Vehicle lane changing data labeling method, system and electronic device

Abstract

The application provides a vehicle lane changing data labeling method, system and electronic equipment. The vehicle lane changing data labeling method comprises: acquiring vehicle trajectory data; filtering out all vehicles with lane changing behaviors according to the time sequence change of the lane number to which the vehicle belongs; positioning the time point corresponding to the vehicle crossing the lane line, and defining the time point as a lane changing critical point; traversing each heading angle threshold in a preset candidate heading angle threshold set, and traversing and searching forward and backward respectively for the vehicle heading angle time sequence based on the lane changing critical point, and combining the heading angle threshold to determine the corresponding lane changing start time and lane changing end time; based on the lane changing duration and a preset experienced lane changing duration, a lane changing time deviation index is calculated, the optimal heading angle threshold is determined according to the lane changing time deviation index, and the lane changing label is generated based on the lane changing start time and the lane changing end time corresponding to the optimal heading angle threshold.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving and data processing technology, and in particular to a method, system and electronic device for labeling vehicle lane change data. Background Technology

[0002] With the deep integration and continuous breakthroughs in artificial intelligence and automotive intelligence technologies, intelligent driving research is gradually moving from functional implementation in specific scenarios to cognitive decision-making at the level of all scenarios and high reliability. Currently, mainstream intelligent driving algorithm architectures increasingly exhibit data-driven and learning-centric characteristics. Key modules such as vehicle trajectory prediction, lane-change intention recognition, and dynamic trajectory planning rely heavily on large-scale, high-quality labeled data for performance. In this context, data quality has become a decisive factor restricting algorithm performance improvement, directly affecting the model's generalization ability and scenario adaptability. In the highly structured yet dynamically complex high-risk driving environment of highways, lane-change behavior is not only a typical traffic control unit but also a crucial entry point for understanding driving intentions and assessing driving risks. However, lane-change intention, as a high-order semantic information, is difficult to obtain directly from raw sensor data. It requires comprehensive reasoning and spatiotemporal modeling of multi-dimensional basic semantic information such as the driving environment, vehicle state, and driving operations to be effectively defined.

[0003] Currently, research on methods for labeling vehicle lane-changing intentions is still in the exploratory stage, and a unified technical paradigm has not yet been formed between academia and industry. A common approach is to define vehicle lane-changing behavior using physical thresholds. This involves monitoring the evolution of vehicle kinematic indicators (such as heading angle, lateral velocity, and lateral displacement) and setting corresponding numerical thresholds to determine the start and end times of lane-changing events.

[0004] Existing annotation methods mostly rely on manual posterior annotation or rule-based heuristic judgment, which often makes it difficult to balance efficiency and accuracy, and have obvious limitations when dealing with complex situations such as ambiguous intent boundaries and diverse driving behaviors. Summary of the Invention

[0005] This invention aims to solve at least one of the technical problems existing in the prior art, and proposes a vehicle lane change data annotation method, system and electronic device, which aims to solve the problems that the existing lane change behavior annotation relies on manual threshold setting, is difficult to adapt to complex and ever-changing driving environments and driving style differences, resulting in low annotation efficiency and limited accuracy.

[0006] In a first aspect, the present invention discloses a method for labeling vehicle lane-changing data, comprising the following steps:

[0007] Acquire vehicle driving trajectory data, which includes the vehicle's unique identifier, vehicle location information, and the lane number to which the vehicle belongs;

[0008] Based on the temporal changes in the lane number of the vehicle, traverse all vehicle driving trajectory data, filter out all vehicles that have lane-changing behavior, and generate a list of lane-changing vehicles.

[0009] For each vehicle in the lane-changing vehicle list, locate the moment when the vehicle crosses the lane line and define that moment as the lane-changing critical point.

[0010] Traverse each heading angle threshold in the preset candidate heading angle threshold set, and with the lane change critical point as the reference, traverse and search the vehicle heading angle time sequence forward and backward respectively, and determine the corresponding lane change start time and lane change end time in combination with the heading angle threshold, and mark the lane change interval based on the lane change start time and lane change end time.

