Red light duration determination method, electronic equipment and computer program product

Abstract

The embodiment of the invention discloses a red light duration determination method, electronic equipment and a computer program product, and the method comprises the steps: obtaining sample data in a target time period, and the sample data comprises a passing track and a residence track of a sample vehicle for a target traffic light in the target time period; forming an intra-period position distribution diagram for the sample data; and determining the red light duration of the target traffic light intersection within the specified time based on the position distribution diagram in the period. According to the technical scheme, the prediction accuracy of the intersection red light duration can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of traffic technology, and in particular to a method for determining the duration of a red light, an electronic device, and a computer program product. Background Art

[0002] One of the main causes of congestion on urban roads is traffic lights, and the red light duration of traffic lights is one of the important information required in various road traffic scenarios. For example, in order to alleviate the user's anxiety in traffic congestion scenarios, the countdown of the traffic light that the user is currently about to pass can be displayed to the user. In addition, the red light duration of the traffic light can also be used to accurately calculate the red light state interval of the target traffic light, so as to serve as an auxiliary feature to predict traffic conditions such as congestion and dissipation. Summary of the invention

[0003] The embodiments of the present disclosure provide a method for determining the duration of a red light, an electronic device, and a computer program product, so as to solve the technical problem in the prior art that the duration of a red light cannot be accurately calculated.

[0004] In a first aspect, an embodiment of the present invention provides a method for determining a red light duration, the method comprising:

[0005] Acquire sample data within a target time period, the sample data including the travel trajectory and stay trajectory of sample vehicles at a target traffic light within the target time period; form a position distribution map within a period for the sample data; and determine the red light duration at the target traffic light intersection within a specified time based on the position distribution map within the period.

[0006] Furthermore, forming a periodic position distribution information graph for the sample data includes: generating a periodic position distribution graph based on the time difference between the timestamp of each trajectory and the moment when the red light of the traffic light wave to which it belongs switches to green light, wherein the horizontal axis of the periodic position distribution graph is the time offset, and the vertical axis is the number of trajectories.

[0007] Furthermore, the method includes determining the red light duration of the target traffic light intersection within a specified time based on the data sufficiency and time resolution of the position distribution map within the period.

[0008] Furthermore, the data sufficiency is used to represent the ratio of the statistical intervals of non-zero trajectories to the total number of statistical intervals under a specific interval statistical length, and the time resolution is the maximum time difference of trajectories that can be counted in the same interval.

[0009] Furthermore, the data sufficiency is proportional to the statistical interval width, and the time resolution is inversely proportional to the statistical interval width.

[0010] Furthermore, the data sufficiency and time resolution of the position distribution map within the period are used to determine the red light duration of the target traffic light intersection within the specified time, including traversing the statistical interval and determining the red light duration of the target traffic light intersection within the specified time based on the number of passing trajectories and the number of resident trajectories in the statistical interval.

[0011] Furthermore, the determining of the red light duration of the target traffic light intersection within the specified time based on the number of trajectories includes: determining whether the interval is a mainstream traffic interval or a mainstream residence interval according to the number of passing trajectories and the number of residence trajectories, and determining the boundary interval between passing and residence, allocating the red and green durations within the interval in proportion, and obtaining the red light duration of the target traffic light intersection within the specified time.

[0012] Furthermore, if the time resolution is not 1, after determining the boundary interval between the passing and the staying, the proportional relationship between the two trajectories in the boundary interval is compared.

[0013] In a second aspect, an embodiment of the present invention provides an electronic device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method provided in the first aspect of the embodiment of the present invention.

[0014] In a third aspect, an embodiment of the present disclosure provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, they are used to implement the method described in the first aspect above.

[0015] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0016] In the disclosed embodiment, sample data within a target time period is obtained, and the sample data includes the passing trajectory and the staying trajectory of the sample vehicle at the target traffic light within the target time period; a position distribution map within a period is formed for the sample data; and the red light duration of the target traffic light intersection within a specified time is determined based on the position distribution map within the period. This technical solution can improve the prediction accuracy of the red light duration at the intersection.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0019] Figure 1 A flow chart showing a method for determining the duration of a red light according to an embodiment of the present disclosure;

[0020] Figure 2 FIG. 1 shows a distribution diagram a of positions within a period according to an embodiment of the present disclosure;

[0021] Figure 3 FIG. 2 shows a position distribution diagram b within a period according to an embodiment of the present disclosure;

[0022] Figure 4 FIG. 4 shows a position distribution diagram c within a period according to an embodiment of the present disclosure; DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The following are explanations of some of the terms that appear in the text:

[0025] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0026] In the existing technology, the red light duration of traffic lights usually depends on the trajectory dwell time, etc. However, the traffic light data obtained by this method is less robust, the data source is single and easily affected by noise, and there are certain assumptions about the distribution of intersection trajectory flow, which cannot meet the needs of current business scenarios. Therefore, it is necessary to propose a solution to more accurately mine the red light duration of various traffic lights on the road to meet the data mining and analysis needs of various road traffic scenarios.

