Signal lamp countdown verification method, device, equipment, medium and program product

Abstract

The invention provides a signal lamp countdown verification method, device and equipment, a medium and a program product, and particularly relates to the technical field of signal lamp countdown service quality evaluation. The method comprises the following steps: matching vehicle track point data with preset road network information, and determining a parking behavior characteristic of a vehicle in a preset area; determining a signal lamp state change moment based on the stay behavior characteristics; and comparing the signal lamp state change moment with preset countdown data to obtain a signal lamp countdown precision evaluation result. The method is used for achieving automatic verification of the countdown precision of the signal lamp, manual field collection is not needed, and the method has the effects of being wide in coverage range, low in cost and high in timeliness.

Description

Technical Field

[0001] This application relates to the field of traffic light countdown service quality assessment technology, and in particular to a traffic light countdown verification method, apparatus, equipment, medium and program product. Background Technology

[0002] Against the backdrop of the rapid development of smart mobility and intelligent transportation systems, traffic light countdown information has become a key function for improving urban traffic efficiency and driving experience. When a vehicle approaches an intersection, drivers can obtain traffic light countdown information through navigation apps or in-vehicle systems, allowing them to anticipate light changes in advance. This optimizes stopping decisions, reduces sudden braking and acceleration, and significantly improves driving safety and road efficiency. Especially during peak hours or in complex intersection scenarios, accurate countdown information helps drivers plan their waiting time effectively, reducing anxiety and fuel consumption. However, the accuracy assessment of current traffic light countdown data still relies on traditional manual road testing methods, which suffer from limited coverage, high costs, and poor timeliness. Summary of the Invention

[0003] This application provides a method, apparatus, equipment, medium, and program product for verifying traffic light countdown accuracy, which can realize automated verification of traffic light countdown accuracy without manual on-site data collection, and has the effects of wide coverage, low cost, and high timeliness.

[0004] In a first aspect, embodiments of this application provide a traffic light countdown verification method, including:

[0005] The vehicle trajectory point data is matched with the preset road network information to determine the vehicle's dwell behavior characteristics in the preset area;

[0006] Based on the aforementioned characteristics of the stopping behavior, the timing of the traffic light state change is determined;

[0007] The timing of the traffic light state change is compared with the preset countdown data to obtain the traffic light countdown accuracy evaluation result.

[0008] Secondly, embodiments of this application provide a traffic light countdown verification device, comprising:

[0009] The first determining module is used to match vehicle trajectory point data with preset road network information to determine the vehicle's stopping behavior characteristics in the preset area;

[0010] The second determining module is used to determine the time of change of the traffic light state based on the dwelling behavior characteristics;

[0011] The comparison module is used to compare the time of change of the traffic light status with the preset countdown data to obtain the accuracy evaluation result of the traffic light countdown.

[0012] Thirdly, embodiments of this application provide a traffic light countdown verification device, including: a memory and a processor;

[0013] The memory stores computer-executed instructions;

[0014] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0016] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0017] The traffic light countdown verification method, apparatus, equipment, medium, and program products provided in this application collect high-frequency vehicle trajectory point data to achieve precise matching between trajectories and road networks, extract dwell behavior features, and use these features to infer the timing of traffic light state changes, thereby replacing traditional manual road testing methods. This concept overcomes the limitations of existing technologies that rely on manual observation, establishing a closed-loop system of "trajectory acquisition - behavior analysis - countdown evaluation - algorithm iteration" through a data-driven approach. While reducing costs, expanding coverage, and improving timeliness, it ensures the objectivity and accuracy of evaluation results, providing strong data support for the refined management and optimization of traffic signal control.

[0018] Furthermore, by using the traffic light stop line as a specific anchor point for road network information, the abstract preset area is concretized into a spatial influence domain defined by the stop line, achieving precise spatial binding between vehicle trajectory point data and traffic light control sections. Then, through spatial correlation, associated trajectory points within this influence domain are filtered out, and target vehicles exhibiting waiting-at-the-light behavior are identified based on their spatial distribution characteristics, effectively eliminating interference from passing vehicles. Finally, by extracting the target vehicle's start time as a stopping behavior feature, and utilizing the high temporal correlation between this time and the traffic light's red-to-green transition time, an objective and quantifiable truth benchmark is provided for subsequent countdown accuracy evaluation.

