Vehicle positioning method and device, storage medium and electronic equipment

Abstract

Embodiments of the present application provide a vehicle positioning method and device, a storage medium and an electronic device, wherein the method comprises: identifying lane lines in a road image to obtain lane line perception results; the lane line perception results comprise a first left-right topology of a plurality of perceived lane lines perceived by the vehicle at a current time and a first virtual-real attribute of each perceived lane line; in the case that a lane in which the vehicle was located at a previous time of the current time is not determined, real lane line information of the vehicle is obtained from a map; the real lane line information comprises a second left-right topology of a plurality of real lane lines in a field range of a current position of the vehicle and a second virtual-real attribute of each real lane line; in the case that the lane line perception results and the real lane line information are successfully matched, a lane in which the vehicle is currently located is determined; and the current pose of the vehicle is adjusted according to a distance error of the lane in which the vehicle is currently located.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of automatic driving, in particular to a vehicle positioning method and device, a storage medium and an electronic device. BACKGROUND

[0002] With the rapid development of artificial intelligence technology, the automatic driving system has become an important research direction in the automotive industry. The navigation positioning system of the automatic driving vehicle is one of the core components, which must meet the strict requirements of high precision, high resolution, high reliability, low cost, low power consumption and miniaturization, so as to ensure the safe operation of the vehicle in complex environments.

[0003] At present, the GNSS / INS integrated navigation system is the most widely used positioning means in the field of automatic driving. It provides stable and reliable positioning services by integrating the global coverage, all-weather operation and high positioning accuracy advantages of the satellite navigation system (GNSS) and the short-time high-precision and immediacy of the inertial navigation system (INS). However, in environments such as urban canyons, tunnels and underground garages where satellite signals are blocked, the positioning accuracy will decrease significantly, and even completely fail to obtain high-precision positioning. SUMMARY

[0004] Embodiments of the present application provide a vehicle positioning method, device, storage medium and electronic device to at least solve the problem of low positioning accuracy of the automatic driving vehicle in complex environments due to GNSS / INS signal blocking in related technologies.

[0005] According to an aspect of the embodiments of the present application, a vehicle positioning method is provided, comprising: acquiring a road image collected by a vehicle at a current time, and identifying lane lines in the road image to obtain a lane line perception result; the lane line perception result comprises a first left-right topology of a plurality of perceived lane lines perceived by the vehicle at the current time, and a first solid-void attribute of each of the plurality of perceived lane lines; in a case where a lane in which the vehicle was located at a previous time of the current time is not determined, acquiring real lane line information in a domain range of a current position of the vehicle from a map; the real lane line information comprises a second left-right topology of a plurality of real lane lines in the domain range of the current position of the vehicle, and a second solid-void attribute of each of the plurality of real lane lines; matching the lane line perception result and the real lane line information to obtain a matching result; in a case where the matching result represents that the lane line perception result and the real lane line information are successfully matched, determining a lane in which the vehicle is currently located according to the second left-right topology; acquiring a current pose of the vehicle, and adjusting the current pose of the vehicle according to a distance error between a perceived lane line of the lane in which the vehicle is currently located and a real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle.

[0006] According to another aspect of the embodiments of the present application, a vehicle positioning device is provided, comprising: an image acquisition module configured to acquire a road image collected by a vehicle at a current time, and identify lane lines in the road image to obtain a lane line perception result; the lane line perception result comprises a first left-right topology of a plurality of perceived lane lines perceived by the vehicle at the current time, and a first solid-void attribute of each of the plurality of perceived lane lines; a map acquisition module configured to, in a case where a lane in which the vehicle was located at a previous time of the current time is not determined, acquire real lane line information in a domain range of a current position of the vehicle from a map; the real lane line information comprises a second left-right topology of a plurality of real lane lines in the domain range of the current position of the vehicle, and a second solid-void attribute of each of the plurality of real lane lines; a matching module configured to match the lane line perception result and the real lane line information to obtain a matching result; a lane determination module configured to, in a case where the matching result represents that the lane line perception result and the real lane line information are successfully matched, determine a lane in which the vehicle is currently located according to the second left-right topology; and a pose adjustment module configured to acquire a current pose of the vehicle, and adjust the current pose of the vehicle according to a distance error between a perceived lane line of the lane in which the vehicle is currently located and a real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle.

[0007] According to a further aspect of the embodiments of the present application, a computer readable storage medium is also provided, which stores a computer program. The computer program is configured to execute the vehicle positioning method when running.

[0008] According to a further aspect of the embodiments of the present application, an electronic device is also provided, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor. The processor executes the vehicle positioning method through the computer program.

[0009] According to a further aspect of the embodiments of the present application, a computer program product is also provided, which comprises a computer program. The computer program is executed by a processor to implement the steps in any of the vehicle positioning method embodiments.

[0010] Through the embodiments of the present application, the vehicle collects road images in real time and identifies lane lines therein to obtain lane line perception results containing "first left-right topology" and "first virtual-real attribute". This step provides a visual-based positioning reference even when satellite signals are unreliable, ensuring the continuity of vehicle positioning in complex environments. Then, real lane line information of "second left-right topology" and "second virtual-real attribute" within the current position range of the vehicle is obtained from a high-precision map, and the lane line perception results are matched with the real lane line information. When the matching is successful, that is, the "first left-right topology" is consistent with the "second left-right topology", and the "first virtual-real attribute" is consistent with the "second virtual-real attribute", the lane where the vehicle is located is determined, significantly improving the positioning accuracy. Finally, based on the matching result, the distance error between the perceived lane line and the real lane line of the lane where the vehicle is currently located is calculated to adjust the current pose of the vehicle to minimize the positioning error. This dynamic adjustment step not only further improves the positioning accuracy, but also ensures the driving safety and stability of the vehicle during autonomous driving. In summary, through the cooperative work of the above steps, stable and accurate vehicle positioning services can be provided in complex environments where satellite signals are blocked, solving the problem of low positioning accuracy of autonomous vehicles in complex environments due to blocked GNSS / INS signals in related technologies. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 is a hardware structure block diagram of an optional vehicle positioning method according to an embodiment of the present application;

[0012] Figure 2 is a flowchart of an optional vehicle positioning method according to an embodiment of the present application;

[0013] Figure 3is a schematic diagram of an optional first left-right topology according to an embodiment of the present application;

[0014] Figure 4 is a flow chart of an optional vehicle positioning according to an embodiment of the present application;

[0015] Figure 5 is a schematic diagram of an optional vehicle lane changing according to an embodiment of the present application;

[0016] Figure 6 is a structural block diagram of an optional vehicle positioning device according to an embodiment of the present application;

[0017] Figure 7 is a structural block diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative work should fall within the scope of protection of the present application.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] According to an aspect of an embodiment of the present application, a vehicle positioning method is provided. Optionally, in the present embodiment, the above-mentioned vehicle positioning method can be applied in a hardware environment composed of a vehicle terminal 102 and a server 104 as shown in Figure 1 Figure 1 ​As shown, the server 104 is connected with the vehicle terminal 102 through a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal, a database can be set on the server or independently of the server, used to provide data storage services for the server 104, and a cloud computing and / or edge computing service can be configured on the server or independently of the server, used to provide data operation services for the server 104.

