Lane line detection method and device, equipment and medium

Abstract

The embodiment of the invention relates to a lane line detection method and device, equipment and a medium, and the method comprises the steps: obtaining a to-be-detected lane line at a road intersection, the information of a driving direction, and a lane set connected to the road intersection, and obtaining a lane line detection result based on the information of the driving direction at the road intersection and a preset lane connection rule; determining an entry lane and an exit lane which have a connection relationship in the driving direction from the lane set, generating a simulated lane line at the road intersection based on the entry lane and the exit lane which have the connection relationship, and matching the simulated lane line with the to-be-detected lane line to determine a detection result of the to-be-detected lane line, and the accuracy of lane line detection is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of high-precision maps, and particularly to a method, apparatus, device, and medium for detecting lane lines. Background Art

[0002] Existing vehicles with intelligent driving functions, during the process of turning on the corresponding intelligent driving functions and driving, collect road data through on-vehicle sensing modules (such as cameras, lidar, etc.). Based on the collected road data, lane lines of the road are automatically generated and used as one of the input signals for the intelligent driving system installed in the vehicle to support the system in realizing corresponding intelligent driving functions. For example, the lane keeping function (controlling the vehicle to drive in a specific lane). Or, during the production process of high-precision maps, road data is also collected through on-vehicle sensors, and based on the collected road data, lane lines of the road are automatically generated as input signals for downstream data production links.

[0003] However, the inventors found that in scenarios where the road traffic relationships are relatively complex, such as at road intersections, whether it is during the driving process of vehicles with intelligent driving functions or during the production process of high-precision maps, the automatically generated lane lines may have some errors. If the incorrect lane lines are input into the intelligent driving system, or if the incorrect lane lines are used as the final result of the high-precision map, it will cause errors in downstream services that rely on lane lines and result in losses. Therefore, a solution is needed to detect the automatically generated lane lines to avoid the incorrect lane lines from appearing in the high-precision map or being input into the intelligent driving system. Summary of the Invention

[0004] To solve the above technical problems, embodiments of the present disclosure provide a method, apparatus, device, and medium for detecting lane lines.

[0005] In a first aspect of the embodiments of the present disclosure, a method for detecting lane lines is provided, including: obtaining the lane lines to be detected at a road intersection, information about the driving direction, and a set of lanes connected to the road intersection; determining, based on the information about the driving direction and a preset lane connection rule, an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes; generating a simulated lane line of the road intersection based on the entry lane and the exit lane having the connection relationship; and matching the simulated lane line with the lane lines to be detected to determine the detection result of the lane lines to be detected.

[0006] In a second aspect of the embodiments of the present disclosure, a device for detecting lane lines is provided, including:

[0007] An obtaining module, configured to obtain the lane lines to be detected at a road intersection, information about the driving direction, and the set of lanes connected to the road intersection;

[0008] The first determination module is configured to determine, based on the information of the driving direction and a preset lane connection rule, an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes.

[0009] The generation module is configured to generate a simulated lane line of the road intersection based on the entry lane and the exit lane having a connection relationship.

[0010] The matching module is configured to match the simulated lane line with the lane line to be detected to determine the detection result of the lane line to be detected.

[0011] A third aspect of the embodiments of the present disclosure provides a computer device, including a memory and a processor. Among them, a computer program is stored in the memory. When the computer program is executed by the processor, the method described in the first aspect above can be implemented.

[0012] A fourth aspect of the embodiments of the present disclosure provides a computer program product. The program product is stored in a storage medium. When the program product runs, the method described in the first aspect above can be implemented.

[0013] A fifth aspect of the embodiments of the present disclosure provides a computer-readable storage medium. A computer program is stored in the storage medium. When the computer program is executed, the method described in the first aspect above can be implemented.

