145] A lane data acquisition module 91 is used to acquire first lane data of a first road section where a vehicle is located at a first moment, and second lane data of a second road section where the vehicle is located at a second moment, where the second moment is a moment before the first moment;

[0146] A lane image acquisition module 92, used to acquire a lane image in front of the vehicle at a first moment, and determine lane line information of each lane line in the lane image;

[0147] The lane positioning module 93 is used to determine the actual lane where the vehicle is located at the first moment based on the first lane data, the second lane data and the lane line information of each lane line in the lane image.

[0148] In some feasible implementations, the lane data acquisition module 91 is used to:

[0149] Determine the positioning information of the vehicle at the first moment;

[0150] Based on the positioning information, determining the first road section where the vehicle is located at the first moment;

[0151] The first lane data of the first road section is obtained.

[0152] In some feasible implementations, the lane positioning module 92 is used to:

[0153] Based on the first lane data and lane line information of each lane line in the lane image, determining a first probability that each lane of the first road section is within the field of view of the vehicle when it is on the second road section;

[0154] Based on the first lane data and the second lane data, determining a second probability that the vehicle is in each lane of the first road section at the first moment, when the vehicle is in each lane of the second road section at the second moment;

[0155] A third probability that the vehicle is in each lane of the second road section at the second moment is determined, and based on the first probability, the second probability and the third probability, an actual lane in which the vehicle is located at the first moment is determined.

[0156] In some feasible implementations, the lane positioning module 92 is used to:

[0157] Based on the first lane data, determine lane line information of each lane line of the first road section;

[0158] Based on the number of lane lines in the lane image, lane line information of each lane line in the lane image and lane line information of each lane line of the first road section, a first probability that each lane of the first road section is within the field of view of the vehicle when it is in the second road section is determined.

[0159] In some feasible implementations, the lane positioning module 92 is used to:

[0160] Determine a lane line combination corresponding to each lane of the first road section, each lane line combination includes lane lines corresponding to a corresponding lane, and the number of lane lines is the same as the number of lane lines in the lane image;

[0161] For each of the above lane line combinations, based on the lane line information of each lane line in the lane line combination and the lane line information of each lane line in the above lane image, the matching degree of the lane line combination with each lane line in the above lane image is determined, and based on the matching degree corresponding to the lane line combination, a first probability that the lane corresponding to the lane line combination is within the field of view of the above vehicle when it is on the above second road section is determined.

[0162] In some feasible implementations, for each of the lane line combinations, the matching degree between the lane line combination and each lane line in the lane image includes the matching degree between each lane line in the lane line combination and the corresponding lane line in the lane image;

[0163] The lane positioning module 92 is used to:

[0164] Determine a lane line weight corresponding to each lane line in the lane image based on the lane line information of each lane line in the lane image;

[0165] Based on the matching degree of each lane line in the lane line combination and the corresponding lane line in the above lane image, and the lane line weight corresponding to each lane line in the above lane image, a first probability is determined that the lane corresponding to the lane line combination is within the field of view of the above vehicle when it is on the above second road section.

[0166] In some feasible implementations, the lane positioning module 92 is used to:

[0167] The lane line information and the lane line information include lane line type and lane line color;

[0168] For each lane line combination, the lane positioning module 92 is used to:

[0169] Determine a type matching degree between a lane line type of each lane line in the lane line combination and a lane line type of a corresponding lane line in the lane image;

[0170] Determine a color match between a lane line color of each lane line in the lane line combination and a lane line color of a corresponding lane line in the lane image;

[0171] Based on the type matching degree and the color matching degree corresponding to each lane line in the lane line combination, the matching degree of each lane line in the lane line combination and the corresponding lane line in the lane image is determined.