[0021] The network can include, but is not limited to, at least one of the following: a wired network, a wireless network. The wired network can include, but is not limited to, at least one of the following: a wide area network, a metropolitan area network, a local area network, and the wireless network can include, but is not limited to, at least one of the following: WIFI, Bluetooth.

[0022] The vehicle positioning method of the embodiment can be executed by the vehicle terminal 102, or jointly executed by the server 104 and the vehicle terminal 102. Taking the vehicle terminal 104 as an example, Figure 2 is a flowchart of an optional vehicle positioning method according to an embodiment of the application, as shown, the flow of the method can include the following steps: Figure 2

[0023] Step S202, acquiring a road image collected by the vehicle at the current time, and identifying lane lines in the road image to obtain a lane line perception result; the lane line perception result includes a first left-right topology of a plurality of perceived lane lines perceived by the vehicle at the current time, and a first solid-void attribute of each of the plurality of perceived lane lines.

[0024] The road image refers to image data of the current driving road collected by a camera or other imaging sensor on the vehicle. The road image includes all visible information of the road entity structure, lane lines, obstacles, traffic signs, etc.

[0025] The lane line refers to a marking line on the road for dividing lanes, which is usually white or yellow, and can be a solid line or a dashed line, used to guide the vehicle to drive and keep safe driving within the lane. The perceived lane line refers to the lane line identified by analyzing the road image through the visual sensor (such as a camera) of the vehicle.

[0026] The first left-right topology refers to the layout of the lane line perceived by the vehicle at the current time through its visual sensor (such as a camera), used to describe the left-right relative relationship between a plurality of perceived lane lines in the current field of view of the vehicle, i.e. the layout structure of the lane line relative to the current position of the vehicle. Through the first left-right topology, it can be determined that the vehicle is driving in which lane and the relative position between the lane lines.

[0027] For example, Figure 3 ​For a schematic diagram of the first left-right topology in one embodiment, as shown in Figure 3 assuming the vehicle is driving on a three-lane road, and the vehicle is in the middle lane. Using the vehicle's camera, the current road image is captured, and through lane line recognition technology, the following information is obtained: a solid line is perceived on the left side of the vehicle, which is marked as L1 and determined as solid; on the left side of L1, a solid line is also perceived, which is marked as L2 and also determined as solid; a dashed line is perceived on the right side of the vehicle, which is marked as R1 and determined as dashed; on the right side of R1, a solid line is also perceived, which is marked as R2 and also determined as solid. Based on this information, the first left-right topology can be constructed:

[0028] L1 (left solid lane line): the first lane line on the left side of the vehicle, which is on the left relative to the current position of the vehicle, and has the attribute of solid.

[0029] L2 (left solid lane line): the lane line on the left side of L1, which is on the left relative to the current position of the vehicle, and has the attribute of solid, indicating that there are two lane lines on the left side of the vehicle.

[0030] R1 (right dashed lane line): the first lane line on the right side of the vehicle, which is on the right relative to the current position of the vehicle, and has the attribute of dashed.

[0031] R2 (right solid lane line): the lane line on the right side of R1, which is on the right relative to the current position of the vehicle, and has the attribute of solid, indicating that there are two lane lines on the right side of the vehicle.

[0032] In some embodiments, the first topology can be represented as a sequence or matrix, where each element represents a lane line and its attribute and relative position. For example, it can be simplified as: left (L1) - solid, left-left (L2) - solid, right (R1) - dashed, right-right (R2) - solid.

[0033] The first left-right topology helps the autonomous driving system to understand and determine the position and direction of the vehicle on the road, especially in GNSS-free or weak-signal environments, where visual information becomes the key basis for positioning. By comparing the first left-right topology at different times, it can also be determined whether the vehicle has changed lanes or adjusted the driving direction.

[0034] The first solid-void attribute refers to the characteristics of perceiving lane lines, distinguishing whether the lane line is a solid line or a dashed line. The first solid-void attribute is usually obtained by actively using the visual sensor (such as a camera) on the vehicle to capture the road image, and then using image processing and machine learning algorithms to achieve the above-mentioned purpose. For example, using lane line detection algorithms such as Hough transform, Canny edge detection, template matching or deep learning models (such as convolutional neural networks CNN) to identify the position of the lane line from the pre-processed road image, wherein these algorithms can detect the boundary of the lane line, including the shape of the solid line or the dashed line; for the detected lane line, further analyze its attribute to determine whether it is a solid line or a dashed line by the following methods:

[0035] 1) Deep learning-based classification: Train a deep learning model, such as using a classifier or a semantic segmentation model, to distinguish between solid and dashed lines by learning the visual features of the lane line, such as line continuity, line segment length, and line density.

[0036] 2) Classification based on geometric features: Analyze the geometric features of the lane line, such as the length and continuity of the line segment. Solid lines usually appear as continuous line segments, while dashed lines appear as intermittent line segments.

[0037] 3) Time series analysis: Determine the attribute of the lane line by analyzing its frequency of appearance and duration in consecutive frames of images. Solid lines should persist in consecutive frames, while dashed lines will intermittently disappear and appear.

[0038] Optionally, the vehicle obtains the road image captured by the camera installed on the vehicle at the current time, and transmits the road image to the vehicle terminal. The vehicle terminal uses image processing and machine learning techniques, such as deep learning convolutional neural networks (CNN) or semantic segmentation models, to analyze the road image and identify the left-right relative relationship between multiple perceived lane lines in the current field of view of the vehicle and the first solid-void attribute of each perceived lane line. The perceived multiple perceived lane lines are arranged in order from left to right or from right to left, and the first left-right topology of the multiple perceived lane lines perceived by the vehicle at the current time is obtained.

[0039] Step S204, in the case where the lane in which the vehicle is located at the previous time of the current time is not determined, obtaining the real lane line information in the domain range of the current position of the vehicle from the map; the real lane line information includes the second left-right topology of multiple real lane lines in the domain range of the current position of the vehicle, and the second solid-void attribute of each real lane line in the multiple real lane lines.

[0040] The current position of the vehicle refers to the coordinate position of the vehicle in geographical space, which is usually obtained through a GPS or GNSS system. However, in environments with poor signal reception, other techniques may be required to assist in determining the position.

[0041] The domain range of the current position of the vehicle refers to an area surrounding the current position of the vehicle, which typically covers all road sections near the vehicle that can affect its driving decisions, for obtaining detailed road information and lane line data.

[0042] The real lane line information refers to the lane line information obtained from map data, including the accurate position, topology, and solid-void attribute of the lane line. The real lane line information is used to compare and verify the information captured by the vehicle sensors in real time (i.e., lane line perception results).

[0043] The second left-right topology refers to the left-right layout relationship of the real lane line described in the map database relative to the current position of the vehicle, providing a reference coordinate system for the autonomous driving system. The representation and example of the second left-right topology are similar to those of the first left-right topology and will not be repeated here.

[0044] The second solid-void attribute refers to the attribute of the real lane line recorded in the map database, including whether the lane line is solid or void, to correct or confirm the attribute of the lane line recognized by the vehicle vision sensor. Unlike the first solid-void attribute, the second solid-void attribute is obtained through data entry and is used to reflect the true solid-void attribute of the real lane line.