[0014] The technical solutions provided by the embodiments of the present disclosure have the following advantages compared with the prior art:

[0015] In the embodiments of the present disclosure, by obtaining the lane line to be detected at the road intersection, the information of the driving direction, and the set of lanes connected to the road intersection, based on the information of the driving direction at the road intersection and a preset lane connection rule, an entry lane and an exit lane having a connection relationship in the driving direction are determined from the set of lanes, and a simulated lane line of the road intersection is generated based on the entry lane and the exit lane having a connection relationship, so as to match the simulated lane line with the lane line to be detected to determine the detection result of the lane line to be detected. The simulated lane line fitted at the road intersection in the embodiments of the present disclosure can be understood as a theoretical lane line. By matching the theoretical lane line with the lane line to be detected actually collected, an accurate detection result can be obtained, such as detecting whether the lane line to be detected is a correct lane line, etc., thereby improving the accuracy of lane line detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure and used together with the specification to explain the principles of the present disclosure.

[0017] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0019] Figure 2 is a schematic diagram of another application scenario provided by an embodiment of the present disclosure;

[0020] Figure 3 is a schematic diagram of a detection logic for lane lines provided by an embodiment of the present disclosure;

[0021] Figure 4 is a flowchart of a method for detecting lane lines provided by an embodiment of the present disclosure;

[0022] Figure 5 is a schematic diagram of a road intersection scenario provided by an embodiment of the present disclosure;

[0023] Figure 6 is a flowchart of a merging method for road intersections provided by an embodiment of the present disclosure;

[0024] Figure 7 is a schematic diagram of a method for determining the distance between two adjacent road intersections provided by an embodiment of the present disclosure;

[0025] Figure 8 is a schematic structural diagram of a lane line detection device provided by an embodiment of the present disclosure;

[0026] Figure 9 is a schematic structural diagram of a computer device in an embodiment of the present disclosure. Detailed Embodiments

[0027] In order to better understand the above objects, features, and advantages of the present disclosure, the following will further describe the solutions of the present disclosure. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0028] In the following description, many specific details are set forth to fully understand the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all the embodiments.

[0029] For example, Figure 1 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure. AsFigure 1 As shown, in some embodiments, the lane line detection solution provided by the embodiments of the present disclosure can be applied to the production scenario of high-precision maps. Among them, a high-precision map can be understood as an electronic map with a precision higher than a preset precision.

[0030] See Figure 1 , in the production scenario of high-precision maps, the production materials of high-precision maps can include the information of the driving direction of the acquisition vehicle on the road and the lane lines collected on the road by the intelligent driving perception module (such as a camera or lidar, etc.) carried on the acquisition vehicle. Among them, the information of the driving direction of the acquisition vehicle can include the direction of the planned route, and / or the information of the guiding arrows on the road where the acquisition vehicle travels, such as the shape and type of the guiding arrows, etc. The lane lines include information such as the identification, shape, and lane line type of the lane lines. When producing a high-precision map, it is possible to determine whether the road contains a road intersection according to the topological structure of the target production road. If so, when producing the lanes at the road intersection, it is possible to obtain from the production materials the lane lines (which may be one or more) collected by the acquisition vehicle at the road intersection, the information of the driving direction of the acquisition vehicle when collecting these lane lines, and the set of lanes connected to the road intersection (including the information of the entry lane and the exit lane). Then, based on the information of the driving direction of the acquisition vehicle and the preset lane connection rules, the entry lane and the exit lane with a connection relationship are determined from the set of lanes connected to the road intersection. Based on the entry lane and the exit lane with a connection relationship, a simulated lane line of the road intersection is generated, and the collected lane lines are matched with the simulated lane line. If the collected lane lines match the model lane lines, it is determined that the collected lane lines are correct lane lines, otherwise they are incorrect lane lines. Further, according to the detection result, the incorrect lane lines can be filtered out, and then the high-precision map can be produced according to the remaining lane lines.

[0031] By detecting the collected lane lines and filtering out the incorrect lane lines, the accuracy of the high-precision map can be improved.

