A lane line recognition method and device, a vehicle, and a storage medium

Abstract

Embodiments of the present application disclose a lane line identification method and device, a vehicle and a storage medium, comprising: acquiring lane line information respectively output by an environment perception device and a high-definition map, and initial confidence corresponding to each lane line; matching lane lines respectively output by the environment perception device and the high-definition map according to the lane line information, determining fusion confidence corresponding to each lane line according to a matching result and the initial confidence corresponding to each lane line; screening target lane lines from lane lines respectively output by the environment perception device and the high-definition map according to the fusion confidence corresponding to each lane line and a preview distance corresponding to the environment perception device, and taking the target lane lines as lane line identification information corresponding to an automatic driving mode. The technical solution of the embodiments of the present application can improve the accuracy and reliability of lane line identification, and guarantee the safety and stability of the vehicle in the automatic driving process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to a lane line identification method and device, a vehicle and a storage medium. BACKGROUND

[0002] Automatic driving is a leading technology that enables vehicles to drive by themselves without driver operation. Among them, the collection and processing of environmental information is the basis for realizing automatic driving of vehicles, and the identification and detection of lane lines are the core of environmental information collection and processing. With the rapid development of automatic driving technology, whether to accurately obtain lane line information has become an important factor affecting the performance of automatic driving.

[0003] In the prior art, lane line information is usually obtained through perception devices or high-precision maps. Perception devices can obtain lane line information by analyzing video images, and high-precision maps can obtain lane line information based on environmental perception and vehicle positioning.

[0004] However, the method of obtaining lane line information through perception devices is easily affected by external factors such as light, climate and road curvature, resulting in inaccurate lane line information; the method of obtaining lane line information through high-precision maps is also inaccurate when vehicle positioning is disturbed. SUMMARY

[0005] The present application provides a lane line identification method, device, vehicle and storage medium, which can improve the accuracy and reliability of lane line identification, and ensure the safety and stability of the vehicle during automatic driving.

[0006] In a first aspect, the present application provides a lane line identification method applied to a vehicle, comprising:

[0007] Obtaining lane line information output by an environmental perception device and a high-precision map respectively, and an initial confidence corresponding to each lane line;

[0008] According to each lane line information, the lane lines output by the environmental perception device and the high-precision map are matched, and according to the matching result and the initial confidence corresponding to each lane line, the fusion confidence corresponding to each lane line is determined;

[0009] According to the fusion confidence corresponding to each lane line and the preview distance corresponding to the environmental perception device, the target lane line is screened from the lane lines output by the environmental perception device and the high-precision map respectively, and the target lane line is taken as the lane line identification information corresponding to the automatic driving mode.

[0010] In a second aspect, the present application further provides a lane line identification device, comprising:

[0011] The information acquisition module is configured to acquire lane line information respectively output by the environment perception device and the high-definition map, and initial confidence corresponding to each lane line;

[0012] The confidence fusion module is configured to match lane lines respectively output by the environment perception device and the high-definition map according to the lane line information, and determine fusion confidence corresponding to each lane line according to a matching result and the initial confidence corresponding to each lane line.

[0013] The target lane line determination module is configured to filter target lane lines from the lane lines respectively output by the environment perception device and the high-definition map according to the fusion confidence corresponding to each lane line and a preview distance corresponding to the environment perception device, and take the target lane lines as lane line recognition information corresponding to the automatic driving mode.

[0014] In a third aspect, an embodiment of the present application further provides a vehicle, which comprises:

[0015] at least one processor; and

[0016] a memory connected with the at least one processor in communication; wherein

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the lane line recognition method provided by any one of the embodiments of the present application.

[0018] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement the lane line recognition method provided by any one of the embodiments of the present application when executed.

[0019] The technical scheme provided by the embodiments of the present application can improve the accuracy and reliability of lane line recognition, and guarantee the safety and stability of the vehicle in the automatic driving process, by acquiring lane line information respectively output by the environment perception device and the high-definition map, and initial confidence corresponding to each lane line; matching lane lines respectively output by the environment perception device and the high-definition map according to the lane line information, and determining fusion confidence corresponding to each lane line according to a matching result and the initial confidence corresponding to each lane line; and filtering target lane lines from the lane lines respectively output by the environment perception device and the high-definition map according to the fusion confidence corresponding to each lane line and a preview distance corresponding to the environment perception device, and taking the target lane lines as lane line recognition information corresponding to the automatic driving mode.