[0045] Optionally, in the case where the lane in which the vehicle was located at the previous time of the current time is not determined, the vehicle terminal extracts lane line information of the domain range of the current position from the high-precision map database, including the accurate coordinates, topology, and solid-void attribute of the lane line, and generates, based on the extracted lane line information, a second left-right topology of multiple real lane lines within the domain range of the current position of the vehicle, and a second solid-void attribute of each real lane line in the multiple real lane lines.

[0046] In step S206, the lane line perception results and the real lane line information are matched to obtain a matching result.

[0047] The matching result is a result obtained by comparing and analyzing the lane line perception result and the real lane line information, and is used to determine whether the lane line perception result of the vehicle at the current time is consistent with the real lane line information in the map. The matching result is mainly based on the comparison of two key aspects: the topological structure of the lane line and the virtual-real attribute of the lane line. If the first left-right topological structure in the lane line perception result is consistent with the second left-right topological structure in the real lane line information in the map, that is, the lane line layout in the field of view of the vehicle is the same as the lane line layout at the position in the map, the topological structure of the lane line is matched successfully. If the first virtual-real attribute of each perceived lane line matches the second virtual-real attribute of the corresponding real lane line in the map, the virtual-real attribute of the lane line is matched successfully. When the lane line layout in the field of view of the vehicle (the first left-right topological structure) is consistent with the lane line layout at the position in the map (the second left-right topological structure), and the first virtual-real attribute of each lane line recognized by the vehicle matches the second virtual-real attribute of the corresponding lane line in the map, the matching result is represented as “matched successfully”.

[0048] Optionally, the vehicle terminal performs structural processing on the lane line perception result and the real lane line information obtained in steps S202 and S204 to form a comparable model, and the model includes the topological structure and the virtual-real attribute of the lane line. By comparing the topological structure (left-right relative relationship) and the virtual-real attribute of the lane line perception result and the real lane line information, the matching between the two is realized, and the matching result is obtained.

[0049] In step S208, in the case that the matching result represents that the matching between the lane line perception result and the real lane line information is successful, the lane in which the vehicle is currently located is determined according to the second left-right topological structure.

[0050] Optionally, in the case that the matching result represents that the matching between the lane line perception result and the real lane line information is successful, the vehicle terminal determines the lane in which the vehicle is currently located according to the second left-right topological structure in the domain range of the current position of the vehicle obtained from the map. In the case that the matching result represents that the matching between the lane line perception result and the real lane line information fails, the vehicle terminal determines that it may be caused by the false detection of the first virtual-real attribute of the perceived lane line, and therefore, in this case, the vehicle terminal does not perform processing.

[0051] In step S210, the current pose of the vehicle is obtained, and the current pose of the vehicle is adjusted according to the distance error between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located, to obtain the adjusted current pose of the vehicle.

[0052] The current pose of the vehicle includes information such as the position, direction, and attitude of the vehicle. Generally, the current pose of the vehicle is obtained by interpolating the original pose of the combined inertial navigation output according to the time stamp of the lane line perception result at the current time.

[0053] The distance error refers to the positional deviation between the perceived lane line and the real lane line. The distance error is a key indicator for evaluating the positioning accuracy of the vehicle, and the smaller the distance error, the more accurate the positioning.

[0054] Optionally, the vehicle terminal obtains the current pose of the vehicle, compares the positional difference between the perceived lane line of the vehicle in the current lane and the real lane line of the vehicle in the current lane in the map, calculates the distance error between the two, and iteratively updates the current pose of the vehicle according to the distance error using a nonlinear least squares method or other optimization algorithms to obtain a final adjusted pose. The final adjusted pose will be used for navigation and control of the vehicle.

[0055] In some embodiments, obtaining the current pose of the vehicle includes the following steps: in the case of poor combined inertial navigation (such as GPS or GNSS system) signal, obtaining the original pose output by the combined inertial navigation; determining the time range between the current time of the vehicle and the time stamp of the original pose, and interpolating the pose corresponding to each time stamp in the time range according to the original pose to obtain the current pose of the vehicle; in the case of good combined inertial navigation (such as GPS or GNSS system) signal, obtaining the current pose of the vehicle through the combined inertial navigation.

[0056] By the above steps S202 to S210, the vehicle collects road images in real time and identifies lane lines therein, obtaining lane line perception results containing "first left-right topology" and "first virtual-real attribute". This step provides a visual-based positioning reference even when satellite signals are unreliable, ensuring the continuity of vehicle positioning in complex environments. Then, the "second left-right topology" and "second virtual-real attribute" of the real lane line information within the current position field of the vehicle are obtained from the high-precision map, and the lane line perception results are matched with the real lane line information. When the matching is successful, that is, the "first left-right topology" is consistent with the "second left-right topology", and the "first virtual-real attribute" is consistent with the "second virtual-real attribute", the lane where the vehicle is located is determined, and the positioning accuracy is significantly improved. Finally, based on the matching result, the distance error between the perceived lane line and the real lane line of the current lane where the vehicle is located is calculated to adjust the current pose of the vehicle to minimize the positioning error. This dynamic adjustment step not only further improves the positioning accuracy, but also ensures the driving safety and stability of the vehicle during autonomous driving. In summary, through the cooperative work of the above steps, the embodiments of the present application can achieve the effect of providing stable and accurate vehicle positioning service in complex environments where satellite signals are blocked, solving the problem of low positioning accuracy of autonomous vehicles in complex environments due to GNSS / INS signal blockage in related technologies.

[0057] In one example embodiment, the first left-right topology includes the left-right relative relationship between the current position of the vehicle and each perceived lane line, and the second left-right topology includes the left-right relative relationship between the current position of the vehicle and each real lane line.

[0058] The left-right relative relationship in the first left-right topology is based on the lane line information perceived by the vehicle at the current time through the camera. The left-right relative relationship in the first left-right topology describes the left-right position of each perceived lane line relative to the vehicle center line. For example, the lane line on the left side of the vehicle can be identified as the first lane line on the left side, and the lane line on the right side of the vehicle can be identified as the first lane line on the right side.

[0059] The left-right relative relationship in the second left-right topology is obtained from the map data and describes the real lane line information within the current position field of the vehicle. The left-right relative relationship in the second left-right topology also describes the left-right position of each real lane line relative to the current position of the vehicle. For example, the map information may indicate that there are two lanes on the left side of the vehicle and one lane on the right side.

[0060] In some embodiments, the matching of the lane line perception results and the real lane line information obtains a matching result, including:

[0061] I. In the case that the lane line perception result and the real lane line information also include road boundary labels, extract the target perception lane line marked by the road boundary label from the multiple perception lane lines, and extract the target real lane line marked by the road boundary label from the multiple real lane lines.

[0062] wherein the road boundary label is a special information marked for the road edge or boundary lane line, used to distinguish the edge of the road and the lane line inside the road. In the lane line perception result perceived by the vehicle, the road boundary label is usually stored together with the coordinates of the perception lane line, the first left-right topology, the first virtual-real attribute and other data. In the high-precision map, the road boundary label is usually stored together with the coordinates of the real lane line, the second left-right topology, the second virtual-real attribute and other data, and provided for use by the autonomous driving system. The road boundary is a strong constraint relationship for the lane line, and according to the ID of the lane line where the road boundary is located, the current lane where the vehicle is located can be reversely calculated. For example, if the “right-right-road edge” is perceived, and the rightmost lane line in the map is also a road edge, it can be inferred that the current ego vehicle is located in the second lane line from the right, and the lane line ID can also be directly determined.