[0032] Exemplarily, Figure 2 is a schematic diagram of another application scenario provided by the embodiments of the present disclosure. As Figure 2 shown, in some embodiments, the lane line detection solution provided by the embodiments of the present disclosure can also be applied to the intelligent driving scenario. See Figure 2, in the intelligent driving scenario, the lane lines on the road ahead of the vehicle can be collected through the intelligent driving perception module installed on the vehicle, and the information about the driving direction of the vehicle on the road ahead can be obtained according to information such as route planning information, navigation information, or guiding arrows on the road. Based on the vehicle positioning information, route planning information, or electronic map, etc., the type of the road ahead and lane-related information (such as the number of lanes, entering lanes, and exiting lanes, etc.) can be determined. In the case where there are multiple roads intersecting ahead, based on the target driving direction of the vehicle at the road intersection and the preset lane connection rules, the entering lane and the exiting lane with a connection relationship can be determined from the set of lanes connected at the road intersection (including the information of entering and exiting lanes). Based on the entering lane and the exiting lane with a connection relationship, the simulated lane lines at this road intersection can be generated, and the collected lane lines are matched with the simulated lane lines. If the collected lane lines match the model lane lines, it is determined that the collected lane lines are correct lane lines, otherwise they are incorrect lane lines. Further, the incorrect lane lines can be filtered according to the detection result, and then the vehicle can be controlled to drive in the lane based on the remaining lane lines after filtering, that is Figure 2 the so-called intelligent driving control mentioned

[0033] By detecting lane lines during intelligent driving, the safety of intelligent driving can be improved.

[0034] Of course, Figure 1 and Figure 2 the scenarios shown are only illustrative and not the only scenarios. In fact, in other embodiments, the solutions provided by the embodiments of the present disclosure can also be applied in any other applicable scenarios.

[0035] Exemplarily, Figure 3 is a schematic diagram of a detection logic of lane lines provided by an embodiment of the present disclosure. As Figure 3 shown, in some application scenarios (such as Figure 1 and Figure 2 application scenarios), the detection logic provided by the embodiments of the present disclosure may include the following execution processes: the execution process of obtaining the lane lines to be detected at the road intersection, the information about the driving direction at the road intersection, and the set of lanes connected at the road intersection; the execution process of determining the entering lane and the exiting lane with a connection relationship in the driving direction from the set of lanes based on the information about the driving direction and the preset lane connection rules; the execution process of generating simulated lane lines based on the entering lane and the exiting lane with a connection relationship; the execution process of matching the simulated lane lines with the lane lines to be detected to obtain the detection result.

[0036] The following explains and illustrates the Figure 3 execution logic shown in combination with exemplary embodiments.

[0037] Exemplarily, Figure 4 is a flowchart of a method for detecting lane lines provided by an embodiment of the present disclosure. This method can be exemplarily executed by a computer device, which can be exemplarily understood as a device with computing and processing capabilities such as a mobile phone, a car computer, a computer, a server, a distributed computing node, etc. As Figure 3 shown, the detection method provided by the embodiment of the present disclosure may include step 401-step 405.

[0038] Step 401, obtain the lane lines to be detected at the road intersection, information on the driving direction, and the set of lanes connected to the road intersection.

[0039] In the embodiment of the present disclosure, the lane lines can be understood as any one of lane lines such as double yellow lines, single yellow lines, dotted lines, etc. The lane lines to be detected can be understood as lane lines extracted from lane images collected by image acquisition devices such as cameras. It can also be understood as lane lines extracted from the road point cloud data collected by radar devices.

[0040] The information on the driving direction may include at least one of the following information: information on the route direction of the planned route at the road intersection, information on the guiding arrows on the vehicle driving lane, such as the shape and type of the guiding arrows, and information on the guiding arrows at the road intersection.

[0041] The set of lanes connected to the road intersection may include the number and types of lanes connected to the road intersection, such as entry lanes or exit lanes, etc.

[0042] In the embodiment of the present disclosure, the lane lines to be detected at the road intersection and the information on the driving direction can be obtained in various ways.

