High-precision map lane line updating method and device, electronic equipment and storage medium

Abstract

The disclosure provides a high-precision map lane line updating method and device, electronic equipment and a storage medium, relates to the technical field of computers, and in particular to the fields of autonomous driving, intelligent transportation and big data. The specific implementation scheme is as follows: determining at least one matching pair that meets a preset condition from at least one first vector point corresponding to collected lane line data and at least one second vector point corresponding to historical lane line data, each matching pair including one first vector point and one second vector point; calculating an evaluation value corresponding to each matching pair; determining a target matching pair according to the evaluation value; and updating the historical lane line data according to the first vector point in the target matching pair.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular to the fields of automatic driving, intelligent transportation and big data, and more particularly to a high-definition map lane line updating method and device, an electronic device and a storage medium. BACKGROUND

[0002] As a scarce resource and a necessity in the field of unmanned driving, the high-definition map plays a core role in the entire field and can help the unmanned vehicle to pre-knowledge the complex information on the road surface, such as slope, curvature, heading, etc., and make correct decisions in combination with intelligent path planning, which is an indispensable data source for unmanned vehicle driving. In order to ensure the safe driving of the unmanned vehicle to the destination, the unmanned driving needs to compare the information collected by the sensor with the stored high-definition map to determine the position and direction. Therefore, the accuracy of high-definition map data collection is very important for unmanned driving. SUMMARY

[0003] The present disclosure provides a high-definition map lane line updating method and device, an electronic device and a storage medium.

[0004] According to an aspect of the present disclosure, a high-definition map lane line updating method is provided, comprising: determining at least one matching pair that satisfies a preset condition from at least one first vector point corresponding to collected lane line data and at least one second vector point corresponding to historical lane line data, each of the matching pairs comprising one first vector point and one second vector point; calculating an evaluation value corresponding to each of the matching pairs; determining a target matching pair according to the evaluation value; and updating the historical lane line data according to the first vector point in the target matching pair.

[0005] According to another aspect of the present disclosure, a high-definition map lane line updating device is provided, comprising: a first determining module configured to determine at least one matching pair that satisfies a preset condition from at least one first vector point corresponding to collected lane line data and at least one second vector point corresponding to historical lane line data, each of the matching pairs comprising one first vector point and one second vector point; a calculating module configured to calculate an evaluation value corresponding to each of the matching pairs; a second determining module configured to determine a target matching pair according to the evaluation value; and a first updating module configured to update the historical lane line data according to the first vector point in the target matching pair.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the high-definition map lane line updating method as described above.

[0007] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the high-definition map lane line updating method as described above.

[0008] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the high-definition map lane line updating method as described above.

[0009] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0011] Figure 1 An exemplary system architecture to which the high-definition map lane line updating method and device according to embodiments of the present disclosure can be applied is schematically shown;

[0012] Figure 2 A flowchart of the high-definition map lane line updating method according to embodiments of the present disclosure is schematically shown;

[0013] Figure 3 A flowchart of the high-definition map lane line updating method according to embodiments of the present disclosure is schematically shown;

[0014] Figure 4 A block diagram of the high-definition map lane line updating device according to embodiments of the present disclosure is schematically shown; and

[0015] Figure 5 A schematic block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0016] Exemplary embodiments of the present disclosure are described herein below with reference to the accompanying drawings, in which various details are set forth to facilitate an understanding of the present disclosure. It should be appreciated that various embodiments of the present disclosure can be practiced with variations of these details as would be obvious to one of ordinary skill in the art, and the scope of the present disclosure is not intended to be limited to the details as described. For clarity and conciseness, descriptions of well-known functions and constructions are omitted from the following description.

[0017] In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with relevant legal regulations, necessary security measures are taken, and the public order and good customs are not violated.

[0018] High-precision maps play an important role in autonomous vehicles. In particular, the data timeliness in high-precision maps is of great significance to autonomous driving. The data update production mode of high-precision maps mainly involves periodically collecting various sensor data of road information by professional collection vehicles, and then discovering and updating data change points through automatic algorithm + manual labeling. Sensor data mainly includes IMU (Inertial Measurement Unit) trajectory data, laser point cloud data and high-speed camera image data. By applying large-scale labeling based on raw data to the production line and developing automatic labeling algorithms, the working time of labeling personnel can be greatly saved, the labeling efficiency can be improved, and the production cost can be reduced.

