Lane matching method and device, equipment, storage medium and program product

Abstract

The invention relates to a lane matching method and device, equipment, a storage medium and a program product, and relates to the technical field of vehicle control. The method is applied to a vehicle and comprises the steps that map lane information and visual lane information are obtained, the map lane information comprises lane information of a plurality of preset lanes, the visual lane information comprises lane information of a to-be-recognized lane where the vehicle is located, and the lane information comprises a lane width value and lane center line position information. According to the visual lane information and the map lane information, a target matching score between the to-be-recognized lane and each preset lane is determined, and the target matching score comprises a first matching score of lane width values between different lanes and a second matching score of lane center line position information between different lanes. And determining a target lane from the plurality of preset lanes according to a preset matching threshold, the target matching score between the target lane and the to-be-identified lane being greater than the preset matching threshold.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a lane matching method, device, equipment, storage medium and program product. Background Art

[0002] In recent years, with the rapid development of intelligent transportation and autonomous driving technologies, there are more and more requirements for the positioning and navigation of autonomous driving vehicles during driving, so that autonomous driving vehicles can accurately understand their own positions in real time and stay in the center of the lane more stably.

[0003] At present, the positioning and navigation of autonomous vehicles during driving are mainly carried out through shape matching of lane lines on high-precision maps and visual lane lines, which provides accurate road identification for autonomous vehicles and helps them drive stably.

[0004] However, in the above technical solution, the shape data of the overall lane line in the map data and perception data are easily affected by environmental factors, so using only the lane line shape as the basis for road recognition may affect the lane matching accuracy of the high-precision map and the visual lane line. Therefore, how to improve the accuracy of lane matching has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a lane matching method, device, equipment, storage medium and program product to at least solve the technical problem of how to improve the lane matching efficiency during vehicle driving in the related art. The technical solution of the present application is as follows:

[0006] According to the first aspect of the present application, a lane matching method is provided, which is applied to a vehicle, and includes: obtaining map lane information and visual lane information, wherein the map lane information includes: obtaining map lane information and visual lane information, wherein the map lane information includes: lane information of multiple preset lanes, wherein the visual lane information includes: lane information of a lane to be identified where the vehicle is located, and wherein the lane information includes: lane width value and lane centerline position information. According to the visual lane information and the map lane information, a target matching score between the lane to be identified and each preset lane is determined, wherein the target matching score includes: a first matching score of lane width value between different lanes, and a second matching score of lane centerline position information between different lanes. According to a preset matching threshold, a target lane is determined from multiple preset lanes, and the target matching score between the target lane and the lane to be identified is greater than the preset matching threshold.

[0007] According to the above technical means, based on the width and centerline position of the lane where the vehicle is located (i.e., the visual lane) from the visual angle, it is matched with all the map lanes in the preset map data to obtain a map lane with a smaller width error and centerline deviation from the visual lane, and then the lane where the vehicle is actually located is determined to achieve lane matching. In this way, based on the width error and centerline deviation between lanes, it can provide valuable reference for lane matching and improve the accuracy of lane matching.

[0008] In a possible implementation, the method further includes: a first matching score of the lane to be identified is used to indicate a lane width deviation degree between the lane to be identified and the preset lane when the lane width value of the lane to be identified and the lane width value of the preset lane are both within a preset width range.

[0009] According to the above technical means, the width matching between lanes is screened by preset width intervals, thereby avoiding invalid matching of lanes with larger widths due to data errors, and improving lane matching efficiency.

[0010] In a possible implementation, the lane information further includes: length values ​​and indication information of lane lines on the left and right sides, the indication information is used to indicate whether the lane lines actually exist, and the second matching score of the lane to be identified satisfies at least one of the following: if the length values ​​of the lane lines on the left and right sides of the lane to be identified are both greater than a preset length threshold, and the indication information of the lane lines on the left and right sides of the lane to be identified both indicate actual existence, then the second matching score of the lane to be identified is used to indicate the degree of deviation between the lane centerline position information of the lane to be identified and the lane line position information of the preset lane. If only the length value of the left lane line of the lane to be identified is greater than the preset length threshold, and the indication information of only the left lane line of the lane to be identified indicates actual existence, then the second matching score of the lane to be identified is equal to the preset matching score. If only the length value of the right lane line of the lane to be identified is greater than the preset length threshold, and the indication information of only the right lane line of the lane to be identified indicates actual existence, then the second matching score of the lane to be identified is equal to the preset matching score.

[0011] According to the above technical means, the lane centerline matching between lanes is screened by the lane line length and the actual existence of the lane line, thereby avoiding invalid matching for non-valid lanes and improving the lane matching efficiency.

[0012] In a possible implementation, the visual lane information further includes: lane information of left and right lanes of the lane to be identified, and the target matching score further includes: a third matching score of the number of left and right lanes between different lanes.

[0013] According to the above technical means, based on the error in the number of left and right lanes between lanes, a valuable reference can be provided for lane matching, thereby improving the accuracy of lane matching.

[0014] In a possible implementation, the lane information also includes: lane line type information on the left and right sides, the lane line type information is used to indicate a dotted lane line or a solid lane line, and the target matching score also includes: a fourth matching score of the lane line type information of the left and right lanes between different lanes.