[0011] Based on the lane change duration of the lane change interval and the preset empirical lane change duration, a lane change time deviation index is calculated. The optimal heading angle threshold is determined according to the lane change time deviation index. A lane change tag is generated based on the lane change start time and lane change end time corresponding to the optimal heading angle threshold.

[0012] In some embodiments, the vehicle lane change data annotation method of the present invention further includes: calculating the instantaneous heading angle of each sampling point based on the vehicle position information, and constructing a heading angle time sequence.

[0013] The instantaneous heading angle at each sampling point is calculated based on the vehicle position information, using the following formula:

[0014]

[0015] In the formula, (x t , y t ) and (x t-1 , y t-1 ) are the horizontal and vertical coordinates of the vehicle at the current time and the previous time, respectively, and θ is the heading angle of the vehicle at that time, which represents the angle between the vehicle's orientation and the horizontal axis of the coordinate system.

[0016] In some embodiments, the vehicle lane change data annotation method of the present invention further includes: a preset search range for a heading angle threshold, and generating a candidate heading angle threshold set within that range according to the principle of equal interval sampling.

[0017] In some embodiments, based on the lane-changing critical point, the vehicle heading angle time series is traversed forward and backward respectively, and the corresponding lane-changing start time and lane-changing end time are determined by combining the heading angle threshold. Specifically, this includes: based on the lane-changing critical point, traversing the heading angle time series forward, if there are multiple consecutive dry sampling points whose heading angles exceed the heading angle threshold, then marking one of the corresponding times as the lane-changing start time; traversing the heading angle time series backward, if there are multiple consecutive sampling points whose heading angles are not greater than the heading angle threshold, then marking one of the corresponding times as the lane-changing end time.

[0018] In some embodiments, when traversing the heading angle time series forward, if there are multiple consecutive dry sampling points whose heading angles exceed the heading angle threshold, then one of the corresponding times is marked as the lane change start time. Specifically, this includes: when traversing the heading angle time series forward, if N consecutive sampling points whose heading angles exceed the heading angle threshold, then the time corresponding to the Nth sampling point is marked as the lane change start time.

[0019] Traverse the heading angle time sequence backward. If there are multiple consecutive sampling points where the heading angle is not greater than the heading angle threshold, mark one of the corresponding times as the lane change termination time. Specifically, this includes: traversing the heading angle time sequence backward. If the heading angle of M consecutive sampling points is not greater than the heading angle threshold, mark the time corresponding to the Mth sampling point as the lane change termination time.

[0020] In some embodiments, a lane change label is generated based on the lane change start time and lane change end time corresponding to the optimal heading angle threshold, specifically including:

[0021] Based on the start and end times of the lane change corresponding to the optimal heading angle threshold, the lane change interval is divided, and all sampled data points within the lane change interval are labeled with corresponding category labels to generate lane change labels.

[0022] Label all data points in the lane change event with categories, specifically: label all data points in the time interval corresponding to the left lane change event as the first category label; label all data points in the time interval corresponding to the right lane change event as the second category label.

[0023] In some embodiments, a lane change time deviation index is calculated based on the lane change duration of the lane change section and a preset empirical lane change duration, specifically including:

[0024] Identify and remove consecutive overlapping lane change sections, and use independent lane change sections as valid data samples;

[0025] Based on the lane change duration corresponding to all valid data samples and the preset empirical lane change duration, the lane change time deviation index corresponding to the heading angle threshold is calculated.

[0026] The lane change time deviation index is calculated as follows:

[0027]

[0028] In the formula, m represents the number of data subsets participating in the evaluation, and n is the number of individual lane-changing events contained in the data subset. t represents the lane change duration marked by the heading angle thresholding method in the j-th lane change interval of the i-th subset of the dataset. E For experience-based lane change time, f s The sampling frequency.

