Traffic signal light release distance determination method and device, and storage medium

Abstract

The present disclosure relates to the technical field of road traffic, in particular to a method and device for determining a release distance of a traffic signal and a storage medium. The method comprises: obtaining driving trajectory information of a plurality of vehicles at a target traffic signal intersection; obtaining a vehicle trajectory point density distribution map of the target traffic signal intersection according to the driving trajectory information; determining a first inflection point and a second inflection point among inflection points of the vehicle trajectory point density distribution map; and determining a first release distance of the traffic signal, the first release distance being a distance between a position corresponding to the first inflection point at the target traffic signal intersection and a position corresponding to the second inflection point at the target traffic signal intersection.

Description

Technical Field

[0001] This disclosure relates to the field of road traffic technology, and more specifically, to a method, apparatus, electronic device, and storage medium for determining the green distance of traffic lights. Background Technology

[0002] The distance a traffic light can travel in one cycle is a measure of an intersection's capacity and indirectly reflects the length of the intersection's cycle. Its value in disseminating traffic information is quite evident. For example, we can estimate how many cycles a vehicle will need to pass through a traffic light by observing the current queue distance—that is, how many red lights we need to wait for—and thus estimate the state of the traffic conditions.

[0003] In existing technologies, the distance between multiple stops at an intersection is often used as the release distance. However, since smooth traffic flow far outweighs congestion, this method results in an extremely uneven sample distribution, leading to low applicability and coverage. Furthermore, the distance between multiple stops is easily affected by abnormal parking, such as the presence of pedestrian crossings or drop-off / pick-up points before the traffic light intersection, causing inaccurate release distances. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for determining the green distance of traffic lights. It can improve the overall efficiency and accuracy of determining the green distance of traffic lights.

[0005] In a first aspect, embodiments of this application provide a method for determining the green distance of a traffic light, comprising: acquiring the driving trajectory information of multiple vehicles at a target traffic light intersection; obtaining a vehicle trajectory point density distribution map of the target traffic light intersection based on the driving trajectory information; determining a first inflection point and a second inflection point among the inflection points of the vehicle trajectory point density distribution map; and determining a first green distance of the traffic light, wherein the first green distance is the distance between the positions of the first inflection point and the second inflection point at the target traffic light intersection.

[0006] Optionally, the driving trajectory information includes the number of times the vehicle stops and the stopping location information before the target traffic light intersection. Determining the first inflection point and the second inflection point in the vehicle trajectory point density distribution map at the target traffic light intersection includes: among the points in the vehicle trajectory point density distribution map whose distance from the target traffic light intersection is less than a preset threshold, selecting the inflection point with the highest vehicle trajectory point density as the first inflection point. Determining the stopping locations for driving trajectories that stop once in the driving trajectory information. Sort the stopping locations and determine a preset distance interval based on a first preset percentile and a second preset percentile. Selecting the inflection point in the vehicle trajectory point density distribution map that is within the preset distance interval as the second inflection point.

[0007] Optionally, the driving trajectory information includes information on the number of times the vehicle stops and the stopping positions before the target traffic light intersection. After determining the first clearance distance of the traffic light, the method further includes: determining the first and second stopping positions in the driving trajectory information where the number of stops is greater than one, wherein the first and second stopping positions are the two stopping positions closest to the target traffic light in the driving trajectory; determining the second clearance distance of the target traffic light, wherein the second clearance distance is the distance between the first and second stopping positions; and determining the actual clearance distance of the target traffic light based on the first and second clearance distances.

[0008] Optionally, determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: determining the actual release distance of the target traffic light based on the first release distance, the second release distance, and a preset weight of the first release distance and the second release distance.

[0009] Optionally, determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: when neither the first release distance nor the second release distance meets a preset condition, acquiring the features of the target traffic light intersection; inputting the features of the target traffic light intersection into a pre-trained classification model to determine the category of the target traffic light intersection; and determining the actual release distance of the target traffic light based on the category of the target traffic light intersection.

[0010] Optionally, before inputting the features of the target traffic light intersection into a pre-trained classification model to determine the category of the target traffic light intersection, the method further includes: inputting the actual green distance of sample traffic lights into a clustering model to obtain the category of the sample traffic light intersection; using the features of the sample traffic lights as training samples and the category of the sample traffic lights as supervision to train the classification model to obtain the pre-trained classification model; determining the actual green distance of the target traffic light intersection based on its category includes: determining sample traffic light intersections with the same category as the target traffic light intersection. The actual green distance of a first sample traffic light intersection is used as the actual green distance of the target traffic light intersection, wherein the first sample traffic light intersection is the sample traffic light intersection with features most closely similar to the features of the target traffic light intersection among the sample traffic light intersections with the same category as the target traffic light intersection.

