Vehicle speed measurement method and device, storage medium and electronic device

Abstract

The application discloses a vehicle speed measurement method and device, a storage medium and an electronic device. The method comprises the following steps: acquiring current image data and current radar data of a target vehicle at a target position, wherein the target position represents a position at which the target vehicle passes a vehicle matching line, the current image data corresponds to an image timestamp, and the current radar data corresponds to a radar timestamp; determining a current interval duration according to the image timestamp of the current image data and the radar timestamp of the current radar data; and determining a moving speed of the target vehicle according to the current radar data in the case where the current interval duration meets a target duration condition. The application solves the technical problem that the vehicle speed measurement accuracy is low due to the existence of false radar data corresponding to a radar target.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation, and more specifically, to a vehicle speed measurement method and device, a storage medium, and an electronic device. Background Technology

[0002] In intelligent transportation systems, the integrated application of radar and video sensors has become a key technology for vehicle monitoring and speed measurement. However, radar sensors have limitations in complex scenarios, especially when faced with vehicles crossing lane lines or multiple target interference, which can easily generate false radar targets. Specifically, when a vehicle crosses lane lines or a large vehicle causes radar beam scattering, the radar may incorrectly identify multiple targets, thus outputting inaccurate speed information, further leading to the technical problem of low vehicle speed measurement accuracy.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a vehicle speed measurement method and device, storage medium and electronic device to at least solve the technical problem of low vehicle speed measurement accuracy due to the existence of false radar target radar data.

[0005] According to one aspect of the embodiments of this application, a vehicle speed measurement method is provided, comprising: acquiring current image data and current radar data corresponding to a target vehicle at a target location, wherein the target location indicates the position where the target vehicle has passed a vehicle matching line, the current image data corresponds to an image timestamp, the current radar data corresponds to a radar timestamp, the target vehicle indicates a vehicle whose moving speed is to be determined, the image timestamp of the current image data is used to indicate the time when an image including the target vehicle is acquired, and the radar timestamp of the current radar data is used to indicate the time when a reflected signal emitted by the target vehicle is detected; determining a current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data; and determining the moving speed of the target vehicle based on the current radar data when the current interval duration meets a target duration condition, wherein the target duration condition is determined by the image timestamp of historical image data and the image timestamp of historical radar data corresponding to historical vehicles that have passed through the target road segment at historical times.

[0006] According to another aspect of the embodiments of this application, a vehicle speed measuring device is also provided, comprising: an acquisition module, configured to acquire current image data and current radar data corresponding to a target vehicle at a target location, wherein the target location indicates the position where the target vehicle has passed a vehicle matching line, the current radar data corresponds to a radar timestamp, the target vehicle indicates a vehicle whose moving speed is to be determined, the image timestamp of the current image data is used to indicate the time when an image including the target vehicle is acquired, and the radar timestamp of the current radar data is used to indicate the time when a reflected signal emitted by the target vehicle is detected; a duration determination module, configured to determine a current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data; and a speed determination module, configured to determine the moving speed of the target vehicle based on the current radar data when the current interval duration meets a target duration condition, wherein the target duration condition is determined by the image timestamp of historical image data and the image timestamp of historical radar data corresponding to historical vehicles that have passed through the target road segment at historical times.

[0007] In an exemplary embodiment, the apparatus is configured to determine the moving speed of the target vehicle based on the current radar data when the current interval duration meets the target duration condition by: acquiring a trusted database, wherein the trusted database stores historical interval durations corresponding to at least one historical vehicle, the historical interval durations being determined by the image timestamps of the corresponding historical image data and the image timestamps of the historical radar data; determining a target duration interval based on the trusted database, wherein the target duration interval is determined by the maximum and minimum historical interval duration values ​​in the trusted database; determining that the interval duration meets the target duration condition when the current interval duration is within the target duration interval; and determining that the interval duration does not meet the target duration condition when the current interval duration is not within the target duration interval.

[0008] In an exemplary embodiment, before the apparatus is configured to acquire a trusted database in the following manner, it further includes: acquiring the historical interval duration corresponding to each of the historical vehicles; performing a clustering operation on the historical interval duration to determine a target cluster; and storing the historical interval duration in the target cluster to the trusted database.

[0009] In an exemplary embodiment, the apparatus is configured to perform a clustering operation on the historical interval durations in the following manner to determine a target cluster: determining a standard deviation parameter and a mean parameter of the historical interval durations; determining the historical interval durations with outlier values ​​and the historical interval durations with normal values ​​based on the standard deviation parameter and the mean parameter; clearing the historical interval durations with outlier values, and performing the clustering operation on the historical interval durations with normal values ​​to determine the target cluster.

[0010] In one exemplary embodiment, the apparatus is configured to determine a current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data in the following manner: determining a first interval duration based on the image timestamp of the current image data and the radar timestamp of the first radar data, wherein the current radar data includes the first radar data; and determining a second interval duration based on the image timestamp of the current image data and the radar timestamp of the second radar data, wherein the current radar data includes the second radar data, and the radar timestamp of the second radar data is different from the radar timestamp of the first radar data.

[0011] In an exemplary embodiment, the apparatus is further configured to: determine the moving speed based on the first radar data when the first interval duration satisfies the target duration condition and the second interval duration does not satisfy the target duration condition; determine the moving speed based on the second radar data when the first interval duration does not satisfy the target duration condition and the second interval duration satisfies the target duration condition; and obtain the center interval duration of the trusted database when both the first interval duration and the second interval duration satisfy the target duration condition, and determine the moving speed based on the center interval duration, the first radar data, and the second radar data.