[0029] In some embodiments, determining the optimal heading angle threshold based on the lane change time deviation index specifically includes: comparing the lane change time deviation indices corresponding to all candidate heading angle thresholds, and taking the heading angle threshold with the smallest lane change time deviation index as the optimal heading angle threshold.

[0030] Secondly, the present invention also discloses a vehicle lane-changing data annotation system, comprising:

[0031] The data acquisition module is used to acquire vehicle driving trajectory data, which includes the vehicle's unique identifier, vehicle location information, and the lane number to which the vehicle belongs.

[0032] The lane-changing vehicle list extraction module is used to traverse all vehicle driving trajectory data based on the temporal changes of the lane number to which the vehicle belongs, filter out all vehicles that have lane-changing behavior, and generate a lane-changing vehicle list.

[0033] The lane change pre-labeling module is used to locate the moment when each vehicle crosses the lane line for each vehicle in the lane change vehicle list, and define the moment when the vehicle crosses the lane line as the lane change critical point. It then iterates through each heading angle threshold in the preset candidate heading angle threshold set, and uses the lane change critical point as a reference to traverse and search the vehicle heading angle time sequence forward and backward respectively. It then determines the corresponding lane change start time and lane change end time by combining the heading angle threshold, and marks the lane change interval based on the lane change start time and lane change end time.

[0034] The lane change tag generation module is used to calculate the lane change time deviation index based on the lane change duration of the lane change interval and the preset empirical lane change duration, determine the optimal heading angle threshold based on the lane change time deviation index, and generate a lane change tag based on the lane change start time and lane change end time corresponding to the optimal heading angle threshold.

[0035] Thirdly, the present invention also discloses an electronic device, comprising:

[0036] One or more processors;

[0037] Memory, used to store one or more programs;

[0038] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the first aspect.

[0039] Fourthly, the present invention also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect.

[0040] The present invention has at least the following beneficial effects:

[0041] This invention automates and adapts the lane change data annotation process, aiming to solve the problems of low annotation efficiency and limited accuracy caused by the reliance on manual threshold setting for existing lane change behavior annotation, which makes it difficult to adapt to complex and ever-changing driving environments and differences in driving styles. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating a vehicle lane-changing data annotation method provided in an embodiment of the present invention.

[0043] Figure 2 A flowchart illustrating another vehicle lane-changing data annotation method provided in an embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram of a vehicle lane-changing data annotation system provided in an embodiment of the present invention;

[0045] Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0047] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0048] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0049] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0050] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0051] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0052] Figure 1 This is a flowchart illustrating a vehicle lane-changing data annotation method according to an embodiment of the present invention. See also... Figure 1 One embodiment of the vehicle lane-changing data annotation method includes the following steps:

[0053] S1. Obtain vehicle driving trajectory data, which includes the vehicle's unique identifier, vehicle location information, and the lane number to which the vehicle belongs.

[0054] S2. Based on the temporal changes of the lane number to which the vehicle belongs, traverse all vehicle driving trajectory data, filter out all vehicles that have lane-changing behavior, and generate a list of lane-changing vehicles.

[0055] S3. For each vehicle in the lane-changing vehicle list, locate the time point corresponding to the vehicle crossing the lane line and define the time point as the lane-changing critical point. Traverse each heading angle threshold in the preset candidate heading angle threshold set. Based on the lane-changing critical point, traverse and search the vehicle heading angle time sequence forward and backward respectively. Combine the heading angle threshold to determine the corresponding lane-changing start time and lane-changing end time. Mark the lane-changing interval based on the lane-changing start time and lane-changing end time, and calculate the lane-changing duration of the lane-changing interval.

[0056] S4. Based on the lane change duration of the lane change interval and the preset empirical lane change duration, calculate the lane change time deviation index, determine the optimal heading angle threshold according to the lane change time deviation index, and generate a lane change tag based on the lane change start time and lane change end time corresponding to the optimal heading angle threshold.