[0020] It is to be understood that the details set forth herein do not limit the scope of the embodiments of the application to the specific embodiments described. Rather, the scope of the embodiments of the application is to be defined by the appended claims. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0022] Figure 1 is a flow chart of a lane line recognition method according to an embodiment of the present application;

[0023] Figure 2 is a flow chart of another lane line recognition method according to an embodiment of the present application;

[0024] Figure 3 is a flow chart of another lane line recognition method according to an embodiment of the present application;

[0025] Figure 4 is a flow chart of a method for screening target lane lines according to an embodiment of the present application;

[0026] Figure 5 is a structural schematic diagram of a lane line recognition device according to an embodiment of the present application;

[0027] Figure 6 is a structural schematic diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the technical personnel in the art better understand the present application scheme, the following will combine the drawings in the embodiments of the present application, and the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0029] It is to be understood that the terminology "first", "second" and the like used in the specification and the claims of the application as well as the foregoing drawings is merely intended to distinguish between similar objects and not necessarily for describing a particular sequential order. It is to be understood that the data used herein can be interchanged, where appropriate, so that the embodiments of the application described herein can be carried out in sequences other than those illustrated or described herein. Furthermore, the terms "comprise", "comprising", "has", "having", "includes", "including", and the like are intended to cover non-exclusive inclusions, such that processes, methods, systems, products, or devices that comprise, have, include or the like a list of steps or elements are not necessarily limited to those steps or elements that are expressly listed, but can include other steps or elements not expressly listed or inherent to such processes, methods, products, or devices.

[0030] Embodiment one

[0031] Figure 1 is a flowchart of a lane line identification method according to an embodiment of the application. The embodiment can be applicable to the case of identifying lane lines. The method can be executed by a lane line identification device, which can be implemented in the form of hardware and / or software, and can be configured in a vehicle.

[0032] As shown in Figure 1 , the lane line identification method disclosed in the embodiment comprises:

[0033] S110, acquiring lane line information respectively output by an environment perception device and a high-definition map, and initial confidence corresponding to each lane line.

[0034] In the embodiment, the environment perception device and the high-definition map can both be deployed in a vehicle. The environment perception device can include a laser radar, a millimeter wave radar, an inertial sensor, an intelligent camera, an ultrasonic radar, etc. The high-definition map can be used to provide road information such as road signs, traffic signs, traffic lights, lane curvature, and slope. The positioning accuracy of the high-definition map can reach centimeter level.

[0035] For example, for the current vehicle, the environment perception device and the high-definition map can respectively output four lane lines, including a first lane line and a second lane line on the left side of the current vehicle, and a first lane line and a second lane line on the right side of the current vehicle. Among them, the horizontal distance between the left first lane line and the current vehicle is less than the horizontal distance between the left second lane line and the current vehicle, and the horizontal distance between the right first lane line and the current vehicle is less than the horizontal distance between the right second lane line and the current vehicle. Each lane line can be represented by the following cubic polynomial equation:

[0036] y = C0 + C1x + C2x 2 +C3x 3

[0037] wherein C0 is a lateral distance of a vehicle body center from a lane line, C1 is a heading angle of the vehicle body relative to the lane line, C2 is a curvature of the lane center line, C3 is a rate of change of the curvature, and x is a preview distance.

[0038] The initial confidence can reflect the confidence of the lane line information output by the environment perception device and the high-definition map respectively.

[0039] S120, according to each lane line information, the lane lines output by the environment perception device and the high-definition map are matched, and according to the matching result and the initial confidence corresponding to each lane line, the fusion confidence corresponding to each lane line is determined.

[0040] In this embodiment, the matching result can be the result of one-to-one correspondence of the lane lines output by the environment perception device and the high-definition map. The value of the fusion confidence can be determined according to the size of the initial confidence corresponding to each lane line.

[0041] In this step, specifically, if the lane lines output by the environment perception device and the high-definition map both have high initial confidence, the fusion confidence of the above lane lines can be set to a high value. If the lane lines output by the environment perception device and the high-definition map both have low initial confidence, the fusion confidence of the above lane lines can be set to a low value, such as 0.

[0042] The advantage of such setting is that in actual application, the lane line information obtained by the environment perception device has high real-time performance but is easily affected by external factors such as light and climate, the lane line information obtained by the high-definition map is not easily affected by weather, but when the vehicle positioning is disturbed, the output lane line information is inaccurate, so a single positioning source cannot guarantee the accuracy of lane line recognition. The embodiment proposes a method for obtaining lane line information based on fusion of the environment perception device and the high-definition map, which can improve the accuracy and reliability of lane line recognition.

[0043] S130, according to the fusion confidence corresponding to each lane line and the preview distance corresponding to the environment perception device, a target lane line is screened from the lane lines output by the environment perception device and the high-definition map, and the target lane line is taken as the lane line recognition information corresponding to the automatic driving mode.