[0012] In an exemplary embodiment, the apparatus is configured to obtain the center interval duration of the trusted database and determine the moving speed of the target vehicle based on the center data point, the first radar data, and the second radar data, provided that both the first interval duration and the second interval duration satisfy the target duration condition, by: performing a sorting operation on each of the historical interval durations stored in the trusted database to determine the center interval duration; obtaining a first distance between the first interval duration and the center interval duration, and obtaining a second distance between the second interval duration and the center interval duration; determining the moving speed based on the first radar data when the first distance is less than the second distance; and determining the moving speed based on the second radar data when the first distance is greater than the second distance.

[0013] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the above-described vehicle speed measurement method when it is run.

[0014] According to another aspect of the embodiments of this application, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the vehicle speed measurement method described above.

[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-described vehicle speed measurement method through the computer program.

[0016] In this embodiment, the current image data and radar data corresponding to the target vehicle's location are acquired, and the current interval duration is determined accordingly. If the current interval duration meets the target duration condition, the current radar data is determined to be valid information, and the true moving speed of the target vehicle is determined based on this. This achieves the goal of accurately matching radar and video data, thereby improving the technical effect of vehicle speed measurement accuracy and solving the technical problem of low vehicle speed measurement accuracy caused by the existence of false radar target radar data. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a schematic diagram of the application environment of an optional vehicle speed measurement method according to an embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating an optional vehicle speed measurement method according to an embodiment of this application.

[0020] Figure 3 This is a schematic diagram of an optional main process for vehicle speed measurement according to an embodiment of this application;

[0021] Figure 4 This is a schematic diagram of an optional radar video matching and fusion sub-sub according to an embodiment of this application;

[0022] Figure 5This is an optional schematic diagram of an incomplete trusted database matching according to an embodiment of this application;

[0023] Figure 6 This is an optional schematic diagram of a completed trusted database matching according to an embodiment of this application;

[0024] Figure 7 This is a schematic diagram of an optional vehicle speed measuring device according to an embodiment of this application;

[0025] Figure 8 This is a schematic diagram of the structure of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] The present application will be described below with reference to embodiments:

[0029] According to one aspect of the embodiments of this application, a vehicle speed measurement method is provided.

[0030] Optionally, in this embodiment, the above-mentioned vehicle speed measurement method can be applied to the field of intelligent traffic management systems, such as highways, urban main roads, and other scenarios that require multi-lane, high-precision vehicle speed monitoring.

[0031] Specifically, such as Figure 1As shown, this method can be applied in a hardware environment consisting of a server 101 and a terminal device 103. The server 101 is responsible for processing and analyzing the large amount of real-time data collected from the terminal device 103 (such as radar sensors or video surveillance equipment). By implementing the speed measurement method of this application, the server can accurately match radar speed measurement data with video data, eliminate false target information, and accurately determine vehicle speed. The terminal device 103 is responsible for collecting image and radar data, providing raw data support to the server, and ensuring the real-time nature and comprehensiveness of the data.

[0032] Furthermore, combined Figure 1 As shown, the above-mentioned vehicle speed measurement method can be implemented by the terminal device 103 or the server 101 respectively, or by the terminal device 103 and the server 101 together. This application embodiment does not limit this.

[0033] It should be noted that the aforementioned server 101 is connected to the terminal device 103 via a network and can be used to provide services to the terminal device or the application 107 installed on the terminal device to implement the aforementioned vehicle speed measurement method. A database 105 can also be set up on or independently of the server 101 to provide data storage services for implementing the aforementioned vehicle speed measurement method. Specifically:

[0034] The aforementioned server 101 and terminal device 103 can be any node in a distributed system, such as a blockchain system. This blockchain system can be formed by connecting multiple nodes through network communication. The nodes can form any type of network, and any type of computing device, such as any electronic device, can become a node in this distributed system by joining the network formed between the nodes.

[0035] The aforementioned server 101 can be a single server, a server cluster consisting of multiple servers, or a cloud server.

[0036] The aforementioned networks may include, but are not limited to, wired networks and wireless networks. The wired networks include local area networks (LANs), metropolitan area networks (MANs), and wide area networks (WANs). The wireless networks include Bluetooth, Wi-Fi, and other networks that enable wireless communication.

[0037] The aforementioned terminal device 103 may be a terminal configured with an application, and may include, but is not limited to, at least one of the following: vehicle terminal, mobile phone (such as Android phone, iOS phone, etc.), laptop computer, tablet computer, handheld computer, MID (Mobile Internet Devices), PAD, desktop computer, smart TV, smart voice interaction device, smart home appliance, aircraft, virtual reality (VR) terminal, augmented reality (AR) terminal, mixed reality (MR) terminal, and other computer devices.

[0038] Alternatively, as an optional implementation, such as Figure 2 As shown, the above vehicle speed measurement methods include:

[0039] S202, acquire the current image data and current radar data corresponding to the target vehicle at the target position. The target position indicates the position where the target vehicle has passed the vehicle matching line. The current image data has an image timestamp, and the current radar data has a radar timestamp. The target vehicle indicates the vehicle whose moving speed is to be determined. The image timestamp of the current image data is used to indicate the time when the image including the target vehicle was acquired, and the radar timestamp of the current radar data is used to indicate the time when the reflected signal emitted by the target vehicle was detected.

[0040] Specifically, the acquisition of the current image data and current radar data of the target vehicle at the target location refers to the system collecting real-time information of the vehicle as it passes through the preset matching line, including but not limited to the capture of images and radar signals.

[0041] Optionally, in the embodiments of this application, the aforementioned target location specifically refers to the specific geographical coordinates reached by the vehicle within the monitoring area and set as the speed matching benchmark, which in this case is the position where the vehicle crosses the vehicle matching line.

[0042] Optionally, in this embodiment of the application, the aforementioned current image data can be generated in real time by the video acquisition module, covering images of vehicles passing through the target location, and the image timestamp accurately records the time when the image data was generated.

[0043] Optionally, in this embodiment of the application, the aforementioned current radar data is related information of the target vehicle's reflected signal detected by the radar sensor, and the radar timestamp identifies the precise time point of radar signal detection.