[0015] According to the above technical means, based on the lane line type deviation of the left and right lanes between the lanes, a valuable reference can be provided for lane matching, thereby improving the accuracy of lane matching.

[0016] In a possible implementation, after the above-mentioned method of "determining a target lane from multiple preset lanes according to a preset matching threshold", it includes: determining the confidence level of the lane to be identified matching the target lane according to the target matching score between the target lane and the lane to be identified.

[0017] According to the above technical means, after providing the vehicle user with the most matching lane recognition result, the matching device can also provide the user with the credibility of the recognition result through the confidence level, so as to provide a reference for the user to apply the lane recognition result.

[0018] According to a second aspect provided by the present application, a lane matching device is provided, which is applied to a vehicle. The device includes: an acquisition module and a processing module.

[0019] The acquisition module is used to acquire map lane information and visual lane information. The map lane information includes: lane information of multiple preset lanes. The visual lane information includes: lane information of the lane to be identified where the vehicle is located. The lane information includes: lane width value and lane centerline position information. The processing module is used to determine the target matching score between the lane to be identified and each preset lane based on the visual lane information and the map lane information. The target matching score includes: a first matching score of the lane width value between different lanes and a second matching score of the lane centerline position information between different lanes. The processing module is also used to determine the target lane from the multiple preset lanes based on a preset matching threshold. The target matching score between the target lane and the lane to be identified is greater than the preset matching threshold.

[0020] In a possible implementation, the processing module is specifically used to, if the length values ​​of the lane lines on both sides of the lane to be identified are greater than a preset length threshold, and the indication information of the lane lines on both sides of the lane to be identified indicates real existence, then the second matching score of the lane to be identified is used to indicate the degree of deviation between the lane centerline position information of the lane to be identified and the lane line position information of the preset lane. The processing module is also used to, if only the length value of the left lane line of the lane to be identified is greater than the preset length threshold, and the indication information of only the left lane line of the lane to be identified indicates real existence, then the second matching score of the lane to be identified is equal to the preset matching score. The processing module is also used to, if only the length value of the right lane line of the lane to be identified is greater than the preset length threshold, and the indication information of only the right lane line of the lane to be identified indicates real existence, then the second matching score of the lane to be identified is equal to the preset matching score.

[0021] In a possible implementation manner, the processing module is further configured to determine a confidence level that the lane to be identified matches the target lane according to a target matching score between the target lane and the lane to be identified.

[0022] According to a third aspect provided by the present application, an electronic device is provided, comprising: a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement a method of any possible implementation of the first aspect above.

[0023] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute a method of any possible implementation of the above-mentioned first aspect.

[0024] According to a fifth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes a method of any possible implementation of the first aspect above.

[0025] Therefore, the above technical features of the present application have the following beneficial effects:

[0026] (1) Based on the width and centerline position of the lane where the vehicle is located (i.e., the visual lane) from the visual angle, it is matched with all the map lanes in the preset map data to obtain a map lane with a smaller width error and centerline deviation than the visual lane, and then the lane where the vehicle is actually located is determined to achieve lane matching. In this way, based on the width error and centerline deviation between lanes, a valuable reference can be provided for lane matching, thereby improving the accuracy of lane matching.

[0027] (2) The lane width matching is screened by presetting the width interval to avoid invalid matching of lanes with larger widths due to data errors, thereby improving the lane matching efficiency.

[0028] (3) The lane centerline matching between lanes is screened based on the lane line length and the actual existence of the lane line to avoid invalid matching for non-valid lanes and improve lane matching efficiency.

[0029] (4) Based on the error in the number of left and right lanes between lanes, it can provide valuable reference for lane matching and improve the accuracy of lane matching.

[0030] (5) The lane line type deviation between the left and right lanes can provide valuable reference for lane matching and improve the accuracy of lane matching.

[0031] (6) After providing the vehicle user with the most matching lane recognition result, the matching device may also provide the user with the degree of credibility of the recognition result through the confidence level, so as to provide a reference for the user in applying the lane recognition result.

[0032] It should be noted that the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0033] 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

[0034] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0035] Figure 1 is a schematic diagram of a communication system according to an exemplary embodiment;

[0036] Figure 2 is a flow chart of a lane matching method according to an exemplary embodiment;

[0037] Figure 3 is a flow chart of another lane matching method according to an exemplary embodiment;

[0038] Figure 4 is a block diagram of a lane matching device according to an exemplary embodiment;

[0039] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0040] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0041] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0042] Before introducing the lane matching method of the embodiment of the present application in detail, the implementation environment and application scenarios of the embodiment of the present application are first introduced.

[0043] With the rise of autonomous driving and intelligent transportation systems, lane matching of high-precision maps and visual lane lines has become a leading technology, providing key support for safer and more efficient road travel. With the continuous advancement of technology, the complexity and variability of the road environment require vehicles to have more accurate positioning and navigation capabilities, and the integration of these two technologies is precisely to meet this challenge. First, in the field of autonomous driving, vehicles need to understand their position on the road in real time and accurately in order to make safe decisions. Lane matching of high-precision maps and visual lane lines can help vehicles accurately locate in complex urban environments, overcome perception errors, and thus ensure driving safety. Secondly, in large-scale scenarios such as highways, lane matching can provide accurate road identification for autonomous driving vehicles, help vehicles drive stably, and respond promptly when the road changes.