[0043] For example, in one acquisition method, the lane lines to be detected at the road intersection and the information on the driving direction can be obtained from a preset data source. Among them, the data source can be a device with data storage and query capabilities such as a hard disk, a database, a server, a distributed storage node, etc. For example, in some scenarios, the lane lines and the driving direction at the road intersection can be collected by a collection device (such as a collection vehicle), and the collected lane lines can be uploaded to the data source for storage as the information on the lane lines to be detected and the driving direction, etc. Then, the lane lines to be detected at the road intersection and the information on the driving direction can be obtained from the data source, and noise detection can be performed on the lane lines to be detected at the road intersection.

[0044] For example, in another acquisition method, the lane line at the road intersection and the information of the driving direction at the road intersection can be directly obtained from the vehicle's intelligent driving perception module or the vehicle computer, and the obtained lane line is used as the lane line to be detected. In this scenario, the road intersection referred to in the embodiment of the present disclosure can be understood as the road intersection that the vehicle is about to pass.

[0045] In one implementation of the disclosed embodiment, the set of lanes connected at the road intersection can be obtained from an electronic map based on the vehicle's positioning information and route planning information. In another implementation, the set of lanes connected at the road intersection can be obtained from an electronic map based on the location of the lane line to be detected. Of course, this is only an example and not a sole limitation.

[0046] For example, in one embodiment, after obtaining the lane lines to be detected, lane lines whose integrity is lower than a preset threshold and / or whose direction is inconsistent with the driving direction can be filtered out from the lane lines to be detected at the road intersection, wherein the lane lines whose integrity is lower than the preset threshold or whose direction is inconsistent with the driving direction can be lane lines for entering lanes, or lane lines for exiting lanes, or can also include lane lines for entering lanes and lane lines for exiting lanes at the same time. Among them, the integrity of the lane line can be exemplarily represented by the ratio of the length of the lane line to the lane length of the lane (entering lane or exiting lane) corresponding to the lane line. By filtering out lane lines whose integrity is lower than the preset threshold and / or whose direction is inconsistent with the driving direction, the detection efficiency and detection accuracy can be improved.

[0047] Step 402: Based on the information of the driving direction at the road intersection and the preset lane connection rule, an entry lane and an exit lane having a connection relationship in the driving direction are determined from the lane set.

[0048] The lane connection rule referred to in the embodiments of the present disclosure refers to the connection rule between the entry lane and the exit lane at the road intersection. In an actual road intersection scenario, if a lane on the entry road (i.e., the entry lane) can enter a lane on the exit road (i.e., the exit lane), then the entry lane and the exit lane can be considered to have a connection relationship.

[0049] In some embodiments, different road intersection types may have the same or different lane connection rules. The lane connection rules corresponding to each road intersection type may be obtained based on traffic regulations and map data analysis. Among them, the road intersection type may include at least one of the following: exit, entrance, divergence, merging, diverging and merging, main and auxiliary road entrances and exits, etc.

[0050] When determining the connection relationship between the entering lane and the exiting lane, the target road intersection type corresponding to the road intersection can be determined first based on the road characteristics and / or lane characteristics of the road intersection. In the correspondence relationship between the preset road intersection types and lane connection rules, the target lane connection rule corresponding to the target road intersection type is searched. Then, based on the driving direction at the road intersection and the target lane connection rule corresponding to the target road intersection type, the entering lane and the exiting lane having a connection relationship in the driving direction are determined. Among them, the road characteristics of the road intersection at least include one of the following:

[0051] The road topological structure of the road intersection, the number of entering roads, the number of exiting roads, the way of road connection (such as the "Y"-shaped connection way, the "T"-shaped connection way, etc., but not limited to the several ways listed here), and at least one of the road widths, curvatures, and azimuth angles of the entering road and the exiting road. The lane characteristics of the road intersection include the number of lanes of the entering lane and / or the exiting lane.

[0052] It can be understood that the above implementation manner is only an exemplary implementation manner rather than the only one. For example, in another implementation manner, the road intersection types may not be classified, but the entering lane and the exiting lane having a connection relationship in the driving direction are directly determined based on the road characteristics, lane characteristics, and driving direction of the road intersection. At this time, the preset lane connection rules may include the mapping relationship between the lane connection relationship and the road characteristics, lane characteristics, and driving direction of the road intersection.