[0063] It should be noted that: the road boundary, as a fixed reference point in the road structure, has obvious characteristics and is easy to capture by the camera. The target lane line marked by the road boundary label can significantly enhance the matching accuracy of the lane line perception result and the real lane line information in the map data. This is because the recognition of the road boundary is usually more stable than the recognition of the lane line and is not easily affected by environmental factors such as light and weather, so as a strong constraint condition, it can reduce the uncertainty in the matching process and improve the reliability of the matching result.

[0064] The target perception lane line refers to the lane line that is closest to the current position of the vehicle or related to the road boundary, which is selected from the multiple perception lane lines in the current field of view of the vehicle through the road boundary label. The target perception lane line is a key object for lane line information matching.

[0065] The target real lane line refers to the real lane line information extracted from the map database, which corresponds to the position of the target perception lane line and has a road boundary label. It contains the accurate coordinates, topology relationship and virtual-real attribute of the target lane line, and is used for comparison and verification with the perception lane line information.

[0066] The first left-right relative relationship describes the left-right orientation relationship between the current position of the vehicle and the target perception lane line, i.e., the target perception lane line is on the left side or the right side of the vehicle. This information helps to determine the relative position of the vehicle on the road.

[0067] The second left-right relative relationship describes the left-right orientation relationship between the current position of the vehicle and the target real lane line, and is also used to determine the relative position of the vehicle on the map, and is an important reference for verifying the accuracy of positioning.

[0068] Optionally, Figure 4 A flowchart for vehicle positioning in an embodiment is shown in FIG. 1, in which case the lane line perception result and the real lane line information also include road boundary labels, the vehicle terminal detects lane lines in the road image through an image processing algorithm to identify the target perception lane line marked as a road boundary, and from the high-precision map data, according to the current position of the vehicle, finds and extracts the target real lane line marked as a road boundary. Figure 4

[0069] II. Comparing the first left-right relative relationship between the current position of the vehicle and the target perception lane line with the second left-right relative relationship between the current position of the vehicle and the target real lane line, and comparing the first virtual-real attribute of the target perception lane line with the second virtual-real attribute of the target real lane line.

[0070] Optionally, as shown in FIG. 2, the vehicle terminal compares the first left-right relative relationship between the current position of the vehicle and the target perception lane line with the second left-right relative relationship between the current position of the vehicle and the target real lane line, checks whether they are consistent, and at the same time, compares the first virtual-real attribute of the target perception lane line with the second virtual-real attribute of the target real lane line, and confirms whether they match. Figure 4

[0071] III. In the case where the first left-right relative relationship matches the second left-right relative relationship, and the first virtual-real attribute of the target perception lane line matches the second virtual-real attribute of the target real lane line, it is determined that the matching result represents a successful match between the lane line perception result and the real lane line information.

[0072] Optionally, as shown in FIG. 3, if the first left-right relative relationship and the second left-right relative relationship match, and the first virtual-real attribute of the target perception lane line matches the second virtual-real attribute of the target real lane line, the vehicle terminal considers that the lane line perception result and the real lane line information match successfully. If the first left-right relative relationship and the second left-right relative relationship do not match, and / or the first virtual-real attribute of the target perception lane line does not match the second virtual-real attribute of the target real lane line, the vehicle terminal does not process. Figure 4

[0073] ​​​By using the road boundary label as a strong constraint condition, the target perception lane line and the target real lane line are extracted from the perception lane line and the real lane line for matching. Since the road boundary has stable features and a clear position, it is a strong constraint information in the road structure. By using the road boundary label, the correspondence between the target lane line and the map data can be ensured to be more accurate, thereby improving the accuracy of lane line matching. This strong constraint-based matching strategy effectively reduces the interference of environmental factors on lane line recognition and enhances the reliability of the matching process. Even in complex conditions such as poor light and blurred lane lines, lane matching can be stably performed. Further, only the left-right relative relationship and the solid-void attribute between the target perception lane line and the target real lane line marked by the road boundary label are compared, rather than full-image matching, which significantly reduces the amount of calculation and reduces the demand for computing resources.

[0074] In one example embodiment, the lane line perception result and the real lane line information are matched to obtain a matching result, and the method further comprises:

[0075] I. In the case that at least one of the lane line perception result and the real lane line information does not include a road boundary label, an augmented matrix is constructed based on the lane line perception result and the real lane line information. Each row of the augmented matrix represents each perception lane line, each column of the augmented matrix represents each real lane line, and an element of the augmented matrix represents a matching degree between a first solid-void attribute of the perception lane line represented by the corresponding row and a second solid-void attribute of the real lane line represented by the corresponding column.

[0076] If the lane line perception result or the real lane line information does not contain the road boundary label, it means that the vehicle terminal cannot directly simplify the matching process through boundary information, and needs to use a more complex matching strategy.

[0077] The calculation of the matching degree can be based on various factors, such as the lane line attributes being completely the same, the matching degree being high, and the lane line attributes being different, the matching degree being low. Specifically, a real number between 0 and 1 can be used to represent the matching degree, 1 representing complete matching and 0 representing complete non-matching.

[0078] Optionally, as Figure 4As shown, when at least one of the lane line perception results and the actual lane line information does not include road boundary labels, the vehicle terminal determines each perceived lane line in the lane line perception results and each actual lane line in the actual lane line information. Each perceived lane line and actual lane line is assigned a unique row and column index. The vehicle terminal calculates the matching degree between the perceived lane line and the actual lane line based on the first solid / dash attribute (e.g., solid line or dashed line) and the second solid / dash attribute of the actual lane line. The vehicle terminal constructs an augmented matrix, where each element represents the matching degree between the corresponding perceived lane line and the actual lane line. The rows of the matrix represent perceived lane lines, the columns represent actual lane lines, and the values ​​of the matrix elements represent the matching degree.

[0079] Second, an optimization algorithm is used to solve the augmented matrix. In the case of only one solution, the matching result is determined to indicate that the lane line perception result and the real lane line information are successfully matched.

[0080] The optimization algorithm is used to solve the augmented matrix and find the optimal matching scheme between perceived lane lines and real lane lines, maximizing the overall matching degree or similarity of the pairings. Common optimization algorithms include the Hungarian algorithm (suitable for solving the maximum matching problem in bipartite graphs), linear programming, dynamic programming, and genetic algorithms. During the optimization algorithm's solution process, if the augmented matrix has only one solution (i.e., there exists a unique way to achieve the optimal matching degree between all perceived lane line results and real lane line information), then this solution indicates a successful match between the perceived lane line results and real lane line information. In this case, the matching between the perceived lane line results and map data is the most accurate, without the uncertainty caused by multiple solutions. Once the optimization algorithm confirms that there is only one solution, the matching result between the perceived lane line results and real lane line information represents a successful match. This means that each perceived lane line can find a corresponding real lane line in the map, and this correspondence has the highest matching degree. Through this process, even without road boundary labels, the optimal match between perceived lane lines and real lane lines can be found using virtual and real attributes and the augmented matrix, thereby ensuring the accuracy and reliability of vehicle positioning.