[0044] Therefore, lane matching between high-precision maps and visual lane lines is the core technology in autonomous driving and intelligent transportation systems. It not only provides accurate positioning and navigation for autonomous vehicles, but also brings more possibilities to urban traffic management and planning. Through continuous innovation and development, this technology will bring a safer, more efficient and intelligent experience to future road travel.

[0045] However, it is not easy to achieve lane matching between high-precision maps and visual lane lines. On the one hand, map data needs to be updated in a timely manner to adapt to changes in the road environment. On the other hand, visual sensors may be affected by factors such as weather and lighting, resulting in reduced reliability of perception data. Therefore, it is necessary to combine multi-sensor fusion technology to verify the data of different sensors and improve the accuracy of positioning and navigation.

[0046] In the existing technical solution, lanes are matched by using the detected road speed limit sign information, classifying the type and speed limit value of the speed limit sign, and finally outputting the information of the current lane to match the lane. The disadvantage is that the lanes are matched by the speed limit information collected in real time by the image, which has a single information dimension and its matching accuracy is too dependent on this information rather than the main attribute information of the lane. This lane matching method has certain limitations and cannot obtain more accurate lane matching information with higher precision.

[0047] That is to say, in the process of providing accurate road identification for autonomous driving vehicles through shape matching of lane lines in high-precision maps and visual lane lines, the shape data of the overall lane lines in map data and perception data are easily affected by environmental factors. Therefore, using only lane line shapes as the basis for road identification may affect the lane matching accuracy of high-precision maps and visual lane lines.

[0048] In summary, how to improve the accuracy of lane matching is a technical problem that needs to be solved urgently.

[0049] In order to solve the above problems, the embodiment of the present application provides a lane matching method, which is applied to the scene of vehicle driving navigation, including: matching the width and centerline position of the lane where the vehicle is located (i.e., the visual lane) from the visual angle with all the map lanes in the preset map data, obtaining a map lane with a smaller width error and centerline deviation from the visual lane, and then determining the lane where the vehicle is actually located to achieve lane matching. In this way, based on the width error and centerline deviation between lanes, a valuable reference can be provided for lane matching, thereby improving the accuracy of lane matching.

[0050] The implementation environment of the embodiments of the present application is introduced below.

[0051] Figure 1 FIG. 1 is a schematic diagram of a communication system according to an exemplary embodiment. Figure 1 As shown, the communication system includes: a collection device 101 and a lane matching device (matching device 102 ). The collection device 101 and the matching device 102 are both deployed in a vehicle 103 , and the collection device 101 can perform wired / wireless communication with the matching device 102 .

[0052] Specifically, the acquisition device 101 can collect visual lane information in the driving scene where the vehicle 103 is located, and transmit the collected visual lane information to the matching device 102. Then, the matching device 102 can perform targeted matching based on the locally preset map lane information and the visual lane information, determine the width error and centerline deviation between the lane to be identified in the visual lane information and each preset lane in the map lane information, and use the preset lane with the smallest width error and centerline deviation as the target lane that matches the visual lane.

[0053] It should be noted that the embodiment of the present application does not limit the acquisition device 101. The acquisition device 101 may be a camera in the vehicle 103, or the acquisition device 101 may be a laser radar in the vehicle 103. Alternatively, the acquisition device 101 may be a millimeter wave radar in the vehicle 103.

[0054] Optionally, the embodiment of the present application does not limit the matching device 102, and the matching device 102 may be a vehicle-mounted host in the vehicle 103. Alternatively, the matching device 102 may be a driving computer in the vehicle 103. Alternatively, the matching device 102 may be a navigation control unit in the vehicle 103.

[0055] For ease of understanding, the lane matching method provided in this application is specifically introduced below with reference to the accompanying drawings. Figure 2 is a flow chart of a lane matching method according to an exemplary embodiment. Figure 2 As shown, the method comprises the following steps:

[0056] S201. Obtain map lane information and visual lane information.

[0057] The map lane information is used to indicate each lane in a preset road map, and the map lane information may include: lane information of multiple preset lanes in the preset road map.

[0058] It should be noted that, in the embodiment of the present application, the lane information may include: lane width value.

[0059] Among them, the map lane width can be the absolute value of the difference between the lateral line deviation of the left lane line of the map (i.e. the horizontal distance between the vehicle in the map lane and the left lane line of the lane) and the lateral deviation of the right lane line of the map (i.e. the horizontal distance between the vehicle in the map lane and the right lane line of the lane), or the map lane width can be the sum of the lateral line deviation of the left lane line of the map and the lateral deviation of the right lane line of the map.

[0060] For example, the map lane width can be the absolute value of the difference between the lateral deviation of the left lane line of the map and the lateral deviation of the right lane line of the map. If the lateral deviation of the left lane line of the map is 1 and the lateral deviation of the right lane line of the map is -2, then the map lane width value is 3.

[0061] In an embodiment of the present application, lane information may also include: lane centerline position.