[0053] To better understand the method for determining the connection relationship between the entering lane and the exiting lane, the following is illustrated with an example.

[0054] Exemplarily, Figure 5 is a schematic diagram of a road intersection scenario provided by an embodiment of the present disclosure. Figure 5 It depicts a scenario of entering a secondary road from a main road. Among them, Figure 5 the left road L1 in is the main road, including three lanes. The right road L2 is the secondary road, including two lanes. Actually, during the process of switching from the main road to the secondary road, it can enter the intersection from the rightmost lane of the main road, that is, Figure 5 the lane L11 in, and then enter the leftmost lane of the secondary road from the intersection, that is, Figure 5 the lane L21 in, thereby realizing the switch from the main road to the secondary road. Therefore, in this scenario, it can be considered that the rightmost lane L11 of the main road has a connection relationship with the leftmost lane L21 of the secondary road.

[0055] Of course, the above example is only for illustrative purposes and does not specifically limit the lane connection relationship of the embodiments of the present disclosure.

[0056] Step 403: Generate the simulated lane lines at the road intersection based on the entering lane and the exiting lane with a connection relationship.

[0057] Among them, the simulated lane lines referred to in the embodiments of the present disclosure can be one or more. In some embodiments, the simulated lane lines at the road intersection can be obtained by fitting the lane line signals of the entering lane and the exiting lane with a connection relationship one or more times. Among them, in the scenario of multiple fittings, the same or different methods can be used for each fitting.

[0058] In some embodiments, in order to further improve the accuracy of lane line detection, after fitting the simulated lane lines at the road intersection, the simulated lane lines can also be screened based on a preset screening rule. For example, in a feasible example, the smoothness of each simulated lane line can be calculated, and the simulated lane line with the highest smoothness can be selected from multiple simulated lane lines, and this simulated lane line can be matched with the lane line to be detected. The calculation method of lane line smoothness can refer to the related technology and will not be elaborated here.

[0059] Step 404: Match the simulated lane lines with the lane lines to be detected to determine the detection results of the lane lines to be detected.

[0060] In the embodiments of the present disclosure, there are various methods for matching the simulated lane lines with the lane lines to be detected at the road intersection. For example, in a feasible embodiment, the simulated lane lines and the lane lines to be detected can be used as inputs, and a pre-trained model is used to match the simulated lane lines and the lane lines to be detected. For another example, in another feasible embodiment, the similarity between the simulated lane lines and the lane lines to be detected can be calculated based on a preset similarity calculation method. If the similarity is lower than a preset threshold, they do not match; if the similarity is higher than or equal to the preset threshold, they match. For yet another example, in yet another feasible embodiment, before or after calculating the similarity between the lane lines to be detected and the simulated lane lines based on the previous method, the distance between the lane lines to be detected and the simulated lane lines can also be judged. If the distance is greater than a preset distance, it is determined that they do not match.

[0061] When the lane lines to be detected match the simulated lane lines, it is determined that the lane lines to be detected are correct lane lines, otherwise they are incorrect lane lines. In an embodiment of the embodiments of the present disclosure, after detecting one or more incorrect lane lines, the incorrect lane lines can be added to a preset list for storage.

[0062] In the embodiments of the present disclosure, by obtaining the lane lines to be detected at the road intersection, the information of the driving direction, and the set of lanes connected to the road intersection, based on the information of the driving direction at the road intersection and the preset lane connection rules, the entry lane and the exit lane having a connection relationship in the driving direction are determined from the set of lanes, and based on the entry lane and the exit lane having a connection relationship, a simulated lane line of the road intersection is generated, so as to match the simulated lane line with the lane lines to be detected to determine the detection result of the lane lines to be detected. The simulated lane line fitted at the road intersection in the embodiments of the present disclosure can be understood as the theoretical lane line. By matching the theoretical lane line with the actually collected lane lines to be detected, an accurate detection result can be obtained, such as detecting whether the lane lines to be detected are correct lane lines, etc., thereby improving the accuracy of lane line detection.