[0011] Optionally, the driving trajectory information is driving trajectory information within a preset time period, and determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: determining the actual release distance of the target traffic light within the preset time period based on the first release distance and the second release distance.

[0012] Secondly, embodiments of this application provide a device for determining the green distance of a traffic light, comprising: a first acquisition module, configured to acquire driving trajectory information of multiple vehicles at a target traffic light intersection; a second acquisition module, configured to obtain a vehicle trajectory point density distribution map of the target traffic light intersection based on the driving trajectory information; a first determination module, configured to determine a first inflection point and a second inflection point among the inflection points of the vehicle trajectory point density distribution map; and a second determination module, configured to determine a first green distance of the traffic light, wherein the first green distance is the distance between the position of the first inflection point at the target traffic light intersection and the position of the second inflection point at the target traffic light intersection.

[0013] Thirdly, embodiments of this application provide a storage medium storing computer instructions thereon, which, when executed by a processor, implement the steps of the method described in any of the first aspects above.

[0014] Fourthly, embodiments of this application provide an electronic device having a processor and a memory, wherein the memory stores computer instructions, which, when executed by the processor, implement the steps of the method described in any of the first aspects above.

[0015] One beneficial effect of this disclosure is that by acquiring the driving trajectory information of multiple vehicles at a target traffic light intersection, and based on the trajectory information, obtaining a vehicle trajectory point density distribution map of the target traffic light intersection, determining a first inflection point and a second inflection point among the inflection points of the vehicle trajectory point density distribution map, and determining the traffic light's green distance based on the distance between the corresponding positions of the first and second inflection points. This method can be applied to more traffic lights, i.e., more scenarios, and also solves the problem of inaccurate green distances obtained due to abnormal parking.

[0016] Other features and advantages of the embodiments of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments of the present disclosure and, together with their description, serve to explain the principles of the embodiments of the present disclosure.

[0018] Figure 1 A flowchart illustrating a method for determining the traffic signal release distance according to an embodiment of the present disclosure is shown.

[0019] Figure 2 A schematic diagram illustrating an example of a method for determining the traffic signal release distance according to an embodiment of the present disclosure is shown.

[0020] Figure 3 A block diagram of a traffic signal light release distance determination device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0021] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0022] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0023] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0024] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0025] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0026] It should be noted that all actions involving the acquisition of signals, information, or data in this application are carried out in compliance with the relevant international data protection laws and policies and with the authorization granted by the owner of the relevant device / account.

[0027] like Figure 1 As shown in the figure, this application discloses a method for determining the traffic signal light release distance, which includes steps S11-S14.

[0028] Step S11: Obtain the driving trajectory information of multiple vehicles at the target traffic light intersection;

[0029] In one example of this embodiment, the driving trajectory information of multiple vehicles passing through the target traffic light can be obtained. Specifically, the driving trajectory information at the target traffic light intersection can be the GPS trajectory points of vehicles within a certain distance range before reaching the traffic light intersection.

[0030] In one example of this embodiment, the driving trajectory information may also include information on the number of times the vehicle stops and the stopping location information within a certain distance before reaching the target traffic light intersection.

[0031] Step S12: Based on the driving trajectory information, obtain the vehicle trajectory point density distribution map of the target traffic light intersection.

[0032] In one embodiment, a kernel density estimation algorithm can be used to process the driving trajectory information to obtain a vehicle trajectory point density distribution map of the target traffic light intersection. Specifically, the kernel density estimation algorithm can be used to process the GPS trajectory points of multiple vehicles into a statistical distribution histogram of vehicle trajectory point density versus distance from the target traffic light, such as... Figure 2 As shown, the horizontal axis of the vehicle trajectory point density distribution map represents the distance to the target traffic light, and the vertical axis represents the vehicle trajectory point density. The curve in the figure represents the smoothed distribution of vehicle trajectory point density at the target traffic light intersection. In this embodiment, since the vehicle trajectory points are marked based on a preset time interval, the vehicle trajectory point density can also reflect the vehicle density.

[0033] Step S13: Determine the first inflection point and the second inflection point in the vehicle trajectory point density distribution map.