[0062] The lane centerline position may be a position in a coordinate system based on the vehicle position as the origin, or the lane centerline position may be a position in a global coordinate system (such as longitude and latitude).

[0063] As a possible implementation, the matching device may pre-store the map lane information, and obtain the map lane information by local acquisition. Alternatively, the matching device may obtain the map lane information by cloud access.

[0064] Exemplarily, the matching device may obtain the map lane information through a locally deployed map service application programming interface (API).

[0065] In an embodiment of the present application, the visual lane information is used to indicate the lane to be identified where the vehicle is located from a visual perspective, and the visual lane information may include: lane information of the lane to be identified where the vehicle is located.

[0066] Among them, for the introduction of the lane information of the lane to be identified, reference can be made to the above description of the lane information of the preset lane, which will not be repeated here.

[0067] As a possible implementation method, a collection device is deployed in the vehicle, and the matching device can obtain visual lane information through the collection device.

[0068] S202: Determine a target matching score between the lane to be identified and each preset lane according to the visual lane information and the map lane information.

[0069] Among them, one preset lane corresponds to one target matching score, and the target matching score is used to reflect the matching degree between the lane to be identified and the corresponding preset lane (that is, the target matching score is proportional to the matching degree).

[0070] It should be noted that, in the embodiment of the present application, the target matching score may include: a first matching score of the lane width values ​​between different lanes, one preset lane corresponds to one first matching score, and the first matching score is used to reflect the lane width error between the lane to be identified and the corresponding preset lane (that is, the first matching score is inversely proportional to the lane width error).

[0071] In some embodiments, the first matching score of the lane to be identified is used to indicate the degree of lane width deviation between the lane to be identified and the preset lane when the lane width value of the lane to be identified and the lane width value of the preset lane are both within a preset width range.

[0072] Exemplarily, if both the left and right lane lines are valid and the map lane width (map_lane_width) and the visual lane width (camera_lane_width) are both valid widths (i.e., within a preset width range), the lane width match score (lane_width_match_score) (i.e., the first match score) is calculated as (1-abs(map_lane_width-camera_lane_width) / lane width match threshold)*20.

[0073] Where abs is used to indicate absolute value calculation, and the lane width match threshold (lane_width_match_thresh) can be equal to 0.15 times the map lane width. If the left and right lane lines on the map are invalid (i.e. the length of the lane line is less than or equal to the preset length threshold, and / or the lane line does not really exist), the lane width match threshold is set to 0.3m.

[0074] That is to say, by screening the width matches between lanes through preset width intervals, invalid matching of lanes with larger widths due to data errors can be avoided, thereby improving lane matching efficiency.

[0075] In an embodiment of the present application, the target matching score may also include: a second matching score of the lane centerline position information between different lanes, one preset lane corresponds to one second matching score, and the second matching score is used to reflect the lane centerline deviation between the lane to be identified and the corresponding preset lane (i.e., the second matching score is inversely proportional to the lane centerline deviation).

[0076] In some embodiments, the lane information may further include: length values ​​of lane lines on the left and right sides and indication information, the indication information being used to indicate whether the lane lines actually exist (i.e., the virtual lane lines in the map do not actually exist). The second matching score of the lane to be identified may satisfy at least one of the following (1)-(3):

[0077] (1) If the lengths of the left and right lane lines of the lane to be identified are both greater than a preset length threshold, and the indication information of the left and right lane lines of the lane to be identified both indicate real existence, then the second matching score of the lane to be identified is used to indicate the degree of deviation between the lane centerline position information of the lane to be identified and the lane line position information of the preset lane;

[0078] (2) If the length of only the left lane line of the lane to be identified is greater than the preset length threshold, and the indication information of only the left lane line of the lane to be identified indicates that it actually exists, then the second matching score of the lane to be identified is equal to the preset matching score;

[0079] (3) If the length value of only the right lane line of the lane to be identified is greater than the preset length threshold, and the indication information of only the right lane line of the lane to be identified indicates that it actually exists, then the second matching score of the lane to be identified is equal to the preset matching score.

[0080] Exemplarily, when the length of the left and right lane lines on the map is greater than 6 meters and the type of the lane lines is not a virtual type, the left and right lane lines on the map are valid.

[0081] If both the visual left and right lane lines and the map left and right lane lines are valid, the difference in lateral deviation between the map left and right lane lines and the visual left and right lane lines is calculated respectively, that is, the lateral deviation of the map lane line minus the absolute value of the lateral deviation of the visual lane line, and then the average of the difference in lateral deviations is taken as the lateral deviation (lateral_error) of the lane (that is, the lane centerline deviation), and the lateral deviation confidence (lateral_error_conf) of the lane is calculated. The lateral deviation confidence of the lane is equal to 1.2m minus the difference in lateral deviations of the left and right lane lines, multiplied by a coefficient of 100.

[0082] If only the left lane line is valid, the lateral deviation difference between the map and the visual left lane line is used as the lateral deviation of the lane, and the lateral deviation confidence is set to 50.

[0083] If only the right lane line is valid, the lateral deviation difference between the map and the visual right lane line is used as the lateral deviation of the lane, and the lateral deviation confidence is set to 50.

[0084] If both the left and right lane lines are invalid, the lateral deviation of the lane is 0, and the lateral deviation confidence is set to 0.