[0027] In the prior art, it is often predicted that the trajectory flow distribution arriving at the intersection is uniform in the time dimension within the cycle. By assuming that the trajectory flow distribution is uniform, the inflection point of the normal residence time and the abnormal residence trajectory in the distribution is found, and the critical residence time of the inflection point is mined as the red light duration. However, the actual traffic control system is relatively complex. There are some intersections whose traffic control design causes the trajectory flow entering the intersection to naturally have the characteristic of uneven distribution in the time dimension within its cycle. The inflection point of the residence distribution found at such intersections is not necessarily the point closest to the actual red light duration.

[0028] In the prior art, there is another way to calculate the duration of a red light, which is often obtained by subtracting the timestamp of the vehicle entering the intersection and starting to wait for the red light, that is, the time stamp of the vehicle leaving the intersection after waiting for the red light. The timestamp of leaving the intersection contains more noise that is difficult to accurately estimate, such as the reaction time caused by congestion or queuing for the light, or the start delay caused by the driver's inattention or driving habits. Therefore, the dwelling duration obtained by subtracting the timestamps before and after the actual trajectory of the vehicle is often different from the actual dwelling duration due to the red light. This difference may cause the accuracy of the existing dwelling method in mining the red light duration to be insufficient and fail to meet business requirements.

[0029] Therefore, there is an urgent need to provide a method for automatically obtaining a traffic light countdown. The following is a more detailed description of the method for determining the red light duration, the electronic device, and the computer program product provided by the present invention in conjunction with the accompanying drawings and embodiments.

[0030] In step S101, sample data within a target time period is obtained, wherein the sample data includes a passing trajectory and a staying trajectory of a sample vehicle for a target traffic light within the target time period;

[0031] In step S102, a position distribution diagram within a period is formed for the sample data;

[0032] In step S103, the red light duration of the target traffic light intersection within a specified time is determined based on the position distribution map within the period.

[0033] In this embodiment, the method for determining the duration of the red light can be performed offline on the server. Sample data can be collected by time period, for example, a day can be divided into multiple time periods, such as one time period is one hour. Sample data may include the passage trajectory data and residence trajectory of all or part of the passing objects passing through the target traffic light intersection during the historical period. The passing object may be a motor vehicle, a non-motor vehicle, a machine capable of traveling on the road, etc. In some embodiments, the passing object may carry a GPS and travel on the road, and the GPS data of the passing object may be transmitted back to the server. The time range before prediction may be multiple consecutive days in the past, and the historical time period may be any one or more time periods that are the same in the multiple consecutive days in the past, such as the time period from 7 to 9 a.m. every day of the week. The prediction time range may be one or more days in the future, and the prediction time period may be the same time period as the historical time period, such as the time range before prediction is 7 days in the past week, the historical time period may be time period A within the 7 days, the prediction time range may be tomorrow, and the prediction time period may be tomorrow's time period A.

[0034] The target traffic light intersection may be an intersection where the target traffic light is located. In some embodiments, the target traffic light intersection may be a timed period traffic light intersection, and the timed period traffic light intersection may be understood as a traffic light cycle that is fixed for at least a period of time in a day. The travel trajectory data or the resident trajectory data may be a GPS trajectory, including information such as time, location, and speed.

[0035] In the disclosed embodiment, since the target traffic light intersection is a timed periodic traffic light intersection, the number of objects passing through the target traffic light intersection changes periodically. Therefore, based on the traffic trajectory data and the resident trajectory data, the number of objects passing through the target traffic light intersection in the historical period of the pre-prediction time range can be statistically analyzed, and then based on the number change, a position distribution map within the cycle is generated to determine the red light duration of the target traffic light intersection within the specified time. Through the disclosed embodiment, the red light duration of various traffic lights on the road can be more accurately mined to meet the data mining and analysis needs of various road traffic scenarios.

[0036] In some embodiments, forming a periodic position distribution information graph for the sample data includes: generating a time difference between the timestamp of each track and the time when the red light of the traffic light wave to which it belongs switches to the green light as follows: Figure 2 The position distribution diagram a within the period, wherein the horizontal axis of the position distribution diagram within the period is the time offset, and the vertical axis is the number of trajectories.

