Real-time update method and device for high-precision map lanes

Abstract

The present application relates to a method and device for real-time updating of high-precision maps. The method includes: obtaining historical high-precision maps and newly added high-precision maps, identifying the original lane line data in the historical high-precision maps and the lane line data to be updated in the newly added high-precision maps; comparing the original lane line data with the lane line data to be updated to obtain the matching line segments of the original lane line data and the lane line data to be updated; calculating the error value of the original lane line data and the lane line data to be updated according to the matching line segments and preset rules; adjusting the lane line data to be updated according to the error value, and updating the adjusted lane line data to be updated to the historical high-precision map. The solution provided by the present application can improve the efficiency and accuracy of high-precision map updates.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a real-time updating method and device for high-precision maps. Background Art

[0002] High-precision maps play an important role in autonomous vehicles. In particular, the timeliness of data in high-precision maps is of great significance to autonomous driving. Only by accurately detecting the changes between the newly added high-precision maps and the historical high-precision maps (addition of maps, modification of maps, and deletion of maps) can data fusion be performed correctly. The traditional method of updating the data of high-precision maps is mainly to collect various sensor data of road information regularly through professional collection vehicles, and then complete the discovery and update of data change points through automated algorithms combined with manual annotation. Sensor data mainly includes IMU (Inertial Measurement Unit) trajectory data, laser point cloud data, and high-speed camera image data. However, due to camera calibration errors and satellite navigation signal errors, different data involve lane line data generated each time, which will cause problems such as offset and deformation, and the use of manual annotation errors will cause map update delays and inaccurate annotations.

[0003] Therefore, the existing process of updating high-precision maps has the problem of low update accuracy. Summary of the invention

[0004] In order to solve or partially solve the problems existing in the related art, the present application provides a real-time update method and device for high-precision maps, which can improve the accuracy of high-precision map updates.

[0005] The first aspect of the present application provides a method for real-time updating of a high-precision map, comprising:

[0006] Obtain historical high-precision maps and newly added high-precision maps, and identify the original lane line data in the historical high-precision maps and the lane line data to be updated in the newly added high-precision maps;

[0007] Compare the original lane line data with the lane line data to be updated to obtain matching line segments of the original lane line data and the lane line data to be updated, where the matching line segments are used to represent the same actual lane line corresponding to the original lane line data and the lane line data to be updated;

[0008] According to the matching line segments, the error value between the original lane line data and the lane line data to be updated is calculated;

[0009] The lane line data to be updated is adjusted according to the error value, and the adjusted lane line data to be updated is updated to the historical high-precision map.

[0010] Optionally, comparing the original lane line data with the lane line data to be updated to obtain matching line segments of the original lane line data and the lane line data to be updated includes:

[0011] Preprocessing the original lane line data and the lane line data to be updated respectively to generate ordered coordinate points of the original lane line data and ordered coordinates of the lane line data to be updated;

[0012] Based on the dynamic programming calculation rules, the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated are matched to obtain the matching line segments of the original lane line data and the lane line data to be updated.

[0013] Optionally, preprocessing the original lane line data and the lane line data to be updated respectively to generate ordered coordinate points of the original lane line data and ordered coordinates of the lane line data to be updated includes:

[0014] Perform equal-distance interpolation on the original lane line data and the lane line data to be updated according to a preset distance to obtain key points of the original lane line data and the lane line data to be updated;

[0015] A coordinate system is established and the connection directions between key points are determined to generate ordered coordinates of the key points.

[0016] Optionally, based on a dynamic programming calculation rule, the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated are matched to obtain matching line segments of the original lane line data and the lane line data to be updated, including:

[0017] Obtain the maximum error distance and maximum error angle values ​​that occur during the collection process of the same lane line data, and generate thresholds for dynamic programming calculation rules based on the maximum error distance and maximum error angle values;

[0018] Based on the threshold of the dynamic programming calculation rule, the score value of the ordered coordinates between the original lane and the lane line data to be updated is calculated according to the distance and angle difference between the ordered coordinates;

[0019] According to the dynamic programming calculation rules, the path with the longest path and the smallest cumulative score is selected as the matching line segment from the ordered coordinate set of the original lane line data and the ordered coordinate set of the lane line data to be updated.