[0085] In summary, if the lateral deviation confidence is greater than 20, the confidence match score (lat_conf_match_score) (ie, the second match score) is (1-abs(lateral_error) / 2.5)*20.

[0086] In other words, the lane centerline matching between lanes is screened by the lane line length and the actual existence of the lane line, thereby avoiding invalid matching for non-valid lanes and improving the lane matching efficiency.

[0087] Optionally, the target matching score may be the sum of the first matching score and the second matching score.

[0088] S203: Determine a target lane from a plurality of preset lanes according to a preset matching threshold.

[0089] As a possible implementation, the matching device may pre-store a preset matching threshold. The matching device may determine the size relationship between the target matching score corresponding to each preset lane and the preset matching threshold according to the preset matching threshold, and use the preset lane whose corresponding target matching score is greater than the preset matching threshold as the target lane that matches the lane to be identified, and then determine the target lane, that is, the target matching score between the target lane and the lane to be identified is greater than the preset matching threshold.

[0090] Exemplarily, the multiple preset lanes may include: preset lane A, preset lane B, and preset lane C. The target matching score between the preset lane A and the lane to be identified is 1, the target matching score between the preset lane B and the lane to be identified is 2, and the target matching score between the preset lane C and the lane to be identified is 3. If the preset matching threshold is 2, the preset lane C is the target lane.

[0091] The technical solution provided by the above embodiment brings at least the following beneficial effects: based on the width and centerline position of the lane where the vehicle is located (i.e., the visual lane) from the visual angle, it is matched with all the map lanes in the preset map data to obtain a map lane with a smaller width error and centerline deviation from the visual lane, thereby determining the lane where the vehicle is actually located and achieving lane matching. In this way, based on the width error and centerline deviation between lanes, a valuable reference can be provided for lane matching, thereby improving the accuracy of lane matching.

[0092] In some embodiments, the visual lane information may further include: lane information of left and right lanes of the lane to be identified, and the target matching score may further include: a third matching score of the number of left and right lanes between different lanes.

[0093] Among them, one preset lane corresponds to one third matching score, and the third matching score is used to reflect the error in the number of left and right lanes between the lane to be identified and the corresponding preset lane (that is, the third matching score is inversely proportional to the number of left and right lanes).

[0094] Exemplarily, the number of lanes on the left and right sides of the current lane is determined by the attributes of the left and right, secondary left and right, and left and right boundary lane lines in the map and vision, as well as whether the type is a solid line or a dashed line.

[0095] If the left lane line is a dotted line type, the secondary left lane line is invalid, the left boundary is valid, and the lateral deviation between the left lane line and the left boundary is less than 3m, the number of left lanes (left_lane_num) is 0.

[0096] If the left lane line, the secondary left lane line and the left boundary are all valid, and the lateral deviation between the secondary left lane line and the left boundary is less than 2m, the left lane number (left_lane_num) is 1.

[0097] Similarly, if the right lane line is a dotted line type, the secondary right lane line is invalid, the right boundary is valid, and the lateral deviation between the right lane line and the right boundary is less than 3m, then the number of right lanes (right_lane_num) is 0.

[0098] If the right lane line, the second right lane line and the right boundary are all valid, and the lateral deviation between the second right lane line and the right boundary is less than 2m, the right lane number (right_lane_num) is 1.

[0099] In summary, if the number of times the left and right lane numbers are 0 is a, and the number of times the left and right lane numbers are 1 is b, then the lane number matching score (lane_num_match_score) (ie, the third matching score) is 15*a+10*b.

[0100] That is to say, based on the error in the number of left and right lanes between lanes, it can provide valuable reference for lane matching and improve the accuracy of lane matching.

[0101] In some embodiments, the lane information may also include: lane line type information on the left and right sides, the lane line type information is used to indicate a dashed lane line or a solid lane line, and the target matching score may also include: a fourth matching score of the lane line type information of the left and right lanes between different lanes.

[0102] Among them, one preset lane corresponds to one fourth matching score, and the fourth matching score is used to reflect the lane line type deviation of the left and right lanes between the lane to be identified and the corresponding preset lane (that is, the fourth matching score is inversely proportional to the lane line type deviation of the left and right lanes).

[0103] Exemplarily, if the map and visual left and right lane lines are valid and the left and right lane lines are of the same type, and the number of times they are the same is n, then the lane line matching score (line_num_match_score) (ie, the fourth matching score) is 10*n.

[0104] That is to say, the lane line type deviation between the left and right lanes based on the lanes can provide valuable reference for lane matching and improve the accuracy of lane matching.

[0105] In some embodiments, after the matching device determines the target lane from multiple preset lanes according to a preset matching threshold (ie, S203), the matching device may also determine the confidence level of the lane to be identified matching the target lane according to the target matching score between the target lane and the lane to be identified.

[0106] Exemplarily, based on the target matching score (max_match_score) corresponding to the target lane, the matching confidence (match_conf) is calculated as max(0, (max_match_score-10) / 50).

[0107] That is to say, after providing the vehicle user with the most matching lane recognition result, the matching device may also provide the user with the credibility of the recognition result through the confidence level, so as to provide a reference for the user in applying the lane recognition result.