[0019] Furthermore, by quantitatively calculating and filtering the relative distance between the stopping point and the traffic light stop line, a spatial constraint mechanism for vehicle waiting positions was established. This limits the evaluation to a subset of vehicles that meet preset distance conditions (such as being close to the stop line), effectively filtering out interfering vehicles that are far from the stop line due to excessively long queues or abnormal parking. This reduces the evaluation uncertainty caused by large differences in vehicle start-up delays, improves the representativeness and timing accuracy of the start-up moment as a proxy truth value for traffic light state changes, and ultimately ensures the accuracy and stability of countdown error calculation.

[0020] Furthermore, the vehicle's start-up time is accurately identified by a speed state transition criterion (from less than or equal to a preset speed threshold to greater than the threshold), avoiding subjective interference from manual visual observation and ensuring the consistency and repeatability of the extracted start-stop time.

[0021] Furthermore, by limiting the time interval between adjacent trajectory points in the vehicle trajectory data to less than a preset time interval threshold, sufficient sampling point density is ensured to accurately capture the critical moment of state transition during the transient process of critical transitions in vehicle motion state (from driving to stationary or from stationary to driving). This avoids missing brief parking states or identification deviations at the start time due to excessively low sampling frequency, thereby ensuring the temporal resolution and accuracy of stationary behavior feature extraction and providing a reliable data foundation for determining the timing of subsequent traffic light state changes and evaluating countdown accuracy.

[0022] Furthermore, by quantifying the time deviation between the actual state change time (determined based on the inversion of vehicle dwell behavior characteristics) and the theoretical state change time (determined based on the output of the countdown prediction model), the accuracy assessment of the traffic light countdown is transformed into a measurable and comparable numerical indicator. This deviation value objectively reflects the degree of temporal deviation between the countdown prediction model and the actual operating state of the traffic light.

[0023] Finally, by collecting time deviation samples over multiple signal cycles and calculating their statistical characteristics (such as mean absolute error, root mean square error, standard deviation, or pass rate), the instantaneous error of a single cycle is transformed into a comprehensive accuracy index with statistical significance. This effectively eliminates random error interference caused by individual driver reaction differences, vehicle dynamic performance dispersion, or instantaneous detection noise, thus improving the stability and reliability of the evaluation results. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0025] Figure 1 Flowchart of the traffic light countdown verification method provided in this application Figure 1 ;

[0026] Figure 2 Flowchart of the traffic light countdown verification method provided in this application Figure 2 ;

[0027] Figure 3 A schematic diagram illustrating the principle of determining vehicle start / stop times provided in this application;

[0028] Figure 4 A schematic diagram of the data processing flow for the traffic light countdown verification method provided in this application;

[0029] Figure 5 A schematic diagram of the traffic light countdown verification device provided in this application;

[0030] Figure 6 A schematic diagram of the signal light countdown verification device provided in this application.

[0031] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0032] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0033] Traffic light countdown information services can provide road users with real-time status and remaining time predictions of traffic lights ahead, assisting drivers in adjusting speed and making start / stop decisions. This has significant technical value in improving traffic efficiency and reducing intersection delays.

[0034] However, existing technologies for evaluating the accuracy of countdown prediction models primarily rely on manual road testing: dispatching technicians to drive test vehicles to target intersections to collect data on-site. While this method can obtain error data with second-level accuracy, it suffers from the following technical limitations:

[0035] First, the implementation cost is high. It requires organizing professional teams to conduct multiple rounds of repeated tests at different times and intersections. The complete evaluation cycle for a single intersection often takes several weeks, requiring huge investment of human and material resources, making it difficult to support the routine evaluation needs of a large-scale road network.

[0036] Second, spatial coverage is limited. Due to the limitations of the scale of test vehicles and scheduling capabilities, it is impossible to simultaneously cover tens of thousands of signalized intersections in a city, resulting in significant spatial sparsity in the evaluation samples, making it difficult to fully reflect the overall performance distribution of the algorithm.