[0063] Exemplarily, Figure 6 is a flowchart of a merging method for a road intersection provided by the embodiments of the present disclosure. In one implementation manner of the embodiments of the present disclosure, Figure 4 In the embodiments, the road intersection mentioned can also be obtained by Figure 6 the method shown. As Figure 6 shown, the merging method for the road intersection provided by the embodiments of the present disclosure may include step 601-step 603.

[0064] Step 601: Determine the road intersections included on the target road according to the topological structure of the target road.

[0065] Among them, the target road can be exemplarily understood as the road for which the corresponding high-precision road will be generated in the high-precision map. Or in some implementation manners, it can also be understood as the road falling on the planned route.

[0066] In one exemplary implementation manner, the topological structure of the target road can be obtained from an electronic map. According to the topological structure of the target road, the positions where the target road intersects with at least one other road can be determined, and this position is determined as the road intersection on the target road. In the embodiments of the present disclosure, there may be one or more road intersections on the target road.

[0067] Step 602: Detect the distance between two adjacent road intersections on the target road.

[0068] In the embodiments of the present disclosure, there are various methods for detecting the distance between two adjacent road intersections.

[0069] For example, in a feasible method, detecting the distance between two adjacent road intersections may include calculating the straight-line distance between the positions where the two road intersections are located. For example, Figure 7It is a schematic diagram of a method for determining the distance between two adjacent road intersections provided by an embodiment of the present disclosure. Among them, the position of G1 is the position of a road intersection included on the target road, and the position of G2 is the position of another road intersection adjacent to this road intersection on the target road. As Figure 7 shown, in an implementation manner of an embodiment of the present disclosure, the distance between G1 and G2 can be calculated based on the coordinates of G1 and G2, and the distance between G1 and G2 is used as the distance between the two road intersections.

[0070] For another example, in another feasible method, the position of any one of the two adjacent road intersections can also be used as the center of a circle to determine whether the adjacent road intersection is within a preset radius of the center position. If so, it is determined that the distance between the two road intersections is less than the preset distance. If the adjacent road intersection is not within the preset radius of the center, it is determined that the distance between the two road intersections is greater than the preset distance. Still taking Figure 7 the road intersections shown as an example, if the road intersection at the G2 position is within the preset radius of the road intersection at the G1 position, it is determined that the distance between the road intersection at the G2 position and the road intersection at the G1 position is less than the preset distance, otherwise it is greater than the preset distance.

[0071] Step 603: If the distance between two adjacent road intersections is less than the preset distance, merge the two adjacent road intersections and the road between the two adjacent road intersections as one road intersection.

[0072] Still taking Figure 7 as an example, when the distance between the road intersection at the G2 position and the road intersection at the G1 position is less than the preset distance, the road intersection at the G2 position, the road intersection at the G1 position, and the road between G1 and G2 can be merged as one road intersection, and lane line detection is performed on the lane lines of this road intersection.

[0073] By merging two adjacent road intersections with a relatively short distance as one road intersection for lane line detection, the embodiment of the present disclosure can improve the efficiency of lane line detection.

[0074] Figure 8 It is a schematic structural diagram of a lane line detection device provided by an embodiment of the present disclosure. This detection device can be exemplarily understood as the computer device in the above embodiment or a partial functional module in the computer device. As Figure 8 shown, the detection device 80 provided by an embodiment of the present disclosure includes:

[0075] An acquisition module 81, configured to acquire the lane lines to be detected at the road intersection, information about the driving direction, and the set of lanes connected to the road intersection;

[0076] A first determination module 82, configured to determine, based on the information of the driving direction and a preset lane connection rule, an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes;

[0077] A generation module 83, configured to generate a simulated lane line of the road intersection based on the entry lane and the exit lane having a connection relationship;

[0078] A matching module 84, configured to match the simulated lane line with the lane line to be detected to determine a detection result of the lane line to be detected.

[0079] In one embodiment, the detection device 80 may further include:

[0080] A second determination module, configured to determine a target road intersection type of the road intersection based on the road features and / or lane features of the road intersection;

[0081] The first determination module 82 is configured to:

[0082] In the corresponding relationship between the preset road intersection types and lane connection rules, search for the target lane connection rule corresponding to the target road intersection type; and

[0083] Based on the driving direction and the target lane connection rule, determine an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes.