[0108] The lane matching method provided in the embodiment of the present application is introduced below with reference to specific examples. Figure 3 As shown, the steps include steps 1 to 7.

[0109] Step 1: Obtain visual lane line and map lane line information. When the current vehicle is driving on a road covered by a high-precision map, the map lane line and visual lane line of the current lane are determined based on the high-precision navigation information and the current positioning information provided by the vehicle positioning sensor. The visual lane line of the current lane is first matched with the map lane line of the current lane to perform lane matching.

[0110] Step 2: Obtain the lane width and lane width matching threshold of the map lane through the map lane lines obtained through the high-precision map and positioning information (i.e., calculate the map lane width and visual lane width, set the lane width matching threshold, and perform lane width matching).

[0111] First, determine the validity of the left and right lane lines of the current vehicle. When the length of the left and right lane lines on the map is greater than 6 meters and the type of the lane lines is not virtual, the left and right lane lines on the map are valid. If valid, set the lateral deviation of the left line of the map to a positive value, and the lateral deviation of the right line of the map to a negative value, and calculate the map lane width (map_lane_width). The map lane width is the absolute value of the lateral deviation of the left line of the map minus the lateral deviation of the right line of the map. Then calculate the map lane width matching threshold (lane_width_match_thresh), and the lane width matching threshold is equal to the map lane width multiplied by 0.15. If the left and right lane lines on the map are invalid, set the lane width matching threshold to 0.3m.

[0112] Step 3: By matching the visual left and right lane lines with the map left and right lane lines, the lateral deviation between the map lane lines and the visual lane lines is calculated to obtain the lateral deviation confidence.

[0113] First, the validity of the visual left and right lane lines and the map left and right lane lines is verified. The validity verification method refers to the validity verification method of the map left and right lane lines in step 2, which will not be repeated here.

[0114] If both the visual left and right lane lines and the map left and right lane lines are valid, the difference in lateral deviation between the map left and right lane lines and the visual left and right lane lines is calculated respectively, that is, the lateral deviation of the map lane line minus the absolute value of the lateral deviation of the visual lane line, and then the average of the difference in lateral deviations is taken as the lateral deviation (lateral_error) of the lane (that is, the lane centerline deviation), and the lateral deviation confidence (lateral_error_conf) of the lane is calculated. The lateral deviation confidence of the lane is equal to 1.2m minus the difference in lateral deviations of the left and right lane lines, multiplied by a coefficient of 100.

[0115] If only the left lane line is valid, the lateral deviation difference between the map and the visual left lane line is used as the lateral deviation of the lane, and the lateral deviation confidence is set to 50.

[0116] If only the right lane line is valid, the lateral deviation difference between the map and the visual right lane line is used as the lateral deviation of the lane, and the lateral deviation confidence is set to 50.

[0117] If both the left and right lane lines are invalid, the lateral deviation of the lane is 0, and the lateral deviation confidence is set to 0.

[0118] Step 4: Calculate the number of lanes on the left and right sides of the current lane by calculating the map and visual lane line type.

[0119] If the left lane line is a dotted line type, the secondary left lane line is invalid, the left boundary is valid, and the lateral deviation between the left lane line and the left boundary is less than 3m, the number of left lanes (left_lane_num) is 0.

[0120] If the left lane line, the secondary left lane line and the left boundary are all valid, and the lateral deviation between the secondary left lane line and the left boundary is less than 2m, the left lane number (left_lane_num) is 1.

[0121] Similarly, if the right lane line is a dotted line type, the secondary right lane line is invalid, the right boundary is valid, and the lateral deviation between the right lane line and the right boundary is less than 3m, then the number of right lanes (right_lane_num) is 0.

[0122] If the right lane line, the second right lane line and the right boundary are all valid, and the lateral deviation between the second right lane line and the right boundary is less than 2m, the right lane number (right_lane_num) is 1.

[0123] Step 5: Determine the degree of match between the lane width, number of lane lines, and number of left and right lanes of the map lane lines and the visual lane lines, and calculate the lane matching score based on the lateral deviation of the lane, the lateral deviation confidence, and the number of left and right lanes (i.e., calculate the matching score through the lateral deviation confidence and the lane and lane line information).

[0124] If both the left and right lane lines are valid and the map lane width and the visual lane width are both valid widths, the lane width match score (lane_width_match_score) (i.e., the first match score) is calculated as (1-abs(map_lane_width-camera_lane_width) / lane_width_match_thresh)*20.

[0125] If the lateral deviation confidence is greater than 20, the confidence match score (lat_conf_match_score) (ie, the second match score) is (1-abs(lateral_error) / 2.5)*20.

[0126] If the map and visual left and right lane lines are valid and the left and right lane lines are of the same type, and the number of times they are the same is n, then the lane line matching score (line_num_match_score) (i.e., the fourth matching score) is 10*n.

[0127] If the number of times the left and right lane numbers are 0 is a, and the number of times the left and right lane numbers are 1 is b, then the lane number matching score (lane_num_match_score) (ie, the third matching score) is 15*a+10*b.