[0037] Third, the timeliness is lagging. The data collection, manual processing, and analysis output cycle is long, making it impossible to achieve real-time online monitoring and dynamic feedback of the countdown algorithm's performance.

[0038] Furthermore, manual observation is susceptible to subjective judgment, making it difficult to guarantee the consistency and repeatability of assessment results. In summary, existing technologies lack automated and large-scale assessment methods based on real traffic flow data, making it difficult to meet the technical requirements of intelligent transportation systems for traffic light countdown service quality control.

[0039] The traffic light countdown verification method provided in this application achieves precise matching between trajectories and road networks by collecting high-frequency vehicle trajectory point data, extracting dwell behavior features, and using these features to infer the timing of traffic light state changes, thus replacing traditional manual road testing methods. This concept overcomes the limitations of existing technologies that rely on manual observation, establishing a closed-loop system of "trajectory acquisition - behavior analysis - countdown evaluation - algorithm iteration" through a data-driven approach. While reducing costs, expanding coverage, and improving timeliness, it ensures the objectivity and accuracy of evaluation results, providing strong data support for the refined management and optimization of traffic signal control.

[0040] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0041] Figure 1 Flowchart of the traffic light countdown verification method provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0042] S101. Match the vehicle trajectory point data with the preset road network information to determine the vehicle's stopping behavior characteristics in the preset area.

[0043] In this step, a spatial correspondence between vehicle trajectory point data and road infrastructure is established, and vehicle dwelling behavior characteristics are extracted. Specifically, discrete vehicle trajectory point data is correlated and matched with preset road network information to determine the dwelling behavior characteristics of vehicles within a preset area defined by specific road facilities (such as traffic light stop lines). These characteristics are manifested as the vehicle's behavior pattern of changing from a driving state to a stationary state or from a stationary state to a driving state within that area.

[0044] S102. Based on the characteristics of the stationary behavior, determine the time when the traffic light status changes.

[0045] In this step, the established characteristics of vehicle dwelling behavior are used to indirectly identify the traffic light status. Based on the characteristics of vehicle dwelling behavior within a preset area (especially the start time), the physical time when the traffic light actually changes state (i.e., the critical time point when the red light changes to the green light) is deduced.

[0046] S103. Compare the time of change of traffic light status with the preset countdown data to obtain the traffic light countdown accuracy evaluation result.

[0047] In this step, the measured time data obtained in S102 is quantitatively compared with the predicted data. Specifically, the actual time of change of the traffic light state determined based on vehicle behavior is compared with the theoretical time of change indicated by the preset countdown data, the degree of deviation between the two is calculated, and an accuracy assessment result characterizing the accuracy of the countdown is generated accordingly.

[0048] The traffic light countdown verification method provided in this application collects high-frequency vehicle trajectory point data to achieve precise matching between trajectories and road networks, extracts dwell behavior features, and uses these features to infer the timing of traffic light state changes, thereby replacing traditional manual road testing methods. This concept overcomes the limitations of existing technologies that rely on manual observation, establishing a closed-loop system of "trajectory acquisition - behavior analysis - countdown evaluation - algorithm iteration" through a data-driven approach. While reducing costs, expanding coverage, and improving timeliness, it ensures the objectivity and accuracy of evaluation results, providing strong data support for the refined management and optimization of traffic signal control.

[0049] Figure 2 Flowchart of the traffic light countdown verification method provided in this application Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, the traffic light countdown verification method is described in detail, which includes:

[0050] S201. When the preset road network information is a traffic light stop line, the preset area is a spatial influence domain set with the traffic light stop line as the reference. The vehicle trajectory point data is spatially associated with the spatial influence domain, and the associated trajectory points located within the spatial influence domain are filtered.

[0051] In this step, when the preset road network information is a traffic light stop line, the preset area is correspondingly determined as the spatial influence domain based on that traffic light stop line. Based on this, vehicle trajectory point data is spatially correlated with this spatial influence domain to filter out correlated trajectory points whose geographical locations are within the range of this spatial influence domain.

[0052] In one possible implementation, the time interval between adjacent trajectory points in the vehicle trajectory point data is less than a preset time interval threshold.