[0034] In one example of this embodiment, after obtaining the vehicle trajectory point density distribution map of the target traffic light intersection, the inflection points of the vehicle trajectory point density distribution can be found in the map. Furthermore, among the inflection points in the map, the points representing vehicle aggregation (i.e., the first inflection point) and the points representing vehicle dissipation (i.e., the second inflection point) can be determined.

[0035] In one example of this embodiment, determining the first inflection point and the second inflection point in the vehicle trajectory point density distribution map of the target traffic light intersection includes: selecting the inflection point with the highest vehicle trajectory point density among the points in the vehicle trajectory point density distribution map whose distance from the target traffic light intersection is less than a preset threshold, and using it as the first inflection point. Determining the stopping positions of driving trajectories that stop once in the driving trajectory information. Sort the stopping positions and determine a preset distance interval based on a first preset percentile and a second preset percentile. Selecting the inflection point in the vehicle trajectory point density distribution map that falls within the preset distance interval as the second inflection point.

[0036] In one example of this embodiment, the first inflection point is generally located at the point with the highest density of vehicle trajectory points within a certain distance from the target traffic light. Therefore, preset thresholds can be set for different traffic light intersections, such as the number of lanes, traffic density, width, speed limit, etc., and the inflection point with the highest density of vehicle trajectory points within a distance less than the preset threshold in the vehicle trajectory point density distribution map can be used as the first inflection point.

[0037] In one example of this embodiment, due to the influence of pedestrian walkways and bus pick-up / drop-off points, the vehicle trajectory point density distribution map may exhibit a bimodal pattern, making it difficult to correctly determine the second inflection point. To address this, the driving trajectory information of multiple vehicles can be filtered to select those trajectories that have only stopped once, and the stopping positions of these trajectories can be determined. These stopping positions can then be sorted, and a preset distance interval can be determined based on preset percentiles. Specifically, for example, the stopping positions of all trajectories that stopped once can be sorted from farthest to closest based on their distance from the target traffic light. The first and second preset percentiles can be set according to the specific characteristics of the target traffic light; for example, the first preset percentile can be set to the 80th percentile, and the second preset percentile to the 100th percentile. Based on the preset percentiles, the 80th and 100th percentile positions of all stopping positions are determined, and the distance interval between these positions and the target traffic light is further determined as the preset distance interval. After determining the preset distance interval, the inflection point in the vehicle trajectory point density distribution map that falls within the preset distance interval can be used as the second inflection point.

[0038] Step S14: Determine the first clearance distance of the traffic signal. The first clearance distance is the distance between the position of the first turning point at the target traffic signal intersection and the position of the second turning point at the target traffic signal intersection.

[0039] In this example, by acquiring the driving trajectory information of multiple vehicles at the target traffic light intersection, and based on the trajectory information, a vehicle trajectory point density distribution map of the target traffic light intersection is obtained. The first and second inflection points are determined from the inflection points in the vehicle trajectory point density distribution map, and the green distance of the traffic light is determined based on the distance between the corresponding positions of the first and second inflection points. This method can be applied to more traffic lights, i.e., more scenarios, and can also solve the problem of inaccurate green distances obtained due to abnormal parking.

[0040] In one example of this embodiment, the driving trajectory information includes the number of times the vehicle stops and the stopping position information in front of the target traffic light intersection. After determining the first clearance distance of the traffic light, the method further includes: determining the first stopping position and the second stopping position in the driving trajectory information where the number of stops is greater than one, wherein the first stopping position and the second stopping position are the two stopping positions closest to the target traffic light in the driving trajectory; determining the second clearance distance of the target traffic light, wherein the second clearance distance is the distance between the first stopping position and the second stopping position; and determining the actual clearance distance of the target traffic light based on the first clearance distance and the second clearance distance.

[0041] In one example of this embodiment, after determining the first clearance distance, it is determined that from the driving trajectory information of multiple vehicles, driving trajectories with more than one stop are selected, and the two parking positions closest to the target traffic light are further determined, and the distance between these two parking positions is used as the second clearance distance of the target traffic light.

[0042] In one example of this embodiment, since there may be multiple parking trajectory information, the average or median of the distance between the two nearest parking positions of multiple trajectories can be used as the second clearance distance of the target traffic light.

[0043] In one example of this embodiment, determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: determining the actual release distance of the target traffic light based on the first release distance, the second release distance, and a preset weight of the first release distance and the second release distance.

[0044] In one example of this embodiment, after calculating the first release distance based on the kernel density estimation algorithm and determining the second release distance based on the parking position, the first release distance and the second release distance can be weighted and fused according to preset weights to obtain the actual release distance of the target traffic light.