[0019] The inventors found that, in the process of implementing the present disclosure, raw data is processed to generate visual labeling data, including 2 / 3-dimensional point cloud views, image views, trajectory data, etc. Labeling personnel refer to these data on a customized labeling tool to find and update lane line change points by comparing existing mother database data. The main elements of labeling include lane line geometry, lane line topology and lane line attributes. The main pain points are as follows: automatic labeling algorithms face a variety of scenarios, which can easily lead to misidentification, such as road wear, road obstruction leading to non-recall, unstable collection quality affected by various factors, and misidentification of automatic labeling algorithms due to environmental and system reasons. Lane line change point discovery is inefficient, labeling personnel need to recheck the whole map data before discovering change points, which is costly. Labeling efficiency is low, labeling personnel need to manually delete, update, add, etc. according to the change point data. High quality requirements for labeling personnel, high-precision maps have certain requirements for data accuracy, and labeling personnel need to be trained for a long time to be qualified for this work, which increases the cost of manual labor.

[0020] In view of this, the present disclosure provides a high-definition map lane line updating method, comprising: determining at least one matching pair that satisfies a preset condition from at least one first vector point corresponding to collected lane line data and at least one second vector point corresponding to historical lane line data. Each matching pair includes a first vector point and a second vector point. For each matching pair, an evaluation value corresponding to the matching pair is calculated. According to the evaluation value, a target matching pair is determined. According to the first vector point in the target matching pair, the historical lane line data is updated.

[0021] Figure 1 An exemplary system architecture to which the high-definition map lane line updating method and device according to embodiments of the present disclosure can be applied is schematically shown.

[0022] It should be noted that, Figure 1 The shown is only an example of a system architecture to which embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, the exemplary system architecture to which the high-definition map lane line updating method and device can be applied can include terminal devices, but the terminal devices can not need to interact with the server to implement the high-definition map lane line updating method and device provided by the embodiments of the present disclosure.

[0023] As Figure 1 shown, the system architecture 100 according to this embodiment can include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired and / or wireless communication links, etc.

[0024] The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0025] The terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smartphones, tablet computers, laptop computers and desktop computers, etc.

[0026] The server 105 can be a server that provides various services, such as a background management server that provides support for content browsed by a user using the terminal device 101, 102, or 103 (for example only). The background management server can perform analysis and the like on received user requests and the like, and feed back the processing results (such as a web page, information, or data obtained or generated according to a user request, or the like) to the terminal device. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in a cloud computing service system that solves the defects of large management difficulty and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server can also be a server of a distributed system, or a server combined with a blockchain.

[0027] It should be noted that the high-precision map lane line updating method provided by the embodiments of the present disclosure can generally be executed by the terminal device 101, 102, or 103. Correspondingly, the high-precision map lane line updating apparatus provided by the embodiments of the present disclosure can also be arranged in the terminal device 101, 102, or 103.

[0028] Alternatively, the high-precision map lane line updating method provided by the embodiments of the present disclosure can also be generally executed by the server 105. Correspondingly, the high-precision map lane line updating apparatus provided by the embodiments of the present disclosure can generally be arranged in the server 105. The high-precision map lane line updating method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the terminal device 101, 102, 103 and / or the server 105. Correspondingly, the high-precision map lane line updating apparatus provided by the embodiments of the present disclosure can also be arranged in a server or a server cluster different from the server 105 and capable of communicating with the terminal device 101, 102, 103 and / or the server 105.

[0029] For example, when it is necessary to update the lane line data, the terminal device 101, 102, 103 can acquire the collected lane line data and the historical lane line data, and then send the acquired collected lane line data and the historical lane line data to the server 105. The server 105 determines at least one matching pair that satisfies a preset condition from at least one first vector point corresponding to the collected lane line data and at least one second vector point corresponding to the historical lane line data, each matching pair including one first vector point and one second vector point, calculates an evaluation value corresponding to each matching pair, determines a target matching pair according to the evaluation value, and updates the historical lane line data according to the first vector point in the target matching pair. Alternatively, a server or server cluster capable of communicating with the terminal device 101, 102, 103 and / or the server 105 can analyze the collected lane line data and the historical lane line data and update the historical lane line data.

[0030] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the above description is only illustrative. Any number of terminal devices, networks, and servers can be provided according to implementation needs.

[0031] Figure 2 A flowchart of a high-definition map lane line updating method according to an embodiment of the present disclosure is schematically shown.

[0032] As Figure 2 shown, the method includes operations S210-S240.

[0033] In operation S210, at least one matching pair that satisfies a preset condition is determined from at least one first vector point corresponding to the collected lane line data and at least one second vector point corresponding to the historical lane line data, each matching pair including one first vector point and one second vector point.

[0034] In operation S220, an evaluation value corresponding to each matching pair is calculated.

[0035] In operation S230, a target matching pair is determined according to the evaluation value.

[0036] In operation S240, the historical lane line data is updated according to the first vector point in the target matching pair.