[0020] Optionally, calculating the error value between the original lane line data and the lane line data to be updated according to the matching line segment includes:

[0021] Obtain the first end point of the matching line segment in the original lane line data, and obtain the second end point of the matching line segment in the lane line data to be updated;

[0022] Calculate the translation vector from the second tail point to the first tail point, and obtain the rotation angle between the second tail point and the first tail point, the translation vector and the rotation angle are error values.

[0023] Optionally, adjusting the lane line data to be updated according to the error value, and updating the adjusted lane line data to be updated to the historical high-precision map, including:

[0024] Eliminate the matching line segments in the lane line data to be updated to obtain the newly added lane line data in the lane line data to be updated;

[0025] Adjust the newly added lane line data according to the error value, and convert the image format of the newly added lane line data into the image format of the original lane line data;

[0026] The adjusted new lane line data will be updated to the historical high-precision map.

[0027] A second aspect of the present application provides a method and apparatus for real-time updating of a high-precision map, comprising:

[0028] An image receiving unit is used to obtain historical high-precision maps and newly added high-precision maps, and identify the original lane line data in the historical high-precision maps and the lane line data to be updated in the newly added high-precision maps;

[0029] An image matching unit, used for comparing the original lane line data with the lane line data to be updated, so as to obtain matching line segments between the original lane line data and the lane line data to be updated;

[0030] An error elimination unit, used for calculating the error value between the original lane line data and the lane line data to be updated according to the matching line segment;

[0031] The image updating unit is used to adjust the lane line data to be updated according to the error value, and update the adjusted lane line data to be updated to the historical high-precision map.

[0032] A third aspect of the present application provides an electronic device, including:

[0033] Processor; and

[0034] The memory stores executable codes, and when the executable codes are executed by the processor, the processor executes the above method.

[0035] A fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor executes the above method.

[0036] The technical solution provided by the present application may include the following beneficial effects: the present application extracts the matching line segments of the original lane line data and the lane line data to be updated, utilizes the positional relationship of the same lane line data segments in different images, obtains the offset distance between the original lane line data and the lane line data to be updated, and processes the lane line data to be updated according to the offset distance, thereby achieving the fitting effect of the newly added high-precision map and the historical high-precision map.

[0037] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0039] Figure 1 It is a schematic diagram of the application environment of the real-time update method of the high-precision map shown in the embodiment of the present application;

[0040] Figure 2 It is a flowchart of a method for real-time updating of a high-precision map shown in an embodiment of the present application;

[0041] Figure 3 is another flowchart of a method for real-time updating of a high-precision map shown in an embodiment of the present application;

[0042] Figure 4 is a schematic diagram of lane line data of a high-precision map shown in an embodiment of the present application;

[0043] Figure 5 It is a structural schematic diagram of a real-time update device for a high-precision map shown in an embodiment of the present application;

[0044] Figure 6 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0046] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "a", "an" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0047] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0048] High-precision maps play an important role in autonomous vehicles. In particular, the timeliness of data in high-precision maps is of great significance to autonomous driving. Only by accurately detecting the changes between the newly added high-precision maps and the historical high-precision maps (addition of maps, modification of maps, and deletion of maps) can data fusion be performed correctly. The traditional method of updating the data of high-precision maps is mainly to collect various sensor data of road information regularly through professional collection vehicles, and then complete the discovery and update of data change points through automated algorithms + manual annotation. Sensor data mainly includes IMU (Inertial Measurement Unit) trajectory data, laser point cloud data, and high-speed camera image data. However, due to camera calibration errors and satellite navigation signal errors, different data involve lane line data generated each time, which will cause problems such as offset and deformation, and the use of manual annotation errors will cause map update delays and inaccurate annotations.

[0049] In response to the above problems, an embodiment of the present application provides a real-time update method for high-precision maps, which can improve the accuracy of real-time update of high-precision maps.