[0044] In this embodiment, the preview distance can be the environment information collection range corresponding to the environment perception device. The target lane line can be the lane line output by the environment perception device or the lane line output by the high-definition map. Optionally, the fusion confidence and the preview distance can be compared with corresponding thresholds respectively, and according to the comparison result, the lane line output by the environment perception device or the high-definition map is screened as the target lane line.

[0045] In actual application, the target lane line can be used as input information of automatic driving control, so that the automatic driving decision system of the vehicle can realize path planning and navigation in combination with the coordinate positions of the facilities around the vehicle.

[0046] The technical scheme of the embodiment can improve the accuracy and reliability of lane line recognition, and guarantee the safety and stability of the vehicle in the automatic driving process.

[0047] Embodiment Two

[0048] Figure 2 is a flowchart of another lane line recognition method according to Embodiment Two of the present application. The present embodiment is a further optimization and expansion based on the above-mentioned embodiments, and can be combined with each optional technical scheme in the above-mentioned embodiments.

[0049] As shown in Figure 2 Another lane line recognition method disclosed by the present embodiment includes:

[0050] S210, acquiring lane line information respectively output by an environment perception device and a high-definition map, and initial confidence degrees corresponding to each lane line.

[0051] S220, determining invalid lane lines in all lane lines respectively output by the environment perception device and the high-definition map, and eliminating the invalid lane lines.

[0052] In the present embodiment, optionally, the invalid lane line can be a fuzzy or special-shaped lane line recognized by the environment perception device or the high-definition map. The fuzzy lane line can be manifested as that the recognized lane line edge is not clear. The special-shaped lane line can be a lane line shape that does not conform to the existing conventional lane line shape.

[0053] In an optional implementation of the embodiment of the present application, the invalid lane line is determined from all lane lines output by the environment perception device, including: acquiring a plurality of adjacent lane lines on the same side of the vehicle output by the environment perception device; sampling the plurality of adjacent lane lines in sequence according to a preset distance according to the starting positions and the ending positions respectively corresponding to the plurality of adjacent lane lines, to obtain a plurality of sampling points respectively corresponding to the plurality of adjacent lane lines; determining the lateral distance of the sampling points between each two adjacent lane lines, and counting the number of target sampling points when the lateral distance is less than a preset threshold; and if the number of target sampling points is greater than half of the total number of sampling points, acquiring the lane line farthest from the vehicle among the plurality of adjacent lane lines as the invalid lane line.

[0054] In the embodiment, the preset threshold can be half of the average lane line width. When the lateral distance of the sampling points between two adjacent lane lines is less than the preset threshold, the sampling points can be determined as target sampling points.

[0055] For example, assuming that the two adjacent lane lines on the left side of the current vehicle output by the environment perception device are A and B (the lateral distance between A and the vehicle is greater than the lateral distance between B and the vehicle), the starting positions and the ending positions of A and B can be extracted respectively, and A and B can be sampled at equal distances according to a preset separation distance. Assuming that the sampling points on lane line A include P1, P2 and P3, and the sampling points on lane line B include Q1, Q2 and Q3, the lateral distances between P1 and Q1, P2 and Q2, and P3 and Q3 can be calculated respectively, and if the lateral distance between P1 and Q1 is less than half of the average lane line width, P1 and Q1 can be determined as target sampling points.

[0056] The advantage of such a setting is that by eliminating the invalid lane line, the subsequent lane line recognition process can be avoided to process the invalid lane line, thereby saving the processing time of the lane line and improving the recognition efficiency of the target lane line.

[0057] In an optional implementation of the embodiment of the present application, the invalid lane line is determined from all lane lines output by the high-definition map, including: acquiring a plurality of adjacent lane lines on the same side of the vehicle output by the high-definition map; sampling the plurality of adjacent lane lines in sequence according to a preset distance according to the starting positions and the ending positions respectively corresponding to the plurality of adjacent lane lines, to obtain a plurality of sampling points respectively corresponding to the plurality of adjacent lane lines; determining the lateral distance of the sampling points between each two adjacent lane lines, and counting the number of target sampling points when the lateral distance is less than a preset threshold; and if the number of target sampling points is greater than half of the total number of sampling points, acquiring the lane line farthest from the vehicle among the plurality of adjacent lane lines as the invalid lane line.

[0058] S230, according to each lane line information, the lane lines output by the environment perception device and the high-precision map are matched, and according to the matching result and the initial confidence corresponding to each lane line, the fusion confidence corresponding to each lane line is determined.

[0059] S240, according to the fusion confidence corresponding to each lane line and the preview distance corresponding to the environment perception device, the target lane line is screened from the lane lines output by the environment perception device and the high-precision map respectively, and the target lane line is taken as the lane line recognition information corresponding to the automatic driving mode.

