Vehicle low-speed slow-moving detection method, electronic device and storage medium

Abstract

The invention relates to a vehicle low-speed and slow-moving detection method, an electronic device and a storage medium, and the method comprises the steps: obtaining map data of a target road section and vehicle data collected by a roadside camera, fusing the map data with the vehicle data, and obtaining vehicle track fusion data; wherein the vehicle track fusion data comprises a lane identifier of each lane, and a vehicle identifier and a vehicle speed of each lane; calculating the average speed of each lane in the target road section according to the vehicle track fusion data, and determining a low-speed threshold value according to the average speed; acquiring the speed of the target vehicle, and judging whether the speed of the target vehicle is smaller than a low-speed threshold; when it is judged that the vehicle speed of the target vehicle is smaller than the low-speed threshold value, it is determined that a low-speed slow-down event exists; the effectiveness of the detection result is improved, and traffic management is guided more effectively.

Description

Technical Field

[0001] The present application relates to the field of traffic safety technology, and in particular to a vehicle slow-moving detection method, an electronic device and a storage medium. Background Art

[0002] Slow-speed events refer to situations where vehicles move at speeds far below normal speeds. Generally, it can be understood that the vehicle speed is significantly lower than the road speed limit or the average speed of surrounding vehicles, and sometimes it may be as low as a few kilometers per hour. Slow-speed vehicles not only affect the traffic order of the highway and reduce traffic efficiency, but also force other vehicles to overtake from the right lane or emergency lane, which can easily increase the probability of scratches and rear-end collisions, especially on turns and uphill sections. Traffic accidents are very likely to occur.

[0003] In traffic management, some lanes generally have a pre-set minimum speed limit, and the minimum speed limit is fixed or cannot be changed within a certain period of time. The traditional slow-moving detection method calculates the average speed of the vehicle after it passes through two checkpoints, compares the average speed of the vehicle with the set fixed minimum speed limit, determines whether the vehicle is driving at a low speed, and then guides traffic management based on the detection results. In some cases, although a certain section of road has not been detected as slow-moving, the lane may become congested after a period of time, or even cause a traffic accident, which will make the detection result ineffective.

[0004] At present, no effective solution has been proposed to address the problem of low utility of vehicle slow-moving detection results in related technologies. Summary of the invention

[0005] Based on this, it is necessary to provide a vehicle slow-moving detection method, electronic device and storage medium that can improve the effectiveness of detection results in response to the above technical problems.

[0006] In a first aspect, the present application provides a vehicle slow-moving detection method, comprising:

[0007] Acquire map data of the target road section and vehicle data collected by a roadside camera, fuse the map data and the vehicle data, and obtain vehicle trajectory fusion data; wherein the vehicle trajectory fusion data includes lane markings of each lane, vehicle markings of each lane, and vehicle speed;

[0008] Calculating the average vehicle speed of each lane in the target road section according to the vehicle trajectory fusion data, and determining a low speed threshold according to the average vehicle speed;

[0009] Obtaining the speed of the target vehicle, and determining whether the speed of the target vehicle is less than the low speed threshold;

[0010] When it is determined that the speed of the target vehicle is less than the low speed threshold, it is determined that a low speed slowing event exists.

[0011] In one embodiment, fusing the map data with the vehicle data to obtain vehicle trajectory fusion data includes:

[0012] The longitude and latitude of the vehicle in the vehicle data are matched with the longitude and latitude of the lane in the map data to determine the lane where the vehicle in the vehicle data is located.

[0013] In one embodiment, matching the longitude and latitude of the vehicle in the vehicle data with the longitude and latitude of the lane in the map data to determine the lane in which the vehicle in the vehicle data is located includes:

[0014] Dividing the lane center line in the map data into equal intervals to obtain a plurality of lane center points;

[0015] Constructing a lane query tree object according to the lane center point; wherein the lane query tree object is used to find the lane center point closest to the target position;

[0016] The longitude and latitude of the vehicles in the vehicle data are input into the lane query tree object to obtain the lane identification corresponding to each vehicle.

[0017] In one embodiment, the longitude and latitude of the vehicle in the vehicle data are input into the lane query tree object to obtain the lane identification corresponding to each vehicle, including:

[0018] Outputting the center point and the distance of the neighboring lane of the current vehicle based on the lane query tree object;

[0019] Determine whether the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, where n is a positive integer;

[0020] When it is determined that the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, it is determined that the current vehicle is in the lane where the center point of the neighboring lane is located, and a corresponding lane mark is returned.