[0172] In some feasible implementations, the lane positioning module 92 is used to:

[0173] Determine a first distance between two leftmost lane lines and a second distance between two rightmost lane lines in the lane image;

[0174] Determine a road edge line in the lane image based on lane line information of each lane line in the lane image;

[0175] If the leftmost lane line and the rightmost lane line in the lane image are both road edge lines, or the left lane line and the rightmost lane line are not road edge lines, then each preset weight in the first weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0176] If the first distance is less than the first threshold, and the leftmost lane line is a road edge line, and the rightmost lane line is a non-road edge line, then each preset weight in the second weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0177] If the first distance is greater than or equal to the first threshold, and the leftmost lane line is a road edge line, and the rightmost lane line is a non-road edge line, then each preset weight in the third weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0178] If the second distance is less than the second threshold, and the rightmost lane line is a road edge line, and the leftmost lane line is a non-road edge line, then each preset weight in the fourth weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0179] If the above-mentioned second distance is greater than or equal to the above-mentioned second threshold, and the above-mentioned rightmost lane line is a road edge line, and the above-mentioned leftmost lane line is a non-road edge line, then each preset weight in the fifth weight combination is determined as the lane line weight corresponding to each lane line in the above-mentioned lane image.

[0180] In some feasible implementations, the lane positioning module 92 is used to:

[0181] Based on the first lane data, determine the lane line information of each lane line of the first road section and the lane distribution information of each lane of the first road section; based on the second lane data, determine the lane line information of each lane line of the second road section and the lane distribution information of each lane of the second road section;

[0182] Based on the lane line information of each lane line of the first road section and the second road section and the lane distribution information of each lane, determining the target lane, and determining the preset probability as a second probability that the vehicle is in the target lane of the first road section at the first moment when the vehicle is in the target lane of the second road section at the second moment;

[0183] Based on the lane line information of each lane line of the first road section and the second road section, and the lane distribution information of each lane, determine the second probability that the vehicle was in each lane other than the target lane of the first road section at the first moment when the vehicle was in the target lane of the second road section at the second moment, and determine the second probability that the vehicle was in each lane of the first road section at the first moment when the vehicle was in each lane other than the target lane of the second road section at the second moment.

[0184] In some feasible implementations, the lane positioning module 92 is used to:

[0185] Based on the first probability, the second probability and the third probability, determining a fourth probability that the vehicle travels from each lane of the second road section to each lane of the first road section;

[0186] For each lane of the first road section, determining the maximum probability among the fourth probabilities that the vehicle travels from each lane of the second road section to the lane as the fifth probability that the vehicle is in the lane at the first moment;

[0187] The lane corresponding to the maximum probability among the fifth probabilities corresponding to the lanes in the first road section is determined as the actual lane where the vehicle is located at the first moment.

[0188] In some feasible implementations, the lane positioning module 92 is used to:

[0189] If the first moment is an initial moment of lane-level positioning, a third probability that the vehicle is in each lane of the second road section at the second moment is determined based on the number of lanes of each lane of the first road section.

[0190] In some feasible implementations, the lane positioning module 92 is used to:

[0191] Constructing a first coordinate system based on the positioning information of the vehicle at the first moment;

[0192] Determine the lane line equations of the two leftmost lane lines in the lane image corresponding to the first coordinate system;

[0193] Based on the lane line equation, a first distance between the two leftmost lane lines in the lane image is determined.

[0194] In a specific implementation, the lane-level positioning device can execute the above-mentioned Figure 2 and / or Figure 3 For the implementation methods provided in each step, please refer to the implementation methods provided in the above steps for details, which will not be repeated here.

[0195] See also Fig.10 , Fig.10 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Fig.10 As shown, the electronic device 1000 in this embodiment may include: a processor 1001, a network interface 1004 and a memory 1005. In addition, the above-mentioned electronic device 1000 may also include: a user interface 1003, and at least one communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. Among them, the user interface 1003 may include a display screen (Display), a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1004 may be a high-speed RAM memory, or it may be a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 1005 may optionally also be at least one storage device located away from the aforementioned processor 1001. As Fig.10 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a device control application program.

