Lane line data processing method, device and equipment

Abstract

The invention relates to a lane line data processing method, device and equipment, and the method comprises the steps: obtaining tail end lane line data, driving track data and a driving course angle under the condition that a missing lane line is detected at the current moment, the tail end lane line data is lane line data detected at the last moment of the current moment, and the driving track data is a lane line data detected at the last moment of the current moment; the driving track data is corresponding track data when the data acquisition device drives from a previous moment to a target moment, and performing data fusion processing on the tail end lane line data, the driving track data and the driving course angle to obtain virtual lane line data; the lane line is supplemented based on the virtual lane line data to obtain the target lane line data, and by means of the technical scheme provided by the invention, the lane lines can be automatically supplemented in real time, the supplementing efficiency and the accuracy of supplementing the lane lines are improved, the completeness of map drawing is ensured, and meanwhile, the labor cost is saved.

Description

Technical Field

[0001] This application relates to the field of driver assistance technology, and in particular to a lane line data processing method, apparatus and equipment. Background Technology

[0002] Crowdsourced mapping refers to a technical model that utilizes numerous vehicle sensors to collect road data, and dynamically constructs and updates high-precision navigation maps through multi-vehicle collaboration, cloud integration, and real-time updates. Vision-based crowdsourced mapping heavily relies on cameras' perception of road information such as lane lines. However, lane lines are easily obscured by other vehicles, shadows, inclement weather (such as rain and snow), road damage, or foreign objects. This can affect the quality of map construction, leading to missing or incorrect lane line data. Consequently, crowdsourced maps may exhibit discontinuous road models, distorted geometry, and incorrect lane topology, directly reducing the reliability and usability of high-precision maps.

[0003] Furthermore, when vehicle sensors collect data on the road, lane lines may be obscured by other vehicles or by extreme weather, resulting in missing lane line data. This can lead to interruptions in the lane lines when the map is generated, increasing the additional manpower cost for subsequent map quality inspection. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a technical solution for lane line data processing, including a method, apparatus, and device. Specifically, when a missing lane line is detected at the current moment, this application performs data fusion processing on the end lane line data, driving trajectory data, and driving heading angle to obtain virtual lane line data. This virtual lane line data is then used to complete the lane lines and obtain the target lane line data. Furthermore, this application can utilize the end lane line data, driving trajectory data, and driving heading angle collected by the data acquisition device during driving to assist in completing the missing lane line data. This enables automated and real-time lane line completion processing, improving completion efficiency and accuracy, ensuring the integrity of map drawing, and saving labor costs.

[0005] On one hand, embodiments of this application provide a lane line data processing method, the method comprising: If a missing lane line is detected at the current moment, acquire the end lane line data, driving trajectory data, and driving heading angle. The end lane line data is the lane line data detected at the previous moment. The driving trajectory data is the trajectory data of the data acquisition device from the previous moment to the target moment. The target moment is the moment when the data acquisition device acquires the lane line data again after the current moment. The driving heading angle is the heading angle corresponding to the data acquisition device. The end lane line data, the driving trajectory data, and the driving heading angle are fused to obtain virtual lane line data. Based on the virtual lane line data, lane lines are completed to obtain the target lane line data.

[0006] Further, the data fusion processing of the end lane line data, the driving trajectory data, and the driving heading angle to obtain virtual lane line data includes: The data processing is performed sequentially on the end lane line data and the driving heading angle corresponding to each moment during the driving trajectory data of the data acquisition device, to obtain the first angle data corresponding to each moment. The first angle data is the angle between the projection vector of the end lane line data on the projection plane and the direction vector corresponding to the driving heading angle. The first angle data corresponding to each time other than the previous time is sequentially processed with the first angle data corresponding to the previous time to obtain multiple offset angle differences; The extension direction of the virtual lane line is determined based on the multiple offset angle differences; The virtual lane line data is obtained based on the extension direction of the virtual lane line and the driving trajectory data.

[0007] Further, determining the extension direction of the virtual lane line based on the plurality of offset angle differences includes: For each time interval corresponding to the offset angle difference, when the offset angle difference is within a preset difference range, the projection vector of the end lane line data on the projection plane is determined as the extension direction of the virtual lane line at each time interval.