[0057] This invention automates and adapts the lane change data annotation process, significantly improving the accuracy and robustness of the annotation. It provides a feasible technical path for large-scale, automated, and high-precision lane change data annotation, and also lays the foundation for data quality assurance for downstream tasks such as lane change intent recognition.

[0058] Specifically, this invention collects and constructs a raw driving dataset containing vehicle unique identifiers, dynamic motion states (vehicle positions), and lane number information. The raw vehicle trajectory data is grouped and filtered according to the vehicle unique identifier. Based on the temporal change characteristics of the lane number to which the vehicle belongs, the dataset is traversed and all vehicles that have changed lanes are extracted to form a lane-changing vehicle list.

[0059] In some embodiments, the vehicle lane change data annotation method of the present invention further includes: a preset search range for a heading angle threshold, and generating a candidate heading angle threshold set within that range according to the principle of equal interval sampling.

[0060] In some embodiments, the vehicle lane change data annotation method of the present invention further includes: calculating the instantaneous heading angle of each sampling point based on the vehicle position information, and constructing a heading angle time sequence.

[0061] Specifically, the present invention sets a reasonable search range for the heading angle threshold based on prior knowledge of the domain and data distribution characteristics, and generates a candidate threshold set within this range according to the principle of equal interval sampling.

[0062] Specifically, this invention detects discrete changes in lane numbers along a vehicle's trajectory to accurately pinpoint the moment a vehicle crosses a lane line. This moment is recorded as the lane-changing critical point and used as the reference position for subsequent traversals. Based on this, the instantaneous heading angle is calculated using the vehicle's planar position coordinates at adjacent timestamps, defined as follows:

[0063]

[0064] In the formula, (x t , y t ) and (x t-1 , y t-1 Let A and B be the vehicle's horizontal and vertical coordinates at the current and previous moments, respectively, and θ be the vehicle's heading angle at that moment, representing the angle between the vehicle's orientation and the horizontal axis of the coordinate system. This calculation is based on the assumption of continuous vehicle motion and can effectively reflect the instantaneous changes in vehicle attitude when the sampling frequency is high enough.

[0065] For each candidate threshold, the present invention uses the heading angle threshold method to identify the start and end points of the lane change. When the heading angle changes continuously beyond the threshold, it is marked as the start time of the lane change event. When the heading angle returns to the threshold range, it is marked as the end time of the lane change.

[0066] In some embodiments, see Figure 2 Using the lane-changing critical point as a reference, the vehicle heading angle time sequence is traversed forward and backward respectively. The corresponding lane-changing start time and lane-changing end time are determined by combining the heading angle threshold. Specifically, the following steps are taken: using the lane-changing critical point as a reference, the heading angle time sequence is traversed forward. If there are multiple consecutive dry sampling points where the heading angle exceeds the heading angle threshold, one of the corresponding times is marked as the lane-changing start time. The heading angle time sequence is traversed backward. If there are multiple consecutive sampling points where the heading angle is not greater than the heading angle threshold, one of the corresponding times is marked as the lane-changing end time.

[0067] In some embodiments, when traversing the heading angle time series forward, if there are multiple consecutive dry sampling points whose heading angles exceed the heading angle threshold, then one of the corresponding times is marked as the lane change start time. Specifically, this includes: when traversing the heading angle time series forward, if N consecutive sampling points whose heading angles exceed the heading angle threshold, then the time corresponding to the Nth sampling point is marked as the lane change start time.

[0068] Traverse the heading angle time sequence backward. If there are multiple consecutive sampling points where the heading angle is not greater than the heading angle threshold, mark one of the corresponding times as the lane change termination time. Specifically, this includes: traversing the heading angle time sequence backward. If the heading angle of M consecutive sampling points is not greater than the heading angle threshold, mark the time corresponding to the Mth sampling point as the lane change termination time.