[0128] The lane matching score (lane_match_score) (i.e., the target matching score) is the sum of the lane width matching score, the confidence matching score, the lane line matching score, and the lane number matching score. The above steps 1 to 5 first match the current lane through the visual lane line of the current lane and the map lane line of the current lane.

[0129] Step 6: Determine the lane matching situation by moving the lane of the map to the left by one lane and to the right by one lane, and calculate the score of matching the left lane and the score of matching the right lane.

[0130] Move the current lane on the map to the left by one lane and use it as the new current lane, that is, match it with the left lane. The visual lane line matches the left lane line of the map lane line: the original right lane line on the map becomes the current left lane line, the original secondary right line becomes the current right line, the original left lane line becomes the current secondary left line, and the current secondary left line is set to invalid. The score of the matching left lane (left_lane_match_score) is calculated through steps 2 to 5, which will not be repeated here.

[0131] Similarly, the current lane of the map is moved one lane to the right as the new current lane, that is, it is matched with the right lane, and the visual lane line matches the right lane line of the map: the original left lane line of the map becomes the current right lane line, the original secondary left line becomes the current left line, the original right lane line becomes the current secondary right line, and the current secondary right line is invalidated. The score of the matching right lane (right_lane_match_score) is calculated through steps 2 to 5, which will not be repeated here.

[0132] Step 7: Compare the matching scores of the three matched lanes to see which lane has the highest matching score. If the highest matching score is the current lane, the lane line remains unchanged. If the highest matching score is the left lane, the lane line needs to be moved one lane to the left. If the highest matching score is the right lane, the lane line needs to be moved one lane to the right. Then calculate the matching confidence and output the lane matching result.

[0133] Select the maximum score (max_match_score) (i.e., the target match score corresponding to the target lane) among the scores for matching the own lane, matching the left lane, and matching the right lane, and calculate the matching confidence (match_conf) as max(0,(max_match_score-10) / 50). If the matching score of the own lane is the largest, the matching lane is the own lane, the map lane line index does not need to change, and the confidence of matching the own lane is output. If the matching score of the left lane is the largest, the matching lane is the left lane, the map lane line needs to be moved one lane to the left like when calculating the matching score, and the confidence of matching the left lane is output. If the matching score of the right lane is the largest, the matching lane is the right lane, the map lane line needs to be moved one lane to the right like when calculating the matching score, and the confidence of matching the right lane is output.

[0134] It can be understood that when the current vehicle is traveling on a road covered by a high-precision map, the map lane line and the visual lane line of the current lane are obtained according to the high-precision navigation information and the current positioning information provided by the vehicle positioning sensor, the lane width matching threshold is set, and the map lane width and the visual lane width are calculated to match the lane width. In addition, the map lane line and the visual lane line are checked for validity, and the lateral deviation difference and lateral deviation confidence information of the map and visual left and right lane lines are calculated. Then, the number of lanes on the left and right sides of the current lane is calculated by the attributes of the left and right, secondary left and right, and left and right boundary lane lines of the map and vision, as well as whether the type is a solid line or a dotted line. Finally, the lane matching score is calculated based on the lateral deviation, lateral deviation confidence, and left and right lanes calculated above. At the same time, the left and right lanes of the map are translated left and right, and matched again to calculate the scores of the left lane matching and the right lane matching. The lane with the largest score is output as the lane, and the corresponding matching confidence is calculated, and finally the lane matching of the high-precision map and the visual lane line is completed. In this way, lane information can be obtained after matching high-precision maps and visual lane lines, making positioning accuracy higher and improving the stability and safety of the intelligent driving system.

[0135] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the lane matching device or equipment includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0136] The embodiment of the present application can exemplarily divide the lane matching device or equipment into functional modules according to the above method. For example, the lane matching device or equipment can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0137] Figure 4 is a block diagram of a lane matching device according to an exemplary embodiment, wherein the lane matching device is applied to a vehicle and is used to perform Figure 2The lane matching device 400 includes: an acquisition module 401 and a processing module 402 .

[0138] The acquisition module 401 is used to acquire map lane information and visual lane information. The map lane information includes: lane information of multiple preset lanes. The visual lane information includes: lane information of the lane to be identified where the vehicle is located. The lane information includes: lane width value and lane centerline position information. The processing module 402 is used to determine the target matching score between the lane to be identified and each preset lane based on the visual lane information and the map lane information. The target matching score includes: a first matching score of the lane width value between different lanes and a second matching score of the lane centerline position information between different lanes. The processing module 402 is also used to determine the target lane from the multiple preset lanes based on a preset matching threshold. The target matching score between the target lane and the lane to be identified is greater than the preset matching threshold.

[0139] In a possible implementation, the processing module 402 is specifically used to indicate the degree of deviation between the lane centerline position information of the lane to be identified and the lane line position information of the preset lane if the length values ​​of the lane lines on both sides of the lane to be identified are greater than the preset length threshold and the indication information of the lane lines on both sides of the lane to be identified indicates real existence. The processing module 402 is also used to equal the preset matching score for the lane to be identified if the length value of only the left lane line of the lane to be identified is greater than the preset length threshold and the indication information of only the left lane line of the lane to be identified indicates real existence. The processing module 402 is also used to equal the preset matching score for the lane to be identified if the length value of only the right lane line of the lane to be identified is greater than the preset length threshold and the indication information of only the right lane line of the lane to be identified indicates real existence.