[0050] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0051] It should be noted that Figure 1The examples shown are only examples of application environments to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios. For example, in another embodiment, an exemplary system architecture to which the high-precision map data update method and apparatus can be applied may include a terminal device, but the terminal device may implement the high-precision map data update method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0052] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a terminal device 102 and a server 104. A network is used to provide a medium for a communication link between the terminal device 102 and the server 104. The network may include various connection types, such as wired and / or wireless communication links, and the like.

[0053] The user can use the terminal device 102 to interact with the server 104 through the network to receive or send messages, etc. Various communication client applications can be installed on the terminal device 102, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0054] The terminal device 102 may be any electronic device having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like.

[0055] The server 104 may be a server that provides various services, such as a background management server that provides support for the content browsed by the user using the terminal device 102 (for example only). The background management server may analyze and process the received data such as the user request, and feed back the processing results (such as web pages, information or data obtained or generated according to the user request, etc.) to the terminal device. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server for a distributed system, or a server combined with a blockchain.

[0056] It should be noted that the high-precision map data updating method provided in the embodiment of the present disclosure can generally be executed by the terminal device 102. Accordingly, the high-precision map data updating device provided in the embodiment of the present disclosure can also be set in the terminal device 102. Alternatively, the high-precision map data updating method provided in the embodiment of the present disclosure can also generally be executed by the server 104. Accordingly, the high-precision map data updating device provided in the embodiment of the present disclosure can generally be set in the server 104.

[0057] The high-precision map data updating method provided in the embodiment of the present disclosure may also be executed by a server or server cluster that is different from the server 104 and can communicate with the terminal device 102 and / or the server 104. Accordingly, the high-precision map data updating device provided in the embodiment of the present disclosure may also be arranged in a server or server cluster that is different from the server 104 and can communicate with the terminal device 102 and / or the server 104.

[0058] For example, when the map data needs to be updated, the terminal device 102 can obtain the newly added map data, and then send the obtained newly added map data to the server 104, and the server 104 obtains the historical high-precision map and the newly added high-precision map, identifies the original lane line data in the historical high-precision map and the lane line data to be updated in the newly added high-precision map; compares the original lane line data with the lane line data to be updated, and determines the matching line segments of the original lane line data and the lane line data to be updated, and the matching line segments are used to represent the same actual lane line corresponding to the original lane line data and the lane line data to be updated; calculates the error value of the original lane line data and the lane line data to be updated according to the matching line segments; adjusts the lane line data to be updated according to the error value, and updates the adjusted lane line data to be updated to the historical high-precision map. The server sends the updated historical high-precision map to the terminal device 102, and the terminal device 102 displays it to the user on the screen.

[0059] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0060] Figure 2 It is a flow chart of the real-time update method of the high-precision map shown in the embodiment of the present application.

[0061] See also Figure 2 , step S201 to step S204.

[0062] Step S201, obtaining a historical high-precision map and a newly added high-precision map, identifying the original lane line data in the historical high-precision map and the lane line data to be updated in the newly added high-precision map.

[0063] The newly added high-precision map includes relevant data for characterizing lane line data, curbs, signs, lane markings, traffic light information, etc. In an embodiment of the present invention, lane line data is used as the newly added data of the high-precision map. Historical high-precision maps and newly added high-precision maps can be stored in one database or in multiple databases. After receiving the newly added high-precision map, it is key to achieve efficient and accurate change comparison between the newly added high-precision map and the historical high-precision map. Only by accurately detecting changes (addition, modification, deletion) can data fusion be performed correctly. Due to problems such as camera calibration errors and RTK errors, the lane line data of the high-precision map generated each time has problems such as offset and deformation. Therefore, before updating the historical high-precision map, it is necessary to eliminate the error data of the newly added map.

[0064] In step S201, identifying lane line data of a historical high-precision image includes performing grayscale processing on the image to obtain the lane line data.

[0065] Step S202, compare the original lane line data and the lane line data to be updated to obtain matching line segments of the original lane line data and the lane line data to be updated, where the matching line segments are used to represent the same actual lane line corresponding to the original lane line data and the lane line data to be updated.

[0066] In step S202, the comparison problem between the newly added high-precision map and the historical high-precision map is simplified to a curve comparison problem of lane line data, and the curve comparison is simplified to obtaining matching line segments between the original lane line data and the newly added lane line data.