[0037] According to an embodiment of the present disclosure, the collected lane line data can include bounding box data including lane line features newly collected at a current time or within a preset time period. The bounding box data can include lane line features within a preset three-dimensional space range centered on a current collection point. The lane line features can include at least one of position data, image data, point cloud data, etc. of the lane line. By vectorizing modeling the newly collected bounding box data, the lane line features represented by the bounding box data can be converted into a representation form of vector points. The historical lane line data can include road network data representing lane line features of historical lane lines stored in a road network database. The road network data can be stored in the road network database in the form of vector points. The point information of the vector points can represent position information corresponding to the points, and the direction information of the vector points can be determined according to the path of the lane line or the driving direction of the vehicle allowed by the lane line. It should be noted that the collected lane line data can also include lane line features collected for lane lines in regions without a limited range. The current time and the preset time period at which the lane line data is collected are later than the storage time of the historical lane line data.

[0038] According to an embodiment of the present disclosure, by giving a predetermined sampling step, the bounding box data and the road network data represented in the form of vector points can be uniformly sampled to obtain first vector points and second vector points, respectively. During sampling, the spatial relationship information such as the predecessor-successor relationship, left-right relationship, etc. between the sampling points can also be determined according to the physical space relationship of the sampling points.

[0039] According to an embodiment of the present disclosure, the preset condition can include at least one of that the two vector points are contained in the same region range of a predefined size, and that the result of matching difference between the two vector points satisfies a preset matching formula. The result of matching difference between the two vector points satisfying the preset matching formula can include at least one of that the distance and the direction angle between the two vector points satisfy corresponding preset ranges, and that the normal distance between the two vector points satisfies a corresponding preset range. In the case that any at least one of the foregoing conditions is satisfied, the corresponding first vector point and the second vector point can be determined as a matching pair.

[0040] According to an embodiment of the present disclosure, an evaluation value calculation formula can be constructed according to at least one of the position information and the direction information of the two vector points in the matching pair, the distance information and the direction angle information between the two vector points, and the position information and the direction information of other vector points having a predecessor-successor relationship, left-right relationship, etc. with any of the vector points. For each matching pair, the corresponding evaluation value can be calculated based on the evaluation value calculation formula.

[0041] According to an embodiment of the present disclosure, the target matching pair determined according to the evaluation value can further obtain new lane line data that has changed compared to the historical lane line data from the matching pairs, that is, the first vector point in the target matching pair. According to the evaluation value, the manner of determining the target matching pair can include that a preset range can be defined in advance, and the matching pair corresponding to the evaluation value located in the preset range can be determined as the target matching pair. The evaluation value can also be sorted according to the sorting result, and then the matching pair corresponding to the preset number of evaluation values with larger values according to the sorting result can be determined as the target matching pair, and the like. It should be noted that the manner of determining the target matching pair is not limited here, and in other embodiments of the present disclosure, other any feasible determination manner can also be included.

[0042] According to an embodiment of the present disclosure, after the target matching pair is determined, the first vector point in the target matching pair can be used to determine the lane line data to be added. Then, the lane line data to be added can be added to the historical lane line data to complete the update of the historical lane line data.

[0043] Through the above embodiments of the present disclosure, the target matching pair is determined according to the evaluation value, the first vector point that may have changed compared to the historical lane line data can be further determined from the first vector point and the second vector point that have been matched into the matching pair, and then the automatic update is performed, which improves the precision recall rate of automatic labeling, can effectively reduce the manual labeling investment, and can effectively improve the accuracy and completeness of the change point discovery, and improves the update efficiency of the high-precision map.

[0044] The method shown in FIG. 1 will be further described below in combination with specific embodiments. Figure 2

[0045] According to an embodiment of the present disclosure, the at least one matching pair satisfying the preset condition can be determined from the at least one first vector point corresponding to the collected lane line data and the at least one second vector point corresponding to the historical lane line data. For each first vector point, the distance and the direction angle between the first vector point and each second vector point can be calculated respectively. The matching pair satisfying the preset condition can be determined according to the first vector point and the second vector point with the distance less than or equal to the second preset threshold value and the direction angle less than or equal to the third preset threshold value.

[0046] According to an embodiment of the present disclosure, the second preset threshold value can be less than or equal to the above sampling step length. The preset condition can include the following preset matching formula (1):

[0047] d∈[0,w d ]&&θ∈[0,w θ ] (1)

[0048] ​wherein d can represent a distance between the first vector point and the second vector point, which can include, for example, an Euclidean distance, a Manhattan distance, a Chebyshev distance, etc.w d may represent a maximum value predefined for the distance, i.e., the second preset threshold described above. θ can represent a direction angle between the first vector point and the second vector point.w θ may represent a maximum value predefined for the direction angle, i.e., the third preset threshold described above.