[0060] The technical scheme of the embodiment, by acquiring the lane line information output by the environment perception device and the high-precision map respectively, and the initial confidence corresponding to each lane line, determining the invalid lane line in all lane lines output by the environment perception device and the high-precision map respectively, and eliminating the invalid lane line, according to each lane line information, the lane lines output by the environment perception device and the high-precision map are matched, according to the matching result and the initial confidence corresponding to each lane line, the fusion confidence corresponding to each lane line is determined, according to the fusion confidence corresponding to each lane line and the preview distance corresponding to the environment perception device, the target lane line is screened from the lane lines output by the environment perception device and the high-precision map respectively, and the target lane line is taken as the lane line recognition information corresponding to the automatic driving mode. The technical means can improve the accuracy and reliability of lane line recognition, and guarantee the safety and stability in the process of automatic driving of the vehicle.

[0061] Embodiment three

[0062] Figure 3 is a flowchart of another lane line recognition method according to the embodiment three of the application. The embodiment is further optimized and expanded based on the above-mentioned embodiments, and can be combined with each optional technical scheme in the above-mentioned embodiments.

[0063] As shown in Figure 3 , another lane line recognition method disclosed by the embodiment includes:

[0064] S310, acquiring the lane line information output by the environment perception device and the high-precision map respectively, and the initial confidence corresponding to each lane line.

[0065] S320, acquiring a plurality of lane lines output by the environment perception device and the high-precision map respectively, the number of which is equal.

[0066] S330, according to the sequence of lane lines from left to right or from right to left, each lane line output by the environment perception device is combined with the corresponding lane line output by the high-precision map, and a plurality of lane line groups are obtained.

[0067] In the embodiment, the lane line group can be a combination of two lane lines, and the two lane lines can be output by the environment perception device and the high-definition map respectively.

[0068] For example, if the environment perception device and the high-definition map output four lane lines respectively, the lane lines output by the environment perception device can be named as X1, X2, X3 and X4 from left to right in sequence, and the lane lines output by the high-definition map can be named as Y1, Y2, Y3 and Y4 from left to right in sequence. Then, the lane lines can be combined in pairs according to the arrangement order to obtain four lane line groups, such as {X1, Y1}, {X2, Y2}, {X3, Y3} and {X4, Y4}.

[0069] S340, a lane line group is obtained from the plurality of lane line groups in sequence as a current lane line group.

[0070] S350, a first lane line corresponding to the environment perception device and a second lane line corresponding to the high-definition map are obtained in the current lane line group, and it is determined whether the first lane line and the second lane line are the same. If yes, S360 is executed, and if no, S370 is executed.

[0071] In the embodiment, optionally, it can be determined whether the first lane line and the second lane line are the same according to at least one of the lateral distance of the vehicle body center from each lane line, the heading angle of the vehicle body relative to each lane line, the curvature of the lane center line, the rate of change of the curvature, and the like.

[0072] In one implementation of the embodiment, it is determined whether the first lane line and the second lane line are the same, including: obtaining a first lateral distance between the first lane line and the vehicle body center, and a second lateral distance between the second lane line and the vehicle body center, and determining a difference between the first lateral distance and the second lateral distance; determining whether the absolute value of the difference is greater than a preset value; and if no, determining that the first lane line and the second lane line are the same.

[0073] In the embodiment, the specific calculation formula of the difference between the first lateral distance and the second lateral distance is as follows:

[0074] △C0=C 0eye -C 0ehr

[0075] Wherein, C 0eye is the first lateral distance, and C 0ehr is the second lateral distance.

[0076] If the absolute value of the difference between the first lateral distance C 0eye and the second lateral distance C 0ehr is greater than the preset value, it can be considered that the lane lines recognized by the environment perception device and the high-definition map are different; if the absolute value of the difference between the first lateral distance C0eye the difference between the first lateral distance C 0ehr and the second lateral distance C 0eye is less than or equal to a preset value, it can be considered that the lane line recognized by the environment perception device and the high-definition map are the same.

[0077] For example, the preset value can be 3, and the specific value can be adjusted according to actual conditions, and the embodiment does not limit this. Specifically, if |△C0|>3, it can be considered that the first lane line and the second lane line are not the same; if |△C0|≤3, it can be considered that the first lane line and the second lane line are the same.

[0078] S360, determine that the first lane line and the second lane line match, and return to perform the operation of sequentially obtaining one lane line group from the plurality of lane line groups as the current lane line group in S340 until the processing of all lane line groups is completed.

[0079] S370, update the second lane line, and determine that the updated second lane line matches the first lane line, and then return to perform the operation of sequentially obtaining one lane line group from the plurality of lane line groups as the current lane line group in S340 until the processing of all lane line groups is completed.