[0067] In one embodiment, if Figure 3 As shown, step S202 compares the original lane line data with the lane line data to be updated to obtain matching line segments of the original lane line data and the lane line data to be updated, including:

[0068] Step S301 , preprocessing the original lane line data and the lane line data to be updated respectively, generating ordered coordinate points of the original lane line data and ordered coordinates of the lane line data to be updated.

[0069] Since the lane line data drawing in reality needs to consider the vehicle dynamics, there will be no sharp turns within a few meters, irregular shapes, etc. Therefore, the use of ordered coordinates can accurately characterize the shape of the lane line. In step S301, the lane line data matching problem is converted into a coordinate point matching problem, and the lane line data is converted into ordered coordinates, and the matching line segments of the lane line data are obtained by comparing the ordered coordinates. Among them, converting the lane line data into ordered coordinates includes: generating ordered coordinate points with directions after interpolating the lane line curve at equal distances, and the position and direction of each coordinate point represent the local shape of the curve. Lane line data change detection can be replaced by ordered coordinate points instead of curves.

[0070] In one embodiment, step S301 includes: performing equidistant interpolation in the original lane line data and the lane line data to be updated according to a preset distance to obtain key points of the original lane line data and the lane line data to be updated; establishing a coordinate system and determining the connection direction between the key points to generate ordered coordinates of the key points.

[0071] Specifically, if Figure 4 As shown, Figure 4 It is a schematic diagram of the lane line data of the high-precision map shown in the embodiment of the present application. The upper curve is the original lane line data, denoted as curve A, and the lower curve is the newly added lane line data, denoted as curve B. In this embodiment, the identified lane line is regarded as a simple straight line. In the metric coordinate system, taking curve A as an example, the straight line data is represented by LineString(0 0,5 0). If interpolation is performed with a spacing of 1 meter, the ordered result is LineString(0 0,10,2 0,3 0,4 0,5 0), that is, the shapes of the two curves before and after the insertion point remain unchanged. Assume that there are a total of 6 points before and after the difference, and each point is numbered as (0 0) is numbered 0, (1 0) is numbered 1, (2 0) is numbered 2, and so on. The numbering here means ordered.

[0072] In this embodiment, the direction calculation method of the calculation point includes:

[0073] a) When it is not the last point, use “=” to indicate the direction of the line connecting the current point and the next point.

[0074] b) If it is the last point, it inherits the direction of the second-to-last point.

[0075] Step S302, based on the dynamic programming calculation rule, the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated are matched to obtain matching line segments of the original lane line data and the lane line data to be updated.

[0076] In one embodiment, based on dynamic programming calculation rules, the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated are matched to obtain matching line segments of the original lane line data and the lane line data to be updated, including: obtaining the maximum error distance and the maximum error angle value that appear in the collection process of the same lane line data, and generating a threshold of the dynamic programming calculation rule based on the maximum error distance and the maximum error angle value; based on the threshold of the dynamic programming calculation rule, the score value of the ordered coordinates between the original lane and the lane line data to be updated is calculated according to the distance and angle difference between the ordered coordinates; according to the dynamic programming calculation rules, in the ordered coordinate set of the original lane line data and the ordered coordinate set of the lane line data to be updated, the ordered path with the longest path and the smallest accumulated score is selected as the matching line segment.

[0077] Specifically, this embodiment includes: after evaluating and testing the autonomous driving vehicle and the autonomous vehicle collection equipment, the maximum error distance and angle value that will appear in the same lane line data after two collections are obtained, and the threshold is set based on this. Here, it is assumed that the threshold is distance C and angle D.