[0069] Specifically, this invention uses the lane-changing critical point as a reference and performs a traversal search of the heading angle sequence along the time axis both forward (historical direction) and backward (future direction). To enhance the robustness of the criterion and suppress the risk of false detection caused by sensor noise, this embodiment adopts a continuous multi-point joint criterion: when the heading angle values ​​of three consecutive adjacent sampling points all exceed a preset threshold, the third sampling point that meets the condition is marked as the lane-changing start point; similarly, traversing backward from the lane-changing critical point, when the heading angle of three consecutive sampling points falls back to within the threshold range, the third point is marked as the lane-changing end point. This multi-point criterion can effectively filter instantaneous disturbances and improve the stability of lane-changing boundary recognition.

[0070] In some embodiments, a lane change label is generated based on the lane change start time and lane change end time corresponding to the optimal heading angle threshold, specifically including:

[0071] Based on the start and end times of the lane change corresponding to the optimal heading angle threshold, the lane change interval is divided, and all sampled data points within the lane change interval are labeled with corresponding category labels to generate lane change labels.

[0072] Label all data points in the lane change event with categories, specifically: label all data points in the time interval corresponding to the left lane change event as the first category label; label all data points in the time interval corresponding to the right lane change event as the second category label.

[0073] Specifically, after locating the start and end points of a lane change, the trajectory segments between them are labeled as lane change events in the corresponding direction. The specific labeling rules are as follows: for a left lane change event, all data points within the interval are labeled as category 0; for a right lane change event, they are labeled as category 2; for trajectory segments that do not belong to any lane change interval, i.e., when the vehicle is maintaining its current lane, they are uniformly labeled as lane keeping category 1.

[0074] This invention introduces an empirical lane-change time parameter based on traffic flow statistics or prior driving behavior. By calculating the deviation between the lane-change duration and the empirical lane-change time, and optimizing and filtering the lane-change labels with the goal of minimizing the deviation, the final lane-change label is determined.

[0075] In real-world highway driving scenarios, vehicles may perform multiple lane changes consecutively (such as changing two lanes in succession to avoid traffic at ramp entrances). In such complex situations, the boundaries between adjacent lane change events often overlap, making it difficult to independently separate the duration of a single lane change. To ensure the accuracy and consistency of the evaluation metrics, this embodiment only selects and retains complete, non-overlapping single lane change events as analysis samples when calculating lane change times, eliminating the interference that continuous lane change scenarios may introduce into the statistical results.

[0076] In some embodiments, a lane change time deviation index is calculated based on the lane change duration of the lane change section and a preset empirical lane change duration, specifically including:

[0077] Identify and remove consecutive overlapping lane change sections, and use independent lane change sections as valid data samples;

[0078] Based on the lane change duration corresponding to all valid data samples and the preset empirical lane change duration, the lane change time deviation index corresponding to the heading angle threshold is calculated.

[0079] Based on the above settings, the lane change time deviation index is calculated as follows:

[0080]

[0081] In the formula, m represents the number of data subsets participating in the evaluation, and n is the number of individual lane-changing events contained in the data subset. t represents the duration of a lane change, labeled using the heading angle thresholding method, within the j-th lane change interval (i.e., lane change event) of the i-th subset of the dataset. E For experience-based lane change time, f s The sampling frequency.

[0082] Preferably, the present invention calculates the global lane change time deviation index corresponding to the heading angle threshold based on the lane change duration corresponding to all valid data samples and the preset empirical lane change duration.

[0083] Of course, it is possible to calculate the lane change time deviation index for a single lane change interval, and determine the optimal heading angle threshold based on the lane change time deviation index for a single lane change interval. The lane change time deviation index for a single lane change interval is the deviation value between the lane change duration of a single lane change interval and the preset empirical lane change duration.

[0084] In some embodiments, determining the optimal heading angle threshold based on the lane change time deviation index specifically includes: comparing the lane change time deviation indices corresponding to all candidate heading angle thresholds, and taking the heading angle threshold with the smallest lane change time deviation index as the optimal heading angle threshold.