[0084] In one embodiment, the road features of the road intersection at least include one of the following:

[0085] The road topology of the road intersection, the number of entry roads, the number of exit roads, the connection mode of the roads, and at least one of the following features of the entry road and the exit road: road width, curvature, and azimuth angle;

[0086] The lane features of the road intersection include the number of lanes of the entry lane and / or the exit lane.

[0087] In one embodiment, the detection device 80 may further include:

[0088] A cleaning module, configured to filter out lane lines with a integrity lower than a preset threshold and / or lane lines with a direction inconsistent with the driving direction from the lane lines to be detected at the road intersection.

[0089] In one embodiment, the cleaning module is configured to determine the integrity of the lane line as the ratio of the length of the lane line to the lane length of the entry lane or the exit lane corresponding to the lane line.

[0090] In one embodiment, a generation module 83 is configured to perform lane line fitting based on the lane lines of the entry lane and the lane lines of the exit lane to obtain simulated lane lines of the road intersection.

[0091] In one embodiment, the detection device 80 may further include:

[0092] A third determination module, configured to determine the road intersections included in the target road according to the topological structure of the target road;

[0093] A detection module, configured to detect the distance between two adjacent road intersections on the target road;

[0094] A merging module, configured to, if the distance between two adjacent road intersections is less than a preset distance, merge the two adjacent road intersections and the road between the two adjacent road intersections as one road intersection.

[0095] The device provided by the embodiments of the present disclosure can execute the method of any of the above embodiments, and its execution manner and beneficial effects are similar, which will not be elaborated here.

[0096] The embodiments of the present disclosure further provide a computer device, including a memory and a processor. Among them, a computer program is stored in the memory. When the computer program is executed by the processor, the method of any of the above method embodiments can be implemented.

[0097] Exemplarily, Figure 9 is a schematic structural diagram of a computer device in the embodiments of the present disclosure. Specifically refer to the following Figure 9 , which shows a schematic structural diagram of a computer device 1400 suitable for implementing the embodiments of the present disclosure. The computer device 1400 in the embodiments of the present disclosure may include, but is not limited to, devices with computing and processing capabilities such as laptop computers, PADs (tablet computers), desktop computers, vehicle-mounted computers, mobile phones, servers, distributed computing nodes, etc. Figure 9 The computer device shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0098] Such as Figure 9As shown, the computer device 1400 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 1401, which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1402 or the program loaded from the storage device 1408 into the random access memory (RAM) 1403. In the RAM 1403, various programs and data required for the operation of the computer device 1400 are also stored. The processing device 1401, the ROM 1402, and the RAM 1403 are connected to each other through a bus 1404. The input / output (I / O) interface 1405 is also connected to the bus 1404.

[0099] Generally, the following devices may be connected to the I / O interface 1405: an input device 1406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1409. The communication device 1409 may allow the computer device 1400 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 9 a computer device 1400 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0100] Specifically, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device 1409, or installed from the storage device 1408, or installed from the ROM 1402. When the computer program is executed by the processing device 1401, the above functions defined in the method of the embodiment of the present disclosure are executed.

[0101] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0102] The above-mentioned computer-readable medium can be included in the above-mentioned computer device; it can also exist separately and not be assembled into the computer device.

[0103] The above-mentioned computer-readable medium carries one or more programs. When the one or more programs are executed by a processing device, the processing device is caused to: obtain the lane lines to be detected at a road intersection, information on the driving direction, and a set of lanes connected to the road intersection; based on the information on the driving direction and a preset lane connection rule, determine an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes; generate a simulated lane line of the road intersection based on the entry lane and the exit lane having the connection relationship; and match the simulated lane line with the lane lines to be detected to determine the detection result of the lane lines to be detected.