[0078] by Figure 4 For example, for the original lane line data A on the left and the lane line data B to be updated on the right, the calculation is as follows. A and B are interpolated at a spacing of 0.5 meters to generate an ordered set of coordinate points (the order is reflected by the numbering). A0 represents the first point of A, A1 represents the second key point of A, A2 represents the third key point of A, and B0 represents the first point of B. B1 represents the second point of B, B2 represents the third point of B, and so on. And generate Table 1. Among them, the number at the intersection of A0 and B0 in Table 1 represents the similarity score of the ordered coordinate point A0 and the ordered coordinate point B0. The ordered coordinate path refers to the path from the ordered coordinates of the original lane line data to the ordered coordinates of the lane line data to be updated. In the embodiment of the present application, taking Table 1 as an example, the ordered coordinates are A0, A1, A2, B0, B1, B2, B3, B4, B5, then the ordered coordinate path includes A0B0, A0B1, A0B2, A0B3, A0B4, A0B5; A1B0, A1B1, A1B2, A1B3, A1B4, A1B5; A2B0, A2B1, A2B2, A2B3, A2B4, A2B5. The optimal path is selected according to the ordered coordinate path, and the optimal path is the matching line segment between the original lane line data and the newly added lane line data.

[0079] The similarity score value 1 or 2 corresponding to each ordered coordinate path in Table 1 is not a real value, but is only used for illustration in this embodiment. For example, if the similarity score value corresponding to A0B0 in Table 1 is 1, it means that the similarity score value corresponding to A0B0 is 1. The similarity score value is used to indicate the similarity between two ordered coordinates. The higher the similarity score, the higher the similarity between the two ordered coordinates, and the more likely they are the same matching line segments. The similarity score is calculated for each conditional path in Table 1, and the calculation result is shown in the intersection point in Table 1.

[0080] Taking A0 and B0 as an example, the calculation method of A0B0 similarity score includes:

[0081] Similarity score between A0 and B0 = distance between A0 and B0 (meters)*10+angle difference between A0 and B0 (degrees);

[0082] If the distance between the ordered coordinates is greater than the threshold D or the angle between the ordered coordinates is greater than the threshold A, the similarity between the ordered coordinates is not large, which does not conform to the dynamic programming calculation rules, and is displayed as unreachable in Table 1. For example, when the distance between A0 and B2 is greater than the threshold D or the angle between A0 and B2 is greater than the threshold A, Table 1 shows that A0 and B2 are unreachable. In Table 1, unreachable is only an embodiment of the present application and does not represent the actual situation.

[0083]

[0084]

[0085] Table 1

[0086] According to Table 1, the path that is reachable among all ordered coordinate paths, with the longest cumulative ordered coordinate path and the smallest cumulative ordered coordinate path score, is selected as the optimal path. The following rules should be followed when selecting a path:

[0087] Rule 1: Multiple paths can be selected.

[0088] Rule 2: A path can start from any reachable position, but the next step can only move to the lower right. For example, if the path selection starts from A0B0, then the next step can only move to path A1B1 or end this selection.

[0089] Rule 3: A point selected once cannot be selected again. If a path already contains A0B0, then other paths cannot contain A0 or B0.

[0090] As shown in Table 1, after selecting according to the three-time rule, the optimal path is A0B0-A1B1-A2B2, then these three points are the unchanged area of ​​the lane line curve, that is, the matching line segment. B3B4B5 is not included in any optimal path, then these three points are the newly added area. Therefore, it can be considered that A0-A1-A2 is the matching line segment of the original lane line data, B0-B1-B2 is the matching line segment of the lane line data to be updated, B3-B4-B5 is the newly added lane line of the lane line data to be updated, and the newly added lane line data is the part of the original lane line data to be updated.

[0091] Step S203, calculating the error value between the original lane line data and the lane line data to be updated according to the matching line segments and preset rules.

[0092] In step S203, the error value between the original lane line data and the lane line data to be updated is calculated according to the matching line segments and preset rules, including: obtaining the first end point of the matching line segment in the original lane line data, obtaining the second end point of the matching line segment in the lane line data to be updated; calculating the translation vector from the second end point to the first end point, and obtaining the rotation angle between the second end point and the first end point, the translation vector and the rotation angle are the error values.

[0093] In one embodiment, the original lane line data and the lane line data to be updated are calculated mainly by the incremental difference method. For example, the unchanged area of ​​the new and old data is first calculated by change detection, and the unchanged area is the matching line segment. The unchanged part of curve A is set to E, and the unchanged part of curve B is set to F. The error value is calculated as follows:

[0094] Calculate the translation vector from the tail point of F to the tail point of E, set it as d. Rotate F (only consider the two-dimensional plane of longitude and latitude, not the elevation value), calculate the angle value with the highest similarity score between E and F after rotation, set it as r.