[0049] According to an embodiment of the present disclosure, the above-mentioned preset matching formula (1) is used. For example, the Euclidean distance d1 and the direction angle θ1 between the first vector point and the second vector point can be calculated first. Then, according to the preset matching formula (1), the first vector point and the second vector point satisfying d1∈[0, wd]&&θ1∈[0, w θ ] are determined as a matching pair.

[0050] Through the above-mentioned embodiments of the present disclosure, at least one first vector point and at least one second vector point can be converted into a matching pair, and through subsequent calculation according to the matching pair, the amount of calculation is effectively reduced, and the updating efficiency of the high-precision map is improved.

[0051] According to an embodiment of the present disclosure, determining the matching pair satisfying the preset condition according to the first vector point and the second vector point with the distance less than or equal to the second preset threshold and the direction angle less than or equal to the third preset threshold can include: calculating a normal distance between the first vector point and the second vector point with the distance less than or equal to the second preset threshold and the direction angle less than or equal to the third preset threshold. Determining the first vector point and the second vector point with the normal distance greater than or equal to a fourth preset threshold as the matching pair.

[0052] According to an embodiment of the present disclosure, the normal distance can represent a perpendicular distance from a point to a vector. For example, in the present embodiment, the normal distance between the first vector point and the second vector point can include at least one of a first perpendicular distance from a point represented by the first vector point to a vector represented by the second vector point, and a second perpendicular distance from a point represented by the second vector point to a vector represented by the first vector point. The normal distance greater than or equal to the fourth preset threshold can include at least one of the first perpendicular distance greater than or equal to the fourth preset threshold, the second perpendicular distance greater than or equal to the fourth preset threshold, etc.

[0053] According to an embodiment of the present disclosure, for the first vector point and the second vector point with the distance less than or equal to the second preset threshold and the direction included angle less than or equal to the third preset threshold, the first vector point and the second vector point can be determined as a matching pair only when the first perpendicular distance is greater than or equal to the fourth preset threshold, or the second perpendicular distance is greater than or equal to the fourth preset threshold, or both the first perpendicular distance and the second perpendicular distance are greater than or equal to the fourth preset threshold according to the relationship between the normal distance between the two vector points and the fourth preset threshold. For the first vector point and the second vector point with both the first perpendicular distance and the second perpendicular distance less than the fourth preset threshold, the first vector point and the second vector point can be determined as invalid change points.

[0054] According to the above embodiments of the present disclosure, the calculation of the normal distance between the first vector point and the second vector point is introduced, and the matching pair with less data and higher proportion of effective change points is determined from the first vector point and the second vector point with the distance less than or equal to the second preset threshold and the direction included angle less than or equal to the third preset threshold according to the relationship between the normal distance and the fourth preset threshold for subsequent calculation, which effectively reduces the calculation amount and improves the updating efficiency of the high-precision map.

[0055] According to an embodiment of the present disclosure, the calculation of the evaluation value corresponding to the matching pair can include determining at least one of the distance, the distance variance and the direction included angle between the first vector point and the second vector point in the matching pair. The evaluation value corresponding to the matching pair is calculated according to at least one of the distance, the distance variance and the direction included angle.

[0056] According to an embodiment of the present disclosure, the distance variance can represent the variance of the distance of a plurality of predecessor-successor matching pairs determined according to the predecessor-successor vector points related to the first vector point and the second vector point in a certain matching pair within the preset range of the first vector point and the second vector point constituting the matching pair.

[0057] According to an embodiment of the present disclosure, the evaluation value can be calculated according to any at least one of the distance, the distance variance and the direction included angle between the first vector point and the second vector point in the matching pair. For example, the distance between the first vector point and the second vector point in a certain matching pair can be represented by d, the distance variance can be represented by w, and the direction included angle can be represented by θ. The calculation method of the evaluation value Score can include the formula (2) as shown below:

[0058]

[0059] It should be noted that the calculation method of the evaluation value can not be limited to the formula (2), and other feasible formulas can be constructed according to any at least one of the distance, the distance variance and the direction included angle between the first vector point and the second vector point in the matching pair, as long as the formula logic is consistent with the greater d, w and θ, the greater Score.

[0060] The above embodiments of this disclosure provide a reliable method for calculating evaluation values. By combining parameters such as the distance, distance variance, and direction angle between the first and second vector points in the matching pair, the evaluation value corresponding to the matching pair can be calculated, which can improve the accuracy of determining target matching based on the evaluation value and improve the update accuracy of high-precision maps.

[0061] According to embodiments of this disclosure, calculating an evaluation value corresponding to a matching pair based on at least one of distance, distance variance, and direction angle may include: determining a distance correlation coefficient, a distance variance correlation coefficient, and a direction angle correlation coefficient, respectively, that are related to at least one of distance, distance variance, and direction angle. The evaluation value corresponding to the matching pair is then calculated based on at least one of the distance correlation coefficient, the distance variance correlation coefficient, and the direction angle correlation coefficient.