[0081] Optionally, such as Figure 4 As shown, the vehicle terminal selects a suitable optimization algorithm, such as the Hungarian algorithm or linear programming algorithm, to find all possible matching combinations in the augmented matrix through the optimization algorithm, evaluate the total matching degree, and determine the matching combination with the highest total matching degree as the optimal matching scheme when there is only one matching combination with the highest total matching degree. The matching result indicates that the lane line perception result and the real lane line information are successfully matched.

[0082] By solving the augmented matrix through the optimization algorithm, the best matching scheme between the perceived lane lines and the real lane lines is found through mathematical optimization method. In the case of only one set of solutions, it can be determined that the matching between the lane line perception result and the real lane line information is successful, thereby ensuring the accuracy and reliability of the vehicle positioning. Even in the environment without road boundary label, high-precision vehicle positioning can be realized through the comparison of virtual and real attributes.

[0083] In an example embodiment, the lane line perception result further includes a first identifier of each perceived lane line, and the real lane line information further includes a second identifier of each real lane line. The first identifier of each perceived lane line is used to mark the perceived lane line within the current visual range of the vehicle; and the second identifier of each real lane line is used to mark each real lane line.

[0084] The first identifier refers to a unique number or mark generated by the vehicle in real time according to the road image collected at the current time, which is used to identify the perceived lane line within the visual range of the vehicle. The first identifier helps the vehicle track the change of the lane line, so as to determine whether the vehicle changes lane or remains in the same lane.

[0085] The second identifier refers to a unique number or mark assigned to each real lane line in the high-precision map, which is used to distinguish and identify different lane lines in the map database. The second identifier is static and reflects the position and attribute of the real lane line in the map data, and is not affected by the change of the external environment. The second identifier is included in the real lane line information, which helps the system to determine the accurate lane position of the vehicle on the map.

[0086] The perceived lane line within the current visual range of the vehicle refers to the lane line information recognized and extracted from the current road image collected by the vision sensor (such as a camera) carried by the vehicle. The perceived lane line within the current visual range of the vehicle is directly observed by the vehicle, including their position, first virtual-real attribute and first identifier.

[0087] In some embodiments, the vehicle positioning method further includes:

[0088] I. In the case where the lane in which the vehicle was located at the previous time of the current time has been determined, the first identifier of the lane line perceived by the vehicle at the current time is compared with the first identifier of the lane line perceived by the vehicle at the previous time of the current time.

[0089] Optionally, as Figure 4As shown, when the lane in which the vehicle was located at the previous moment is already determined, the vehicle terminal identifies the lane line from the road image collected at the current moment, obtains the lane line perception result containing the first identifier, and compares the first identifier of the lane line perceived at the current moment with the first identifier recorded by the vehicle at the previous moment.

[0090] 2. If the first identifier of the lane line perceived by the vehicle at the current moment is different from the first identifier of the lane line perceived by the vehicle at the previous moment, the lane change direction of the vehicle is determined according to the first left and right topology.

[0091] Specifically, if the first identifier of the lane line perceived at the current moment is consistent with the first identifier recorded by the vehicle at the previous moment, it is determined that the vehicle may remain in the same lane; if the first identifier of the lane line perceived at the current moment is inconsistent with the first identifier recorded by the vehicle at the previous moment, it is determined that the vehicle has changed lanes.

[0092] For example, Figure 5 This is a schematic diagram of a vehicle changing lanes in one embodiment, such as... Figure 5 As shown, suppose an autonomous vehicle is traveling in the middle lane of a city street with three lanes. A camera in front of the vehicle captures real-time road images and identifies lane markings. At a certain point in time, the vehicle's lane recognition system identifies the three lane markings: the left lane, the right lane, and the rightmost lane, and assigns them different first identifiers. For example, the left lane is labeled L1, the right lane is labeled R1, and the rightmost lane is labeled R2. When the vehicle changes lanes from the middle lane to the right lane, R1, originally labeled as the right lane, becomes the first identifier L1 for the left lane, and R2, originally labeled as the rightmost lane, becomes the first identifier R1 for the right lane. By comparing the first identifiers before and after the lane change, it can be determined whether the vehicle has changed lanes, and if so, whether the change was to the right.

[0093] Optionally, if the first identifier of the lane line perceived by the vehicle at the current moment is different from the first identifier of the lane line perceived by the vehicle at the previous moment, the vehicle terminal determines the position change of the lane line relative to the vehicle (such as changing from the left lane line to the right lane line) based on the first left and right topology collected at the current moment, thereby determining the direction of the vehicle's lane change (changing lanes to the left or to the right).

[0094] Third, determine the current lane of the vehicle based on the second left and right topology and the direction of lane change.

[0095] Optionally, the vehicle terminal determines the lane in which the vehicle is currently located according to the determined lane-changing direction and the second left-right topology in the real lane line information corresponding to the current time.

[0096] Four, obtaining the current pose of the vehicle, and adjusting the current pose of the vehicle according to the distance error between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located, to obtain the adjusted current pose of the vehicle.

[0097] Optionally, the vehicle terminal obtains the current pose of the vehicle, compares the position difference between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located in the map, calculates the distance error therebetween, and iteratively updates the current pose of the vehicle according to the distance error using a nonlinear least squares method or other optimization algorithm to obtain a final adjusted pose, which will be used for navigation and control of the vehicle.

[0098] Through the embodiment, in the case that the lane in which the vehicle was located at the previous time of the current time has been determined, the first identifier of the perceived lane line perceived at the adjacent time is compared in real time, whether the vehicle has performed a lane-changing action can be identified in real time, the first identifier of the perceived lane line is introduced, the driving trajectory of the vehicle can be tracked more accurately, and it is ensured that the vehicle can accurately identify a new lane when changing lanes, and safety hazards caused by positioning deviation are avoided.

[0099] In one example embodiment, the vehicle positioning method described above further comprises:

[0100] One, in the case that the first identifier of the lane line perceived by the vehicle at the current time is the same as the first identifier of the lane line perceived by the vehicle at the previous time of the current time, the lane in which the vehicle was located at the previous time of the current time is determined as the lane in which the vehicle is currently located.

[0101] Optionally, in the case that the first identifier of the lane line perceived by the vehicle at the current time is the same as the first identifier of the lane line perceived by the vehicle at the previous time of the current time, the vehicle terminal determines that the vehicle has not changed lanes, and directly determines the lane in which the vehicle was located at the previous time as the lane in which the vehicle is currently located.

[0102] Two, obtaining the current pose of the vehicle, and adjusting the current pose of the vehicle according to the distance error between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located, to obtain the adjusted current pose of the vehicle.

[0103] Optionally, the vehicle terminal acquires the current pose of the vehicle, compares the position difference between the perceived lane line of the vehicle in the current lane and the real lane line of the vehicle in the current lane in the map, calculates the distance error between the two, iteratively updates the current pose of the vehicle according to the distance error using a nonlinear least squares method or other optimization algorithm, and obtains a final adjusted pose. The final adjusted pose will be used for navigation and control of the vehicle.

[0104] Through the embodiment, in the case that the first identifier of the lane line perceived by the vehicle at the current time is the same as the first identifier of the lane line perceived by the vehicle at the last time of the current time, it is determined that the vehicle does not change lanes, and at this time, the lane in which the vehicle is located at the last time of the current time is determined as the current lane of the vehicle. The complete lane matching process can be avoided, thereby significantly reducing the consumption of computing resources and improving the operation efficiency of the system.