[0021] In one embodiment, calculating the average vehicle speed of each lane in the target road section according to the vehicle trajectory fusion data includes:

[0022] Acquire multi-frame vehicle trajectory fusion data within a preset time interval;

[0023] Based on the vehicle trajectory fusion data of each frame, the average speed of vehicles appearing in each lane is calculated as the average lane speed of a single frame;

[0024] The average vehicle speeds of all the single-frame lanes of the same lane are accumulated, and the accumulated value is divided by the total number of frames of the vehicle trajectory fusion data to obtain the average vehicle speed of each lane.

[0025] In one embodiment, determining the low speed threshold according to the average vehicle speed includes:

[0026] The low speed threshold is determined according to an average vehicle speed of a first lane and / or a second lane in the target road section; wherein the first lane is a lane where the target vehicle is located, and the second lane is adjacent to the first lane.

[0027] In one embodiment, obtaining the speed of the target vehicle and determining whether the speed of the target vehicle is less than the low speed threshold includes:

[0028] Determining whether the speed of the target vehicle is less than a first low-speed threshold determined based on the first lane;

[0029] In the case where it is determined that the speed of the target vehicle is less than the first low-speed threshold, determining whether the speed of the target vehicle is less than a second low-speed threshold determined based on the second lane;

[0030] When it is determined that the speed of the target vehicle is less than the second low-speed threshold, it is determined that the low-speed slowing event occurs.

[0031] In one embodiment, when it is determined that the speed of the target vehicle is less than the low speed threshold, the method further includes:

[0032] Determine whether the driving state of the target vehicle meets preset conditions; wherein the preset conditions include: whether the time for which the vehicle maintains a slow-speed driving state is greater than a preset time, and / or whether the distance between the current position of the vehicle in the slow-speed driving state and the position of the last slow-speed driving state is greater than a preset distance;

[0033] When it is determined that the driving state of the target vehicle meets the preset condition, it is determined that the slow-speed slow-moving event exists on the target road section, and information about the slow-speed slow-moving event and information about the target vehicle are sent to a preset receiving end.

[0034] In a second aspect, the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0035] In a third aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0036] The above-mentioned vehicle slow-moving detection method, electronic device and storage medium obtain vehicle trajectory fusion data by fusing map data and vehicle data collected by roadside cameras, calculate the average speed of each lane based on the vehicle trajectory fusion data, and determine the low-speed threshold based on the average speed of the lane, so as to judge whether the target vehicle is in a slow-moving state. Since the low-speed threshold is calculated based on the real-time traffic speed, it is more real-time and accurate, and realizes the adaptive dynamic judgment of the speed difference between the vehicle and the surrounding lanes with the help of upstream and downstream information of the lane, which can improve the effectiveness of the detection results and guide traffic management more effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A diagram showing an application environment of a vehicle slow-moving detection method in an embodiment;

[0038] Figure 2 is a hardware structure block diagram of a terminal in one embodiment;

[0039] Figure 3 A schematic diagram of a process flow of a vehicle slow-moving detection method in one embodiment;

[0040] Figure 4 A schematic diagram of a process of fusing map data and vehicle data in one embodiment;

[0041] Figure 5 The figure is a flow chart of a vehicle slow-moving detection method in another embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0044] The vehicle slow-moving detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 1 communicates with the server 2 through the network. The data storage system 3 can store the data that the server 2 needs to process. The data storage system 3 can be integrated on the server 2, or it can be placed on the cloud or other network servers. The terminal 1 obtains the map data of the target road section and the vehicle data collected by the roadside camera through the server 2, and performs vehicle slow-moving detection based on these two parts of data. Among them, the terminal 1 can be but is not limited to various personal computers, laptops, tablet computers, vehicle-mounted electronic terminals, and Internet of Things devices. The server 2 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0045] Figure 2 1 is a hardware structure diagram of a terminal 1 according to an embodiment of the present application. Figure 1 As shown, terminal 1 may include one or more ( Figure 2 Only one is shown in the figure) processor 101 and memory 102 for storing data, wherein processor 101 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 103 and an input and output device 104 for communication functions. It can be understood by those skilled in the art that Figure 2 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 2 More or fewer components as shown, or with Figure 2 Different configurations shown.