[0053] In this embodiment, a preset time interval threshold (e.g., 1 second) is set, and only trajectory point data with a time interval between adjacent trajectory points less than or equal to this threshold are selected as valid input. This requires that the trajectory point acquisition frequency be no less than 1Hz (at least one positioning point per second). By limiting the acquisition frequency of vehicle trajectory point data, sufficient sampling point density is ensured to accurately capture the critical moment of state transition during transient processes where the vehicle speed undergoes a critical change (from moving to stationary or from stationary to moving).

[0054] Specifically, trajectory point data uploaded by vehicles can be received in real time through data acquisition interfaces deployed on mobile terminals (such as smartphone applications) or in-vehicle terminals (vehicle-mounted SDK). The trajectory point data includes, but is not limited to, longitude, latitude, timestamp, and instantaneous speed fields.

[0055] S202. Based on the spatial distribution characteristics of associated trajectory points, identify target vehicles that exhibit dwelling behavior within the spatial influence domain.

[0056] In this step, based on the associated trajectory points selected in S201, specific vehicles exhibiting stationary behavior (i.e., traffic light waiting behavior) are identified by analyzing their distribution patterns within the spatial influence domain.

[0057] In one possible implementation, based on the spatial distribution characteristics of associated trajectory points, target vehicles exhibiting stationary behavior within the spatial influence domain are identified, which may specifically include the following steps:

[0058] Based on the spatial characteristics of the associated trajectory points, identify vehicles exhibiting stationary behavior and determine their stationary locations;

[0059] Calculate the relative distance between the stopping point and the stop line of the traffic light;

[0060] When the relative distance meets the preset distance condition, the vehicle exhibiting the behavior of stopping is identified as the target vehicle.

[0061] In this embodiment, to eliminate the time delay uncertainty introduced by the excessive distance between the vehicle's stopping position and the traffic light stop line, vehicles exhibiting stopping behavior can be filtered based on relative distance. Specifically, the relative distance between the stopping position and the traffic light stop line is determined. The geographical location information of the traffic light stop line can be obtained based on high-precision map data to ensure the accuracy of the spatial reference. Since the coordinate system of the original GPS trajectory points differs from the road network coordinate system, the spatial distance between them and the stop line cannot be directly calculated. Therefore, the vehicle trajectory points can first be projected onto the corresponding road network segment using a map matching algorithm to obtain the projected position points. Based on the projected position points, the stopping position points are determined, and then the longitudinal distance between the stopping position point and the traffic light stop line is calculated as the relative distance. The map matching algorithm can employ expert system models, Hidden Markov Models (HMMs), and deep learning methods based on neural networks, etc.

[0062] For example, a preset distance threshold (e.g., 10 meters) can be set to identify only vehicles whose relative distance is less than or equal to the preset distance threshold as target vehicles for the extraction of subsequent vehicle start times, while vehicles outside the range are excluded, so as to reduce the impact of time delay deviations caused by excessively long queues or abnormal parking positions on the evaluation results.

[0063] S203. Determine the start time of the target vehicle within the spatial influence domain to serve as a characteristic of its stationary behavior.

[0064] In this step, for the target vehicle identified in S202, key time parameters are extracted from its trajectory point data to quantitatively characterize its dwell behavior features.

[0065] In one possible implementation, determining the start time of the target vehicle within the spatial influence domain as a characteristic of its stationary behavior can specifically include the following steps:

[0066] Analyze the associated trajectory points of the target vehicle within the spatial influence domain, and identify the start time when the vehicle speed changes from less than or equal to a preset speed threshold to greater than the preset speed threshold, as a feature of stationary behavior.

[0067] Specifically, the sequence of associated trajectory points of the target vehicle within the spatial influence domain is analyzed to identify the critical transition moment when the vehicle's motion state changes from stationary to moving, i.e., the start moment (e.g., the time point when the vehicle's instantaneous speed changes from less than or equal to a preset speed threshold to greater than that threshold).

[0068] At signalized intersections, when the traffic light changes from red to green, the queue of vehicles will sequentially initiate their movement. Therefore, the timing of a target vehicle's initiation is highly correlated with the actual time of the traffic light's transition from red to green, and can serve as an important proxy variable for inferring the latter.