[0105] In one example embodiment, the lane line in the road image is identified to obtain a lane line perception result, comprising:

[0106] The lane line in the road image is identified to obtain a plurality of perceived lane lines; each perceived lane line comprises a first virtual-real attribute; each perceived lane line is sorted according to the left-right relative relationship between the current position of the vehicle and each perceived lane line to obtain a sorting result; in the case that the sorting result represents that there is a missed lane line, the missed lane line is determined according to the sorting result, and the missed lane line and each perceived lane line are re-sorted to obtain a first left-right topology.

[0107] The missed lane line refers to a lane line that is not identified in the perception process of the lane line due to the limitation of image quality, lighting conditions, vehicle field of view or other factors. After each perceived lane line is sorted in the embodiment of the application, it is determined whether there is a missed lane line by judging whether the left and right lane lines of each lane exist. For example, the lane line perception result comprises: {“left-left-solid line”, “right-solid line”, “right-right-road edge”}, wherein the left lane line is missing, and the missing left lane line is the missed lane line. The missing left lane line is filled in, and the first virtual-real attribute of the missing left lane line is marked as unknown.

[0108] Optionally, the vehicle terminal uses image processing and machine learning techniques, such as deep learning convolutional neural networks (CNN) or semantic segmentation models, to analyze the road image, identify the left-right relative relationship between multiple perceived lane lines in the current field of view of the vehicle and the first virtual-real attribute of each perceived lane line, and sequentially arrange the multiple perceived lane lines in the order from left to right or from right to left to obtain a sorting result; in the case that there is a situation that the left and right lane lines of a lane are missing in the sorting result, it is determined that the sorting result represents that there is a missing lane line, at this time, according to the sorting result, the missing lane line is determined, and the missing lane line and each perceived lane line are re-arranged to obtain a first left-right topology.

[0109] Through the embodiment, in the case that there is a missing lane line, the missing lane line is determined according to the sorting result, and the missing lane line is filled in, which can ensure that all lane lines in the field of view of the vehicle are accurately acquired, improve the completeness of lane line identification, and thus improve the accuracy of vehicle positioning.

[0110] In one example embodiment, the current pose of the vehicle is adjusted according to the distance error between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle, including:

[0111] The current pose of the vehicle is iteratively updated using a nonlinear least squares method to minimize the target function; the target function is the sum of squared residuals of the distance error between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located; the pose that minimizes the target function is determined as the adjusted current pose of the vehicle.

[0112] The nonlinear least squares method is an iterative optimization algorithm for adjusting the vehicle pose to minimize the distance error between the perceived lane line and the real lane line, thereby improving the accuracy of vehicle positioning.

[0113] Minimizing the target function means that the adjusted vehicle pose is closest to the position of the real lane line, which improves the accuracy of positioning.

[0114] Optionally, the vehicle terminal extracts boundary points of the real lane line of the current lane in the map according to the current position of the vehicle and the current lane, and extracts boundary points of the perceived lane line of the current lane in the perceived lane line, determines the correspondence between the boundary points of the real lane line of the current lane and the boundary points of the perceived lane line of the current lane, constructs a target function according to the distance error between the perceived lane line and the real lane line, and the target function is expressed in the form of residual sum of squares, that is, the square sum of the distance error between all corresponding boundary points of the perceived lane line and the real lane line, and starts the iterative optimization process by using the nonlinear least squares method with the current pose of the vehicle as the starting point. In each iteration, the nonlinear least squares method will predict the position of the lane line based on the current pose parameter, then calculate the residual between the predicted position and the position of the real lane line, and through gradient descent or other optimization strategies, the algorithm will adjust the pose parameter to reduce the value of the target function (residual sum of squares), until the target function reaches the set convergence condition, or reaches the maximum iteration number, and the pose that minimizes the target function is determined as the adjusted current pose of the vehicle.

[0115] Through the embodiment, the nonlinear least squares method continuously adjusts the current pose of the vehicle through iterative optimization to minimize the distance error between the perceived lane line and the real lane line on the map, and can gradually correct the pose estimation until the best matching state is reached, thereby significantly improving the accuracy of vehicle positioning.

[0116] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the application is not limited by the action sequence described, because according to the application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the application.

[0117] From the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and necessary general hardware servers, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk, an optical disk), and includes a plurality of instructions for causing an end device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the method of each embodiment of the present application.

[0118] According to another aspect of the embodiments of the present application, there is also provided a vehicle positioning apparatus for implementing the vehicle positioning method provided in the above-described embodiments, which has been described above and will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

[0119] Figure 6 is a structural block diagram of an optional vehicle positioning apparatus according to the embodiments of the present application, as shown in Figure 6 The apparatus can include:

[0120] An image acquisition module 601 is configured to acquire a road image collected by the vehicle at a current time, and identify lane lines in the road image to obtain a lane line perception result. The lane line perception result includes a first left-right topology of a plurality of perceived lane lines perceived by the vehicle at the current time, and a first solid-void attribute of each of the plurality of perceived lane lines.

[0121] A map acquisition module 602 is configured to acquire, in a case where a lane in which the vehicle was located at a previous time of the current time is not determined, real lane line information within a domain range of a current position of the vehicle from a map. The real lane line information includes a second left-right topology of a plurality of real lane lines within the domain range of the current position of the vehicle, and a second solid-void attribute of each of the plurality of real lane lines.

[0122] A matching module 603 is configured to match the lane line perception result and the real lane line information to obtain a matching result.

[0123] A lane determination module 604 is configured to, in a case where the matching result represents a successful matching between the lane line perception result and the real lane line information, determine a lane in which the vehicle is currently located according to the second left-right topology.

[0124] A pose adjustment module 605 is configured to acquire a current pose of the vehicle, and adjust the current pose of the vehicle according to a distance error between a perceived lane line of the lane in which the vehicle is currently located and a real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle.

[0125] In an example embodiment, the first left-right topology includes a left-right relative relationship between the current position of the vehicle and each of the perceived lane lines, and the second left-right topology includes a left-right relative relationship between the current position of the vehicle and each of the real lane lines; the matching module 603 is further configured to, in a case where the lane line perception result and the real lane line information further include road boundary labels, extract a target perceived lane line marked by a road boundary label from the plurality of perceived lane lines, and extract a target real lane line marked by a road boundary label from the plurality of real lane lines; compare the first left-right relative relationship between the current position of the vehicle and the target perceived lane line with the second left-right relative relationship between the current position of the vehicle and the target real lane line, and compare the first virtual-real attribute of the target perceived lane line with the second virtual-real attribute of the target real lane line; and in a case where the first left-right relative relationship matches the second left-right relative relationship, and the first virtual-real attribute of the target perceived lane line matches the second virtual-real attribute of the target real lane line, determine that the matching result represents a successful match between the lane line perception result and the real lane line information.