[0062] According to embodiments of this disclosure, for example, the distance correlation coefficient can be determined based on the distance d. The distance variance correlation coefficient can be determined based on the distance variance w. The correlation coefficient of the direction angle can be determined based on the direction angle θ. The evaluation score can also be calculated using the following formula (3):

[0063]

[0064] The above embodiments of this disclosure provide another reliable method for calculating evaluation values. By combining normalization coefficients related to parameters such as the distance, distance variance, and direction angle between the first and second vector points in the matching pair, the evaluation value corresponding to the matching pair can be calculated. This can improve the accuracy of determining target matching based on the evaluation value and improve the update accuracy of high-precision maps.

[0065] According to embodiments of this disclosure, determining a target matching pair based on an evaluation value may include: if the evaluation value is greater than or equal to a first preset threshold, determining the matching pair corresponding to the evaluation value as the target matching pair.

[0066] According to an embodiment of the present disclosure, the first preset threshold can be predefined and used as a basis for distinguishing whether the first vector point in the matching pair is a change point. For example, in a case where the evaluation value calculated for a certain matching pair is less than the first preset threshold, it can be determined that the first vector point in the matching pair does not belong to a change point, and the matching pair cannot be used as a target matching pair. In a case where the evaluation value calculated for a certain matching pair is greater than or equal to the first preset threshold, it can be determined that the first vector point in the matching pair belongs to a change point, and the matching pair can be used as a target matching pair. Thus, the historical lane line data can be updated according to the first vector point in the target matching pair and the lane line data associated with the first vector point.

[0067] According to the above embodiments of the present disclosure, a manner of determining a target matching pair according to an evaluation value is provided, which improves the accuracy and completeness of change point determination on the basis of reasonable use of the evaluation value, and makes the update of the high-definition map more accurate.

[0068] According to an embodiment of the present disclosure, for the first vector points and the second vector points outside the matching pairs, the first vector points and the second vector points can be used as effective change points for updating the lane lines in the high-definition map. In this case, the high-definition map lane line updating method can further include determining at least one target first vector point and at least one target second vector point included in at least one matching pair. From the at least one first vector point, other first vector points except the target first vector points are determined. From the at least one second vector point, other second vector points except the target second vector points are determined. The historical lane line data is updated according to the other first vector points and the other second vector points.

[0069] According to an embodiment of the present disclosure, when the first vector points sampled from the bounding box data and the second vector points sampled from the road network data are matched, there can be a case where the first vector points and the second vector points cannot be matched with each other. For example, at least one of the following can occur: the second vector points do not match the first vector points, i.e., there are other first vector points; the first vector points do not match the second vector points, i.e., there are other second vector points, etc. In any case where the first vector points and the second vector points do not match each other, the other first vector points and the other second vector points are independent, and thus cannot match the historical lane line data and the collected lane line data, respectively. Therefore, the other first vector points and the other second vector points can be determined as effective change points, and the historical lane line data can be updated according to the other first vector points and the other second vector points.

[0070] According to the above embodiments of the present disclosure, the lane line data can be updated according to the first vector points and the second vector points outside the matching pairs, which can further improve the completeness of the lane line updating and improve the accuracy of the high-definition map.

[0071] According to an embodiment of the present disclosure, the updating the historical lane line data according to the other first vector points and the other second vector points can comprise: determining to-be-added lane line data according to the other first vector points; adding data related to the to-be-added lane line data in the historical lane line data; determining to-be-deleted lane line data according to the other second vector points; and deleting data related to the to-be-deleted lane line data in the historical lane line data.

[0072] According to an embodiment of the present disclosure, the lane line change can comprise at least one of a new road, lane line repainting, expansion, reduction, and the like. These change manners are all operations of adding, modifying, deleting, and the like at the lane line level. For all the adding, modifying, deleting, and the like, a unified adding, deleting, and the like mode can be used when updating the historical lane line data.

[0073] For example, in a case where the historical lane line data is added, the collected lane line data can comprise the added lane line data, and the at least one first vector point determined according to the collected lane line data can comprise a first vector point representing the added lane line data. When the first vector point and the second vector point are matched, other first vector points that do not match the historical lane line data can appear. In this case, the other first vector points are new points relative to each point in the historical lane line data. Therefore, the lane line data corresponding to the other first vector points can be determined as to-be-added lane line data. In the process of updating the historical lane line data, the historical lane line data can be updated by adding the to-be-added lane line data.

[0074] For example, in a case where the historical lane line data is deleted, the collected lane line data does not comprise the deleted lane line data. When the first vector point and the second vector point are matched, other second vector points that do not match the collected lane line data can appear. In this case, the other second vector points are redundant points relative to each point in the collected lane line data. Therefore, the lane line data corresponding to the other second vector points can be determined as to-be-deleted lane line data. In the process of updating the historical lane line data, the historical lane line data can be updated by deleting the to-be-deleted lane line data.