[0196] exist Fig.10 In the electronic device 1000 shown, the network interface 1004 can provide a network communication function; the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 to achieve:

[0197] Acquire data of a first lane of a first road section where a vehicle is located at a first moment, and data of a second lane of a second road section where the vehicle is located at a second moment, wherein the second moment is a moment before the first moment;

[0198] Acquire a lane image in front of the vehicle at a first moment, and determine lane line information of each lane line in the lane image;

[0199] Based on the first lane data, the second lane data and lane line information of each lane line in the lane image, the actual lane in which the vehicle is located at the first moment is determined.

[0200] In some feasible implementations, the processor 1001 is configured to:

[0201] Determine the positioning information of the vehicle at the first moment;

[0202] Based on the positioning information, determining the first road section where the vehicle is located at the first moment;

[0203] The first lane data of the first road section is obtained.

[0204] In some feasible implementations, the processor 1001 is configured to:

[0205] Based on the first lane data and lane line information of each lane line in the lane image, determining a first probability that each lane of the first road section is within the field of view of the vehicle when it is on the second road section;

[0206] Based on the first lane data and the second lane data, determining a second probability that the vehicle is in each lane of the first road section at the first moment, when the vehicle is in each lane of the second road section at the second moment;

[0207] A third probability that the vehicle is in each lane of the second road section at the second moment is determined, and based on the first probability, the second probability and the third probability, an actual lane in which the vehicle is located at the first moment is determined.

[0208] In some feasible implementations, the processor 1001 is configured to:

[0209] Based on the first lane data, determine lane line information of each lane line of the first road section;

[0210] Based on the number of lane lines in the lane image, lane line information of each lane line in the lane image and lane line information of each lane line of the first road section, a first probability that each lane of the first road section is within the field of view of the vehicle when it is in the second road section is determined.

[0211] In some feasible implementations, the processor 1001 is configured to:

[0212] Determine a lane line combination corresponding to each lane of the first road section, each lane line combination includes lane lines corresponding to a corresponding lane, and the number of lane lines is the same as the number of lane lines in the lane image;

[0213] For each of the above lane line combinations, based on the lane line information of each lane line in the lane line combination and the lane line information of each lane line in the above lane image, the matching degree of the lane line combination with each lane line in the above lane image is determined, and based on the matching degree corresponding to the lane line combination, a first probability that the lane corresponding to the lane line combination is within the field of view of the above vehicle when it is on the above second road section is determined.

[0214] In some feasible implementations, for each of the lane line combinations, the matching degree between the lane line combination and each lane line in the lane image includes the matching degree between each lane line in the lane line combination and the corresponding lane line in the lane image;

[0215] The processor 1001 is used for:

[0216] Determine a lane line weight corresponding to each lane line in the lane image based on the lane line information of each lane line in the lane image;

[0217] Based on the matching degree of each lane line in the lane line combination and the corresponding lane line in the above lane image, and the lane line weight corresponding to each lane line in the above lane image, a first probability is determined that the lane corresponding to the lane line combination is within the field of view of the above vehicle when it is on the above second road section.

[0218] In some feasible implementations, the lane line information and the lane line information include lane line type and lane line color;

[0219] For each lane line combination, the processor 1001 is used to:

[0220] Determine a type matching degree between a lane line type of each lane line in the lane line combination and a lane line type of a corresponding lane line in the lane image;

[0221] Determine a color match between a lane line color of each lane line in the lane line combination and a lane line color of a corresponding lane line in the lane image;

[0222] Based on the type matching degree and the color matching degree corresponding to each lane line in the lane line combination, the matching degree of each lane line in the lane line combination and the corresponding lane line in the lane image is determined.