[0080] In the embodiment, if the first lane line and the second lane line are not the same, the second lane line can be updated according to the difference between the first lateral distance and the second lateral distance.

[0081] In one embodiment of the embodiment, updating the second lane line includes: adding the second lateral distance corresponding to the second lane line to the absolute value of the difference to obtain an updated lateral distance; and translating the second lane line according to the updated lateral distance to obtain an updated second lane line.

[0082] In one specific embodiment, if the absolute value of the difference between the first lateral distance C 0eye and the second lateral distance C 0ehr is greater than a preset value, and the difference △C0 between the first lateral distance C 0eye and the second lateral distance C 0ehr is less than a preset difference, the first flag can be set; otherwise, if the absolute value of the difference between the first lateral distance C 0eye and the second lateral distance C 0ehr is greater than a preset value, and the difference △C0 between the first lateral distance C 0eye and the second lateral distance C 0ehr is greater than a preset difference, the second flag can be set.

[0083] Exemplarily, the first flag can be -1, and the second flag can be 1, and the specific values can be adjusted according to actual conditions, and the embodiment does not limit this.

[0084] In a specific embodiment, when the second lane line is translated, the translation direction can be determined according to the flag. For example, when the flag is 1, the second lane line can be translated to the left; otherwise, when the flag is -1, the second lane line can be translated to the right.

[0085] S380, according to the matching result and the initial confidence of each lane line, determine the fusion confidence corresponding to each lane line, according to the fusion confidence corresponding to each lane line and the preview distance corresponding to the environment perception device, screen the target lane line from the lane line output by the environment perception device and the high-precision map respectively, and take the target lane line as the lane line recognition information corresponding to the automatic driving mode.

[0086] In an optional implementation of the embodiment of the application, according to the fusion confidence corresponding to each lane line and the preview distance corresponding to the environment perception device, the target lane line is screened from the lane line output by the environment perception device and the high-precision map respectively, which includes the following steps, as shown in Figure 4

[0087] If the fusion confidence of the current lane line is equal to the preset confidence, it is judged whether the preview distance corresponding to the environment perception device is less than the preset distance; if the preview distance is less than the preset distance, the lane line output by the environment perception device is obtained as the target lane line; if the preview distance is greater than or equal to the preset distance, the lane line output by the high-precision map is obtained as the target lane line.

[0088] If the fusion confidence of the current lane line is not equal to the preset confidence, it is judged whether the fusion confidence is equal to the first optional confidence; if the fusion confidence is equal to the first optional confidence, the lane line output by the environment perception device is obtained as the target lane line. If the fusion confidence is not equal to the first optional confidence, it is continued to judge whether the fusion confidence is equal to the second optional confidence.

[0089] If the fusion confidence is equal to the second optional confidence, the lane line output by the high-precision map is obtained as the target lane line. If the fusion confidence is not equal to the second optional confidence, it can be determined that the target lane line does not exist.

[0090] Exemplarily, the preset confidence can be 3, the preset distance can be 50 meters, the first optional confidence can be set to 2, and the second optional confidence can be set to 1, and the specific values can be adjusted according to actual conditions, and the embodiment does not limit this.

[0091] ​In a specific embodiment, if the lane line output by the environment perception device and the lane line output by the high-definition map both correspond to a high initial confidence, the fusion confidence of the lane line can be set to 3. If the initial confidence of the lane line output by the environment perception device is high and the initial confidence of the lane line output by the high-definition map is low, the fusion confidence of the lane line can be set to 2. If the initial confidence of the lane line output by the environment perception device is low and the initial confidence of the lane line output by the high-definition map is high, the fusion confidence of the lane line can be set to 1. If the lane line output by the environment perception device and the lane line output by the high-definition map both correspond to a low initial confidence, the fusion confidence of the lane line can be set to 0.

[0092] In one implementation of the embodiment, if the fusion confidence of the current lane line is equal to 3 and the preview distance is less than 50 meters, the lane line output by the environment perception device can be selected as the target lane line. If the fusion confidence is equal to 3 and the preview distance is greater than 50 meters, the lane line output by the high-definition map can be selected as the target lane line. If the fusion confidence is 2, the pre-processed lane line output by the environment perception device can be obtained as the target lane line. If the fusion confidence is 1, the pre-processed lane line output by the high-definition map can be obtained as the target lane line. If the fusion confidence is not 1, for example, the fusion confidence is 0, it can be determined that the target lane line does not exist.

[0093] The advantage of such a setting is that by combining the fusion confidence of the lane line and the preview distance of the environment perception device to jointly screen the target lane line, the effectiveness and reliability of the screening result of the target lane line can be improved.