[0069] S204. Based on the characteristics of the stationary behavior, determine the time when the traffic light status changes.

[0070] In this step, the actual state transition time of the traffic light is deduced based on the dwell behavior features extracted in S203 (especially the start time of the target vehicle).

[0071] Specifically, based on the start-up time data of one or more target vehicles, statistical analysis methods (such as cluster analysis) are used to determine representative time points. These representative time points are defined as the actual moments when the traffic light changes from red to green.

[0072] S205. Compare the time of change of traffic light status with the preset countdown data to obtain the traffic light countdown accuracy evaluation result.

[0073] In one possible implementation, the timing of the traffic light state change is compared with preset countdown data to obtain a traffic light countdown accuracy assessment result, which may specifically include the following steps:

[0074] Calculate the time deviation between the moment when the traffic light changes state and the theoretical moment when the countdown prediction model outputs the state change time;

[0075] Based on the time deviation, an accuracy assessment result for the traffic light countdown is generated.

[0076] In this embodiment, the actual state change time obtained from the inversion of vehicle dwell behavior characteristics (as the true value) is compared with the theoretical state change time calculated by a preset countdown prediction model. The difference between the two is calculated to obtain the time deviation, which quantifies the degree of deviation between the countdown prediction and the actual traffic light switching. Based on this time deviation, a final accuracy evaluation result is generated according to preset evaluation rules.

[0077] In one possible implementation, generating a traffic light countdown accuracy assessment result based on the time deviation may specifically include the following steps:

[0078] Obtain the time deviation within multiple signal periods;

[0079] Calculate the statistical characteristic values ​​of time deviation within multiple signal periods;

[0080] Based on statistical feature values, the accuracy assessment results of the traffic light countdown are generated.

[0081] In this embodiment, the time deviation extracted within a single signal cycle may be affected by factors such as individual driver reaction differences, vehicle dynamic performance dispersion, or instantaneous detection noise, resulting in random errors. Therefore, by continuously collecting or periodically sampling data, time deviation data for multiple signal cycles (e.g., covering different traffic conditions such as morning peak, off-peak, and evening peak, or multiple consecutive signal timing cycles) are obtained to construct a statistically significant sample set, thereby eliminating random interference and improving the reliability of the evaluation conclusions.

[0082] Reference Figure 3 The diagram shown illustrates the principle of determining vehicle stop and start times provided in this application. As shown, the red cross markers represent vehicle trajectory points during red light periods, the green cross markers represent vehicle trajectory points during green light periods, t0 represents the start time of waiting at the light, t1 represents the start time of starting, and L represents the longitudinal distance between the vehicle's stopping position and the traffic light stop line.

[0083] Based on the above trajectory point data, it can be observed that when the traffic light changes from red to green, the vehicle's motion state changes from stationary to moving. The timing of this change (starting moment) is highly correlated with the timing of the traffic light change.

[0084] To reduce the time delay uncertainty caused by the difference in the depth of the vehicle queue position, this embodiment adopts a spatial constraint screening strategy: only vehicles whose longitudinal distance L between them and the traffic light stop line meets the preset distance condition (e.g., L≤10 meters) are selected as evaluation objects, and interference samples that cause large start delays due to excessive parking positions are excluded.

[0085] Based on the target vehicles selected above, their start time (denoted as T1) is obtained and compared with the preset theoretical state change time of the red light countdown (denoted as T2). The time deviation between the two is calculated as the countdown error E. For example, the error calculation model can be expressed as:

[0086] E = |T1 - T2|

[0087] Where E represents the accuracy assessment result of the traffic light countdown, T1 represents the measured state change time determined based on the actual stopping and starting behavior of the vehicle, and T2 represents the theoretical state change time indicated by the preset countdown data. The error value is obtained through the above absolute value calculation.