[0223] In some feasible implementations, the processor 1001 is configured to:

[0224] Determine a first distance between two leftmost lane lines and a second distance between two rightmost lane lines in the lane image;

[0225] Determine a road edge line in the lane image based on lane line information of each lane line in the lane image;

[0226] If the leftmost lane line and the rightmost lane line in the lane image are both road edge lines, or the left lane line and the rightmost lane line are not road edge lines, then each preset weight in the first weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0227] If the first distance is less than the first threshold, and the leftmost lane line is a road edge line, and the rightmost lane line is a non-road edge line, then each preset weight in the second weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0228] If the first distance is greater than or equal to the first threshold, and the leftmost lane line is a road edge line, and the rightmost lane line is a non-road edge line, then each preset weight in the third weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0229] If the second distance is less than the second threshold, and the rightmost lane line is a road edge line, and the leftmost lane line is a non-road edge line, then each preset weight in the fourth weight combination is determined as the lane line weight corresponding to each lane line in the lane image;

[0230] If the above-mentioned second distance is greater than or equal to the above-mentioned second threshold, and the above-mentioned rightmost lane line is a road edge line, and the above-mentioned leftmost lane line is a non-road edge line, then each preset weight in the fifth weight combination is determined as the lane line weight corresponding to each lane line in the above-mentioned lane image.

[0231] In some feasible implementations, the processor 1001 is configured to:

[0232] Based on the first lane data, determine the lane line information of each lane line of the first road section and the lane distribution information of each lane of the first road section; based on the second lane data, determine the lane line information of each lane line of the second road section and the lane distribution information of each lane of the second road section;

[0233] Based on the lane line information of each lane line of the first road section and the second road section, and the lane distribution information of each lane, determining the target lane, and determining the preset probability as a second probability that the vehicle is in the target lane of the first road section at the first moment when the vehicle is in the target lane of the second road section at the second moment;

[0234] Based on the lane line information of each lane line of the first road section and the second road section, and the lane distribution information of each lane, determine the second probability that the vehicle was in each lane other than the target lane of the first road section at the first moment when the vehicle was in the target lane of the second road section at the second moment, and determine the second probability that the vehicle was in each lane of the first road section at the first moment when the vehicle was in each lane other than the target lane of the second road section at the second moment.

[0235] In some feasible implementations, the processor 1001 is configured to:

[0236] Based on the first probability, the second probability and the third probability, determining a fourth probability that the vehicle travels from each lane of the second road section to each lane of the first road section;

[0237] For each lane of the first road section, determining the maximum probability among the fourth probabilities that the vehicle travels from each lane of the second road section to the lane as the fifth probability that the vehicle is in the lane at the first moment;

[0238] The lane corresponding to the maximum probability among the fifth probabilities corresponding to the lanes in the first road section is determined as the actual lane where the vehicle is located at the first moment.

[0239] In some feasible implementations, the processor 1001 is configured to:

[0240] If the first moment is an initial moment of lane-level positioning, a third probability that the vehicle is in each lane of the second road section at the second moment is determined based on the number of lanes of each lane of the first road section.

[0241] In some feasible implementations, the processor 1001 is configured to:

[0242] Constructing a first coordinate system based on the positioning information of the vehicle at the first moment;

[0243] Determine the lane line equations of the two leftmost lane lines in the lane image corresponding to the first coordinate system;

[0244] Based on the lane line equation, a first distance between the two leftmost lane lines in the lane image is determined.

[0245] It should be understood that in some feasible implementations, the processor 1001 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0246] In a specific implementation, the electronic device 1000 can execute the above-mentioned functions through its built-in functional modules. Figure 2 and / or Figure 3 For the implementation methods provided in each step, please refer to the implementation methods provided in the above steps for details, which will not be repeated here.

[0247] The present application also provides a computer-readable storage medium, which stores a computer program and is executed by a processor to implement Figure 2 and / or Figure 3 For the methods provided in each step, please refer to the implementation methods provided in the above steps for details, which will not be repeated here.

[0248] The computer-readable storage medium may be an internal storage unit of the lane-level positioning device and / or electronic device, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. The computer-readable storage medium may also include a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. Further, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0249] The embodiment of the present application provides a computer program product or a computer program, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 2 and / or Figure 3 The methods provided in each step.

[0250] The terms "first", "second", etc. in the claims, specification and drawings of the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or electronic device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or electronic devices. Mentioning "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. Displaying the phrase at various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. The term "and / or" used in the present application specification and the attached claims refers to any combination of one or more of the items listed in association and all possible combinations, and includes these combinations.