[0008] Further, when the offset angle difference is within a preset difference range, determining the projection vector of the end lane line data on the projection plane as the extension direction of the virtual lane line at each time step includes: When the offset angle difference is within the preset difference range, the extension direction of the virtual lane line at the current moment is consistent with the extension direction at the previous moment.

[0009] Furthermore, the method also includes: When the offset angle difference is not within the preset difference range, obtain the first direction vector corresponding to the driving heading angle at the first moment corresponding to the offset angle difference that is not within the preset difference range, and the second direction vector corresponding to the driving heading angle at the second moment, wherein the second moment is a moment that is at least a preset time interval from the first moment. Determine the second angle data between the first direction vector and the second direction vector; The extension direction of the virtual lane line is determined based on the correspondence between the second angle data and the preset angle range.

[0010] Further, determining the extension direction of the virtual lane line based on the correspondence between the second angle data and the preset angle range includes: When the second angle data is within the preset angle range, the extension direction of the virtual lane line at the current moment remains the extension direction at the previous moment; When the second angle data is not within the preset angle range, the extension direction of the virtual lane line at the current moment is obtained by shifting the extension direction of the previous moment by a preset angle in the offset direction. The preset angle is the offset of the driving heading angle of the data acquisition device at the second moment relative to the previous moment.

[0011] Further, the process of completing lane lines based on the virtual lane line data to obtain target lane line data includes: The target lane line data is obtained by smoothing the end virtual lane line data corresponding to the virtual lane line data and the lane line data collected again.

[0012] Furthermore, before acquiring the end lane line data, driving trajectory data, and driving heading angle, the method further includes: Determine the intersection-union ratio (IUU) of the lane line data corresponding to each adjacent time point. The IUU is the ratio between the intersecting image pixels of the lane line data corresponding to each adjacent time point and the total image pixels of the collected lane line data. The lane line data is updated based on the intersection-merge ratio data and the lane line data corresponding to each adjacent time point.

[0013] On the other hand, embodiments of this application provide a lane line data processing device, the device comprising: The acquisition module is used to acquire end lane line data, driving trajectory data, and driving heading angle when a missing lane line is detected at the current moment. The end lane line data is the lane line data detected at the previous moment, the driving trajectory data is the trajectory data of the data acquisition device from the previous moment to the target moment, the target moment is the moment when the data acquisition device acquires the lane line data again after the current moment, and the driving heading angle is the heading angle corresponding to the data acquisition device. The virtual lane line data determination module is used to perform data fusion processing on the end lane line data, the driving trajectory data and the driving heading angle to obtain virtual lane line data. The target lane line data determination module is used to complete the lane lines based on the virtual lane line data to obtain the target lane line data.

[0014] On the other hand, a lane line data processing device is provided, which includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the lane line data processing method described above.

[0015] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction, at least one program, code set, or instruction set is stored therein, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the lane line data processing method described above.

[0016] Implementing this application will have the following beneficial effects: This application, upon detecting a missing lane line at the current moment, performs data fusion processing on the end lane line data, driving trajectory data, and driving heading angle to obtain virtual lane line data. This virtual lane line data is then used to complete the target lane line data. Furthermore, this application utilizes the end lane line data, driving trajectory data, and driving heading angle collected by data acquisition equipment during driving to assist in completing the missing lane line data. This enables automated and real-time lane line completion processing, improving completion efficiency and accuracy, ensuring the integrity of map drawing, and saving labor costs. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic diagram of an implementation environment provided for an embodiment of this application; Figure 2 A flowchart illustrating a lane line data processing method provided in an embodiment of this application; Figure 3 A flowchart illustrating a method for determining virtual lane line data provided in an embodiment of this application; Figure 4 A flowchart illustrating a method for determining the extension direction of a virtual lane line, provided in an embodiment of this application; Figure 5 A schematic diagram of the structure of a lane line data processing device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0021] Please see Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application, such as... Figure 1 The implementation environment shown may include terminal 01 and server 02. In practical applications, terminal 01 and server 02 can be connected wirelessly to realize interaction between terminal 01 and server 02.

[0022] In this application embodiment, terminal 01 can be a mobile device. For example, terminal 01 can include, but is not limited to, smartphones, tablets, PDA smart terminals, in-vehicle smart terminals, wearable devices, and smart home control terminals. Both terminal 01 and server 02 can serve as the execution subject of this application embodiment.