[0045] In one example of this embodiment, since the number of trajectories with one stop and the number of trajectories with more than one stop in the driving trajectory are not fixed, the reliability of the first and second release distances determined in this embodiment may differ. Therefore, the preset weight can be determined based on the driving trajectory information of multiple vehicles to make the obtained actual release distance more accurate. For example, it can be determined based on the number of trajectories with one stop and the number of trajectories with more than one stop in the driving trajectory information.

[0046] In one example of this embodiment, determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: when one of the first release distance and the second release distance meets a preset condition, the release distance that meets the preset condition is taken as the actual release distance.

[0047] In one example of this embodiment, due to the uncertainty of the driving trajectory information, one of the determined first release distance and second release distance may be too large, too small, or have no value. Therefore, the preset condition can be that the release distance is within a reasonable distance range. When one of the first release distance and the second release distance meets the preset condition, and the other does not meet the preset condition, the release distance that meets the preset condition can be used as the actual release distance.

[0048] In one example of this embodiment, determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: when neither the first release distance nor the second release distance meets the preset conditions, acquiring the features of the target traffic light intersection, inputting the features of the target traffic light intersection into a pre-trained classification model, determining the category of the target traffic light intersection, and determining the actual release distance of the target traffic light based on the category of the target traffic light intersection.

[0049] In one example of this embodiment, before inputting the features of the target traffic light intersection into a pre-trained classification model to determine the category of the target traffic light intersection, the method further includes: inputting the actual release distance of sample traffic lights into a clustering model to obtain the category of the sample traffic light intersection; using the features of the sample traffic lights as training samples and the categories of the sample traffic lights as supervision to train the classification model to obtain a pre-trained classification model. Determining the actual release distance of the target traffic light intersection based on its category includes: identifying sample traffic light intersections of the same category as the target traffic light intersection; using the actual release distance of the first sample traffic light intersection as the actual release distance of the target traffic light intersection; the first sample traffic light intersection being the sample traffic light intersection whose features are closest to those of the target traffic light intersection among the sample traffic light intersections of the same category.

[0050] In one example of this embodiment, other traffic lights whose actual clearance distances are obtained using the method described above can be used as sample traffic lights. The actual clearance distances of the sample traffic lights are then input into the clustering model to obtain multiple cluster centers, which correspond to the categories of the sample traffic light intersections.

[0051] After obtaining the categories of the sample traffic lights, the features of the sample traffic light intersections can be input into the classification model, and the classification model can be trained using the categories of the sample traffic lights as supervision. The features of the sample traffic light intersections can include the speed limit, width, number of lanes, popularity, and congestion probability of the intersection.

[0052] In one example of this embodiment, when neither the first nor the second release distance meets the preset conditions, features of the target traffic light intersection can be acquired, such as speed limit, width, number of lanes, traffic volume, and congestion probability. These features are then input into a trained classification model to determine the category to which the target traffic light intersection belongs. Based on this category, the actual release distance for the target traffic light intersection is determined.

[0053] In one example of this embodiment, when determining the actual release distance, samples with the same type as the target traffic light intersection can be identified from the training samples. The actual release time of the traffic light intersection whose features are closest to the target traffic light intersection among the samples of traffic light intersections with the same type is taken as the actual release time of the target traffic light intersection.

[0054] In one example of this embodiment, after identifying samples that match the type of the target traffic light intersection in the training samples, the average value of the actual release distance of the traffic lights that match the type of the target traffic light intersection can be calculated, and this average value can be used as the actual release distance of the target traffic light.

[0055] In one example of this embodiment, the driving trajectory information is the driving trajectory information within a preset time period. Determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: determining the actual release distance of the target traffic light within the preset time period based on the first release distance and the second release distance.

[0056] In one example of this embodiment, since the greening time of the traffic signal may be different in different time periods, the greening distance of the traffic signal will also be different in different time periods. Therefore, when obtaining the driving trajectory information, the driving trajectory information of a specific time period can be obtained, and the greening distance of the target traffic signal in the specific time period can be determined based on the driving trajectory information of the specific time period.

[0057] See Figure 3 As shown, this embodiment provides a device 100 for determining the green distance of a traffic signal, including:

[0058] The first acquisition module 101 is used to acquire the driving trajectory information of multiple vehicles at the target traffic light intersection. The second acquisition module 102 is used to obtain a vehicle trajectory point density distribution map of the target traffic light intersection based on the driving trajectory information. The first determination module 103 is used to determine a first inflection point and a second inflection point among the inflection points in the vehicle trajectory point density distribution map. The second determination module 104 is used to determine a first clearance distance for the traffic light, where the first clearance distance is the distance between the positions of the first inflection point and the second inflection point at the target traffic light intersection.