[0044] Optionally, in the embodiments of this application, the target vehicle refers to the vehicle that the system is monitoring and attempting to determine its speed, which can be various motor vehicles, including cars, trucks, buses, etc.

[0045] Understandably, one current image data can correspond to multiple current radar data, and different current radar data correspond to different current radar targets, which can be real target vehicles or false radar targets.

[0046] It should be noted that the type, size, speed, and specific manner in which the target vehicle passes the matching line (such as driving in a straight line or driving over the line) can vary. Furthermore, parameters such as the specific location of the matching line, the acquisition frequency of image and radar data, and the accuracy of the timestamps can also be flexibly adjusted according to actual monitoring needs; this application does not impose any limitations on these aspects.

[0047] S204, determine the current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data;

[0048] Optionally, in the embodiments of this application, the image timestamp of the current image data mentioned above refers to the precise time identifier added by the system to the video stream whenever an image frame containing the target vehicle is captured. This time identifier reflects the instantaneous time when the image data is generated, including but not limited to millisecond-level or higher precision timestamp records.

[0049] Optionally, in the embodiments of this application, the radar timestamp of the current radar data refers to the precise time point recorded synchronously by the system when the radar sensor detects the reflected signal of the target vehicle. Similarly, this timestamp can also achieve millisecond-level or higher time accuracy, ensuring accurate time positioning of radar detection events.

[0050] It should be noted that the calculation of the current interval duration involves the time difference between image time and radar time. This time difference needs to be calculated precisely to assess the correlation between image data and radar data. Under different environmental conditions, such as network transmission delay, system clock synchronization error, and data processing time, the specific value of the current interval duration may vary, and this application does not limit it.

[0051] S206, if the current interval duration meets the target duration condition, determine the moving speed of the target vehicle based on the current radar data. The target duration condition is determined by the image timestamp of the historical image data corresponding to the historical vehicles that passed through the target road segment at historical times and the image timestamp of the historical radar data.

[0052] Optionally, in the embodiments of this application, the aforementioned target duration condition refers to a time difference threshold range established by the system based on historical data. It is derived from the time difference statistics of historical image data and historical radar data corresponding to vehicles that have previously passed through the same road segment. The purpose is to identify whether the current interval duration conforms to a typical radar and video data synchronization mode, including but not limited to the time difference distribution characteristics determined by statistical methods such as standard deviation and average value.

[0053] It should be noted that the speed of the target vehicle can be calculated in various ways, such as by direct analysis of radar data, or by combining the target size change and field of view in image data, or by comprehensive analysis of radar and video data. This application does not limit the calculation in this way.

[0054] In an exemplary embodiment, considering that microwave radar, widely used in intelligent transportation systems for speeding penalties, cannot provide x / y position coordinates, and that the video target fusion process relies on a simple target association strategy, it cannot effectively handle interference from false targets such as radar splitting. On the one hand, when a vehicle crosses the line and occupies multiple lanes, the radar may simultaneously receive reflected signals from different lanes, misjudging them as multiple vehicles and thus outputting speed data in multiple lanes, causing matching confusion. On the other hand, large vehicles, due to their length, may have radar beams simultaneously illuminating the wheels, chassis, and cargo box, generating multiple reflection points and forming false targets, further exacerbating the difficulty of data association. These problems result in low matching accuracy in existing systems, frequently leading to false and missed shots, affecting traffic enforcement efficiency and system reliability. Therefore, the vehicle speed measurement method described above can accurately eliminate false radar targets and improve the accuracy of radar video fusion matching. The main process of vehicle speed measurement is as follows: Figure 3 As shown, including but not limited to:

[0055] System initialization includes platform initialization and algorithm creation: input, target detection, target tracking, license plate detection and recognition, fusion matching, alarm capture, result output, and frame handle creation; the frame handle is responsible for scheduling the above operators, passing the image of each frame and the results of the dependent preceding operators to each operator, and distributing operator configurations, such as lane marking configuration for the fusion matching operator and rule configuration parameters for alarm capture.

[0056] The radar sensor acquires the radar data and trigger timestamp of each lane (the radar timestamp mentioned above), and the video sensor collects image data in the scene frame by frame. The data from the two sensors are sent to the framework, which schedules them to various operators for analysis and processing. For example, the image data will first go through target detection, target tracking, license plate detection and recognition, and then be sent to the fusion matching operator along with the radar data. After that, it will go through the alarm capture and result operators to obtain the result output.

[0057] Specifically, Figure 4 To facilitate the processing flow of the fusion matching operator, the fusion matching operator will obtain each frame of image data, image timestamp, video target data (i.e., data that marks the location of the target vehicle), radar speed triggered by each lane, and radar timestamp triggered by each radar. Then, it will perform fusion matching of radar video according to lane marking configuration. The matching method is divided into two stages: the stage where the trusted database matching is not completed and the stage where the trusted database matching is completed. The detailed process is as follows.

[0058] Before the trusted database is fully established, the sub-process for establishing the trusted database is as follows: Figure 5 As shown:

[0059] The process iterates through all vehicles in the image data (the target vehicle is any one of them), calculates the vehicle's current lane, and determines whether it has crossed the matching line. Vehicles that have crossed the matching line but have not been matched with radar will enter the fusion matching process. The minimum time difference method is used for fusion matching. Then, the matching results of isolated cars that have not crossed the line (determined by license plate) are stored in a trusted database. After obtaining a certain amount of trusted data, outliers are first removed using the 3σ standard deviation method. Then, the K-means algorithm is used to obtain the centroid, segment range, and data volume of each segment, thus completing the establishment of the trusted database.