[0085] This invention discloses an adaptive lane-change data annotation method for highways. This method is based on continuous heading angle change detection combined with lane-change critical point localization and continuous multi-point joint criteria to identify the start / end time of lane changes. Furthermore, in continuous lane-change scenarios, it employs a sample selection strategy that retains only complete single lane-change events for analysis, thereby improving annotation quality. This vehicle lane-change data annotation method automates and adapts the lane-change data annotation process, significantly improving the accuracy and robustness of the annotation. It provides a feasible technical path for large-scale, automated, and high-precision lane-change data annotation, and lays the foundation for data quality assurance for subsequent downstream tasks such as lane-change intention recognition.

[0086] Based on the same inventive concept, this invention provides a vehicle lane change data annotation system. Figure 3 This is a schematic diagram of a vehicle lane-change data annotation system provided in an embodiment of the present invention. See also: Figure 3 A vehicle lane-changing data annotation system, comprising:

[0087] The data acquisition module is used to acquire vehicle driving trajectory data, which includes the vehicle's unique identifier, vehicle location information, and the lane number to which the vehicle belongs.

[0088] The lane-changing vehicle list extraction module is used to traverse all vehicle driving trajectory data based on the temporal changes of the lane number to which the vehicle belongs, filter out all vehicles that have lane-changing behavior, and generate a lane-changing vehicle list.

[0089] The lane change pre-labeling module is used to locate the moment when each vehicle crosses the lane line for each vehicle in the lane change vehicle list, and define the moment when the vehicle crosses the lane line as the lane change critical point. It then iterates through each heading angle threshold in the preset candidate heading angle threshold set, and uses the lane change critical point as a reference to traverse and search the vehicle heading angle time sequence forward and backward respectively. It then determines the corresponding lane change start time and lane change end time by combining the heading angle threshold, and marks the lane change interval based on the lane change start time and lane change end time.

[0090] The lane change tag generation module is used to calculate the lane change time deviation index based on the lane change duration of the lane change interval and the preset empirical lane change duration, determine the optimal heading angle threshold based on the lane change time deviation index, and generate a lane change tag based on the lane change start time and lane change end time corresponding to the optimal heading angle threshold.

[0091] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 4As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the vehicle lane change data annotation methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0092] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0093] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0094] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0095] This invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in any of the vehicle lane change data annotation methods described in the above embodiments. The computer-readable storage medium may be volatile or non-volatile.

[0096] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described vehicle lane change data annotation method.

[0097] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0098] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0099] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0100] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0101] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0102] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0103] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0104] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[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 invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in 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 using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0106] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A method for labeling vehicle lane-changing data, characterized in that, Includes the following steps: Acquire vehicle driving trajectory data, which includes the vehicle's unique identifier, vehicle location information, and the lane number to which the vehicle belongs; Based on the temporal changes in the lane number of the vehicle, traverse all vehicle driving trajectory data, filter out all vehicles that have lane-changing behavior, and generate a list of lane-changing vehicles. For each vehicle in the lane-changing vehicle list, locate the moment when the vehicle crosses the lane line and define the moment when the vehicle crosses the lane line as the lane-changing critical point. Iterate through each heading angle threshold in the preset candidate heading angle threshold set. Based on the lane-changing critical point, iterate through the vehicle heading angle time sequence forward and backward respectively. Combine the heading angle threshold to determine the corresponding lane-changing start time and lane-changing end time. Based on the lane-changing start time and lane-changing end time, mark the lane-changing interval. Based on the lane change duration of the lane change interval and the preset empirical lane change duration, a lane change time deviation index is calculated. The optimal heading angle threshold is determined according to the lane change time deviation index. A lane change tag is generated based on the lane change start time and lane change end time corresponding to the optimal heading angle threshold.

2. The method according to claim 1, characterized in that, Also includes: Based on the vehicle location information, the instantaneous heading angle of each sampling point is calculated, and a heading angle time sequence is constructed.