[0075] According to an embodiment of the present disclosure, the modifying operation on the historical lane line data can comprise at least one of adding a new lane line and deleting an existing lane line. For the corresponding modification manner, an implementation scheme corresponding to the above-mentioned adding operation and deleting operation can be used to update the historical lane line data.

[0076] Through the above embodiments of the disclosure, the updating operation for the lane line can be simplified to an adding, deleting, or the like operation for the historical lane line data, the scene complexity is simplified, and the updating efficiency is improved.

[0077] Figure 3 A schematic diagram of a whole flowchart of a high-definition map lane line updating method according to an embodiment of the disclosure is shown.

[0078] As shown in the method includes operations S301-S312. Figure 3

[0079] In operation S301, the bounding box data is sampled to obtain at least one first vector point.

[0080] In operation S302, the road network data is sampled to obtain at least one second vector point.

[0081] In operation S303, the first vector point and the second vector point are matched one by one, the distance d, the direction angle θ and the normal distance d between the first vector point and the second vector point are calculated ⊥ , and the first preset threshold value value1, the second preset threshold value value2, the third preset threshold value value3 and the fourth preset threshold value value4 are defined.

[0082] In operation S304, it is determined whether d is less than or equal to value2 and θ is less than or equal to value3 at the same time. If yes, operation S305 or S306-S308 is executed, and if no, operation S311-S312 is executed.

[0083] In operation S305, it is determined whether d ⊥ is greater than or equal to value4. If yes, operation S306-S308 is executed, and if no, operation S310 is executed.

[0084] In operation S306, the first vector point and the second vector point are determined as a matched pair.

[0085] In operation S307, an evaluation value score corresponding to the matched pair is calculated.

[0086] In operation S308, it is determined whether score is greater than or equal to value1. If yes, operation S309 is executed, and if no, operation S310 is executed.

[0087] In operation S309, the road network data is updated according to the first vector point.

[0088] In operation S310, it is determined that the first vector point and the second vector point are both invalid change points.

[0089] ​In operation S311, it is determined that both the first vector point and the second vector point are valid change points.

[0090] In operation S312, lane line data related to the first vector point is added in the road network data, and lane line data related to the second vector point in the road network data is deleted.

[0091] Through the above embodiments of the present disclosure, for the matching pair calculation evaluation value, the valid change point can be further determined from the first vector point and the second vector point that have been matched as the matching pair, which improves the accuracy and completeness of the valid change point discovery. In combination with the automated updating operation, the precision of the automated labeling is improved, the manual labeling input is effectively reduced, and the updating efficiency of the high-precision map is improved. In addition, the updating operation for the lane line data is unified as the addition and deletion mode, which simplifies the scene complexity.

[0092] Figure 4 A block diagram of a high-precision map lane line updating device according to an embodiment of the present disclosure is schematically shown.

[0093] As shown in Figure 4 The high-precision map lane line updating device 400 includes a first determination module 410, a calculation module 420, a second determination module 430, and a first updating module 440.

[0094] The first determination module 410 is configured to determine at least one matching pair that satisfies a preset condition from at least one first vector point corresponding to the collected lane line data and at least one second vector point corresponding to the historical lane line data. Each matching pair includes one first vector point and one second vector point.

[0095] The calculation module 420 is configured to calculate an evaluation value corresponding to each matching pair.

[0096] The second determination module 430 is configured to determine a target matching pair according to the evaluation value.

[0097] The first updating module 440 is configured to update the historical lane line data according to the first vector point in the target matching pair.

[0098] According to an embodiment of the present disclosure, the calculation module includes a first determination unit and a first calculation unit.

[0099] The first determination unit is configured to determine at least one of a distance, a distance variance, and a direction angle between the first vector point and the second vector point in the matching pair.

[0100] The first calculation unit is configured to calculate an evaluation value corresponding to the matching pair according to at least one of the distance, the distance variance, and the direction angle.

[0101] According to an embodiment of the present disclosure, the first calculation unit comprises a first determination subunit and a first calculation subunit.

[0102] The first determination subunit is configured to determine a distance correlation coefficient, a distance variance correlation coefficient and a direction angle correlation coefficient respectively in relation to at least one of the distance, the distance variance and the direction angle.

[0103] The first calculation subunit is configured to calculate an evaluation value corresponding to the matching pair according to at least one of the distance correlation coefficient, the distance variance correlation coefficient and the direction angle correlation coefficient.

[0104] According to an embodiment of the present disclosure, the second determination module comprises a second determination unit.