[0060] After the trusted database is established, the trusted data matching process will begin, with sub-processes as follows: Figure 6 As shown:

[0061] Iterate through all vehicles in the image data, calculate the current lane, and determine whether the vehicle has crossed the matching line. Vehicles that have crossed the matching line but have not been matched with radar will enter the fusion matching process. Calculate the radar video trigger time difference, and use the 3σ standard deviation method based on reliable data to determine whether they are outliers.

[0062] If the value is an anomaly, it is not radar data for that vehicle and can be identified as false radar target discard data.

[0063] If the value is not an outlier and is within the segment range, the fusion match is successful, and the data is updated in the trusted database.

[0064] If it is not an outlier, but deviates from the normal segmentation range, then the subsequent received radar target is marked and the judgment is delayed, and the result closest to the centroid is taken as the final matching result.

[0065] The final alarm capture operator will determine whether the successfully matched target exceeds the speed limit based on the speed limit rules, thereby triggering an alarm. Finally, the result operator will output the alarm result.

[0066] This application's embodiments acquire current image data and current radar data corresponding to the target vehicle's location, and determine the current interval duration accordingly. If the current interval duration meets the target duration condition, the current radar data is determined to be valid information, thereby determining the target vehicle's true speed. This achieves the goal of accurately matching radar and video data, thus improving the accuracy of vehicle speed measurement and solving the technical problem of low vehicle speed measurement accuracy due to the existence of false radar target-corresponding radar data.

[0067] As an optional approach, determining the moving speed of the target vehicle based on the current radar data when the current interval duration meets the target duration condition includes: acquiring a trusted database, wherein the trusted database stores at least one historical interval duration corresponding to the historical vehicle, the historical interval duration being determined by the image timestamp of the corresponding historical image data and the image timestamp of the historical radar data; determining a target duration interval based on the trusted database, wherein the target duration interval is determined by the maximum and minimum historical interval duration values ​​in the trusted database; determining that the interval duration meets the target duration condition when the current interval duration is within the target duration interval; and determining that the interval duration does not meet the target duration condition when the current interval duration is not within the target duration interval.

[0068] Optionally, in this application embodiment, the aforementioned trusted database refers to a storage system used to save a dataset of historical interval durations when vehicles pass through a target location, including but not limited to time difference information of various types of vehicles such as cars, trucks, and motorcycles passing through monitoring points under different conditions.

[0069] Optionally, in the embodiments of this application, the aforementioned historical interval duration refers to the time difference calculated from the image timestamp of the image data and the radar timestamp of the radar data when a vehicle passed through a specific monitoring point in the past, covering various vehicle models and driving conditions.

[0070] Optionally, in this embodiment, the target duration interval is defined by the maximum and minimum values ​​of historical interval durations statistically analyzed in a trusted database. This is used to define a reasonable and expected interval duration threshold to ensure that the matching of real-time data falls within the normal time window range and to eliminate interference from abnormal data.

[0071] It should be noted that the collection and analysis of historical data needs to take into account a variety of factors, such as road conditions, weather changes, and traffic flow, in order to establish a comprehensive and adaptable target time interval. This application does not impose any limitations on this.

[0072] For example, this application embodiment constructs a trusted database that stores historical interval durations. This database can determine a target duration interval based on the time difference between historical image data and historical radar data, in order to filter and verify the current interval duration obtained in real time, ensuring that it is within a reasonable time range, thereby achieving accurate determination of the target vehicle's moving speed.

[0073] In one exemplary embodiment:

[0074] S1, the system acquires in real time the current image data and current radar data of the target vehicle. The two sets of data carry precise image timestamps and radar timestamps respectively, which are used for subsequent time interval calculations.

[0075] S2, calculate the current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data, and determine the target duration interval by referring to the pre-established trusted database.

[0076] S3. Check if the current interval is within the target time range. If the condition is met, the vehicle speed measurement data is considered valid and the target vehicle's speed can be determined accordingly; otherwise, it is considered abnormal or false data and is not accepted.

[0077] Through the embodiments of this application, a method combining dynamic time windows and historical data analysis is adopted to achieve accurate measurement of the target vehicle's speed, effectively eliminating false alarms caused by complex situations such as radar splitting and vehicles crossing the line, thereby improving the enforcement accuracy and system stability of the intelligent transportation system.

[0078] As an optional approach, before obtaining the trusted database, the method further includes: obtaining the historical interval duration corresponding to each of the aforementioned historical vehicles; performing a clustering operation on the historical interval duration to determine a target cluster; and storing the historical interval duration in the target cluster to the trusted database.

[0079] It should be noted that clustering is a data analysis technique used to classify historical time interval data into several clusters, each representing a type of similar time difference features. This application does not limit this; the clustering algorithm can be K-means, DBSCAN, or any other suitable algorithm. The selection of target clusters is based on the clustering results of the algorithm and expert experience, aiming to screen out a set of time differences that reflect real vehicle behavior for subsequent matching and verification with real-time data.

[0080] For example, embodiments of this application collect historical interval duration data, perform cluster analysis on it, select target clusters, and store the historical interval durations in a trusted database, providing a reliable benchmark for real-time data matching.

[0081] In one exemplary embodiment:

[0082] S1: The system continuously monitors and records historical image data and corresponding image timestamps of all historical vehicles passing through the vehicle matching line, as well as corresponding historical radar data and radar timestamps, for subsequent analysis.

[0083] S2, the software module performs clustering operations, dividing the historical interval duration data into multiple clusters. Each cluster represents a set of similar time difference characteristics, such as scenarios where cars pass quickly and large vehicles pass slowly.

[0084] S3. Select the target cluster, that is, those clusters that represent normal vehicle behavior, and store their historical interval data in a trusted database as a reference standard for real-time data matching.