[0023] In one specific embodiment, when terminal 01 is the executing entity, terminal 01 is used for lane line data, driving trajectory data, and driving heading angle, and performs data fusion processing on the end lane line data, driving trajectory data, and driving heading angle to obtain virtual lane line data. In one specific embodiment, terminal 01 can be a data processing module in a data acquisition device, wherein the data processing module is communicatively connected to the acquisition module in the data acquisition device. After the acquisition module in the data acquisition device acquires the end lane line data, driving trajectory data, and driving heading angle, it can send the end lane line data, driving trajectory data, and driving heading angle to the data processing module so that the data processing module can perform analysis and processing. The results of the analysis and processing can be sent to server 02 for cloud storage by server 02.

[0024] In practical applications, data acquisition equipment can be a data acquisition vehicle or an acquisition module located on a data acquisition vehicle.

[0025] In another specific embodiment, when the server 02 is the execution subject, the terminal 01 is used to collect lane line data, driving trajectory data and driving heading angle, and transmit the lane line data, driving trajectory data and driving heading angle to the server 02, so that the server 02 can analyze and process the lane line data, driving trajectory data and driving heading angle to determine virtual lane line data, and perform lane line completion based on the virtual lane line data to obtain target lane line data, and analyze and store the target lane line data.

[0026] It should be noted that the following description of the lane line data processing method is based on terminal 01 as the execution subject. Furthermore, it should be noted that... Figure 1 The diagram shown is merely a schematic representation of an implementation environment, which may include more or fewer nodes; this application makes no limitation on this.

[0027] Figure 2 This is a flowchart illustrating a lane line data processing method provided in an embodiment of this application. The following is a summary of the process. Figure 2 The technical solution of this application is described in detail. It should be noted that this specification provides the method operation steps as shown in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operation steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many steps and does not represent the only execution order. The method specifically includes the following steps: S101: If a missing lane line is detected at the current moment, acquire the end lane line data, driving trajectory data, and driving heading angle. The end lane line data is the lane line data detected at the previous moment. The driving trajectory data is the trajectory data of the data acquisition device from the previous moment to the target moment. The target moment is the moment when the data acquisition device acquires lane line data again after the current moment. The driving heading angle is the heading angle corresponding to the data acquisition device.

[0028] In this embodiment, the current time, the previous time, and the target time are all times when the data acquisition device collects lane line data. There is a preset time interval between the previous time and the current time, and at least two preset time intervals between the current time and the target time. The multiple acquisition times are sequential. In one embodiment, the data acquisition device is a data acquisition vehicle or an acquisition module located on a data acquisition vehicle. When the data acquisition device is a data acquisition vehicle, the driving heading angle is the heading angle of the vehicle. When the data acquisition device is an acquisition module located on a data acquisition vehicle, the driving heading angle is the heading angle of the data acquisition vehicle where the acquisition module is located. The data acquisition device has a corresponding driving heading angle at each time. That is, the driving heading angle includes the heading angle corresponding to each acquisition time during the driving process of the data acquisition device. Therefore, the driving time of the data acquisition device can be utilized.

[0029] In an optional implementation, prior to step S101, the method further includes: S1011: Determine the intersection-union ratio (IUGR) of the lane line data corresponding to each adjacent time point. The IUGR is the ratio between the intersecting image pixels of the lane line data corresponding to each adjacent time point and the total image pixels of the acquired lane line data. S1012: Update the lane line data based on the intersection-merger ratio data and the lane line data corresponding to each adjacent time point.

[0030] In this embodiment, image data carrying lane line data is acquired by a data acquisition device during driving. The lane line data can then be segmented using a segmentation model to obtain lane line data. The obtained lane line data is then transformed to obtain lane line data in the same coordinate system. In a specific embodiment, the image data acquired at the current moment and the image data acquired at the next moment can be compared to determine the image pixels corresponding to the intersecting lane line data of the lane line data acquired at the current moment and the lane line data acquired at the next moment. Then, the image pixels corresponding to the intersecting lane line data can be divided by the image pixels of the lane line data acquired at the current moment and the image pixels of the lane line data acquired at the next moment, respectively, to obtain the intersection-union ratio data corresponding to the current moment and the next moment.