[0251] Those of ordinary skill in the art will appreciate that the units and algorithmic steps of each example described in connection with the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of function in the above description. Skilled artisans may implement the described functions using different methods for each particular application, but such implementation should not be considered to exceed the scope of this application.

[0252] The foregoing disclosure is only a preferred embodiment of the present application and cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made in accordance with the claims of the present application still fall within the scope covered by the present application.

Claims

1. A lane-level positioning method, It is characterized in that The method comprises: Acquire first lane data of a first road section where a vehicle is located at a first moment, and second lane data of a second road section where the vehicle is located at a second moment, where the second moment is a moment before the first moment; Acquire a lane image in front of the vehicle at a first moment, and determine lane line information of each lane line in the lane image; Determine, based on the first lane data and lane line information of each lane line in the lane image, a first probability that each lane of the first road section is within a field of view of the vehicle when the vehicle is on the second road section; Determine, based on the first lane data and the second lane data, a second probability that the vehicle is in each lane of the first road section at the first moment, when the vehicle is in each lane of the second road section at the second moment; A third probability that the vehicle is in each lane of the second road section at the second moment is determined, and based on the first probability, the second probability and the third probability, the actual lane in which the vehicle is located at the first moment is determined.

2. The method according to claim 1, It is characterized in that The obtaining of first lane data of a first road section where the vehicle is located at a first moment includes: Determine the positioning information of the vehicle at the first moment; Based on the positioning information, determining a first road section where the vehicle is located at the first moment; Acquire first lane data of the first road section.

3. The method according to claim 1, It is characterized in that The determining, based on the first lane data and lane line information of each lane line in the lane image, a first probability that each lane of the first road section is within the field of view of the vehicle when the vehicle is on the second road section comprises: Determining lane line information of each lane line of the first road section based on the first lane data; Based on the number of lane lines in the lane image, lane line information of each lane line in the lane image and lane line information of each lane line of the first road section, a first probability that each lane of the first road section is within the field of view of the vehicle when it is on the second road section is determined.

4. The method according to claim 3, It is characterized in that The determining, based on the number of lane lines in the lane image, lane line information of each lane line in the lane image, and lane line information of each lane line of the first road section, a first probability that each lane of the first road section is within the field of view of the vehicle when the vehicle is on the second road section includes: Determine a lane line combination corresponding to each lane of the first road section, each lane line combination includes lane lines corresponding to a corresponding lane, and the number of lane lines is the same as the number of lane lines in the lane image; For each of the lane line combinations, a degree of matching between the lane line combination and each lane line in the lane image is determined based on lane line information of each lane line in the lane line combination and lane line information of each lane line in the lane image, and a first probability that the lane corresponding to the lane line combination is within the field of view of the vehicle when it is on the second road section is determined based on the matching degree corresponding to the lane line combination.

5. The method according to claim 4, It is characterized in that For each lane line combination, the matching degree between the lane line combination and each lane line in the lane image includes the matching degree between each lane line in the lane line combination and the corresponding lane line in the lane image; The determining, based on the matching degree corresponding to the lane line combination, a first probability that the lane corresponding to the lane line combination is within the field of view of the vehicle when the vehicle is on the second road section includes: Determining a lane line weight corresponding to each lane line in the lane image based on lane line information of each lane line in the lane image; Based on the matching degree of each lane line in the lane line combination and the corresponding lane line in the lane image, and the lane line weight corresponding to each lane line in the lane image, a first probability is determined that the lane corresponding to the lane line combination is within the field of view of the vehicle when it is on the second road section.

6. The method according to claim 5, It is characterized in that The lane line information and the lane line information include lane line type and lane line color; For each lane line combination, based on lane line information of each lane line in the lane line combination and lane line information of each lane line in the lane image, determining a matching degree between each lane line in the lane line combination and a corresponding lane line in the lane image, including: Determine a type matching degree between a lane line type of each lane line in the lane line combination and a lane line type of a corresponding lane line in the lane image; Determine a color match between a lane line color of each lane line in the lane line combination and a lane line color of a corresponding lane line in the lane image; Based on the type matching degree and the color matching degree corresponding to each lane line in the lane line combination, the matching degree of each lane line in the lane line combination and the corresponding lane line in the lane image is determined.