[0095] The calculation method of the angle value with the highest similarity score includes: starting from the tail point, E and F insert points at an equal distance of 0.5 meters. If min(E length, F length)>=10 meters, insert 20 points, otherwise insert min(E length, F length)*2 points. Set the point number when inserting points. The tail point number is 0, the point number 0.5 meters away from the tail point is 1, and so on.

[0096] After E and F are inserted, the smaller the sum of the distances between points with the same number is, the higher the score is. The rotation angle r and translation vector d with the highest similarity score are selected as the error value between E and F.

[0097] Step S203 can maximize the acquisition of key points corresponding to the original lane line data and the lane line data to be updated by the incremental interpolation method, and calculate the error value between the original lane line data and the lane line data to be updated by the incremental interpolation method, which can improve the accuracy of the error value.

[0098] Step S204 adjusts the lane line data to be updated according to the error value, and updates the adjusted lane line data to be updated to the historical high-precision map.

[0099] Specifically, the lane line data to be updated is adjusted according to the error value, and the adjusted lane line data to be updated is updated to the historical high-precision map, including: eliminating matching line segments in the lane line data to be updated to obtain newly added lane line data in the lane line data to be updated; adjusting the newly added lane line data according to the error value, converting the image format of the newly added lane line data into the image format of the original lane line data; and updating the adjusted newly added lane line data to the historical high-precision map.

[0100] In one embodiment, the newly added curve F is calculated according to the rotation angle r and the translation vector d to obtain the adjusted lane line data to be updated, and the adjusted lane line data to be updated is updated to the historical high-precision map to obtain the updated high-precision map.

[0101] This application extracts the matching line segments of the original lane line data and the lane line data to be updated, uses the positional relationship of the same lane line data segments in different images, obtains the offset distance between the original lane line data and the lane line data to be updated, and processes the lane line data to be updated according to the offset distance, thereby achieving the fitting effect of the newly added high-precision map and the historical high-precision map.

[0102] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a real-time update device for a high-precision map, an electronic device and corresponding embodiments.

[0103] Figure 5 It is a structural diagram of a real-time update device for a high-precision map shown in an embodiment of the present application.

[0104] See also Figure 5 , a real-time update device for high-precision maps, including:

[0105] The image receiving unit 501 is used to obtain the historical high-precision map and the newly added high-precision map, and identify the original lane line data in the historical high-precision map and the lane line data to be updated in the newly added high-precision map.

[0106] The image matching unit 502 is used to compare the original lane line data and the lane line data to be updated to obtain matching line segments of the original lane line data and the lane line data to be updated, and the matching line segments are used to represent the same actual lane line corresponding to the original lane line data and the lane line data to be updated.

[0107] In one embodiment, the image matching unit includes a first matching unit and a second matching unit, including: the first matching unit is used to pre-process the original lane line data and the lane line data to be updated respectively, and generate ordered coordinate points of the original lane line data and the ordered coordinates of the lane line data to be updated; the second matching unit is used to match the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated based on dynamic programming calculation rules to obtain matching line segments of the original lane line data and the lane line data to be updated.

[0108] In one embodiment, the original lane line data and the lane line data to be updated are preprocessed respectively to generate ordered coordinate points of the original lane line data and ordered coordinates of the lane line data to be updated, including: performing equidistant interpolation in the original lane line data and the lane line data to be updated respectively according to preset distances to obtain key points of the original lane line data and the lane line data to be updated; establishing a coordinate system and determining the connection direction between the key points to generate ordered coordinates of the key points.

[0109] In one embodiment, based on dynamic programming calculation rules, the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated are matched to obtain matching line segments of the original lane line data and the lane line data to be updated, including: obtaining the maximum error distance and the maximum error angle value that appear in the collection process of the same lane line data; generating a threshold of the dynamic programming calculation rule according to the maximum error distance and the maximum error angle value; based on the threshold of the dynamic programming calculation rule, calculating the score value of the ordered coordinates between the original lane and the lane line data to be updated according to the distance and angle difference between the ordered coordinates; according to the dynamic programming calculation rules, in the ordered coordinate set of the original lane line data and the ordered coordinate set of the lane line data to be updated, the path with the longest path and the smallest accumulated score is selected as the matching line segment.