[0088] Reference Figure 4The diagram shows the data processing flow of the traffic light countdown verification method provided in this application. The original vehicle trajectory point data collected by mobile terminals or vehicle-mounted terminals typically includes information such as longitude, latitude, timestamp, and instantaneous speed, serving as the basis for subsequent analysis. The vehicle trajectory points are matched with preset road network information, and a projection algorithm maps the original GPS trajectory points to the corresponding road network segments to obtain projected position points. Based on the projected position points, stopping positions are determined, and the relative distance between these stopping positions and the traffic light stop line is calculated. Only vehicles meeting preset distance conditions are selected as target vehicles. This technical step filters out vehicles that are too far from the stop line due to excessively long queues, reducing evaluation errors caused by vehicle start-up delays. For the target vehicles filtered by distance, the temporal characteristics of their trajectory points within the spatial influence domain are analyzed to identify the critical moment when the vehicle's motion state changes from stationary to moving, i.e., the start-up moment. The extracted start-up moment is compared with the theoretical state change moment indicated by the preset countdown data to calculate the time deviation, thereby estimating or generating a traffic light countdown accuracy evaluation result. This application abandons the traditional manual on-site road testing method, which does not require dispatching test vehicles and professional personnel for on-site data collection. Instead, it automatically identifies the characteristics of vehicle stopping behavior at the traffic light stop line based on large-scale vehicle trajectory point data, and extracts the starting moment of the vehicle from stationary to moving as the proxy truth value of the traffic light state change moment, thereby automatically evaluating the accuracy of the red light countdown obtained by big data mining.

[0089] The traffic light countdown verification method provided in this application collects high-frequency vehicle trajectory point data to achieve precise matching between trajectories and road networks, extracts dwell behavior features, and uses these features to infer the timing of traffic light state changes, thereby replacing traditional manual road testing methods. This concept overcomes the limitations of existing technologies that rely on manual observation, establishing a closed-loop system of "trajectory acquisition - behavior analysis - countdown evaluation - algorithm iteration" through a data-driven approach. While reducing costs, expanding coverage, and improving timeliness, it ensures the objectivity and accuracy of evaluation results, providing strong data support for the refined management and optimization of traffic signal control.

[0090] Because the embodiments of this application can realize the normalized and automated evaluation of the countdown quality of traffic lights, the accuracy evaluation data can be generated and fed back to the algorithm development end every day, thereby supporting technicians to quickly locate fault cases and perform root cause analysis, effectively shortening the algorithm optimization iteration cycle and improving the model update efficiency.

[0091] Figure 5 The schematic diagram of the signal light countdown verification device provided in this application is as follows: Figure 5 As shown, the traffic light countdown verification device 50 provided in this embodiment includes:

[0092] The first determining module 501 is used to match vehicle trajectory point data with preset road network information to determine the vehicle's stopping behavior characteristics in the preset area.

[0093] The second determining module 502 is used to determine the time of change of traffic light status based on the characteristics of the dwelling behavior;

[0094] The comparison module 503 is used to compare the time of change of traffic light status with the preset countdown data to obtain the accuracy evaluation result of the traffic light countdown.

[0095] In one possible implementation, when the preset road network information is a traffic light stop line, the preset area is a spatial influence domain set based on the traffic light stop line, and the first determining module is specifically used for:

[0096] The vehicle trajectory point data is spatially correlated with the spatial influence domain, and the correlated trajectory points located within the spatial influence domain are filtered.

[0097] Based on the spatial distribution characteristics of associated trajectory points, target vehicles exhibiting dwelling behavior within the spatial influence domain are identified.

[0098] Determine the start time of the target vehicle within the spatial influence domain to serve as a characteristic of its stationary behavior.

[0099] In one possible implementation, the first determining module is specifically used for:

[0100] Based on the spatial characteristics of the associated trajectory points, identify vehicles exhibiting stationary behavior and determine their stationary locations;

[0101] Calculate the relative distance between the stopping point and the stop line of the traffic light;

[0102] When the relative distance meets the preset distance condition, the vehicle exhibiting the behavior of stopping is identified as the target vehicle.

[0103] In one possible implementation, the first determining module is specifically used for:

[0104] Analyze the associated trajectory points of the target vehicle within the spatial influence domain, and identify the start time when the vehicle speed changes from less than or equal to a preset speed threshold to greater than the preset speed threshold, as a feature of stationary behavior.

[0105] In one possible implementation, the time interval between adjacent trajectory points in the vehicle trajectory point data is less than a preset time interval threshold.