[0059] Optionally, the driving trajectory information includes the number of times the vehicle stops before the target traffic light intersection and the stopping location information. The first determining module is specifically used to determine the stopping location of the driving trajectory with one stop in the driving trajectory information, among the points in the vehicle trajectory point density distribution map whose distance from the target traffic light intersection is less than a preset threshold, take the inflection point with the highest vehicle trajectory point density as the first inflection point, sort the stopping locations, determine the preset distance interval according to the first preset percentile and the second preset percentile, and take the inflection point in the vehicle trajectory point density distribution map that is located within the preset distance interval as the second inflection point.

[0060] Optionally, the driving trajectory information includes the number of times the vehicle stops and the stopping positions at the target traffic light intersection. The device further includes: a third determining module, used to determine, after determining the first clearance distance of the traffic light, the first and second stopping positions in the driving trajectory information where the number of stops is greater than one, wherein the first and second stopping positions are the two stopping positions closest to the target traffic light in the driving trajectory; a fourth determining module, used to determine the second clearance distance of the target traffic light, wherein the second clearance distance is the distance between the first and second stopping positions; and a fifth determining module, used to determine the actual clearance distance of the target traffic light based on the first and second clearance distances.

[0061] Optionally, the fifth determining module is specifically used to determine the actual release distance of the target traffic light based on the first release distance, the second release distance, and the preset weights of the first release distance and the second release distance.

[0062] Optionally, the fifth determining module includes: an acquisition submodule, used to acquire features of the target traffic light intersection when neither the first nor the second release distance meets preset conditions; a first determining submodule, used to input the features of the target traffic light intersection into a pre-trained classification model to determine the category of the target traffic light intersection; and a second determining submodule, used to determine the actual release distance of the target traffic light intersection based on its category.

[0063] Optionally, the fifth determining module further includes: a clustering submodule, used to input the actual release distance of sample traffic lights into the clustering model before inputting the features of the target traffic light intersection into the pre-trained classification model to determine the category of the target traffic light intersection, thereby obtaining the category of the sample traffic light intersection; a training submodule, used to use the features of the sample traffic lights as training samples and the categories of the sample traffic lights as supervision to train the classification model and obtain a pre-trained classification model; and a third determining submodule, specifically used to determine sample traffic light intersections of the same category as the target traffic light intersection, using the actual release distance of the first sample traffic light intersection as the actual release distance of the target traffic light intersection, wherein the first sample traffic light intersection is the sample traffic light intersection whose features are closest to those of the target traffic light intersection among the sample traffic light intersections of the same category.

[0064] Optionally, the driving trajectory information is the driving trajectory information within a preset time period. The fifth determining module is specifically used to determine the actual release distance of the target traffic light within the preset time period based on the first release distance and the second release distance.

[0065] This embodiment provides an electronic device, including: a processor, a memory, and a computer program stored in the memory. When the computer program is executed by the processor, it implements the various processes of the above-described method embodiment for determining the traffic signal light release distance and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0066] This embodiment provides a computer-readable storage medium storing executable commands. When executed by a processor, the executable commands implement the various processes of the above-described method embodiment for determining the traffic signal release distance and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0067] The various embodiments in this disclosure are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and apparatus embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0068] The foregoing has described specific embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] Embodiments of this disclosure may be systems, methods, and / or computer program products. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the embodiments of this disclosure.

[0070] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0071] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0072] Computer program instructions used to perform the operations of embodiments of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on a user's computer, partially on a user's computer, as a standalone software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of embodiments of this disclosure.

[0073] Various aspects of embodiments of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0074] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0075] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0076] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions. It will be known to those skilled in the art that implementation in hardware, implementation in software, and implementation in a combination of software and hardware are equivalent.