[0085] Furthermore, when measuring the speed of the target vehicle subsequently, the vehicle type is first determined based on the current image data. Then, the current interval is checked to see if it falls within the target duration range, meaning that different types of vehicles correspond to different target duration ranges. Specifically:

[0086] When the system detects a target vehicle, say a sedan, the video intelligent analysis module determines it to be a small vehicle and identifies a target time interval for the sedan. If the current interval is 0.007 seconds, falling within the target time interval of 0.005 to 0.01 seconds, the system determines that the current interval meets the target time condition and calculates the sedan's speed based on the current radar data. Conversely, if the current interval is 0.04 seconds, significantly exceeding the normal range for a sedan, it indicates abnormal radar data, possibly a false radar target or a vehicle crossing the line. Therefore, this data will not be included in the speed measurement results; instead, the system will continue searching or waiting for the next data point with a more suitable time difference.

[0087] As an optional approach, the above-mentioned clustering operation on the historical interval duration to determine the target cluster includes: determining the standard deviation parameter and the mean parameter of the historical interval duration; determining the historical interval duration with outlier values ​​and the historical interval duration with normal values ​​based on the standard deviation parameter and the mean parameter; clearing the historical interval duration with outlier values, and performing the above-mentioned clustering operation on the historical interval duration with normal values ​​to determine the target cluster.

[0088] Optionally, in this embodiment, the standard deviation parameter refers to a statistic that measures the dispersion of historical interval duration data. This includes, but is not limited to, obtaining the standard deviation by calculating the square root of the average of the sum of squared deviations between historical interval durations and the mean, used to identify outliers in the dataset. The mean parameter represents the average level of the historical interval duration data, including but not limited to, calculating it by summing all historical interval durations and dividing by the total historical data volume, serving as a benchmark for determining whether the data deviates from the normal range.

[0089] Optionally, in this embodiment, the historical interval of outliers refers to data points that deviate significantly from the standard deviation and mean parameters, including but not limited to outliers identified by the 3σ principle or IQR method. These data points may be caused by external interference or measurement errors and need to be removed to improve the accuracy of clustering results. The historical interval of normal values ​​refers to data that conforms to the standard deviation and mean parameters or is within an acceptable deviation range, including but not limited to historical intervals falling within ±2σ of the mean. These data will be used for cluster analysis to determine the target clusters.

[0090] For example, embodiments of this application identify and remove outlier abnormal data by calculating the standard deviation and mean of historical intervals, perform clustering operations on the remaining normal data, and determine target clusters to guide the matching and verification of real-time data.

[0091] In one exemplary embodiment:

[0092] S1, the system collects and records the historical interval duration data of all historical vehicles passing through the target location, and records the corresponding image timestamp and radar timestamp.

[0093] S2 calculates the average and standard deviation of historical interval durations, identifies and separates historical interval durations with outliers, and ensures data cleanliness and reliability.

[0094] S3 performs clustering on the cleaned normal value historical interval dataset, groups it according to data similarity, and determines the target cluster as a reference for subsequent real-time data matching.

[0095] Through the embodiments of this application, statistical analysis and outlier detection algorithms are used to effectively clean and cluster historical data, ensuring the accuracy and representativeness of target clusters, and achieving the goal of optimizing radar video fusion matching algorithms and improving the performance of vehicle speed measurement systems.

[0096] As an optional approach, determining the current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data includes: determining a first interval duration based on the image timestamp of the current image data and the radar timestamp of the first radar data, wherein the current radar data includes the first radar data; and determining a second interval duration based on the image timestamp of the current image data and the radar timestamp of the second radar data, wherein the current radar data includes the second radar data, and the radar timestamp of the second radar data is different from the radar timestamp of the first radar data.

[0097] Optionally, in this embodiment, the current image data refers to a real-time acquired video frame, which contains information about the target vehicle, including but not limited to features such as vehicle outline, color, and type, as well as a precise timestamp corresponding to the image, used to identify the time of image capture. The first radar data and the second radar data refer to different reflected signals detected by the radar sensor within the same monitoring time, respectively corresponding to different parts of the target vehicle (such as the front or rear of the vehicle), or radar signals from different vehicles, each carrying a unique radar timestamp reflecting the time of radar signal reception.

[0098] It should be noted that different radar data may originate from different reflection points of the same vehicle, or from vehicles in different lanes; this application does not limit this.

[0099] For example, in this application embodiment, the time interval is determined by obtaining the timestamp of the current image data and the timestamp of the radar data. Furthermore, by comparing the time difference of different radar signals, the real target and the interference signal are distinguished, thereby improving the quality of data matching.

[0100] In one exemplary embodiment:

[0101] S1, the system captures and parses the current image data in real time, extracts the image timestamp, and simultaneously receives the first radar data and the second radar data sent by the radar sensor, each with its own radar timestamp.

[0102] S2, the software algorithm module calculates the first interval duration based on the image timestamp and the radar timestamp of the first radar data, assuming the calculated first interval duration is 0.002 seconds; then, it calculates the second interval duration based on the same image timestamp and the radar timestamp of the second radar data, assuming the calculated second interval duration is 0.007 seconds. Since the two interval durations are significantly different, this indicates that the first radar data and the second radar data may correspond to different parts of the target vehicle or different vehicles, and the system needs further analysis and matching to determine the true speed measurement target.

[0103] S3, the algorithm continues to analyze the first and second interval durations, combining historical data and information from the trusted database to determine which set of data better matches the actual driving state of the target vehicle, thereby eliminating interference and retaining valid speed measurement data.

[0104] Through the embodiments of this application, time difference analysis of multi-source data is used to achieve refined management of radar signals and accurate positioning of target vehicles, eliminating speed measurement errors caused by complex environmental factors such as radar splitting and vehicle crossing the line, thereby improving the overall performance and reliability of the speed measurement system.