[0140] In a possible implementation manner, the processing module 402 is further configured to determine a confidence level that the lane to be identified matches the target lane according to a target matching score between the target lane and the lane to be identified.

[0141] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0142] Figure 5 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 5 As shown, the electronic device 500 includes but is not limited to: a processor 501 and a memory 502 .

[0143] The memory 502 is used to store executable instructions of the processor 501. It can be understood that the processor 501 is configured to execute instructions to implement the lane matching method in the above embodiment.

[0144] It should be noted that those skilled in the art can understand that Figure 5 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Figure 5 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0145] The processor 501 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 502, and calling data stored in the memory 502, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 501 may include one or more processing units. Optionally, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 501.

[0146] The memory 502 may be used to store software programs and various data. The memory 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a processing unit), etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0147] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 502 including instructions. The above instructions can be executed by a processor 501 of an electronic device 500 to implement the lane matching method in the above embodiment.

[0148] In actual implementation, Figure 4 The functions of the acquisition module 401 and the processing module 402 can be obtained by Figure 5 The processor 501 in the embodiment calls the computer program stored in the memory 502. The specific execution process can refer to the description of the lane matching method in the above embodiment, which will not be repeated here.

[0149] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0150] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, and the one or more instructions can be executed by a processor of an electronic device to complete the lane matching method in the above embodiment.

[0151] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned lane matching method embodiment are implemented, and the same technical effect as the above-mentioned lane matching method can be achieved. To avoid repetition, they will not be repeated here.

[0152] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0156] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0157] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A lane matching method, characterized in that: Applied to a vehicle, the method comprises: Acquire map lane information and visual lane information, wherein the map lane information includes lane information of a plurality of preset lanes, the visual lane information includes lane information of a lane to be identified where the vehicle is located, and the lane information includes lane width value and lane centerline position information; Determine, according to the visual lane information and the map lane information, a target matching score between the lane to be identified and each of the preset lanes, the target matching score comprising: a first matching score of lane width values ​​between different lanes, and a second matching score of lane centerline position information between different lanes; According to a preset matching threshold, a target lane is determined from the plurality of preset lanes, and a target matching score between the target lane and the lane to be identified is greater than the preset matching threshold.

2. The method according to claim 1, characterized in that: The first matching score of the lane to be identified is used to indicate a lane width deviation degree between the lane to be identified and the preset lane when the lane width value of the lane to be identified and the lane width value of the preset lane are both within a preset width range.

3. The method according to claim 1, characterized in that The lane information further includes: length values ​​and indication information of lane lines on the left and right sides, wherein the indication information is used to indicate whether the lane lines actually exist, and the second matching score of the lane to be identified satisfies at least one of the following: If the length values ​​of the lane lines on the left and right sides of the lane to be identified are both greater than the preset length threshold, and the indication information of the lane lines on the left and right sides of the lane to be identified both indicate real existence, then the second matching score of the lane to be identified is used to indicate the degree of deviation between the lane centerline position information of the lane to be identified and the lane line position information of the preset lane; If the length value of only the left lane line of the lane to be identified is greater than the preset length threshold, and the indication information of only the left lane line of the lane to be identified indicates that it actually exists, then the second matching score of the lane to be identified is equal to the preset matching score; If the length value of only the right lane line of the lane to be identified is greater than the preset length threshold, and the indication information of only the right lane line of the lane to be identified indicates real existence, then the second matching score of the lane to be identified is equal to the preset matching score.

4. The method according to claim 1, characterized in that: The visual lane information further includes: lane information of left and right lanes of the lane to be identified, and the target matching score further includes: a third matching score of the number of left and right lanes between different lanes.

5. The method according to claim 4, characterized in that The lane information also includes: lane line type information on the left and right sides, and the lane line type information is used to indicate a dashed lane line or a solid lane line. The target matching score also includes: a fourth matching score of the lane line type information of the left and right lanes between different lanes.

6. The method according to any one of claims 1 to 5, characterized in that After determining the target lane from the plurality of preset lanes according to the preset matching threshold, the method further includes: A confidence level that the lane to be identified matches the target lane is determined based on a target matching score between the target lane and the lane to be identified.

7. A lane matching device, characterized in that: Applied to a vehicle, the device comprises: An acquisition module, used to acquire map lane information and visual lane information, wherein the map lane information includes lane information of a plurality of preset lanes, the visual lane information includes lane information of a lane to be identified where the vehicle is located, and the lane information includes lane width value and lane centerline position information; A processing module, configured to determine a target matching score between the lane to be identified and each of the preset lanes according to the visual lane information and the map lane information, wherein the target matching score includes: a first matching score of lane width values ​​between different lanes, and a second matching score of lane centerline position information between different lanes; The processing module is further used to determine a target lane from the multiple preset lanes according to a preset matching threshold, and a target matching score between the target lane and the lane to be identified is greater than the preset matching threshold.

8. An electronic device, characterized in that: include: processor; A memory for storing the processor executable instructions; wherein the processor is configured to execute the instructions to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the method as claimed in any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises computer program instructions which, when executed, implement the method according to any one of claims 1 to 6.

Images