[0105] The second determination unit is configured to determine the matching pair corresponding to the evaluation value as the target matching pair in a case where the evaluation value is greater than or equal to a first preset threshold.

[0106] According to an embodiment of the present disclosure, the first determination module comprises a second calculation unit and a third determination unit.

[0107] The second calculation unit is configured to calculate the distance and the direction angle between the first vector point and each second vector point respectively for each first vector point.

[0108] The third determination unit is configured to determine the matching pair satisfying the preset condition according to the first vector point and the second vector point with the distance less than or equal to a second preset threshold and the direction angle less than or equal to a third preset threshold.

[0109] According to an embodiment of the present disclosure, the third determination unit comprises a second calculation subunit and a second determination subunit.

[0110] The second calculation subunit is configured to calculate a normal distance between the first vector point and the second vector point with the distance less than or equal to the second preset threshold and the direction angle less than or equal to the third preset threshold.

[0111] The second determination subunit is configured to determine the first vector point and the second vector point with the normal distance greater than or equal to a fourth preset threshold as the matching pair.

[0112] According to an embodiment of the present disclosure, the high-definition map lane line updating device further comprises a third determination module, a fourth determination module, a fifth determination module and a second updating module.

[0113] The third determination module is configured to determine at least one target first vector point and at least one target second vector point included in the at least one matching pair.

[0114] The fourth determination module is configured to determine, from the at least one first vector point, a first vector point other than the target first vector point.

[0115] The fifth determining module is configured to determine, from the at least one second vector point, a second vector point other than the target second vector point.

[0116] The second updating module is configured to update the historical lane line data according to the other first vector point and the other second vector point.

[0117] According to an embodiment of the present disclosure, the second updating module comprises a fourth determining unit, an adding unit, a fifth determining unit and a deleting unit.

[0118] The fourth determining unit is configured to determine, according to the other first vector point, to-be-added lane line data.

[0119] The adding unit is configured to add, in the historical lane line data, data related to the to-be-added lane line data.

[0120] The fifth determining unit is configured to determine, according to the other second vector point, to-be-deleted lane line data.

[0121] The deleting unit is configured to delete, in the historical lane line data, data related to the to-be-deleted lane line data.

[0122] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0123] According to an embodiment of the present disclosure, an electronic device comprises at least one processor and a memory connected with the at least one processor in communication; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the high-definition map lane line updating method as described above.

[0124] According to an embodiment of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to perform the high-definition map lane line updating method as described above.

[0125] According to an embodiment of the present disclosure, a computer program product comprises a computer program, and the computer program, when executed by a processor, implements the high-definition map lane line updating method as described above.

[0126] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0127] As shown in Figure 5 The device 500 includes a computing unit 501 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 502 or a computer program loaded into a random access memory (RAM) 503 from a storage unit 508. Various programs and data required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0128] Various components in the device 500 are connected to the I / O interface 505, including an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; the storage unit 508, such as a magnetic disk, a magneto-optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0129] The computing unit 501 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs various methods and processes described above, such as the high-definition map lane line updating method. For example, in some embodiments, the high-definition map lane line updating method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the high-definition map lane line updating method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the high-definition map lane line updating method by any other appropriate means, such as by means of firmware.

[0130] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0131] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0132] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0133] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0134] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0135] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0136] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, without limitation herein, so long as the desired results of the technology described in the present disclosure are achieved.

[0137] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for updating lane lines in a high-precision map, comprising: From at least one first vector point corresponding to the collected lane line data and at least one second vector point corresponding to the historical lane line data, at least one matching pair that meets preset conditions is determined, and each matching pair includes one first vector point and one second vector point; For each of the matching pairs, calculate the evaluation value corresponding to the matching pair; Based on the evaluation values, target matching pairs are determined; as well as Update the historical lane line data based on the first vector point in the target matching pair; The calculated evaluation value corresponding to the matching pair includes: Determine at least one of the distance, distance variance, and direction angle between the first vector point and the second vector point in the matching pair; calculate an evaluation value corresponding to the matching pair based on at least one of the distance, distance variance, and direction angle; the calculated evaluation value is positively correlated with at least one of the distance, distance variance, and direction angle. The step of determining the target matching pair based on the evaluation value includes: If the evaluation value is greater than or equal to a first preset threshold, the matching pair corresponding to the evaluation value is determined as the target matching pair.

2. The method according to claim 1, wherein, The step of calculating the evaluation value corresponding to the matching pair based on at least one of the distance, distance variance, and direction angle includes: Determine the distance correlation coefficient, distance variance correlation coefficient, and direction angle correlation coefficient respectively, which are related to at least one of the distance, distance variance, and direction angle; and The evaluation value corresponding to the matching pair is calculated based on at least one of the distance correlation coefficient, distance variance correlation coefficient, and direction angle correlation coefficient.