[0105] As an optional approach, the method further includes: determining the moving speed based on the first radar data when the first interval duration meets the target duration condition and the second interval duration does not meet the target duration condition; determining the moving speed based on the second radar data when the first interval duration does not meet the target duration condition and the second interval duration meets the target duration condition; and obtaining the center interval duration of the trusted database when both the first interval duration and the second interval duration meet the target duration condition, and determining the moving speed based on the center interval duration, the first radar data, and the second radar data.

[0106] Optionally, in this embodiment, the first interval duration refers to the time difference calculated based on the timestamps of the current image data and the first radar data, including but not limited to a value such as 0.002 seconds, used to initially determine the correlation between the target vehicle and the first radar signal. The second interval duration is the time difference calculated based on the timestamps of the current image data and the second radar data, for example, 0.007 seconds, used to evaluate the matching degree between the target vehicle and the second radar signal. The center interval duration is the center value obtained after clustering historical interval duration data in the trusted database, representing the typical time difference characteristics of a specific vehicle type at the target location, such as 0.005 seconds, serving as a reference for data matching in complex scenarios.

[0107] It should be noted that the target duration condition is a time difference threshold range determined based on vehicle type and driving conditions. For example, for small cars, the target duration range may be set to 0.004 seconds to 0.006 seconds, while for large trucks it may be relaxed to 0.008 seconds to 0.012 seconds. This application does not limit this.

[0108] For example, embodiments of this application determine which set of radar data to use to determine the moving speed of the target vehicle by comparing the matching of the first interval duration and the second interval duration with the target duration condition, or by using the center interval duration for comprehensive judgment when both data meet the conditions, so as to improve the accuracy of the speed measurement results.

[0109] In one exemplary embodiment, taking the application scenario of computer vision and radar signal processing as an example:

[0110] S1, the system captures and parses the current image data in real time, confirms that the target vehicle is a sedan, and receives multiple sets of radar data. The first interval calculated from the radar timestamp and image timestamp of the first radar data is 0.005 seconds, and the second interval calculated from the radar timestamp and image timestamp of the second radar data is 0.01 seconds.

[0111] S2, based on the target duration range of the car (0.004 seconds to 0.006 seconds), it is determined that the first interval duration of 0.005 seconds meets the condition, while the second interval duration of 0.01 seconds is out of range.

[0112] S3. Based on the above conditions, the system selects the first radar data corresponding to the first interval duration of 0.005 seconds to determine the moving speed of the target vehicle. This time difference falls within the target duration range of the sedan, indicating that it has a high correlation and is more consistent with the actual driving state of the vehicle.

[0113] Through the embodiments of this application, by comparing and analyzing multiple sets of interval durations, intelligent filtering of real-time radar data is achieved, ensuring the accuracy and effectiveness of speed measurement data, and achieving the goal of optimizing the performance of the vehicle speed measurement system and improving the accuracy of traffic law enforcement.

[0114] As an optional solution, when both the first interval duration and the second interval duration meet the target duration condition, obtaining the center interval duration from the trusted database and determining the moving speed of the target vehicle based on the center data point, the first radar data, and the second radar data includes: performing a sorting operation on each of the historical interval durations stored in the trusted database to determine the center interval duration; obtaining a first distance between the first interval duration and the center interval duration, and obtaining a second distance between the second interval duration and the center interval duration; determining the moving speed based on the first radar data when the first distance is less than the second distance; and determining the moving speed based on the second radar data when the first distance is greater than the second distance.

[0115] Optionally, in this embodiment, the central interval duration refers to the value in the middle position after sorting the historical interval duration data in the trusted database. This value may be determined by methods including but not limited to the median or weighted average, and represents the trend and distribution center of most historical data, used for comparison and reference of subsequent real-time data. The sorting operation refers to arranging all historical interval durations stored in the trusted database in ascending or descending order to find the central interval duration located in the middle of the data sequence.

[0116] Optionally, in this embodiment, the historical interval duration represents the actual time difference between the image timestamp and the radar timestamp of a past vehicle at the same location, including but not limited to a range from 0.001 seconds to 0.01 seconds. The first distance and the second distance refer to the difference between the current interval duration and the center interval duration, including but not limited to absolute values ​​or relative proportions, used to assess the degree of agreement between the current data and historical trends.

[0117] It should be noted that the specific methods of sorting operations include, but are not limited to, common computer sorting algorithms such as bubble sort, quick sort, and merge sort. This application does not limit these methods and aims to find the center or trend value of historical intervals in the database through sorting, so as to provide a benchmark for real-time data matching.

[0118] For example, in this embodiment of the application, after the historical interval duration data reaches a certain amount, a sorting operation is performed to determine the center interval duration, and then the distance between the current data and the center interval duration is calculated. Based on this, radar data that is closer to the historical trend is selected for speed calculation.

[0119] In one exemplary embodiment, a computer science application scenario involving data processing and matching verification is used as an example:

[0120] S1, the system determines the center interval duration to be 0.005 seconds based on accumulated historical data, which serves as a time difference reference for normal vehicle behavior.

[0121] S2, receives in real time a first interval duration of 0.004 seconds and a second interval duration of 0.006 seconds, both of which meet the target duration condition (e.g., the range of 0.003 seconds to 0.007 seconds).

[0122] S3, calculate the first distance as 0.001 seconds (0.004 seconds - 0.005 seconds) and the second distance as 0.001 seconds (0.006 seconds - 0.005 seconds). Since the first distance equals the second distance, the system can select either radar data to determine the movement speed. However, in practice, to maintain consistency, the determination can be made based on specific application logic or randomly. For example, in this scenario, the first radar data is selected to determine the movement speed.

[0123] Alternatively, if the first distance is less than the second distance, it indicates that the current target vehicle is more closely correlated with the time of the first radar data, and the deviation between the first interval duration and the center interval duration is smaller. Therefore, the first radar data can be used to determine the moving speed of the target vehicle. Similarly, if the first distance is greater than the second distance, it indicates that the current target vehicle is more synchronized with the time of the second radar data, that is, the deviation between the second interval duration and the center interval duration is smaller. Therefore, the second radar data can be used to determine the moving speed of the target vehicle.