[0126] In an example embodiment, the matching module 603 is further configured to, in a case where at least one of the lane line perception result and the real lane line information does not include road boundary labels, construct an augmented matrix based on the lane line perception result and the real lane line information; each row of the augmented matrix represents each perceived lane line, each column of the augmented matrix represents each real lane line, and an element of the augmented matrix represents a matching degree between a first virtual-real attribute of a perceived lane line represented by a corresponding row and a second virtual-real attribute of a real lane line represented by a corresponding column; and solve the augmented matrix using an optimization algorithm, and in a case where there is only one solution, determine that the matching result represents a successful match between the lane line perception result and the real lane line information.

[0127] In an example embodiment, the lane line perception result further comprises a first identifier of each perceived lane line, the real lane line information further comprises a second identifier of each real lane line, the first identifier of each perceived lane line is used to mark the perceived lane line within the current field of view of the vehicle, and the second identifier of each real lane line is used to mark each real lane line. The map obtaining module 602 is further configured to, in a case where the lane in which the vehicle was located at a previous time of the current time has been determined, compare the first identifier of the lane line perceived by the vehicle at the current time with the first identifier of the lane line perceived by the vehicle at the previous time of the current time, determine a lane changing direction of the vehicle according to the first left-right topology in a case where the first identifier of the lane line perceived by the vehicle at the current time is different from the first identifier of the lane line perceived by the vehicle at the previous time of the current time, determine the lane in which the vehicle is currently located according to the second left-right topology and the lane changing direction, obtain the current pose of the vehicle, and adjust the current pose of the vehicle according to a distance error between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle.

[0128] In an example embodiment, the map obtaining module 602 is further configured to, in a case where the first identifier of the lane line perceived by the vehicle at the current time is the same as the first identifier of the lane line perceived by the vehicle at the previous time of the current time, determine the lane in which the vehicle was located at the previous time of the current time as the lane in which the vehicle is currently located, obtain the current pose of the vehicle, and adjust the current pose of the vehicle according to a distance error between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle.

[0129] In an example embodiment, the image obtaining module 601 is configured to identify lane lines in a road image to obtain a plurality of perceived lane lines, each perceived lane line comprising a first virtual-real attribute, sort each perceived lane line according to a left-right relative relationship between a current position of the vehicle and each perceived lane line to obtain a sorting result, and in a case where the sorting result indicates that there is a missed lane line, determine the missed lane line according to the sorting result, and re-sort the missed lane line and each perceived lane line to obtain a first left-right topology.

[0130] In an example embodiment, the pose adjusting module 605 is further configured to iteratively update the current pose of the vehicle using a nonlinear least squares method to minimize a target function, the target function being a sum of squares of residuals of a distance error between the perceived lane line of the lane in which the vehicle is currently located and the real lane line of the lane in which the vehicle is currently located, and determine the pose that minimizes the target function as the adjusted current pose of the vehicle.

[0131] It should be noted that the above modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules can be run in the hardware environment shown in Figure 1 , which includes a network environment, by software or by hardware.

[0132] According to another aspect of the embodiments of the present application, a storage medium is further provided. Optionally, in the present embodiment, the above storage medium can be used to store program codes for executing any of the above vehicle positioning methods.

[0133] Optionally, in the present embodiment, the above storage medium can be located on at least one of the network devices in the network shown in the above embodiments.

[0134] Optionally, in the present embodiment, the storage medium is configured to store program codes for executing any of the above vehicle positioning methods.

[0135] Optionally, the specific examples in the present embodiment can refer to the examples described in the above embodiments, and the present embodiment will not be described here.

[0136] Optionally, in the present embodiment, the above storage medium can include, but is not limited to, a U disk, a ROM, a RAM, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0137] According to another aspect of the embodiments of the present application, an electronic device for implementing the above vehicle positioning method is further provided. The electronic device can be a smart device, and can be a server, a terminal, or a combination thereof.

[0138] Figure 7 is a structural block diagram of an optional electronic device according to the embodiments of the present application, as shown in Figure 7 , which includes a processor 702, a communication interface 704, a memory 706 and a communication bus 708, wherein the processor 702, the communication interface 704 and the memory 706 complete mutual communication through the communication bus 708, wherein,

[0139] the memory 706 is configured to store computer programs;

[0140] the processor 702 is configured to execute the computer programs stored in the memory 706, and implement the program codes of any of the above vehicle positioning methods.

[0141] Optionally, the communication bus can be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 7 only one bus or one type of bus is shown with a thick line, but this does not indicate that there is only one bus or only one type of bus. The communication interface is used for communication between the electronic device and other devices.

[0142] The memory can include a RAM and can also include a non-volatile memory, for example, at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0143] As an example, the aforementioned memory 706 can include, but is not limited to, each module in the aforementioned vehicle positioning device. In addition, other module units in the aforementioned vehicle positioning device can also be included, but are not limited to, and will not be described in this example.

[0144] The aforementioned processor can be a general-purpose processor, which can include, but is not limited to, a CPU (Central Processing Unit), an NP (Network Processor), and the like; it can also be a DSP (Digital Signal Processing), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0145] Optionally, the specific examples in the present embodiment can refer to the examples described in the above-described embodiments, and the present embodiment will not be described here.

[0146] Those of ordinary skill in the art can understand that Figure 7 The structure shown is only schematic, and the device implementing the above-mentioned vehicle positioning method can be a terminal device, which can be a smart phone (such as an Android phone, an iOS phone, and the like), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, and the like. Figure 7 This does not limit the structure of the electronic device. For example, the electronic device can also include more thanFigure 7 more or less components than those shown, such as no network interface, one network interface, multiple network interfaces, etc., or a different configuration of components such as an external interface directly to another device or directly to a network (e.g., bus interface, personal area network interface, home area network interface, etc.). Similarly, the single processor 1010 might include multiple processors 1010 or be replaced with multiple processors 1010 or parts of it such as an external controller. Figure 7

[0147] Embodiments of the present application also provide a computer program product, which includes a computer program. The computer program is executed by a processor to implement the steps in any of the method embodiments.

[0148] Embodiments of the present application also provide another computer program product, which includes a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps in any of the method embodiments.

[0149] Embodiments of the present application also provide a computer program, which includes computer instructions. The computer instructions are stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium. The processor executes the computer instructions to cause the computer device to perform the steps in any of the method embodiments.

[0150] Those skilled in the art can understand that all or part of the steps in the above-described various embodiments can be completed by a program instructing related hardware of a terminal device, and the program can be stored in a computer readable storage medium, which can include a flash disk, a ROM, a RAM, a magnetic disk or an optical disk, etc.

[0151] The above-mentioned sequence numbers of embodiments of the present application are only for description, and do not represent advantages or disadvantages of the embodiments.

[0152] The integrated units in the above-described embodiments, if realized in the form of software function units and sold or used as independent products, can be stored in the above-mentioned computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or partly, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0153] In the above-described embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0154] ​In several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other manners. Of course, the described apparatus embodiments are merely schematic, and the division of units is merely logical function division, and there can be other division manners in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, units or modules, and can be in electrical, mechanical or other forms.

[0155] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the solutions provided in the embodiments.

[0156] In addition, each functional unit in the embodiments of the present application can be integrated in a processing unit, or each unit can exist physically as a separate unit, or at least two units can be integrated in a unit. The integrated unit can be implemented in a form of hardware, or in a form of software functional unit.