3. The method according to claim 1, wherein, Determining at least one matching pair that satisfies preset conditions from at least one first vector point corresponding to the collected lane line data and at least one second vector point corresponding to the historical lane line data includes: For each of the first vector points, calculate the distance and the angle of orientation between the first vector point and each of the second vector points; and Based on the first vector point and the second vector point whose distance is less than or equal to the second preset threshold and whose directional angle is less than or equal to the third preset threshold, a matching pair that satisfies the preset conditions is determined.

4. The method according to claim 3, wherein, The step of determining a matching pair that satisfies the preset conditions based on a first vector point and a second vector point whose distance is less than or equal to a second preset threshold and whose directional angle is less than or equal to a third preset threshold includes: Calculate the normal distance between a first vector point and a second vector point, where the distance is less than or equal to a second preset threshold and the directional angle is less than or equal to a third preset threshold; and The first vector point and the second vector point whose normal distance is greater than or equal to a fourth preset threshold are determined as the matching pair.

5. The method according to any one of claims 1 to 4, further comprising: Determine at least one target first vector point and at least one target second vector point included in the at least one matching pair; From the at least one first vector point, determine other first vector points besides the target first vector point; From the at least one second vector point, determine other second vector points besides the target second vector point; as well as The historical lane line data is updated based on the other first vector points and the other second vector points.

6. The method according to claim 5, wherein updating the historical lane line data based on the other first vector points and the other second vector points comprises: Based on the other first vector points, determine the lane line data to be added; Add data related to the lane line data to be added to the historical lane line data; Based on the other second vector points, determine the lane line data to be deleted; as well as Delete the data in the historical lane line data that is related to the lane line data to be deleted.

7. A high-precision map lane line updating device, comprising: The first determining module is used to determine at least one matching pair that satisfies preset conditions from at least one first vector point corresponding to the collected lane line data and at least one second vector point corresponding to the historical lane line data, wherein each matching pair includes a first vector point and a second vector point. A calculation module is used to calculate an evaluation value corresponding to each of the matching pairs; The second determining module is used to determine the target matching pair based on the evaluation value; as well as The first update module is used to update the historical lane line data based on the first vector point in the target matching pair; The computing module includes: The first determining unit is configured to determine at least one of the following: the distance, the distance variance, and the direction angle between the first vector point and the second vector point in the matching pair; The first calculation unit is configured to calculate an evaluation value corresponding to the matching pair based on at least one of the distance, distance variance, and direction angle; the calculated evaluation value is positively correlated with at least one of the distance, distance variance, and direction angle. The second determining module includes: The second determining unit is used to determine the matching pair corresponding to the evaluation value as the target matching pair when the evaluation value is greater than or equal to the first preset threshold.

8. The apparatus according to claim 7, wherein, The first computing unit includes: The first determining subunit is configured to determine, respectively, a distance correlation coefficient, a distance variance correlation coefficient, and a direction angle correlation coefficient that are related to at least one of the distance, distance variance, and direction angle; and The first calculation subunit is used to calculate the evaluation value corresponding to the matching pair based on at least one of the distance correlation coefficient, distance variance correlation coefficient, and direction angle correlation coefficient.

9. The apparatus according to claim 7, wherein, The first determining module includes: The second calculation unit is configured to calculate, for each of the first vector points, the distance and the included angle between the first vector point and each of the second vector points; and The third determining unit is used to determine a matching pair that satisfies the preset conditions based on the first vector point and the second vector point whose distance is less than or equal to the second preset threshold and whose directional angle is less than or equal to the third preset threshold.

10. The apparatus according to claim 9, wherein, The third determining unit includes: The second calculation subunit is used to calculate the normal distance between a first vector point and a second vector point, wherein the distance is less than or equal to a second preset threshold and the directional angle is less than or equal to a third preset threshold; and The second determining subunit is used to determine the first vector point and the second vector point whose normal distance is greater than or equal to a fourth preset threshold as the matching pair.

11. The apparatus according to any one of claims 7 to 10, further comprising: The third determining module is used to determine at least one target first vector point and at least one target second vector point included in the at least one matching pair; The fourth determining module is used to determine other first vector points besides the target first vector point from the at least one first vector point; The fifth determining module is used to determine other second vector points besides the target second vector point from the at least one second vector point; as well as The second update module is used to update the historical lane line data based on the other first vector points and the other second vector points.

12. The apparatus of claim 11, wherein the second updating module comprises: The fourth determining unit is used to determine the lane line data to be added based on the other first vector points; An adding unit is used to add data related to the lane line data to be added to the historical lane line data; The fifth determining unit is used to determine the lane line data to be deleted based on the other second vector points; as well as The deletion unit is used to delete data related to the lane line data to be deleted from the historical lane line data.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images