[0046] The memory 102 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the vehicle slow-speed detection method in the present embodiment. The processor 101 executes various functional applications and data processing by running the computer program stored in the memory 102, that is, to implement the above method. The memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 102 may further include a memory remotely arranged relative to the processor 101, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0047] The transmission device 103 is used to receive or send data via a network. The above network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 103 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 103 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0048] The vehicle slow-moving detection method of the related technology is based on a fixed low-speed threshold. If the low-speed threshold does not match the actual traffic speed, the detection result will become ineffective and cannot effectively guide traffic management. For example, a one-way lane has a speed limit of 40km / h, and the average speed of the lane is 80km / h during a certain period of time. A vehicle deliberately drives at a speed of about 40km / h, which will cause inconsistency with the actual natural traffic speed. Although the vehicle does not violate traffic regulations, after a period of time, the lane may be congested or even cause a traffic accident.

[0049] Based on the analysis of the above situation, in one embodiment, Figure 3 A vehicle slow-moving detection method is provided. Figure 1 or Figure 2 The terminal in is used as an example to illustrate, including the following steps:

[0050] Step S101, obtaining map data of the target road section and vehicle data collected by the roadside camera, fusing the map data and the vehicle data to obtain vehicle trajectory fusion data; wherein the vehicle trajectory fusion data includes lane markings of each lane, vehicle markings of each lane, and vehicle speed.

[0051] The target road section may be a certain ordinary road section or a highway section. The map data may be data that can accurately represent lane-level details, such as a high-definition map (HD Map), whose accuracy can reach the centimeter level. In this step, the map data includes at least lane markings and longitude and latitude. In some embodiments, the map data also includes information such as lane type, vehicle speed, and vehicle heading angle. Roadside cameras are cameras installed on both sides of the target road section, which are used to capture vehicle images and obtain vehicle data. In this step, the vehicle data includes at least vehicle identification, vehicle longitude and latitude, and vehicle speed. In some embodiments, the vehicle data also includes information such as license plate numbers.

[0052] The lane in which the vehicle in the vehicle data is located can be determined by matching the vehicle longitude and latitude in the vehicle data with the lane longitude and latitude in the map data, that is, associating the vehicle identification and the lane identification, thereby obtaining vehicle trajectory fusion data.

[0053] Step S102, calculating the average vehicle speed of each lane in the target road section according to the vehicle trajectory fusion data, and determining the low speed threshold according to the average vehicle speed.

[0054] The multi-frame vehicle trajectory fusion data within the preset time interval can be obtained; based on each frame of vehicle trajectory fusion data, the average speed of the vehicles appearing in each lane is calculated as the single-frame lane average speed; the average speed of all single-frame lanes of the same lane is accumulated, and the accumulated value is divided by the total number of frames of the vehicle trajectory fusion data to obtain the average speed of each lane. For example, assuming that the acquisition frame rate of the roadside camera is 10HZ, that is, 10 frames of vehicle data are generated in 1 second, and each frame of vehicle data carries the vehicle speed (instantaneous speed), then after the vehicle data is fused with the map data, the multi-frame vehicle trajectory fusion data can be obtained. Assuming that the preset time interval is 5 minutes, 3000 frames of vehicle trajectory fusion data will be generated every 5 minutes. Assuming that each frame has lanes A, B, C, and D, taking lane A as an example, the single-frame lane average speed of lane A = the sum of all vehicle speeds of lane A in a single frame / the number of vehicles in lane A in a single frame, and the average speed of lane A = the sum of all single-frame lane average speeds of lane A in lane A / 3000. The average speed of other lanes is also calculated using the same principle as lane A.

[0055] After obtaining the average speed of each lane, the low speed threshold is determined according to the average speed of the first lane and / or the second lane in the target road section; wherein the first lane is the lane where the target vehicle is located, and the second lane is adjacent to the first lane. In some embodiments, the first low speed threshold is determined based on the first lane, and the first low speed threshold can be the average speed value of the first lane, or the value obtained by multiplying the average speed of the first lane by a preset ratio (e.g., 20%). In some embodiments, the second low speed threshold is determined based on the second lane, and the second low speed threshold can be the average speed value of the second lane, or the value obtained by multiplying the average speed of the second lane by a preset ratio (e.g., 20%). In some embodiments, the third low speed threshold is determined based on the first lane and the second lane, and the third low speed threshold can be the average speed value of all vehicles in the first lane and the second lane, or the value obtained by multiplying the average speed of all vehicles in the first lane and the second lane by a preset ratio (e.g., 20%). Wherein, the preset ratio can be determined according to the minimum speed limit percentage specified in the traffic management method of the actual road section.