7. The method according to claim 5, It is characterized in that The determining, based on lane line information of each lane line in the lane image, a lane line weight corresponding to each lane line in the lane image includes: Determine a first distance between two leftmost lane lines and a second distance between two rightmost lane lines in the lane image; Determining a road edge line in the lane image based on lane line information of each lane line in the lane image; If the leftmost lane line and the rightmost lane line in the lane image are both road edge lines, or the left lane line and the rightmost lane line are not road edge lines, then each preset weight in the first weight combination is determined as the lane line weight corresponding to each lane line in the lane image; If the first distance is less than a first threshold, and the leftmost lane line is a road edge line and the rightmost lane line is a non-road edge line, then each preset weight in the second weight combination is determined as a lane line weight corresponding to each lane line in the lane image; If the first distance is greater than or equal to the first threshold, and the leftmost lane line is a road edge line and the rightmost lane line is a non-road edge line, then each preset weight in the third weight combination is determined as the lane line weight corresponding to each lane line in the lane image; If the second distance is less than a second threshold, and the rightmost lane line is a road edge line and the leftmost lane line is a non-road edge line, then each preset weight in the fourth weight combination is determined as the lane line weight corresponding to each lane line in the lane image; If the second distance is greater than or equal to the second threshold, and the rightmost lane line is a road edge line and the leftmost lane line is a non-road edge line, then each preset weight in the fifth weight combination is determined as the lane line weight corresponding to each lane line in the lane image.

8. The method according to claim 1, It is characterized in that The determining, based on the first lane data and the second lane data, a second probability that the vehicle is in each lane of the second road section at the first moment, when the vehicle is in each lane of the second road section at the second moment, comprises: Determine lane line information of each lane line of the first road section and lane distribution information of each lane of the first road section based on the first lane data, and determine lane line information of each lane line of the second road section and lane distribution information of each lane of the second road section based on the second lane data; Determine a target lane based on lane line information of each lane line of the first road section and the second road section and lane distribution information of each lane, and determine a preset probability as a second probability that the vehicle is in the target lane of the first road section at the first moment when the vehicle is in the target lane of the second road section at the second moment; Based on the lane line information of each lane line of the first road section and the second road section, and the lane distribution information of each lane, determine the second probability that the vehicle is in each lane other than the target lane of the first road section at the first moment when the vehicle is in the target lane of the second road section at the second moment, and determine the second probability that the vehicle is in each lane of the first road section at the first moment when the vehicle is in each lane other than the target lane of the second road section at the second moment.

9. The method according to claim 1, It is characterized in that The determining, based on the first probability, the second probability, and the third probability, the actual lane in which the vehicle is located at the first moment includes: Determining a fourth probability that the vehicle travels from each lane of the second road section to each lane of the first road section based on the first probability, the second probability, and the third probability; For each lane of the first road section, determining the maximum probability among the fourth probabilities that the vehicle travels from each lane of the second road section to the lane as the fifth probability that the vehicle is in the lane at the first moment; The lane corresponding to the maximum probability among the fifth probabilities corresponding to the lanes in the first road section is determined as the actual lane where the vehicle is located at the first moment.

10. The method according to claim 1, It is characterized in that The determining a third probability that the vehicle is in each lane of the second road section at the second moment includes: If the first moment is an initial moment of lane-level positioning, a third probability that the vehicle is in each lane of the second road section at the second moment is determined based on the lane number of each lane of the first road section.

11. The method according to claim 7, It is characterized in that Determining a first distance between two leftmost lane lines in the lane image includes: Constructing a first coordinate system based on the positioning information of the vehicle at the first moment; Determine lane line equations of the two leftmost lane lines in the lane image corresponding to the first coordinate system; Based on the lane line equation, a first distance between two leftmost lane lines in the lane image is determined.