[0031] Furthermore, if any cross-combination ratio (CCR) data in the current and next time intervals exceeds a preset threshold, it indicates that the lane line data collected at the current time and the lane line data collected at the next time interval are the same lane line data. Therefore, the two can be merged on the map to incrementally update the lane line data, thereby improving the reliability of drawing lane line data.

[0032] It should be noted that the data acquisition device can acquire data from multiple parallel lane lines simultaneously, and each lane line has a unique identifier, which can avoid the occurrence of intersections during the lane line data drawing process, thereby further improving the reliability of the drawn lane line data.

[0033] S102: Perform data fusion processing on the end lane line data, driving trajectory data, and driving heading angle to obtain virtual lane line data.

[0034] In this embodiment, virtual lane line data is generated by using the end lane line data, driving trajectory data and driving heading angle collected by the data acquisition device during driving. This helps to complete the missing lane line data, so as to realize the automatic and real-time lane line completion process, improve the completion efficiency and accuracy of lane line completion, ensure the integrity of map drawing, and save labor costs.

[0035] It should be noted that virtual lane line data is generated directly as the data acquisition device moves when missing lane lines are detected. In other words, virtual lane lines can be generated directly on the global map, and lane lines can be filled in in real time, thereby improving the efficiency of lane line filling.

[0036] In one alternative implementation, such as Figure 3 As shown, this is a flowchart illustrating a method for determining virtual lane line data provided in an embodiment of this application. Specifically, step S102 includes: S1021: Sequentially process the end lane line data and the driving heading angle corresponding to each moment during the driving trajectory data of the data acquisition device to obtain the first angle data corresponding to each moment. The first angle data is the angle between the projection vector of the end lane line data on the projection plane and the direction vector corresponding to the driving heading angle. S1022: Sequentially perform difference processing on the first angle data corresponding to the time other than the previous time and the first angle data corresponding to the previous time to obtain multiple offset angle differences; S1023: Determine the extension direction of the virtual lane line based on multiple offset angle differences; S1024: Obtain virtual lane line data based on the extension direction and driving trajectory data of the virtual lane lines.

[0037] In this embodiment, the heading angle is the angle between the driving direction corresponding to the data acquisition device and the due north direction. The projection plane is a plane formed by the due east direction as the X-axis and the due north direction as the Y-axis. The projection vector of the end lane line data on the projection plane is the vector mapped onto the projection plane by the end lane line data. The direction vector corresponding to the heading angle is a vector formed by the driving direction corresponding to the heading angle and a preset length. The preset length is the extension length in the driving direction starting from the origin corresponding to the heading angle. Here, the extension length is not specifically limited.

[0038] In one specific embodiment, the magnitude relationship between multiple offset angle differences and a preset difference range can be determined one by one according to the acquisition sequence, so as to determine the extension direction of the virtual lane line based on the correspondence between the two. The driving trajectory data includes the position and offset direction of the data acquisition device. Then, when the extension direction of the virtual lane line is determined, it can be extended along the extension direction of the virtual lane line from the determined lane line data to the location of the data acquisition device or a preset length in front of the location, so as to generate the virtual lane line data corresponding to that moment.

[0039] Furthermore, this application can fully utilize the driving trajectory data and driving heading angle of the data acquisition device, and the position and offset relationship between them and the end lane line data to generate virtual lane line data, thereby improving the accuracy of lane line completion. Moreover, the entire process of determining virtual lane line data only involves the first angle data and the difference in offset angle, thus avoiding overly complex calculations and improving the efficiency of lane line completion.

[0040] In practical applications, the first angle data is equal to the angle between the projection vector of the last lane line data at the previous moment onto the projection plane and the direction vector at any other moment besides the previous moment. Specifically, let the first angle data be θ, and the projection vector be... The direction vector is Then the data for the first angle is equal to:

[0041] In the formula, Let the magnitude of the projection vector be . Let be the magnitude of the direction vector. It should be noted that the first angle data at any given time can be determined according to the above formula.

[0042] Furthermore, the offset angle difference is equal to the difference between the first angle data at any time other than the previous time and the first angle data at the previous time. Specifically, let the offset angle difference be D, then the offset angle difference is equal to:

[0043] In the formula, This refers to the first angle data corresponding to the previous moment. Let n be any time other than the previous time, where n is 1, 2, 3, 4, or 5, etc.

[0044] In an optional implementation, step S1023 may include: S10231: For the offset angle difference corresponding to each time moment, when the offset angle difference is within the preset difference range, the projection vector of the end lane line data on the projection plane is determined as the extension direction of the virtual lane line at each time moment.