[0110] The error elimination unit 503 is used to calculate the error value between the original lane line data and the lane line data to be updated according to the matching line segment.

[0111] In one embodiment, the error value between the original lane line data and the lane line data to be updated is calculated based on the matching line segment, including: obtaining the first end point of the matching line segment in the original lane line data, obtaining the second end point of the matching line segment in the lane line data to be updated; calculating the translation vector from the second end point to the first end point, and obtaining the rotation angle between the second end point and the first end point, the translation vector and the rotation angle being the error value.

[0112] The image updating unit 504 is used to adjust the lane line data to be updated according to the error value, and update the adjusted lane line data to be updated to the historical high-precision map.

[0113] In one embodiment, the lane line data to be updated is adjusted according to the error value, and the adjusted lane line data to be updated is updated to the historical high-precision map, including: eliminating matching line segments in the lane line data to be updated to obtain newly added lane line data in the lane line data to be updated; adjusting the newly added lane line data according to the error value, converting the image format of the newly added lane line data into the image format of the original lane line data; and updating the adjusted newly added lane line data to the historical high-precision map.

[0114] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0115] Figure 6 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.

[0116] See also Figure 6 , the electronic device 600 includes a memory 610 and a processor 620 .

[0117] The processor 620 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0118] The memory 610 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 620 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 610 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 610 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0119] The memory 610 stores executable codes, and when the executable codes are processed by the processor 620 , the processor 620 can execute part or all of the above-mentioned methods.

[0120] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0121] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0122] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A real-time update method for a high-precision map, characterized in that: include: Receive historical high-precision maps and newly added high-precision maps, and obtain the original lane line data in the historical high-precision maps and the lane line data to be updated in the newly added high-precision maps; Compare the ordered coordinates of the original lane line data with the ordered coordinates of the lane line data to be updated, select the optimal path according to the ordered coordinate path to determine the matching line segment of the original lane line data and the lane line data to be updated, and the matching line segment is used to represent the same actual lane line corresponding to the original lane line data and the lane line data to be updated; wherein the ordered coordinate path refers to the path from the ordered coordinates of the original lane line data to the ordered coordinates of the lane line data to be updated; the optimal path is the matching line segment between the original lane line data and the lane line data to be updated, which satisfies the selection of a reachable path among all ordered coordinate paths, the longest cumulative ordered coordinate path and the smallest cumulative ordered coordinate path score, and the score is used to represent the similarity between any ordered coordinate of the original lane line data and any ordered coordinate of the lane line data to be updated, the higher the score, the higher the similarity between the two ordered coordinates, and the more likely they are the same matching line segment; and the following rules must be observed when selecting the path: Rule 1: multiple paths can be selected; Rule 2: the path can start from any reachable position, but can only move to the lower right from the next step; Rule 3: a point selected once cannot be selected again; Calculating the error value between the original lane line data and the lane line data to be updated according to the matching line segment and the preset rule; Adjust the lane line data to be updated according to the error value, and update the adjusted lane line data to be updated to the historical high-precision map; The adjusting the lane line data to be updated according to the error value, and updating the adjusted lane line data to be updated to the historical high-precision map, includes: The matching line segments in the lane line data to be updated are eliminated to obtain the newly added lane line data in the lane line data to be updated.

2. The method according to claim 1, characterized in that The comparing the original lane line data with the lane line data to be updated to determine a matching line segment between the original lane line data and the lane line data to be updated includes: Preprocessing the original lane line data and the lane line data to be updated respectively to generate ordered coordinate points of the original lane line data and ordered coordinates of the lane line data to be updated; Based on dynamic programming calculation rules, the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated are matched to obtain matching line segments of the original lane line data and the lane line data to be updated.

3. The method according to claim 2, characterized in that The preprocessing of the original lane line data and the lane line data to be updated respectively to generate ordered coordinate points of the original lane line data and ordered coordinates of the lane line data to be updated includes: Performing equal-distance interpolation on the original lane line data and the lane line data to be updated according to a preset distance to obtain key points of the original lane line data and the lane line data to be updated; The connection directions between the key points are determined to generate ordered coordinates of the key points.