[0056] Step S103, obtaining the speed of the target vehicle, and determining whether the speed of the target vehicle is less than a low speed threshold.

[0057] In one embodiment, the speed of the target vehicle is compared to a first low-speed threshold. In some embodiments, the speed of the target vehicle is compared to a second low-speed threshold. In some embodiments, the speed of the target vehicle is compared to a third low-speed threshold.

[0058] Step S104: When it is determined that the speed of the target vehicle is less than the low speed threshold, it is determined that a slow-moving event exists.

[0059] In one embodiment, the speed of the target vehicle is compared with the first low-speed threshold. If the speed of the target vehicle is less than the first low-speed threshold, it can be determined that the target vehicle is in a slow-speed slow state and there is a slow-speed slow event. In some embodiments, the speed of the target vehicle is compared with the second low-speed threshold. If the speed of the target vehicle is less than the second low-speed threshold, it can be determined that the target vehicle is in a slow-speed slow state and there is a slow-speed slow event. In some embodiments, the speed of the target vehicle is compared with the third low-speed threshold. If the speed of the target vehicle is less than the third low-speed threshold, it can be determined that the target vehicle is in a slow-speed slow state and there is a slow-speed slow event.

[0060] In the above steps S101 to S104, the vehicle trajectory fusion data is obtained by fusing the map data and the vehicle data collected by the roadside camera, the average speed of each lane is calculated based on the vehicle trajectory fusion data, and the low-speed threshold is determined based on the average speed of the lane to determine whether the target vehicle is in a low-speed slow-moving state. Since the low-speed threshold is calculated based on the real-time traffic speed, it is more real-time and accurate, and realizes the adaptive dynamic judgment of the speed difference between the vehicle and the surrounding lanes with the help of the upstream and downstream information of the lane, which can improve the effectiveness of the detection results and guide traffic management more effectively.

[0061] In one embodiment, obtaining the speed of the target vehicle and determining whether the speed of the target vehicle is less than a low speed threshold includes:

[0062] Determine whether the speed of the target vehicle is less than a first low-speed threshold determined based on the first lane; if it is determined that the speed of the target vehicle is less than the first low-speed threshold, determine whether the speed of the target vehicle is less than a second low-speed threshold determined based on the second lane; if it is determined that the speed of the target vehicle is less than the second low-speed threshold, there is a slow-moving event.

[0063] When judging whether the vehicle in the self-lane is in a slow-speed slowing state based on the low-speed threshold of the self-lane, the embodiment may have a rear vehicle in a slow-speed slowing state due to an accident ahead or other vehicles slowing down. In order to reduce the misjudgment of this passive slow-speed slowing vehicle, the embodiment preferentially compares the speed of the target vehicle with the low-speed threshold of the self-lane. If the speed of the target vehicle is less than the low-speed threshold of the self-lane, two results can be obtained at this time: the target vehicle belongs to active slow-speed slowing and the target vehicle belongs to passive slow-speed slowing. In order to further verify, the speed of the target vehicle is continued to be compared with the low-speed threshold of the left and right adjacent lanes. If the speed of the target vehicle is also less than the low-speed threshold of the left and right adjacent lanes, it can be determined that the target vehicle belongs to active slow-speed slowing, and there is a slow-speed slowing event at this time. Because the speed of the target vehicle is less than the low-speed threshold of the left and right adjacent lanes, it means that the left and right adjacent lanes are not congested, and the target vehicle can speed up by changing lanes, but its speed is less than the low-speed threshold of the left and right adjacent lanes. It can be determined that its subjective intention of deliberately not changing lanes is large, which belongs to active slow-speed slowing.

[0064] In one embodiment, Figure 4 A flowchart of the fusion of map data and vehicle data is provided, such as Figure 4 As shown, matching the longitude and latitude of the vehicle in the vehicle data with the longitude and latitude of the lane in the map data to determine the lane where the vehicle in the vehicle data is located includes the following steps:

[0065] Step S201, dividing the lane center line in the map data into equal intervals to obtain a plurality of lane center points.