[0045] Specifically, the preset difference range is a range consisting of the minimum preset angle difference and the maximum preset angle difference. For example, the minimum preset angle difference can be -3 degrees and the maximum preset angle difference can be +3 degrees. When the offset angle difference is within the preset difference range, it indicates that the data acquisition device is traveling along the lane line and maintaining a straight line. Then, multiple offset angle differences are compared with the preset difference range according to the acquisition sequence. If multiple consecutive offset angle differences are within the preset difference range, the projection vector of the end lane line data on the projection plane can be determined as the extension direction of the virtual lane line at multiple consecutive moments. This enables the determination of the extension direction of the virtual lane line during the straight-line travel of the data acquisition device, thereby improving the accuracy of the determination of the extension direction of the virtual lane line during the straight-line travel of the data acquisition device.

[0046] In one specific implementation, step S10231 may include: S102311: When the offset angle difference is within the preset difference range, the extension direction of the virtual lane line at the current moment is consistent with the extension direction at the previous moment.

[0047] Specifically, when the offset angle difference is within the preset difference range, it indicates that the data acquisition device is traveling along the lane line and maintaining a straight line. Consequently, the extension direction of the virtual lane line at the current moment is consistent with the extension direction at the previous moment, so as to cover the determination of the extension direction of the virtual lane line by the data acquisition device during straight-line driving, thereby improving the accuracy of the determination of the extension direction of the virtual lane line by the data acquisition device during straight-line driving.

[0048] In one alternative implementation, such as Figure 4 As shown, it is a flowchart illustrating a method for determining the extension direction of a virtual lane line according to an embodiment of this application. Specifically, the method further includes: S10232: When the offset angle difference is not within the preset difference range, obtain the first direction vector corresponding to the driving heading angle at the first moment corresponding to the offset angle difference that is not within the preset difference range, and the second direction vector corresponding to the driving heading angle at the second moment, wherein the second moment is a moment that is at least a preset time interval from the first moment. S10233: Determine the second angle data between the first direction vector and the second direction vector; S10234: Determine the extension direction of the virtual lane line based on the correspondence between the second angle data and the preset angle range.

[0049] In this embodiment, when the offset angle difference is not within the preset difference range, that is, when the offset angle difference is less than -3 degrees or greater than +3 degrees, it indicates that the data acquisition device is driving on a curve or changing lanes. This further determines whether the data acquisition device is driving on a curve or changing lanes. Specifically, the first moment is the moment corresponding to the first offset angle difference that is not within the preset difference range during the sequential comparison process, the second moment is the moment after the first moment, the first direction vector is the direction vector corresponding to the driving heading angle at the first moment, the second direction vector is the second direction vector corresponding to the driving heading angle at the second moment, and the preset angle range is the range consisting of the minimum preset angle and the maximum preset angle. For example, the minimum preset angle can be -3 degrees, the maximum preset angle can be +3 degrees, and the second angle data is equal to the angle between the first direction vector and the second direction vector.

[0050] Furthermore, by determining the correspondence between the second angle data between the first and second direction vectors and the preset angle range, it can be determined whether the data acquisition device is driving on a curve or changing lanes, so as to determine the extension direction of the virtual lane line corresponding to the driving state of the data acquisition device. This enables the determination of the extension direction of the virtual lane line during the data acquisition device's driving on a curve or changing lanes, thereby improving the accuracy of the determination of the extension direction of the virtual lane line during the data acquisition device's driving on a curve or changing lanes.

[0051] It should be noted that the determination of the second angle data can be done in the same way as the determination of the first angle data, and will not be repeated here.

[0052] In an optional implementation, step S10234 may include: S102341: When the second angle data is within the preset angle range, the extension direction of the virtual lane line at the current moment remains the extension direction at the previous moment. S102342: When the second angle data is not within the preset angle range, the extension direction of the virtual lane line at the current moment is obtained by offsetting the extension direction at the previous moment by a preset angle. The preset angle is the offset of the driving heading angle of the data acquisition device at the second moment relative to the previous moment.