12. A lane-level positioning device, It is characterized in that The device comprises: A lane data acquisition module, used to acquire first lane data of a first road section where a vehicle is located at a first moment, and second lane data of a second road section where the vehicle is located at a second moment, where the second moment is a moment before the first moment; A lane image acquisition module, used to acquire a lane image in front of the vehicle at a first moment, and determine lane line information of each lane line in the lane image; a lane positioning module, configured to determine, based on the first lane data and lane line information of each lane line in the lane image, a first probability that each lane of the first road section is within a field of view of the vehicle when the vehicle is on the second road section; The lane positioning module is used to determine, based on the first lane data and the second lane data, a second probability that the vehicle is in each lane of the first road section at the first moment, when the vehicle is in each lane of the second road section at the second moment; The lane positioning module is used to determine a third probability that the vehicle is in each lane of the second road section at the second moment, and determine the actual lane where the vehicle is located at the first moment based on the first probability, the second probability and the third probability.

13. The device according to claim 12, It is characterized in that When acquiring the first lane data of the first road section where the vehicle is located at the first moment, the lane positioning module is used to: Determine the positioning information of the vehicle at the first moment; Based on the positioning information, determining a first road section where the vehicle is located at the first moment; Acquire first lane data of the first road section.

14. The device according to claim 12, It is characterized in that The lane positioning module, when determining a first probability that each lane of the first road section is within the field of view of the vehicle when the vehicle is on the second road section based on the first lane data and the lane line information of each lane line in the lane image, is used to: Determining lane line information of each lane line of the first road section based on the first lane data; Based on the number of lane lines in the lane image, lane line information of each lane line in the lane image and lane line information of each lane line of the first road section, a first probability that each lane of the first road section is within the field of view of the vehicle when it is on the second road section is determined.

15. The device according to claim 14, It is characterized in that The lane positioning module, when determining a first probability that each lane of the first road section is within the field of view of the vehicle when the vehicle is on the second road section based on the number of lane lines in the lane image, lane line information of each lane line in the lane image, and lane line information of each lane line of the first road section, is used to: Determine a lane line combination corresponding to each lane of the first road section, each lane line combination includes lane lines corresponding to a corresponding lane, and the number of lane lines is the same as the number of lane lines in the lane image; For each of the lane line combinations, a degree of matching between the lane line combination and each lane line in the lane image is determined based on lane line information of each lane line in the lane line combination and lane line information of each lane line in the lane image, and a first probability that the lane corresponding to the lane line combination is within the field of view of the vehicle when it is on the second road section is determined based on the matching degree corresponding to the lane line combination.

16. The device according to claim 15, It is characterized in that For each lane line combination, the matching degree between the lane line combination and each lane line in the lane image includes the matching degree between each lane line in the lane line combination and the corresponding lane line in the lane image; The lane positioning module, when determining a first probability that the lane corresponding to the lane line combination is within the field of view of the vehicle when the vehicle is on the second road section based on the matching degree corresponding to the lane line combination, is used to: Determining a lane line weight corresponding to each lane line in the lane image based on lane line information of each lane line in the lane image; Based on the matching degree of each lane line in the lane line combination and the corresponding lane line in the lane image, and the lane line weight corresponding to each lane line in the lane image, a first probability is determined that the lane corresponding to the lane line combination is within the field of view of the vehicle when it is on the second road section.

17. The device according to claim 16, It is characterized in that The lane line information and the lane line information include lane line type and lane line color; For each of the lane line combinations, the lane positioning module, when determining the degree of matching between each lane line in the lane line combination and the corresponding lane line in the lane image based on the lane line information of each lane line in the lane line combination and the lane line information of each lane line in the lane image, is used to: Determine a type matching degree between a lane line type of each lane line in the lane line combination and a lane line type of a corresponding lane line in the lane image; Determine a color match between a lane line color of each lane line in the lane line combination and a lane line color of a corresponding lane line in the lane image; Based on the type matching degree and the color matching degree corresponding to each lane line in the lane line combination, the matching degree of each lane line in the lane line combination and the corresponding lane line in the lane image is determined.