[0157] The above descriptions are merely preferred embodiments of the present application, and it should be pointed out that, for those skilled in the art, some improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A vehicle positioning method characterized by, The method comprises: acquiring a road image collected by a vehicle at a current time, and identifying lane lines in the road image to obtain a lane line perception result; the lane line perception result comprises a first left-right topology of a plurality of perceived lane lines perceived by the vehicle at the current time, and a first virtual-real attribute of each of the plurality of perceived lane lines; in a case where a lane in which the vehicle was located at a previous time of the current time is not determined, acquiring real lane line information in a field range of a current position of the vehicle from a map; the real lane line information comprises a second left-right topology of a plurality of real lane lines in the field range of the current position of the vehicle, and a second virtual-real attribute of each of the plurality of real lane lines; matching the lane line perception result and the real lane line information to obtain a matching result; in a case where the matching result represents a successful matching between the lane line perception result and the real lane line information, determining a lane in which the vehicle is currently located according to the second left-right topology; acquiring a current pose of the vehicle, and adjusting the current pose of the vehicle according to a distance error between a perceived lane line of the lane in which the vehicle is currently located and a real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle; wherein the matching the lane line perception result and the real lane line information to obtain a matching result comprises, in a case where at least one of the lane line perception result and the real lane line information does not comprise a road boundary label, constructing an augmented matrix based on the lane line perception result and the real lane line information; each row of the augmented matrix represents each perceived lane line, each column of the augmented matrix represents each real lane line, and an element of the augmented matrix represents a matching degree between a first virtual-real attribute of a perceived lane line represented by a corresponding row and a second virtual-real attribute of a real lane line represented by a corresponding column; solving the augmented matrix by using an optimization algorithm, and in a case where there is only one set of solutions, determining that the matching result represents a successful matching between the lane line perception result and the real lane line information.

2. The method of claim 1, wherein, the first left-right topology comprises a left-right relative relationship between the current position of the vehicle and each perceived lane line, and the second left-right topology comprises a left-right relative relationship between the current position of the vehicle and each real lane line; the matching the lane line perception result and the real lane line information to obtain a matching result further comprises: in a case where the lane line perception result and the real lane line information further comprise the road boundary label, extracting a target perceived lane line marked by the road boundary label from the plurality of perceived lane lines, and extracting a target real lane line marked by the road boundary label from the plurality of real lane lines; comparing a first left-right relative relationship between the current position of the vehicle and the target perceived lane line with a second left-right relative relationship between the current position of the vehicle and the target real lane line, and comparing a first virtual-real attribute of the target perceived lane line with a second virtual-real attribute of the target real lane line; in a case where the first left-right relative relationship matches the second left-right relative relationship and the first virtual-real attribute of the target perceived lane line matches the second virtual-real attribute of the target real lane line, determining that the matching result represents a successful matching between the lane line perception result and the real lane line information.

3. The method of claim 1, wherein, the lane line perception result further comprises a first identifier of each perceived lane line, and the real lane line information further comprises a second identifier of each real lane line, the first identifier of each perceived lane line being used to mark a perceived lane line within a current field of view of the vehicle; the second identifier of each real lane line is used to mark each real lane line; the method further comprises: in a case where a lane in which the vehicle is located at a previous time of a current time has been determined, comparing a first identifier of a lane line perceived by the vehicle at the current time with a first identifier of a lane line perceived by the vehicle at the previous time of the current time; in a case where the first identifier of the lane line perceived by the vehicle at the current time is different from the first identifier of the lane line perceived by the vehicle at the previous time of the current time, determining a lane change direction of the vehicle according to the first left-right topology structure; determining a lane in which the vehicle is currently located according to the second left-right topology structure and the lane change direction; obtaining a current pose of the vehicle, and adjusting the current pose of the vehicle according to a distance error between a perceived lane line of the lane in which the vehicle is currently located and a real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle.

4. The method of claim 3, wherein, the method further comprises: in a case where the first identifier of the lane line perceived by the vehicle at the current time is the same as the first identifier of the lane line perceived by the vehicle at the previous time of the current time, determining a lane in which the vehicle is located at the previous time of the current time as the lane in which the vehicle is currently located; obtaining a current pose of the vehicle, and adjusting the current pose of the vehicle according to a distance error between a perceived lane line of the lane in which the vehicle is currently located and a real lane line of the lane in which the vehicle is currently located, to obtain an adjusted current pose of the vehicle.

5. The method of claim 1, wherein, the method further comprises: identifying lane lines in the road image to obtain a lane line perception result, comprising: identifying lane lines in the road image to obtain the plurality of perceived lane lines; each perceived lane line comprises a first virtual-real attribute; sorting each perceived lane line according to a left-right relative relationship between a current position of the vehicle and each perceived lane line to obtain a sorting result; In a case where the ranking result indicates that there is a missed lane line, a missed lane line is determined according to the ranking result, and the missed lane line and each of the perceived lane lines are ranked again to obtain the first left-right topology.

6. The method according to any one of claims 1 to 5, characterized in that, The distance error between the perceived lane line of the lane in which the vehicle currently locates and the real lane line of the lane in which the vehicle currently locates is used to adjust the current pose of the vehicle to obtain an adjusted current pose of the vehicle. The current pose of the vehicle is iteratively updated using a nonlinear least squares method to minimize a target function, and the target function is a residual sum of squares of the distance error between the perceived lane line of the lane in which the vehicle currently locates and the real lane line of the lane in which the vehicle currently locates. The pose that minimizes the target function is determined as the adjusted current pose of the vehicle.

7. A vehicle positioning apparatus characterized by comprising: Comprise: An image acquisition module is configured to acquire a road image collected by a vehicle at a current time and identify lane lines in the road image to obtain a lane line perception result; The lane line perception result comprises a first left-right topology of a plurality of perceived lane lines perceived by the vehicle at the current time and a first solid-void attribute of each of the plurality of perceived lane lines; A map acquisition module is configured to acquire real lane line information within a domain range of a current position of the vehicle from a map in a case where a lane in which the vehicle is located at a previous time of the current time is not determined; The real lane line information comprises a second left-right topology of a plurality of real lane lines within the domain range of the current position of the vehicle and a second solid-void attribute of each of the plurality of real lane lines; A matching module is configured to match the lane line perception result and the real lane line information to obtain a matching result; A lane determination module is configured to determine a lane in which the vehicle currently locates according to the second left-right topology in a case where the matching result indicates that the lane line perception result and the real lane line information are successfully matched. A pose adjustment module is configured to acquire a current pose of the vehicle and adjust the current pose of the vehicle according to a distance error between a perceived lane line of the lane in which the vehicle currently locates and a real lane line of the lane in which the vehicle currently locates to obtain an adjusted current pose of the vehicle. The matching module is further configured to construct an augmented matrix based on the lane line perception result and the real lane line information in a case where at least one of the lane line perception result and the real lane line information does not comprise a road boundary label. Each row of the augmented matrix represents each perceived lane line, each column of the augmented matrix represents each real lane line, and an element of the augmented matrix represents a matching degree between the first solid-void attribute of the perceived lane line represented by the corresponding row and the second solid-void attribute of the real lane line represented by the corresponding column. An optimization algorithm is used to solve the augmented matrix, and in a case where there is only one solution, it is determined that the matching result indicates that the lane line perception result and the real lane line information are successfully matched.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the steps of the method in any one of claims 1 to 6.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

Images