[0124] Through the embodiments of this application, intelligent filtering and speed calculation of radar data are achieved by using center interval duration calculation and real-time data comparison, ensuring the accuracy and rationality of speed measurement results, and achieving the goal of optimizing the vehicle speed measurement system and improving traffic supervision efficiency.

[0125] It is understood that in the specific embodiments of this application, data such as user information are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0126] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0127] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0128] Based on this understanding, the technical solution of this application, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0129] According to another aspect of the embodiments of this application, a vehicle speed measuring device for implementing the above-described vehicle speed measuring method is also provided. This vehicle speed measuring device can be used to implement the vehicle speed measuring method provided in the above embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0130] Figure 7This is a structural block diagram of an optional vehicle speed measuring device according to an embodiment of this application, such as... Figure 7 As shown, the vehicle speed measuring device includes:

[0131] The acquisition module 702 is used to acquire the current image data and current radar data of the target vehicle at the target position. The target position indicates the position where the target vehicle has passed the vehicle matching line. The current radar data has a radar timestamp. The target vehicle indicates the vehicle whose moving speed is to be determined. The image timestamp of the current image data is used to indicate the time when the image of the target vehicle was acquired. The radar timestamp of the current radar data is used to indicate the time when the reflected signal emitted by the target vehicle was detected.

[0132] The duration determination module 704 is used to determine the current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data.

[0133] The speed determination module 706 is used to determine the moving speed of the target vehicle based on the current radar data when the current interval duration meets the target duration condition. The target duration condition is determined by the image timestamp of the historical image data corresponding to the historical vehicles that passed through the target road segment at historical times and the image timestamp of the historical radar data.

[0134] In an exemplary embodiment, the apparatus is configured to determine the moving speed of a target vehicle based on current radar data if the current interval duration meets a target duration condition by: acquiring a trusted database, wherein the trusted database stores historical interval durations corresponding to at least one historical vehicle, the historical interval durations being determined by image timestamps of corresponding historical image data and image timestamps of historical radar data; determining a target duration interval based on the trusted database, wherein the target duration interval is determined by the maximum and minimum historical interval duration values ​​in the trusted database; determining that the interval duration meets the target duration condition if the current interval duration is within the target duration interval; and determining that the interval duration does not meet the target duration condition if the current interval duration is not within the target duration interval.

[0135] In an exemplary embodiment, before the apparatus acquires the trusted database in the following manner, it further includes: acquiring the historical interval duration corresponding to each historical vehicle; performing a clustering operation on the historical interval duration to determine a target cluster; and storing the historical interval duration in the target cluster to the trusted database.

[0136] In an exemplary embodiment, the apparatus is configured to perform a clustering operation on historical interval durations to determine a target cluster by: determining a standard deviation parameter and a mean parameter of the historical interval durations; determining the historical interval durations of outliers and the historical interval durations of normal values ​​based on the standard deviation parameter and the mean parameter; clearing the historical interval durations of outliers and performing a clustering operation on the historical interval durations of normal values ​​to determine the target cluster.

[0137] In one exemplary embodiment, the apparatus is configured to determine a current interval duration based on an image timestamp of current image data and a radar timestamp of current radar data in the following manner: determining a first interval duration based on an image timestamp of current image data and a radar timestamp of first radar data, wherein the current radar data includes the first radar data; and determining a second interval duration based on an image timestamp of current image data and a radar timestamp of second radar data, wherein the current radar data includes the second radar data, and the radar timestamp of the second radar data is different from the radar timestamp of the first radar data.

[0138] In an exemplary embodiment, the apparatus is further configured to: determine a moving speed based on first radar data when the first interval duration satisfies the target duration condition and the second interval duration does not satisfy the target duration condition; determine a moving speed based on second radar data when the first interval duration does not satisfy the target duration condition and the second interval duration satisfies the target duration condition; and obtain the center interval duration of a trusted database when both the first interval duration and the second interval duration satisfy the target duration condition, and determine a moving speed based on the center interval duration, the first radar data, and the second radar data.

[0139] In an exemplary embodiment, the apparatus is configured to, when both the first interval duration and the second interval duration meet the target duration condition, obtain the center interval duration from a trusted database and determine the moving speed of the target vehicle based on the center data point, first radar data, and second radar data, by: performing a sorting operation on each historical interval duration stored in the trusted database to determine the center interval duration; obtaining a first distance between the first interval duration and the center interval duration, and obtaining a second distance between the second interval duration and the center interval duration; determining the moving speed based on the first radar data when the first distance is less than the second distance; and determining the moving speed based on the second radar data when the first distance is greater than the second distance.

[0140] Regarding the apparatus in the above embodiments, the terms "module" or "unit" refer to a computer program or part of a computer program with a predetermined function, which works together with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit. The specific manner in which each module performs its operations has been described in detail in the embodiments relating to the method, and will not be elaborated upon here.

[0141] According to another aspect of the embodiments of this application, an electronic device is provided.

[0142] The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor is configured to perform the steps in any of the above method embodiments via the computer program. In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor. Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0143] According to one aspect of this application, a computer program product is also provided, which includes a computer program.

[0144] The computer program product includes a computer program / instructions containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable media 811. When the computer program is executed by central processing unit 801, it performs various functions provided in the embodiments of this application. The sequence numbers of the embodiments of this application above are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0145] Figure 8 A schematic block diagram of a computer system architecture for implementing embodiments of the present application is shown. Figure 8As shown, the computer system 800 includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes based on programs stored in ROM 802 or programs loaded into RAM 803 from storage section 808. Random access memory 803 also stores various programs and data required for system operation. The CPU 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0146] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card, such as a local area network card or modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. Removable media 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 810 as needed so that computer programs read from them can be installed into storage section 808 as needed.