[0066] Specifically, the map data includes lane id, lane centerline, lane width (in meters), where the lane centerline can be a sequence of multiple longitude and latitude points, a straight lane can contain 2 longitude and latitude points, and a curved lane can contain 3 or more longitude and latitude points. The lane centerline in the map data is divided into equally spaced points (the interval can be 0.2m), and multiple lane center points are obtained. Each lane center point corresponds to a lane id data, which is defined as lane center point data. The lane center point data is a two-dimensional array. In two-dimensional space, each lane center point consists of x and y coordinates.

[0067] Step S202, constructing a lane query tree object according to the lane center point; wherein the lane query tree object is used to find the lane center point closest to the target position.

[0068] Define a node class, and save the data of each lane center point based on the defined node class. Select a coordinate axis in the two-dimensional space as the starting dimension as the basis for node splitting, for example, start from the X axis, and then use other dimensions alternately, such as the Y axis next, the X axis again in the next layer, and so on. For all lane center points on the selected dimension, sort them according to the coordinate values ​​of the dimension, find the middle value, and use this as the boundary to divide all lane center points into two groups, one group contains all lane center points less than the middle value, and the other group contains all lane center points greater than the middle value. Each point represents a hyperplane, which is perpendicular to the currently selected dimension and divides the space into two by the middle value. Take the middle point as a node, recursively repeat the above steps for all points in the left half to build the left subtree, and all points in the right half are used to build the right subtree. Switch to the next dimension for splitting each time recursively until all points are assigned to the appropriate position in the tree. When there are no more points to split, the lane query tree object is built. At this point, the lane query tree object has organized the lane center point data and can be used to quickly query one or more lane center points closest to a given location.

[0069] Step S203: input the longitude and latitude of the vehicle in the vehicle data into the lane query tree object to obtain the lane identification corresponding to each vehicle.

[0070] Inputting the vehicle's latitude and longitude into the constructed lane query tree object will output the center point of the current vehicle's neighboring lane and the neighboring distance; determine whether the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, where n is a positive integer (for example, n=2); if it is determined that the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, determine that the current vehicle is in the lane where the center point of the neighboring lane is located, and return the corresponding lane identification; otherwise, return an empty string.

[0071] In the above steps S201 to S203, the lane center point data set is recursively divided into two subsets, each point represents a hyperplane, and the hyperplane divides the space into two. As a result, the time complexity of finding the nearest neighbor point in the tree is reduced from linear to logarithmic level, which is conducive to improving data query efficiency.

[0072] In one embodiment, when it is determined that the speed of the target vehicle is less than the low speed threshold, the method further includes:

[0073] Determine whether the driving state of the target vehicle meets the preset conditions; wherein the preset conditions include: whether the time the vehicle maintains a low-speed slow-moving state is greater than a preset time (e.g., 5s), and / or, the distance between the vehicle's current low-speed slow-moving state position and the vehicle's last low-speed slow-moving state position is greater than a preset distance (e.g., 5m); when it is determined that the driving state of the target vehicle meets the preset conditions, determine that a low-speed slow-moving event exists on the target road section, and send information about the low-speed slow-moving event and the target vehicle's information to a preset receiving end.

[0074] In this embodiment, considering that the vehicle data collected by the camera is incorrect, an additional condition judgment is introduced, that is, judging whether the driving state of the target vehicle meets the preset conditions, thereby improving the reliability of the detection result. Among them, the information of the slow-moving event includes but is not limited to the slow-moving speed, slow-moving duration, slow-moving trajectory, etc., and the information of the target vehicle includes but is not limited to the license plate number, vehicle location, etc. The preset receiving end can be a traffic management platform or other cloud service platform.

[0075] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0076] In one embodiment, Figure 5 A flow chart of another vehicle slow-moving detection method is provided, such as Figure 5 As shown, the process includes the following steps:

[0077] Step S301, obtaining map data of the target road section. The map data may be high-precision map data, including information such as lane identification, lane longitude and latitude, lane type, vehicle speed, and vehicle heading angle.

[0078] Step S302, obtaining vehicle data collected by the roadside camera. The vehicle data can be obtained from the roadside AI camera, including vehicle identification, vehicle latitude and longitude, vehicle speed, license plate number and other information.