[0053] In this embodiment of the application, when the second angle data is within the preset angle range, it indicates that the data acquisition device is in a lane-changing driving state, and the direction of the lane line has not changed. Therefore, the extension direction of the virtual lane line at the current moment remains the extension direction corresponding to the previous moment, so as to cover the determination of the extension direction of the virtual lane line by the data acquisition device during the lane-changing driving process, thereby improving the accuracy of the determination of the extension direction of the virtual lane line by the data acquisition device during the lane-changing driving process.

[0054] Furthermore, when the second angle data is not within the preset angle range, it indicates that the data acquisition device is driving on a curve, and the direction of the lane line is constantly changing. Therefore, the current extension direction of the virtual lane line is obtained by offsetting it by a preset angle from the previous extension direction. This offset direction is consistent with the turning direction of the data acquisition device. For example, if the data acquisition device turns left, it offsets to the left; if it turns right, it offsets to the right. The preset angle is the angle of offset between the current and previous moments. Its value is not specifically limited here; it can be directly obtained. This can cover the determination of the virtual lane line's extension direction during curve driving, thereby improving the accuracy of the data acquisition device's determination of the virtual lane line's extension direction during curve driving.

[0055] S103: Perform lane line completion based on virtual lane line data to obtain target lane line data.

[0056] In this embodiment of the application, the target lane line data is the complete lane line data after completion. By using virtual lane line data to complete the lane lines, the integrity of the map drawing can be ensured, while saving the manpower cost of subsequent map quality inspection.

[0057] It should be noted that the solid and dashed lines corresponding to lane lines can be determined based on the lane lines before the missing lane lines. In other words, the solid and dashed lines corresponding to lane lines are consistent with the solid and dashed lines of the end lane line data.

[0058] In an optional implementation, step S103 may include: S1031: Smooth the end virtual lane line data corresponding to the virtual lane line data and the lane line data collected again to obtain the target lane line data.

[0059] In this embodiment, the distance before and after the intersection of the virtual lane line data at the end and the lane line data collected again can be taken, and a Bezier curve can be used for smoothing. If there is no intersection, the virtual lane line data at the end and the lane line data collected again can be directly connected. By smoothing the virtual lane line data, it is intended to ensure that it is smoothly connected with the real lane lines, thereby ensuring the topological accuracy of the lane line map, improving the overall quality of the map data, and providing a reliable data foundation for high-precision applications such as autonomous driving.

[0060] As can be seen from the above technical solutions of the embodiments of this application, the following technical effects are achieved: This application, upon detecting a missing lane line at the current moment, performs data fusion processing on the end lane line data, driving trajectory data, and driving heading angle to obtain virtual lane line data. This virtual lane line data is then used to complete the target lane line data. Furthermore, this application utilizes the end lane line data, driving trajectory data, and driving heading angle collected by data acquisition equipment during driving to assist in completing the missing lane line data. This enables automated and real-time lane line completion processing, improving completion efficiency and accuracy, ensuring the integrity of map drawing, and saving labor costs.

[0061] This application also provides a lane line data processing device, such as... Figure 5 The diagram shown is a structural schematic of a lane line data processing device provided in an embodiment of this application. The lane line data processing device includes: The acquisition module 10 is used to acquire the end lane line data, driving trajectory data and driving heading angle when a missing lane line is detected at the current time. The end lane line data is the lane line data detected at the previous time. The driving trajectory data is the trajectory data of the data acquisition device from the previous time to the target time. The target time is the time when the data acquisition device acquires lane line data again after the current time. The driving heading angle is the heading angle corresponding to the data acquisition device.

[0062] The virtual lane line data determination module 20 is used to perform data fusion processing on the end lane line data, driving trajectory data and driving heading angle to obtain virtual lane line data.

[0063] The target lane line data determination module 30 is used to complete the lane lines based on the virtual lane line data to obtain the target lane line data.

[0064] Furthermore, the virtual lane line data determination module 20 includes: The first angle data determination unit 201 is used to process the end lane line data and the driving heading angle corresponding to each moment during the driving trajectory data of the data acquisition device, and obtain the first angle data corresponding to each moment. The first angle data is the angle between the projection vector of the end lane line data on the projection plane and the direction vector corresponding to the driving heading angle.

[0065] The offset angle difference determination unit 202 is used to sequentially perform difference processing on the first angle data corresponding to the time other than the previous time and the first angle data corresponding to the previous time to obtain multiple offset angle differences.