[0094] The technical solution of the embodiment obtains a plurality of lane lines output by the environment perception device and a plurality of lane lines output by the high-definition map, respectively; combines each lane line output by the environment perception device with a corresponding lane line output by the high-definition map in the order of the lane lines from left to right or from right to left, to obtain a plurality of lane line groups; obtains a first lane line and a second lane line in a current lane line group, and determines whether the first lane line and the second lane line are the same; if yes, it is determined that the first lane line and the second lane line match; if no, the second lane line is updated, and it is determined that the updated second lane line matches the first lane line; according to the matching result and the initial confidence, a fusion confidence is determined, and according to the fusion confidence and the preview distance, a target lane line is screened, and the target lane line is taken as the technical means of the lane line recognition information corresponding to the automatic driving mode, which can improve the accuracy and reliability of lane line recognition and ensure the safety and stability of the vehicle during automatic driving.

[0095] Embodiment Four

[0096] Figure 5A structural schematic diagram of a lane line recognition device provided for Embodiment Four of the present application, the present embodiment can be applied to the case of recognizing lane lines, and the lane line recognition device can be realized in the form of hardware and / or software and can be configured in a vehicle.

[0097] As shown in Figure 5 , the lane line recognition device disclosed in the present embodiment comprises:

[0098] An information acquisition module 51 is configured to acquire lane line information respectively output by an environment perception device and a high-definition map, and initial confidence degrees corresponding to respective lane lines;

[0099] A confidence degree fusion module 52 is configured to match lane lines respectively output by the environment perception device and the high-definition map according to the respective lane line information, and determine a fusion confidence degree corresponding to each lane line according to a matching result and the initial confidence degree corresponding to the respective lane line;

[0100] A target lane line determination module 53 is configured to filter a target lane line from the lane lines respectively output by the environment perception device and the high-definition map according to the fusion confidence degree corresponding to each lane line and a preview distance corresponding to the environment perception device, and take the target lane line as lane line recognition information corresponding to an automatic driving mode.

[0101] The technical solution in the present embodiment can improve the accuracy and reliability of lane line recognition, and guarantee the safety and stability in the automatic driving process of a vehicle, by acquiring lane line information respectively output by an environment perception device and a high-definition map, and initial confidence degrees corresponding to respective lane lines; matching lane lines respectively output by the environment perception device and the high-definition map according to the respective lane line information, and determining a fusion confidence degree corresponding to each lane line according to a matching result and the initial confidence degree corresponding to the respective lane line; and filtering a target lane line from the lane lines respectively output by the environment perception device and the high-definition map according to the fusion confidence degree corresponding to each lane line and a preview distance corresponding to the environment perception device, and taking the target lane line as lane line recognition information corresponding to an automatic driving mode.

[0102] Optionally, the lane line recognition device further comprises a lane line preprocessing module, which comprises:

[0103] An invalid lane line elimination unit is configured to determine invalid lane lines from all lane lines respectively output by the environment perception device and the high-definition map, and eliminate the invalid lane lines;

[0104] A neighboring lane line acquisition unit is configured to acquire a plurality of neighboring lane lines located on the same side of a vehicle and output by the environment perception device;

[0105] The sampling point acquisition unit is configured to sample the plurality of adjacent lane lines in sequence according to a preset distance based on the starting positions and the ending positions of the plurality of adjacent lane lines, and obtain a plurality of sampling points corresponding to the plurality of adjacent lane lines respectively.

[0106] The sampling point quantity statistics unit is configured to determine a lateral distance of the corresponding sampling points between every two adjacent lane lines, and count a quantity of target sampling points when the lateral distance is less than a preset threshold.

[0107] The invalid lane line determination unit is configured to acquire, as an invalid lane line, a lane line farthest from the vehicle among the plurality of adjacent lane lines if the quantity of target sampling points is greater than half of the total quantity of sampling points.

[0108] Optionally, the confidence fusion module 52 comprises:

[0109] The lane line acquisition unit is configured to acquire a plurality of lane lines output by the environment perception device and the high-definition map respectively, the plurality of lane lines having an equal quantity.

[0110] The lane line group acquisition unit is configured to combine each lane line output by the environment perception device with a corresponding lane line output by the high-definition map according to a sequence of the lane lines from left to right or from right to left, and obtain a plurality of lane line groups.

[0111] The current lane line group determination unit is configured to acquire a lane line group in sequence among the plurality of lane line groups as a current lane line group.

[0112] The lane line judgment unit is configured to acquire a first lane line corresponding to the environment perception device and a second lane line corresponding to the high-definition map in the current lane line group, and judge whether the first lane line and the second lane line are the same; if yes, it is determined that the first lane line and the second lane line are matched; if not, the second lane line is updated, and it is determined that the updated second lane line and the first lane line are matched.