[0079] Step S303, based on the longitude and latitude of the vehicle and the longitude and latitude of the lane, the lane where the vehicle is located is matched to obtain vehicle trajectory fusion data. The specific fusion method is as follows:

[0080] (1) Split the lane centerline. Split the lane centerline in the map data into equally spaced points to obtain multiple lane center points. Specifically, the map data contains the lane id, lane centerline, and lane width (in meters). The lane centerline can be a sequence of multiple longitude and latitude points. A straight lane can contain 2 longitude and latitude points, and a curved lane can contain 3 or more longitude and latitude points. Split the lane centerline in the map data into equally spaced points (the interval can be selected to be 0.2m) to obtain multiple lane center points. Each lane center point corresponds to a lane id data, which is defined as lane center point data. The lane center point data is a two-dimensional array. In two-dimensional space, each lane center point consists of x and y coordinates.

[0081] (2) Construct a lane query tree object based on the lane center point; the lane query tree object is used to find the lane center point closest to the target position. Specifically, define a node class, and save the data of each lane center point based on the defined node class. Select a coordinate axis in the two-dimensional space as the starting dimension as the basis for node splitting, for example, start from the X axis, and then use other dimensions alternately, such as the Y axis next, the X axis again in the next layer, and so on. For all lane center points on the selected dimension, sort them according to the coordinate values ​​of the dimension, find the middle value, and use this as the boundary to divide all lane center points into two groups, one group contains all lane center points less than the middle value, and the other group contains all lane center points greater than the middle value. Each point represents a hyperplane, which is perpendicular to the currently selected dimension and divides the space into two by the middle value. Take the middle point as a node, recursively repeat the above steps for all points in the left half to construct the left subtree, and all points in the right half are used to construct the right subtree. Switch to the next dimension for splitting each time recursively until all points are assigned to appropriate positions in the tree. When there are no more points to split, the lane query tree object is built. At this point, the lane query tree object has organized the lane center point data and can be used to quickly query one or more lane center points closest to a given location.

[0082] (3) Perform lane query. Input the longitude and latitude of the vehicle in the vehicle data into the lane query tree object to obtain the lane identification corresponding to each vehicle. Specifically, input the longitude and latitude of the vehicle into the constructed lane query tree object, and the center point and distance of the neighboring lane of the current vehicle will be output; determine whether the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, where n is a positive integer (for example, n=2); if it is determined that the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, determine that the current vehicle is in the lane where the center point of the neighboring lane is located, and return the corresponding lane identification; otherwise, return an empty string.

[0083] Step S304, calculating the average vehicle speed of each lane in the target road section according to the vehicle trajectory fusion data.

[0084] Step S305, determine whether the speed of the target vehicle is greater than the preset speed; if so, proceed to step S305, otherwise end the process. This is to filter stopped vehicles. Since there is a certain error in the speed detection of the AI ​​camera, it is necessary to filter out the parking data here. Among them, the preset speed can be adjusted according to the situation, for example, 5km / h.

[0085] Step S306, determine whether the current lane of the target vehicle is valid; if so, proceed to step S307; otherwise, end the process. Specifically, obtain the current lane id of the target vehicle and determine whether it is an empty string. If so, it means that the current lane is invalid.

[0086] Step S307, obtain the current lane ID of the target vehicle and the IDs of the left and right adjacent lanes in the drivable area, determine the first low-speed threshold based on the average speed of the current lane, and determine the second low-speed threshold based on the average speed of the left and right adjacent lanes. The first low-speed threshold is 20% of the average speed of the current lane, and the second low-speed threshold is 20% of the average speed of the left and right lanes. The 20% here can be modified according to actual conditions or traffic regulations.

[0087] Step S308, determine whether the speed of the target vehicle is less than the first low-speed threshold; if so, proceed to step S309, otherwise end the process.

[0088] Step S309, determine whether the speed of the target vehicle is less than the second low-speed threshold; if so, proceed to step S310, otherwise end the process.

[0089] Step S310, updating and caching the vehicle slow-moving continuous state. Specifically, recording and continuously calculating the duration of the vehicle's slow-moving state and the location (latitude and longitude) where the slow-moving state first occurred.

[0090] Step S311, determine whether the duration of the vehicle's slow-speed state is greater than 5 seconds and the distance from the first slow-speed state position is not less than 5 meters; if so, proceed to step S312; otherwise, end the process. The 5 seconds and 5 meters here can be adjusted according to the situation.

[0091] Step S312, triggering a slow-speed event. Specifically, the basic information of the target vehicle (license plate number, vehicle location, etc.) and event information (slow-speed driving speed, slow-speed driving duration, slow-speed driving trajectory, etc.) are sent to the traffic management platform.