[0066] The extension direction determination unit 203 is used to determine the extension direction of the virtual lane line based on multiple offset angle differences.

[0067] The virtual lane line data determination unit 204 is used to obtain virtual lane line data based on the extension direction of the virtual lane line and the driving trajectory data.

[0068] Furthermore, the extension direction determining unit 203 includes: The first extension direction determination subunit 2031 is used to determine the projection vector of the end lane line data on the projection plane as the extension direction of the virtual lane line at each time when the offset angle difference is within a preset difference range.

[0069] Furthermore, the first extension direction defining sub-unit 2031 includes: The first extension direction determination structure 20311 is used to ensure that the extension direction of the virtual lane line at the current moment is consistent with the extension direction at the previous moment when the offset angle difference is within a preset difference range.

[0070] Furthermore, the device also includes: The first direction vector determination unit 2032 is used to obtain the first direction vector corresponding to the driving heading angle at the first moment when the offset angle difference is not within the preset difference range, and the second direction vector corresponding to the driving heading angle at the second moment when the offset angle difference is not within the preset difference range. The second moment is a moment that is at least a preset time interval from the first moment.

[0071] The second angle data determination unit 2033 is used to determine the second angle data between the first direction vector and the second direction vector.

[0072] The second extension direction determination unit 2034 is used to determine the extension direction of the virtual lane line based on the correspondence between the second angle data and the preset angle range.

[0073] Furthermore, the second extension direction determining unit 2034 includes: The second extension direction determination subunit 20341 is used to ensure that the extension direction of the virtual lane line at the current moment remains the same as the extension direction at the previous moment when the second angle data is within the preset angle range.

[0074] The third extension direction determination subunit 20342 is used to determine the extension direction of the virtual lane line at the current moment when the second angle data is not within the preset angle range. The extension direction is obtained by offsetting the virtual lane line in the offset direction by a preset angle based on the extension direction corresponding to the previous moment. The preset angle is the offset of the driving heading angle of the data acquisition device at the second moment relative to the previous moment.

[0075] Furthermore, the target lane line data determination module 30 includes: The target lane line data determination unit 301 is used to smooth the end virtual lane line data corresponding to the virtual lane line data and the lane line data collected again to obtain the target lane line data.

[0076] Furthermore, the device also includes: The intersection-to-overlap ratio (CTO) data determination module 40 is used to determine the CTO data of the lane line data corresponding to each adjacent time point. The CTO data is the ratio between the intersecting image pixels of the lane line data corresponding to each adjacent time point and the total image pixels of the acquired lane line data.

[0077] The update module 50 is used to update the lane line data based on the intersection-merge ratio data and the lane line data corresponding to each adjacent time point.

[0078] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0079] This application provides a lane line data processing device, which includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set. The at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the lane line data processing method provided in the above method embodiments.

[0080] Memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. Memory can primarily include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for the functions, etc.; the data storage area can store data created based on the use of the device, etc. Furthermore, memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory can also include a memory controller to provide the processor with access to the memory.

[0081] The lane line data processing device can be a server. This application embodiment also provides a schematic diagram of the server structure. Please refer to [link / reference]. Figure 6 The server 600 is used to implement the data processing method provided in the above embodiments. The server 600 can vary significantly due to different configurations or performance, and may include one or more processors 610 (e.g., one or more processors) and storage 630, and one or more storage media 620 (e.g., one or more mass storage devices) for storing applications 623 or data 622. The memory 630 and storage media 620 can be temporary or persistent storage. The program stored in the storage media 620 may include one or more modules, each module including a series of instruction operations on the server. Furthermore, the processor 610 may be configured to communicate with the storage media 620 and execute a series of instruction operations in the storage media 620 on the server 600. The server 600 may also include one or more power supplies 660, one or more wired or wireless network interfaces 650, one or more input / output interfaces 640, and / or one or more operating systems 621, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0082] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in a server to store at least one instruction, at least one program, code set, or instruction set related to implementing a lane line data processing method in the method embodiments. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the lane line data processing method provided in the above method embodiments.