[0147] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0148] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer programs / instructions. For example, embodiments of this application include a computer program / instruction comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication portion, and / or installed from a removable medium. When the computer program is executed by a central processing unit, it performs various functions defined in the system of this application. In such embodiments, the computer program / instruction can be downloaded and installed from a network via a communication portion, and / or installed from a removable medium. When the computer program / instruction is executed by a central processing unit, the aforementioned vehicle speed measurement method is performed.

[0149] According to one aspect of this application, a computer-readable storage medium is also provided.

[0150] The processor of the aforementioned electronic device can read the computer instructions from a computer-readable storage medium, and execute the computer instructions to cause the electronic device to perform the vehicle speed measurement method provided in the various optional implementations of the aforementioned vehicle speed measurement.

[0151] Optionally, in this embodiment, the computer-readable storage medium described above may be configured to store methods for performing the embodiments of this application.

[0152] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0153] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0154] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or 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 one or more electronic devices to execute all or part of the steps of the methods described in the various embodiments of this application.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed application can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and 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 displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0156] 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.

[0157] Furthermore, the functional units in the various embodiments of this application 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0158] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for measuring vehicle speed, characterized in that, include: Acquire the current image data and current radar data of the target vehicle at the target location, wherein the target location indicates the position where the target vehicle has passed the vehicle matching line, the current image data corresponds to an image timestamp, the current radar data corresponds to a radar timestamp, the target vehicle refers to the vehicle whose moving speed is to be determined, the image timestamp of the current image data is used to indicate the time when the image including the target vehicle was acquired, and the radar timestamp of the current radar data is used to indicate the time when the reflected signal emitted by the target vehicle was detected; The current interval duration is determined based on the image timestamp of the current image data and the radar timestamp of the current radar data. If the current interval duration meets the target duration condition, the moving speed of the target vehicle is determined based on the current radar data, wherein the target duration condition is determined by the image timestamp of historical image data corresponding to historical vehicles that passed through the target road segment at historical times and the image timestamp of historical radar data.

2. The method according to claim 1, characterized in that, Determining the moving speed of the target vehicle based on the current radar data when the current interval duration meets the target duration condition includes: A trusted database is obtained, wherein the trusted database stores the historical interval duration corresponding to at least one of the historical vehicles, and the historical interval duration is determined by the image timestamp of the corresponding historical image data and the image timestamp of the historical radar data. The target duration interval is determined based on the trusted database, wherein the target duration interval is determined by the historical interval duration with the largest value and the historical interval duration with the smallest value in the trusted database; If the current interval duration is within the target duration range, it is determined that the interval duration meets the target duration condition; If the current interval duration is not within the target duration range, it is determined that the interval duration does not meet the target duration condition.

3. The method according to claim 2, characterized in that, Before obtaining the trusted database, the method further includes: Obtain the historical interval duration corresponding to each of the historical vehicles; Perform clustering operations on the historical interval durations to determine the target cluster; The historical interval durations within the target cluster are stored in the trusted database.

4. The method according to claim 3, characterized in that, The step of performing clustering operations on the historical interval duration to determine the target cluster includes: Determine the standard deviation and mean parameters of the historical interval duration; The historical interval durations of outlier values ​​and normal values ​​are determined based on the standard deviation parameter and the mean parameter. The historical interval duration with abnormal values ​​is cleared, and the clustering operation is performed on the historical interval duration with normal values ​​to determine the target cluster.

5. The method according to claim 1, characterized in that, The step of determining the current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data includes: The first interval duration is determined based on the image timestamp of the current image data and the radar timestamp of the first radar data, wherein the current radar data includes the first radar data; The second interval duration is determined based on the image timestamp of the current image data and the radar timestamp of the second radar data, wherein the current radar data includes the second radar data, and the radar timestamp of the second radar data is different from the radar timestamp of the first radar data.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: If the first interval duration satisfies the target duration condition, and the second interval duration does not satisfy the target duration condition, the moving speed is determined based on the first radar data. If the first interval duration does not meet the target duration condition, but the second interval duration meets the target duration condition, the moving speed is determined based on the second radar data. If both the first interval duration and the second interval duration meet the target duration condition, the center interval duration of the trusted database is obtained, and the moving speed is determined based on the center interval duration, the first radar data, and the second radar data.

7. The method according to claim 6, characterized in that, When both the first interval duration and the second interval duration meet the target duration condition, the step of obtaining the center interval duration of the trusted database and determining the moving speed of the target vehicle based on the center data point, the first radar data, and the second radar data includes: A sorting operation is performed on each of the historical interval durations stored in the trusted database to determine the central interval duration; Obtain a first distance between the first interval duration and the center interval duration, and obtain a second distance between the second interval duration and the center interval duration; If the first distance is less than the second distance, the moving speed is determined based on the first radar data; If the first distance is greater than the second distance, the moving speed is determined based on the second radar data.

8. A vehicle speed measuring device, characterized in that, include: The acquisition module is used to acquire the current image data and current radar data of the target vehicle at the target position. The target position indicates the position where the target vehicle has passed the vehicle matching line. The current radar data has a radar timestamp. The target vehicle refers to the vehicle whose moving speed is to be determined. The image timestamp of the current image data is used to indicate the time when the image including the target vehicle was acquired. The radar timestamp of the current radar data is used to indicate the time when the reflected signal emitted by the target vehicle was detected. The duration determination module is used to determine the current interval duration based on the image timestamp of the current image data and the radar timestamp of the current radar data. The speed determination module is used to determine the moving speed of the target vehicle based on the current radar data when the current interval duration meets the target duration condition. The target duration condition is determined by the image timestamp of historical image data corresponding to historical vehicles that passed through the target road segment at historical times and the image timestamp of historical radar data.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

Images