[0113] The lane line group polling unit is configured to return to perform the operation of acquiring a lane line group in sequence among the plurality of lane line groups as a current lane line group until the processing of all the lane line groups is completed.

[0114] The distance difference determination unit is configured to acquire a first lateral distance between the first lane line and the center of the vehicle body and a second lateral distance between the second lane line and the center of the vehicle body, and determine a difference between the first lateral distance and the second lateral distance.

[0115] The difference absolute value judgment unit is configured to judge whether the absolute value of the difference is greater than a preset value; if not, it is determined that the first lane line and the second lane line are the same.

[0116] The lateral distance update unit is used to add the second lateral distance corresponding to the second lane line to the absolute value of the difference to obtain the updated lateral distance;

[0117] The second lane line update unit is used to translate the second lane line according to the updated lateral distance to obtain the updated second lane line.

[0118] Optionally, the target lane line determination module 53 includes:

[0119] The fusion confidence judgment unit is used to determine whether the fusion confidence of the current lane line is equal to the preset confidence.

[0120] The aiming distance judgment unit is used to determine whether the aiming distance corresponding to the environmental perception device is less than the preset distance if the fusion confidence of the current lane line is equal to the preset confidence.

[0121] The lane line filtering and determination unit is used to obtain the lane line output by the environmental sensing device as the target lane line if the pre-aiming distance corresponding to the environmental sensing device is less than the preset distance.

[0122] If the pre-aiming distance corresponding to the environmental perception device is greater than or equal to the preset distance, the lane line output by the high-precision map is used as the target lane line.

[0123] The lane line recognition device provided in this embodiment of the invention can execute the lane line recognition method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Content not described in detail in this embodiment can be referred to the description in any method embodiment of this application.

[0124] Example 5

[0125] Figure 6 A schematic diagram of the structure of a vehicle 10 that can be used to implement an embodiment of the present invention is shown. For example... Figure 6 As shown, vehicle 10 includes at least one processor 11 and a memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer program stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of vehicle 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. Input / output (I / O) interface 15 is also connected to bus 14.

[0126] A plurality of components in the vehicle 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the vehicle 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0127] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the lane line identification method.

[0128] In some embodiments, the lane line identification method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the vehicle 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the lane line identification method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the lane line identification method by any other appropriate means, such as by means of firmware.

[0129] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0130] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a remote machine or entirely on a remote machine or server.

[0131] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0132] To provide for interaction with a user, the systems and techniques described here can be implemented on a vehicle having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the vehicle. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0133] The systems and techniques described herein can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described herein, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0134] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can 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 large management difficulty and weak business scalability in traditional physical host and VPS service.

[0135] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, and the present disclosure is not limited herein as such.

[0136] The specific embodiments described above are not intended to limit the scope of the present disclosure. Those skilled in the art will understand that various modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments without departing from the spirit and principles of the present disclosure. Any further modifications, equivalents, and / or alternatives come within the scope of the present disclosure as recited by the claims.

Claims

1. A lane line recognition method characterized by, The method is applied to a vehicle and comprises the following steps: obtaining lane line information respectively output by an environment perception device and a high-definition map, and initial confidence degrees corresponding to the lane lines; matching the lane lines respectively output by the environment perception device and the high-definition map according to the lane line information, and determining fusion confidence degrees corresponding to each lane line according to a matching result and the initial confidence degrees corresponding to the lane lines; screening target lane lines from the lane lines respectively output by the environment perception device and the high-definition map according to the fusion confidence degrees corresponding to each lane line and a preview distance corresponding to the environment perception device, and taking the target lane lines as lane line recognition information corresponding to an automatic driving mode; the matching the lane lines respectively output by the environment perception device and the high-definition map according to the lane line information comprises the following steps: obtaining a plurality of lane lines respectively output by the environment perception device and the high-definition map, the number of the lane lines being equal; combining each lane line output by the environment perception device with a corresponding lane line output by the high-definition map in a left-to-right or right-to-left order to obtain a plurality of lane line groups; obtaining a lane line group from the plurality of lane line groups as a current lane line group; obtaining a first lane line corresponding to the environment perception device and a second lane line corresponding to the high-definition map in the current lane line group, and determining whether the first lane line is identical to the second lane line; if yes, determining that the first lane line is matched with the second lane line; if no, updating the second lane line and determining that the updated second lane line is matched with the first lane line; returning to the operation of obtaining a lane line group from the plurality of lane line groups as the current lane line group until processing of all the lane line groups is completed; the screening the target lane lines from the lane lines respectively output by the environment perception device and the high-definition map according to the fusion confidence degrees corresponding to each lane line and the preview distance corresponding to the environment perception device comprises the following steps: determining whether a fusion confidence degree of a current lane line is equal to a preset confidence degree; if yes, determining whether a preview distance corresponding to the environment perception device is less than a preset distance; if the fusion confidence degree of the current lane line is equal to the preset confidence degree and the preview distance is less than the preset distance, obtaining a lane line output by the environment perception device as a target lane line; if the fusion confidence degree of the current lane line is equal to the preset confidence degree and the preview distance is not less than the preset distance, obtaining a lane line output by the high-definition map as the target lane line.