[0083] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0084] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system and server embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0086] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A lane line data processing method, characterized in that, The method includes: If a missing lane line is detected at the current moment, acquire the end lane line data, driving trajectory data, and driving heading angle. The end lane line data is the lane line data detected at the previous moment. The driving trajectory data is the trajectory data of the data acquisition device from the previous moment to the target moment. The target moment is the moment when the data acquisition device acquires the lane line data again after the current moment. The driving heading angle is the heading angle corresponding to the data acquisition device. The end lane line data, the driving trajectory data, and the driving heading angle are fused to obtain virtual lane line data. Based on the virtual lane line data, lane lines are completed to obtain the target lane line data.

2. The method according to claim 1, characterized in that, The process of fusing the end lane line data, the driving trajectory data, and the driving heading angle to obtain virtual lane line data includes: The data processing is performed sequentially on the end lane line data and the driving heading angle corresponding to each moment during the driving trajectory data of the data acquisition device, to obtain the first angle data corresponding to each moment. The first angle data is the angle between the projection vector of the end lane line data on the projection plane and the direction vector corresponding to the driving heading angle. The first angle data corresponding to each time other than the previous time is sequentially processed with the first angle data corresponding to the previous time to obtain multiple offset angle differences; The extension direction of the virtual lane line is determined based on the multiple offset angle differences; The virtual lane line data is obtained based on the extension direction of the virtual lane line and the driving trajectory data.

3. The method according to claim 2, characterized in that, Determining the extension direction of the virtual lane line based on the multiple offset angle differences includes: For each time interval corresponding to the offset angle difference, when the offset angle difference is within a preset difference range, the projection vector of the end lane line data on the projection plane is determined as the extension direction of the virtual lane line at each time interval.

4. The method according to claim 3, characterized in that, When the offset angle difference is within a preset difference range, determining the projection vector of the end lane line data onto the projection plane as the extension direction of the virtual lane line at each time step includes: When the offset angle difference is within the preset difference range, the extension direction of the virtual lane line at the current moment is consistent with the extension direction at the previous moment.

5. The method according to claim 3, characterized in that, The method further includes: When the offset angle difference is not within the preset difference range, obtain the first direction vector corresponding to the driving heading angle at the first moment corresponding to the offset angle difference that is not within the preset difference range, and the second direction vector corresponding to the driving heading angle at the second moment, wherein the second moment is a moment that is at least a preset time interval from the first moment. Determine the second angle data between the first direction vector and the second direction vector; The extension direction of the virtual lane line is determined based on the correspondence between the second angle data and the preset angle range.

6. The method according to claim 5, characterized in that, Determining the extension direction of the virtual lane line based on the correspondence between the second angle data and the preset angle range includes: When the second angle data is within the preset angle range, the extension direction of the virtual lane line at the current moment remains the extension direction at the previous moment; When the second angle data is not within the preset angle range, the extension direction of the virtual lane line at the current moment is obtained by shifting the extension direction of the previous moment by a preset angle in the offset direction. The preset angle is the offset of the driving heading angle of the data acquisition device at the second moment relative to the previous moment.

7. The method according to claim 1, characterized in that, The process of completing lane lines based on the virtual lane line data to obtain target lane line data includes: The target lane line data is obtained by smoothing the end virtual lane line data corresponding to the virtual lane line data and the lane line data collected again.

8. The method according to claim 1, characterized in that, Before acquiring the end lane line data, driving trajectory data, and driving heading angle, the method further includes: Determine the intersection-union ratio (IUU) of the lane line data corresponding to each adjacent time point. The IUU is the ratio between the intersecting image pixels of the lane line data corresponding to each adjacent time point and the total image pixels of the collected lane line data. The lane line data is updated based on the intersection-merge ratio data and the lane line data corresponding to each adjacent time point.

9. A lane line data processing device, characterized in that, The device includes: The acquisition module is used to acquire end lane line data, driving trajectory data, and driving heading angle when a missing lane line is detected at the current moment. The end lane line data is the lane line data detected at the previous moment, the driving trajectory data is the trajectory data of the data acquisition device from the previous moment to the target moment, the target moment is the moment when the data acquisition device acquires the lane line data again after the current moment, and the driving heading angle is the heading angle corresponding to the data acquisition device. The virtual lane line data determination module is used to perform data fusion processing on the end lane line data, the driving trajectory data and the driving heading angle to obtain virtual lane line data. The target lane line data determination module is used to complete the lane lines based on the virtual lane line data to obtain the target lane line data.

10. A lane line data processing device, characterized in that, The lane line data processing device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the lane line data processing method as described in any one of claims 1 to 8.

Images