[0077] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for determining the green distance of a traffic signal, characterized in that, The method includes: Obtain the driving trajectory information of multiple vehicles at the target traffic light intersection; Based on the driving trajectory information, a vehicle trajectory point density distribution map of the target traffic light intersection is obtained; Among the inflection points in the vehicle trajectory point density distribution map, determine the first inflection point and the second inflection point; The first clearance distance of the traffic light is determined, which is the distance between the position of the first turning point at the target traffic light intersection and the position of the second turning point at the target traffic light intersection. The driving trajectory information includes the number of times the vehicle stops and the stopping location information before the target traffic light intersection. In the vehicle trajectory point density distribution map of the target traffic light intersection, the first inflection point and the second inflection point are determined, including: Among the points in the vehicle trajectory point density distribution map whose distance from the target traffic light intersection is less than a preset threshold, the inflection point with the highest vehicle trajectory point density is taken as the first inflection point. Determine the parking location of the driving trajectory with one stop in the driving trajectory information; The parking locations are sorted, and a preset distance range is determined based on the first preset percentile and the second preset percentile. The inflection point located within the preset distance range in the vehicle trajectory point density distribution map is taken as the second inflection point.

2. The method according to claim 1, characterized in that, The driving trajectory information includes the number of times the vehicle stops and the stopping location information before the target traffic light intersection. After determining the first green distance of the traffic light, the method further includes: In the driving trajectory information, determine the first and second parking positions in the driving trajectory with more than one stop, and the first and second parking positions are the two parking positions in the driving trajectory that are closest to the target traffic light; Determine a second permitted distance for the target traffic light, wherein the second permitted distance is the distance between the first stop position and the second stop position; The actual release distance of the target traffic light is determined based on the first release distance and the second release distance.

3. The method according to claim 2, characterized in that, Determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: The actual release distance of the target traffic light is determined based on the first release distance, the second release distance, and the preset weights of the first release distance and the second release distance.

4. The method according to claim 2, characterized in that, Determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: When neither the first release distance nor the second release distance meets the preset conditions, the characteristics of the target traffic signal intersection are obtained; The features of the target traffic light intersection are input into a pre-trained classification model to determine the category of the target traffic light intersection; The actual clearance distance of the target traffic signal is determined based on the type of the target traffic signal intersection.

5. The method according to claim 4, characterized in that, Before inputting the features of the target traffic light intersection into a pre-trained classification model to determine the category of the target traffic light intersection, the method further includes: Input the actual release distance of the sample traffic lights into the clustering model to obtain the category of the sample traffic light intersection; The features of the sample traffic lights are used as training samples, and the categories of the sample traffic lights are used as supervision to train the classification model, thereby obtaining the pre-trained classification model. Determining the actual green distance of the target traffic light based on the type of the target traffic light intersection includes: Identify sample traffic light intersections that are of the same category as the target traffic light intersection; The actual release distance of the first sample traffic light intersection is taken as the actual release distance of the target traffic light intersection. The first sample traffic light intersection is the sample traffic light intersection whose features are closest to those of the target traffic light intersection among the sample traffic light intersections of the same category as the target traffic light intersection.

6. The method according to claim 2, characterized in that, The driving trajectory information is the driving trajectory information within a preset time period. Determining the actual release distance of the target traffic light based on the first release distance and the second release distance includes: Based on the first and second release distances, the actual release distance of the target traffic light within a preset time period is determined.

7. A device for determining the green distance of a traffic signal, characterized in that, The device includes: The first acquisition module is used to acquire the driving trajectory information of multiple vehicles at the target traffic light intersection; The second acquisition module is used to obtain a vehicle trajectory point density distribution map of the target traffic light intersection based on the driving trajectory information. The driving trajectory information includes the number of times the vehicle stops and the stopping location information before the target traffic light intersection. In the vehicle trajectory point density distribution map of the target traffic light intersection, the module determines a first inflection point and a second inflection point, including: Among the points in the vehicle trajectory point density distribution map whose distance from the target traffic light intersection is less than a preset threshold, the inflection point with the highest vehicle trajectory point density is taken as the first inflection point. Determine the parking location of the driving trajectory with one stop in the driving trajectory information; The parking locations are sorted, and a preset distance range is determined based on the first preset percentile and the second preset percentile. The inflection point located within the preset distance interval in the vehicle trajectory point density distribution map is taken as the second inflection point; The first determining module is used to determine the first inflection point and the second inflection point among the inflection points of the vehicle trajectory point density distribution map; The second determining module is used to determine the first release distance of the traffic light, wherein the first release distance is the distance between the position of the first turning point at the target traffic light intersection and the position of the second turning point at the target traffic light intersection.

8. A storage medium, characterized in that, It stores computer instructions that, when executed by a processor, implement the steps of the method described in any one of claims 1-6.

9. An electronic device, characterized in that, The device has a processor and a memory, the memory storing computer instructions that, when executed by the processor, implement the steps of the method according to any one of claims 1-6.

Images