2. The method of claim 1, wherein, after obtaining the lane line information respectively output by the environment perception device and the high-definition map, the method further comprises the following steps: determining invalid lane lines from all the lane lines respectively output by the environment perception device and the high-definition map, and eliminating the invalid lane lines.

3. The method of claim 2, wherein, the determining the invalid lane lines from all the lane lines output by the environment perception device comprises the following steps: obtaining a plurality of adjacent lane lines located on the same side of the vehicle and output by the environment perception device; According to the starting positions and the ending positions corresponding to the plurality of adjacent lane lines respectively, the plurality of adjacent lane lines are sampled in sequence according to a preset distance, to obtain a plurality of sampling points corresponding to the plurality of adjacent lane lines respectively; A lateral distance between every two adjacent lane lines corresponding to the sampling points is determined, and a target sampling point quantity when the lateral distance is less than a preset threshold is counted; If the target sampling point quantity is greater than half of a total sampling point quantity, a lane line farthest from the vehicle is obtained from the plurality of adjacent lane lines as an invalid lane line.

4. The method of claim 1, wherein, The first lane line and the second lane line are determined to be identical, including: A first lateral distance between the first lane line and a vehicle body center and a second lateral distance between the second lane line and the vehicle body center are obtained, and a difference between the first lateral distance and the second lateral distance is determined; It is determined whether the absolute value of the difference is greater than a preset value; If not, it is determined that the first lane line and the second lane line are identical.

5. The method of claim 4, wherein, The second lane line is updated, including: The second lateral distance corresponding to the second lane line is added to the absolute value of the difference to obtain an updated lateral distance; The second lane line is translated according to the updated lateral distance to obtain an updated second lane line.

6. A lane line recognition apparatus characterized by comprising: The device is applied to a vehicle, and the device includes: An information acquisition module is configured to acquire lane line information output by an environment perception device and a high-definition map respectively, and initial confidence degrees corresponding to each lane line; A confidence fusion module is configured to match lane lines output by the environment perception device and the high-definition map respectively according to the lane line information, and determine a fusion confidence degree corresponding to each lane line according to a matching result and the initial confidence degrees corresponding to each lane line; A target lane line determination module is configured to filter a target lane line from the lane lines output by the environment perception device and the high-definition map respectively according to the fusion confidence degree corresponding to each lane line and a preview distance corresponding to the environment perception device, and take the target lane line as lane line recognition information corresponding to an automatic driving mode. The confidence fusion module includes: A lane line acquisition unit is configured to acquire a plurality of lane lines output by the environment perception device and the high-definition map respectively, the number of the lane lines being equal; A lane line group acquisition unit is configured to combine each lane line output by the environment perception device with a corresponding lane line output by the high-definition map according to a left-to-right or right-to-left order of the lane lines, to obtain a plurality of lane line groups; A current lane line group determination unit is configured to acquire a lane line group from the plurality of lane line groups in sequence as a current lane line group; A lane line judgment unit is configured to acquire a first lane line corresponding to the environment perception device and a second lane line corresponding to the high-definition map from the current lane line group, and determine whether the first lane line and the second lane line are identical; if yes, it is determined that the first lane line and the second lane line are matched; if not, the second lane line is updated, and it is determined that an updated second lane line and the first lane line are matched. The lane line group polling unit is configured to return an operation of sequentially obtaining a lane line group from the plurality of lane line groups as a current lane line group until processing of all the lane line groups is completed. The target lane line determination module comprises: The fusion confidence judgment unit is configured to judge whether the fusion confidence of the current lane line is equal to a preset confidence. The pre-look distance judgment unit is configured to, if the fusion confidence of the current lane line is equal to the preset confidence, judge whether a pre-look distance corresponding to the environment perception device is less than a preset distance. The lane line screening determination unit is configured to, if the fusion confidence of the current lane line is equal to the preset confidence and the pre-look distance is less than the preset distance, obtain a lane line output by the environment perception device as a target lane line; and if the fusion confidence of the current lane line is equal to the preset confidence and the pre-look distance is not less than the preset distance, obtain a lane line output by the high-definition map as the target lane line.

7. A vehicle characterized by comprising: The vehicle comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the lane line identification method in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the lane line identification method in any one of claims 1-5 when executed by the processor.

Images