3. The method according to claim 1, characterized in that, Also includes: The search range for the preset heading angle threshold is determined, and a set of candidate heading angle thresholds is generated within this range according to the principle of equal interval sampling.

4. The method according to claim 1, characterized in that, Using the lane-changing critical point as a reference, the vehicle heading angle time series is traversed forward and backward respectively. The corresponding lane-changing start time and lane-changing end time are determined by combining the heading angle threshold. Specifically, the process includes: using the lane-changing critical point as a reference, traversing the heading angle time series forward. If there are multiple consecutive dry sampling points where the heading angle exceeds the heading angle threshold, then one of the corresponding times is marked as the lane-changing start time; traversing the heading angle time series backward. If there are multiple consecutive sampling points where the heading angle is not greater than the heading angle threshold, then one of the corresponding times is marked as the lane-changing end time.

5. The method according to claim 4, characterized in that, Traverse the heading angle time series forward. If there are multiple consecutive dry sampling points where the heading angle exceeds the heading angle threshold, mark one of the corresponding times as the lane change start time. Specifically, this includes: traversing the heading angle time series forward. If the heading angle of N consecutive sampling points exceeds the heading angle threshold, mark the time corresponding to the Nth sampling point as the lane change start time. Traverse the heading angle time sequence backward. If there are multiple consecutive sampling points where the heading angle is not greater than the heading angle threshold, mark one of the corresponding times as the lane change termination time. Specifically, this includes: traversing the heading angle time sequence backward. If the heading angle of M consecutive sampling points is not greater than the heading angle threshold, mark the time corresponding to the Mth sampling point as the lane change termination time.

6. The method according to claim 1, characterized in that, Lane change labels are generated based on the lane change start and end times corresponding to the optimal heading angle threshold, specifically including: Based on the start and end times of the lane change corresponding to the optimal heading angle threshold, the lane change interval is divided, and all sampled data points within the lane change interval are labeled with corresponding category labels to generate lane change labels.

7. The method according to claim 1, characterized in that, Based on the lane change duration of the lane change section and the preset empirical lane change duration, the lane change time deviation index is calculated, specifically including: Identify and remove consecutive overlapping lane change sections, and use independent lane change sections as valid data samples; Based on the lane change duration corresponding to all valid data samples and the preset empirical lane change duration, the lane change time deviation index corresponding to the heading angle threshold is calculated.

8. The method according to claim 1, characterized in that, Determining the optimal heading angle threshold based on the lane change time deviation index specifically includes: comparing the lane change time deviation index corresponding to all candidate heading angle thresholds, and taking the heading angle threshold with the smallest lane change time deviation index as the optimal heading angle threshold.

9. A vehicle lane-changing data annotation system, characterized in that, include: The data acquisition module is used to acquire vehicle driving trajectory data, which includes the vehicle's unique identifier, vehicle location information, and the lane number to which the vehicle belongs. The lane-changing vehicle list extraction module is used to traverse all vehicle driving trajectory data based on the temporal changes of the lane number to which the vehicle belongs, filter out all vehicles that have lane-changing behavior, and generate a lane-changing vehicle list. The lane change pre-labeling module is used to locate the moment when each vehicle crosses the lane line for each vehicle in the lane change vehicle list, and define the moment when the vehicle crosses the lane line as the lane change critical point. It then iterates through each heading angle threshold in the preset candidate heading angle threshold set, and uses the lane change critical point as a reference to traverse and search the vehicle heading angle time sequence forward and backward respectively. It then determines the corresponding lane change start time and lane change end time by combining the heading angle threshold, and marks the lane change interval based on the lane change start time and lane change end time. The lane change tag generation module is used to calculate the lane change time deviation index based on the lane change duration of the lane change interval and the preset empirical lane change duration, determine the optimal heading angle threshold based on the lane change time deviation index, and generate a lane change tag based on the lane change start time and lane change end time corresponding to the optimal heading angle threshold.

10. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 8.

Images