[0092] In the above steps S301 to S312, by utilizing map data and vehicle data collected in real time by roadside cameras, the average speed of the lane is calculated in real time, and based on the upstream and downstream information of the lane, the speed difference between the vehicle and the surrounding lanes is adaptively and dynamically judged. The low-speed threshold of each lane changes dynamically according to the speed of lane traffic vehicles and is no longer a fixed threshold. It has stronger real-time and accuracy, and can achieve an event detection frequency of seconds, thereby improving the effectiveness of the detection results and guiding traffic management more effectively.

[0093] In one embodiment, based on the same inventive concept as the above method, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any of the above method embodiments.

[0094] Optionally, 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.

[0095] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0096] Obtaining map data of the target road section and vehicle data collected by roadside cameras, fusing the map data and vehicle data to obtain vehicle trajectory fusion data; wherein the vehicle trajectory fusion data includes lane markings of each lane, vehicle markings of each lane, and vehicle speed;

[0097] The average speed of each lane in the target road section is calculated based on the vehicle trajectory fusion data, and the low-speed threshold is determined based on the average speed;

[0098] Obtain the speed of the target vehicle and determine whether the speed of the target vehicle is less than a low speed threshold;

[0099] When it is determined that the speed of the target vehicle is less than the low speed threshold, it is determined that a low speed slowing event exists.

[0100] In one embodiment, the processor may be configured to perform the following steps through a computer program:

[0101] The longitude and latitude of the vehicle in the vehicle data are matched with the longitude and latitude of the lane in the map data to determine the lane where the vehicle in the vehicle data is located.

[0102] In one embodiment, the processor may be configured to perform the following steps through a computer program:

[0103] The lane centerline in the map data is divided into equal intervals to obtain multiple lane center points;

[0104] A lane query tree object is constructed according to the lane center point; wherein the lane query tree object is used to find the lane center point closest to the target position;

[0105] The vehicle latitude and longitude in the vehicle data are input into the lane query tree object to obtain the lane identification corresponding to each vehicle.

[0106] In one embodiment, the processor may be configured to perform the following steps through a computer program:

[0107] Output the center point and distance of the neighboring lanes of the current vehicle based on the lane query tree object;

[0108] Determine whether the nearest neighbor distance is not greater than 1 / n of the lane width of the lane where the center point of the nearest lane is located, where n is a positive integer;

[0109] When it is determined that the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, it is determined that the current vehicle is in the lane where the center point of the neighboring lane is located, and the corresponding lane mark is returned.

[0110] In one embodiment, the processor may be configured to perform the following steps through a computer program:

[0111] Acquire multi-frame vehicle trajectory fusion data within a preset time interval;

[0112] Based on the vehicle trajectory fusion data of each frame, the average speed of vehicles appearing in each lane is calculated as the average lane speed of a single frame;

[0113] The average lane speeds of all single-frames in the same lane are accumulated, and the accumulated value is divided by the total number of frames of the vehicle trajectory fusion data to obtain the average speed of each lane.

[0114] In one embodiment, the processor may be configured to perform the following steps through a computer program:

[0115] The low speed threshold is determined according to the average vehicle speed of the first lane and / or the second lane in the target road section; wherein the first lane is the lane where the target vehicle is located, and the second lane is adjacent to the first lane.

[0116] In one embodiment, the processor may be configured to perform the following steps through a computer program:

[0117] Determining whether the speed of the target vehicle is less than a first low-speed threshold determined based on the first lane;

[0118] In the case where it is determined that the speed of the target vehicle is less than the first low-speed threshold, determining whether the speed of the target vehicle is less than a second low-speed threshold determined based on the second lane;

[0119] When it is determined that the vehicle speed of the target vehicle is less than the second low-speed threshold, it is determined that a low-speed slowing event occurs.

[0120] In one embodiment, the processor may be configured to perform the following steps through a computer program:

[0121] Determine whether the driving state of the target vehicle meets preset conditions; wherein the preset conditions include: whether the time for which the vehicle maintains the slow-speed slow-moving state is greater than a preset time, and / or whether the distance between the current position of the vehicle in the slow-speed slow-moving state and the position of the last slow-speed slow-moving state is greater than a preset distance;

[0122] When it is determined that the driving state of the target vehicle meets the preset conditions, it is determined that there is a slow-speed event on the target road section, and information about the slow-speed event and information about the target vehicle are sent to a preset receiving end.