[0104] Computer program code for performing the operations of this disclosure may be written in one or more programming languages, or combinations thereof, including but not limited to object-oriented programming languages such as Java, Smalltalk, C++, and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or alternatively, may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0106] The units described in the embodiments of the present disclosure may be implemented in software or in hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself.

[0107] The functions described above herein may be performed, at least in part, by one or more hardware logic components. By way of example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and the like.

[0108] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0109] Embodiments of the present disclosure also provide a computer-readable storage medium storing a computer program, which when executed by a processor can implement the methods of any of the foregoing Figures 4 - 7 embodiments, the execution manners and beneficial effects of which are similar and will not be elaborated herein.

[0110] Embodiments of the present disclosure also provide a computer program product stored in a storage medium, which when running can implement Figures 4 - 7 the methods of any of the foregoing embodiments, the execution manners and beneficial effects of which are similar and will not be elaborated herein.

[0111] It should be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0112] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting lane lines, wherein, comprising: Obtaining the lane lines to be detected at a road intersection, information on the driving direction, and the set of lanes connected to the road intersection; Based on the information on the driving direction and a preset lane connection rule, determining an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes; Based on the entry lane and the exit lane having the connection relationship, generating a simulated lane line of the road intersection; Matching the simulated lane line with the lane lines to be detected to determine the detection result of the lane lines to be detected.

2. The method according to claim 1, wherein, the method further comprises: Based on the road characteristics and / or lane characteristics of the road intersection, determining the target road intersection type of the road intersection; The determining an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes based on the information on the driving direction and a preset lane connection rule includes: Searching in the corresponding relationship between the preset road intersection types and lane connection rules for the target lane connection rule corresponding to the target road intersection type; Based on the driving direction and the target lane connection rule, determining an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes.

3. The method according to claim 2, wherein, the road characteristics of the road intersection at least include one of the following: The road topology of the road intersection, the number of entry roads, the number of exit roads, the connection mode of the roads, and at least one of the following characteristics of the entry roads and the exit roads: road width, curvature, and azimuth angle; The lane characteristics of the road intersection include the number of lanes of the entry lane and / or the exit lane.

4. The method according to any one of claims 1 - 3, wherein, before the determining an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes based on the information on the driving direction and a preset lane connection rule, the method further comprises: Filtering out lane lines with a integrity lower than a preset threshold and / or lane lines whose directions are inconsistent with the driving direction from the lane lines to be detected at the road intersection.

5. The method according to claim 4, wherein, the method further comprises: Determining the ratio of the length of a lane line to the lane length of the entry lane or the exit lane corresponding to the lane line as the integrity of the lane line.

6. The method according to any one of claims 1 - 3, wherein, the generating a simulated lane line of the road intersection based on the entry lane and the exit lane having the connection relationship includes: Performing lane line fitting based on the lane line of the entry lane and the lane line of the exit lane to obtain the simulated lane line of the road intersection.

7. The method according to claim 1, wherein, before the obtaining the lane lines to be detected at a road intersection, information on the driving direction, and the set of lanes connected to the road intersection, the method further comprises: Determine the road intersections included on the target road according to the topological structure of the target road; Detect the distance between two adjacent road intersections on the target road; If the distance between two adjacent road intersections is less than a preset distance, then merge the two adjacent road intersections and the road between the two adjacent road intersections as one road intersection.

8. A lane line detection device, Wherein, It includes: An acquisition module, configured to acquire the lane lines to be detected at the road intersection, information on the driving direction, and the set of lanes connected to the road intersection; A first determination module, configured to determine, based on the information on the driving direction and a preset lane connection rule, an entry lane and an exit lane having a connection relationship in the driving direction from the set of lanes; A generation module, configured to generate a simulated lane line of the road intersection based on the entry lane and the exit lane having the connection relationship; A matching module, configured to match the simulated lane line with the lane lines to be detected to determine the detection result of the lane lines to be detected.

9. A computer device, Wherein, It includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the method described in any one of claims 1-7 is implemented.

10. A computer-readable storage medium, Wherein, The storage medium stores a computer program, and when the computer program is executed, the method described in any one of claims 1-7 is implemented.

Images