[0106] In one possible implementation, the comparison module is specifically used for:

[0107] Calculate the time deviation between the moment when the traffic light changes state and the theoretical moment when the countdown prediction model outputs the state change time;

[0108] Based on the time deviation, an accuracy assessment result for the traffic light countdown is generated.

[0109] In one possible implementation, the comparison module is specifically used for:

[0110] Obtain the time deviation within multiple signal periods;

[0111] Calculate the statistical characteristic values ​​of time deviation within multiple signal periods;

[0112] Based on statistical feature values, the accuracy assessment results of the traffic light countdown are generated.

[0113] The traffic light countdown verification device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0114] Figure 6 A schematic diagram of the traffic light countdown verification device provided in this application. Figure 6 As shown, the traffic light countdown verification device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the device 60 also includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus.

[0115] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.

[0116] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0117] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0118] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0119] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0120] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0121] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0122] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0123] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0124] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0125] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0126] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0127] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0128] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0129] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for verifying a countdown of a signal light, characterized by, include: The vehicle trajectory point data is matched with the preset road network information to determine the vehicle's dwell behavior characteristics in the preset area; Based on the aforementioned characteristics of the stopping behavior, the timing of the traffic light state change is determined; The timing of the traffic light state change is compared with the preset countdown data to obtain the traffic light countdown accuracy evaluation result.

2. The method according to claim 1, characterized in that, When the preset road network information is a traffic light stop line, the preset area is a spatial influence domain set based on the traffic light stop line. Matching vehicle trajectory point data with the preset road network information to determine the vehicle's stopping behavior characteristics within the preset area includes: The vehicle trajectory point data is spatially correlated with the spatial influence domain, and the associated trajectory points located within the spatial influence domain are filtered. Based on the spatial distribution characteristics of the associated trajectory points, target vehicles exhibiting dwelling behavior within the spatial influence domain are identified. The start time of the target vehicle within the spatial influence domain is determined as a characteristic of the stationary behavior.

3. The method according to claim 2, characterized in that, The identification of target vehicles exhibiting dwelling behavior within the spatial influence domain based on the spatial distribution characteristics of the associated trajectory points includes: Based on the spatial characteristics of the associated trajectory points, identify vehicles exhibiting stopping behavior and determine their stopping locations; Calculate the relative distance between the stopping point and the stop line of the traffic light; When the relative distance meets the preset distance condition, the vehicle exhibiting the stopping behavior is identified as the target vehicle.

4. The method according to claim 2, characterized in that, Determining the start time of the target vehicle within the spatial influence domain as a characteristic of the stationary behavior includes: Analyze the associated trajectory points of the target vehicle within the spatial influence domain, and identify the start time when the vehicle speed changes from less than or equal to a preset speed threshold to greater than the preset speed threshold, as a feature of the stationary behavior.

5. The method according to any one of claims 1-4, characterized in that, The time interval between adjacent trajectory points in the vehicle trajectory point data is less than a preset time interval threshold.

6. The method according to any one of claims 1-4, characterized in that, The step of comparing the time of the traffic light state change with preset countdown data to obtain the traffic light countdown accuracy evaluation result includes: Calculate the time deviation between the moment when the traffic light changes state and the moment when the countdown prediction model outputs the theoretical moment when the state changes; Based on the time deviation, an accuracy assessment result for the traffic light countdown is generated.

7. The method according to claim 6, characterized in that, The process of generating the traffic light countdown accuracy assessment result based on the time deviation includes: Obtain the time deviation within multiple signal periods; Calculate the statistical characteristic values ​​of the time deviation within the multiple signal periods; Based on the statistical feature values, the accuracy evaluation result of the traffic light countdown is generated.

8. A signal light countdown verification device, characterized in that, include: The first determining module is used to match vehicle trajectory point data with preset road network information to determine the vehicle's stopping behavior characteristics in the preset area; The second determining module is used to determine the time of change of the traffic light state based on the dwelling behavior characteristics; The comparison module is used to compare the time of change of the traffic light status with the preset countdown data to obtain the accuracy evaluation result of the traffic light countdown.

9. A signal light countdown verification device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium or computer program product, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7; And / or, The computer program product includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images