[0123] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0124] In addition, in combination with the vehicle slow-moving detection method provided in the above embodiments, a storage medium can also be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the vehicle slow-moving detection methods in the above embodiments is implemented.

[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0126] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0127] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0128] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle slow-moving detection method, characterized in that: include: Acquire map data of the target road section and vehicle data collected by a roadside camera, fuse the map data and the vehicle data, and obtain vehicle trajectory fusion data; wherein the vehicle trajectory fusion data includes lane markings of each lane, vehicle markings of each lane, and vehicle speed; Calculating the average vehicle speed of each lane in the target road section according to the vehicle trajectory fusion data, and determining a low speed threshold according to the average vehicle speed; Obtaining the speed of the target vehicle, and determining whether the speed of the target vehicle is less than the low speed threshold; When it is determined that the speed of the target vehicle is less than the low speed threshold, it is determined that a low speed slowing event exists.

2. The vehicle slow-moving detection method according to claim 1, characterized in that: The map data and the vehicle data are integrated to obtain vehicle trajectory fusion data, including: The longitude and latitude of the vehicle in the vehicle data are matched with the longitude and latitude of the lane in the map data to determine the lane where the vehicle in the vehicle data is located.

3. The vehicle slow-moving detection method according to claim 2, characterized in that: Matching the longitude and latitude of the vehicle in the vehicle data with the longitude and latitude of the lane in the map data to determine the lane where the vehicle in the vehicle data is located, includes: Dividing the lane center line in the map data into equal intervals to obtain a plurality of lane center points; Constructing a lane query tree object according to the lane center point; wherein the lane query tree object is used to find the lane center point closest to the target position; The longitude and latitude of the vehicles in the vehicle data are input into the lane query tree object to obtain the lane identification corresponding to each vehicle.

4. The vehicle slow-moving detection method according to claim 3, characterized in that: Inputting the latitude and longitude of the vehicle in the vehicle data into the lane query tree object to obtain the lane identification corresponding to each vehicle, including: Outputting the center point and the distance of the neighboring lane of the current vehicle based on the lane query tree object; Determine whether the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, where n is a positive integer; When it is determined that the neighboring distance is not greater than 1 / n of the lane width of the lane where the center point of the neighboring lane is located, it is determined that the current vehicle is in the lane where the center point of the neighboring lane is located, and a corresponding lane mark is returned.

5. The vehicle slow-moving detection method according to claim 1, characterized in that: Calculating the average vehicle speed of each lane in the target road section according to the vehicle trajectory fusion data includes: Acquire multi-frame vehicle trajectory fusion data within a preset time interval; Based on the vehicle trajectory fusion data of each frame, the average speed of vehicles appearing in each lane is calculated as the average lane speed of a single frame; The average vehicle speeds of all the single-frame lanes of the same lane are accumulated, and the accumulated value is divided by the total number of frames of the vehicle trajectory fusion data to obtain the average vehicle speed of each lane.

6. The vehicle slow-moving detection method according to claim 1, characterized in that: Determining a low speed threshold according to the average vehicle speed includes: The low speed threshold is determined according to an average vehicle speed of a first lane and / or a second lane in the target road section; wherein the first lane is a lane where the target vehicle is located, and the second lane is adjacent to the first lane.

7. The vehicle slow-moving detection method according to claim 6, characterized in that: Acquiring the speed of the target vehicle and determining whether the speed of the target vehicle is less than the low speed threshold includes: Determining whether the speed of the target vehicle is less than a first low-speed threshold determined based on the first lane; In the case where it is determined that the speed of the target vehicle is less than the first low-speed threshold, determining whether the speed of the target vehicle is less than a second low-speed threshold determined based on the second lane; When it is determined that the speed of the target vehicle is less than the second low-speed threshold, it is determined that the low-speed slowing event occurs.

8. The vehicle slow-moving detection method according to claim 1, characterized in that: In the case where it is determined that the speed of the target vehicle is less than the low speed threshold, the method further includes: Determine whether the driving state of the target vehicle meets preset conditions; wherein the preset conditions include: whether the time for which the vehicle maintains a slow-speed driving state is greater than a preset time, and / or whether the distance between the current position of the vehicle in the slow-speed driving state and the position of the last slow-speed driving state is greater than a preset distance; When it is determined that the driving state of the target vehicle meets the preset condition, it is determined that the slow-speed slow-moving event exists on the target road section, and information about the slow-speed slow-moving event and information about the target vehicle are sent to a preset receiving end.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images