4. The method according to claim 2, characterized in that The method of matching the ordered coordinates of the original lane line data with the ordered coordinates of the lane line data to be updated based on the dynamic programming calculation rule to obtain matching line segments of the original lane line data and the lane line data to be updated includes: Obtain the maximum error distance and maximum error angle values ​​that occur during the collection process of the same lane line data; Generate a threshold value of the dynamic programming calculation rule according to the maximum error distance and the maximum error angle value; Calculate the fractional values ​​of the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated based on the threshold of the dynamic programming calculation rule, the distance between the ordered coordinates, and the angle difference between the ordered coordinates; Based on the dynamic programming calculation rule, the ordered coordinate path with the longest path and the smallest accumulated score value is selected as the matching line segment from the ordered coordinates of the original lane line data and the ordered coordinates of the lane line data to be updated.

5. The method according to claim 1, characterized in that Calculating the error value between the original lane line data and the lane line data to be updated according to the matching line segment and the preset rule includes: Obtaining a first end point of a matching line segment in the original lane line data, and obtaining a second end point of a matching line segment in the lane line data to be updated; A translation vector from the second tail point to the first tail point is calculated, and a rotation angle between the second tail point and the first tail point is obtained, wherein the translation vector and the rotation angle are the error value.

6. The method according to claim 1, characterized in that The adjusting the lane line data to be updated according to the error value, and updating the adjusted lane line data to be updated to the historical high-precision map, includes: After acquiring the newly added lane line data in the lane line data to be updated, adjusting the newly added lane line data according to the error value, and converting the image format of the newly added lane line data into the image format of the original lane line data; The adjusted newly added lane line data is updated to the historical high-precision map.

7. A real-time update device for high-precision maps, characterized in that: include: An image receiving unit is used to receive historical high-precision maps and newly added high-precision maps, and obtain the original lane line data in the historical high-precision maps and the lane line data to be updated in the newly added high-precision maps; An image matching unit is used to compare the ordered coordinates of the original lane line data with the ordered coordinates of the lane line data to be updated, and select an optimal path according to the ordered coordinate path to determine the matching line segment of the original lane line data and the lane line data to be updated, wherein the matching line segment is used to represent the same actual lane line corresponding to the original lane line data and the lane line data to be updated; wherein the ordered coordinate path refers to the path from the ordered coordinates of the original lane line data to the ordered coordinates of the lane line data to be updated; the optimal path is the matching line segment between the original lane line data and the lane line data to be updated, which satisfies the requirement of selecting a reachable path among all ordered coordinate paths, with the longest cumulative ordered coordinate path and the smallest cumulative ordered coordinate path score, wherein the score is used to represent the similarity between any ordered coordinate of the original lane line data and any ordered coordinate of the lane line data to be updated, and the higher the score, the higher the similarity between the two ordered coordinates, and the more likely they are the same matching line segment; and the following rules shall be observed when selecting a path: Rule 1: multiple paths can be selected; Rule 2: the path can start from any reachable position, but can only move to the lower right from the next step; Rule 3: a point selected once cannot be selected again; An error elimination unit, used to calculate the error value between the original lane line data and the lane line data to be updated according to the matching line segments and preset rules; An image updating unit is used to adjust the lane line data to be updated according to the error value, and update the adjusted lane line data to be updated to the historical high-precision map; the adjusting the lane line data to be updated according to the error value, and updating the adjusted lane line data to be updated to the historical high-precision map, including: eliminating matching line segments in the lane line data to be updated to obtain newly added lane line data in the lane line data to be updated.

8. The device according to claim 7, characterized in that The image matching unit comprises: A first matching unit is used to pre-process the original lane line data and the lane line data to be updated respectively, and generate ordered coordinate points of the original lane line data and ordered coordinates of the lane line data to be updated; The second matching unit is used to match the ordered coordinates of the original lane line data with the ordered coordinates of the lane line data to be updated based on dynamic programming calculation rules to obtain matching line segments of the original lane line data and the lane line data to be updated.

9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having executable codes stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1 to 6.

Images