18. The device according to claim 16, It is characterized in that When the lane positioning module determines the lane line weight corresponding to each lane line in the lane image based on the lane line information of each lane line in the lane image, it is used to: Determine a first distance between two leftmost lane lines and a second distance between two rightmost lane lines in the lane image; Determining a road edge line in the lane image based on lane line information of each lane line in the lane image; If the leftmost lane line and the rightmost lane line in the lane image are both road edge lines, or the left lane line and the rightmost lane line are not road edge lines, then each preset weight in the first weight combination is determined as the lane line weight corresponding to each lane line in the lane image; If the first distance is less than a first threshold, and the leftmost lane line is a road edge line and the rightmost lane line is a non-road edge line, then each preset weight in the second weight combination is determined as a lane line weight corresponding to each lane line in the lane image; If the first distance is greater than or equal to the first threshold, and the leftmost lane line is a road edge line and the rightmost lane line is a non-road edge line, then each preset weight in the third weight combination is determined as the lane line weight corresponding to each lane line in the lane image; If the second distance is less than a second threshold, and the rightmost lane line is a road edge line and the leftmost lane line is a non-road edge line, then each preset weight in the fourth weight combination is determined as the lane line weight corresponding to each lane line in the lane image; If the second distance is greater than or equal to the second threshold, and the rightmost lane line is a road edge line and the leftmost lane line is a non-road edge line, then each preset weight in the fifth weight combination is determined as the lane line weight corresponding to each lane line in the lane image.

19. The device according to claim 12, It is characterized in that The lane positioning module, when determining, based on the first lane data and the second lane data, a second probability that the vehicle is in each lane of the second road section at the first moment, is used to: Determine lane line information of each lane line of the first road section and lane distribution information of each lane of the first road section based on the first lane data, and determine lane line information of each lane line of the second road section and lane distribution information of each lane of the second road section based on the second lane data; Determine a target lane based on lane line information of each lane line of the first road section and the second road section and lane distribution information of each lane, and determine a preset probability as a second probability that the vehicle is in the target lane of the first road section at the first moment when the vehicle is in the target lane of the second road section at the second moment; Based on the lane line information of each lane line of the first road section and the second road section, and the lane distribution information of each lane, determine the second probability that the vehicle is in each lane other than the target lane of the first road section at the first moment when the vehicle is in the target lane of the second road section at the second moment, and determine the second probability that the vehicle is in each lane of the first road section at the first moment when the vehicle is in each lane other than the target lane of the second road section at the second moment.

20. The device according to claim 12, It is characterized in that When determining the actual lane in which the vehicle is located at the first moment based on the first probability, the second probability and the third probability, the lane positioning module is used to: Determining a fourth probability that the vehicle travels from each lane of the second road section to each lane of the first road section based on the first probability, the second probability, and the third probability; For each lane of the first road section, determining the maximum probability among the fourth probabilities that the vehicle travels from each lane of the second road section to the lane as the fifth probability that the vehicle is in the lane at the first moment; The lane corresponding to the maximum probability among the fifth probabilities corresponding to the lanes in the first road section is determined as the actual lane where the vehicle is located at the first moment.

21. The device according to claim 12, It is characterized in that When determining the third probability that the vehicle is in each lane of the second road section at the second time, the lane positioning module is used to: If the first moment is an initial moment of lane-level positioning, a third probability that the vehicle is in each lane of the second road section at the second moment is determined based on the lane number of each lane of the first road section.

22. The device according to claim 18, It is characterized in that The lane positioning module, when determining a first distance between two leftmost lane lines in the lane image, is used to: Constructing a first coordinate system based on the positioning information of the vehicle at the first moment; Determine lane line equations of the two leftmost lane lines in the lane image corresponding to the first coordinate system; Based on the lane line equation, a first distance between two leftmost lane lines in the lane image is determined.

23. An electronic device, It is characterized in that comprising a processor and a memory, wherein the processor and the memory are connected to each other; The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 11 when calling the computer program.

24. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 11.

Images