[0037] In some embodiments, the data sufficiency is used to indicate the proportion of the statistical intervals of non-zero trajectories in the total number of statistical intervals under a specific interval statistical length, and the time resolution is the maximum time difference of the trajectories that can be counted in the same interval. The specific calculation method is: the data sufficiency is equal to the number of intervals where the number of trajectories is not 0 / the number of all statistical intervals divided by the specific statistical interval length, and the number of all statistical intervals is equal to the cycle divided by the interval width. For example, if the traffic light cycle is 115s and the interval width is 5s, a total of 23 statistical intervals are counted every five seconds. The higher the data sufficiency, the smaller the overall variance of the algorithm, and the stronger the robustness of the algorithm in the face of different data. The resolution is 1 / the width of the statistical interval, which represents the difference in the time dimension. For example, a time resolution of 1 / 5s means that the trajectories counted in the same interval differ by a maximum of 5s in the time dimension. The higher the time resolution, the smaller the overall bias of the algorithm, which means that the distortion rate of the original data features is lower. It is worth noting that the data sufficiency is proportional to the width of the statistical interval, and the time resolution is inversely proportional to the width of the statistical interval. In this embodiment, an innovative balance is achieved between data sufficiency and temporal resolution. Given distributed data, this embodiment selects the maximum temporal resolution that satisfies the sufficiency requirement based on the data distribution at different intersections in order to achieve optimal overall generalization performance of the algorithm and minimize error.

[0038] In some embodiments, the determination of the red light duration of the target traffic light intersection within the specified time based on the data sufficiency and time resolution of the position distribution map within the period includes traversing the statistical interval and determining the red light duration of the target traffic light intersection within the specified time based on the number of passing trajectories and the number of resident trajectories in the statistical interval. Specifically, the interval is determined to be a mainstream passing interval or a mainstream resident interval based on the number of passing trajectories and the number of resident trajectories, and the boundary interval between passing and resident is determined, and the red and green duration within the interval is proportionally distributed to obtain the red light duration of the target traffic light intersection within the specified time.

[0039] The specific traversal method steps are as follows:

[0040] First, compare and traverse the distribution ratio of each interval to find the intersection area where the passage / residence are the mainstream of the interval, that is, the area where the i-th green passing trajectory is the mainstream and the red residence trajectory is the mainstream. Figure 3 In the position distribution diagram b shown in the cycle, the i-th green passing trajectory is the mainstream, and then the red resident trajectory is the mainstream. If there is no intermediate mixed zone, that is, the previous interval is the mainstream of green light passing, and the next interval is the mainstream of red light passing, in this case, the endpoint anchoring method is used to determine the red light duration. Figure 3 In the distribution diagram b of the period shown in the figure, in this case, the confidence anchor point type is the interval endpoint type. It can be considered that there are 10 significant green light intervals corresponding to 50s confidence green light duration, and 19 significant red light intervals, that is, 95s significant red light duration. It is further obtained that the red-green dividing line is near the interval endpoint. When the mainstream item of the traffic light at the intermediate junction is not significant, the interval anchoring method is used, such as Figure 4 As shown in the period position distribution diagram c, when the traffic light mainstream item is not significant, the interval anchoring method can be used. In this case, the confidence anchor point type is interval type, such as Figure 4 From the position distribution diagram c within the period shown, it can be considered that the red-green dividing line should be located in the mixed storage interval.

[0041] The method of traversing the offset interval relative to the moment when the green light is on (the origin of the coordinate axis) has the advantage of end-to-end within the system. The prediction result of the red light duration in the traffic system will eventually be used to predict the moment when the traffic light changes from green to red in the downstream system. The upstream red-to-green moment in the system is selected as the reference system, which can take the upstream systematic deviation into consideration. The calculated red light duration can be more accurately applied to downstream tasks, which is more helpful for the ultimate systematic goal of more accurately predicting the robustness of the moment when the traffic light changes from red to green.

[0042] In some embodiments, if the time resolution is not 1, after determining the boundary interval of passing and staying, the proportional relationship of the two trajectories in the boundary interval is compared. Through this embodiment, the system can be compatible with trajectory data from multiple sources, and trajectories of different vehicle types, dotting frequencies, and dotting qualities can be more compatibly integrated into the same prediction system, with a higher tolerance for trajectory noise, and thus more accurately evaluate the red light duration of the embodiment of the present application, making the prediction more accurate.

[0043] In some embodiments, the number of valid trajectories is calculated according to the proportion of valid trajectories, and conditional filtering is performed on them to find out the parts that can be accurately predicted with confidence, such as requiring that the number of valid trajectories is greater than 250 and the data coverage ratio is greater than 38%.

[0044] The red light determination method provided in the embodiment of the present application utilizes the timestamps of the passage trajectory and the residence trajectory reaching the light, combined with the moment when the light turns green, to cross-validate and analyze the distribution of the green light duration and the red light duration within the cycle, thereby obtaining a high-precision red light duration.

[0045] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0046] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0047] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device obtains the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0048] The computer program instructions for performing the operation of the present invention can be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages. Computer-readable program instructions can be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). In certain embodiments, by utilizing the state information of computer-readable program instructions to customize electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLAs), the electronic circuits can execute computer-readable program instructions, thereby realizing various aspects of the present invention.

[0049] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0050] 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 device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0051] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are 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 implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0052] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of an instruction, and a part of the module, program segment or instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0053] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A method for determining the duration of a red light, wherein: include: Acquire sample data within a target time period, wherein the sample data includes a passing trajectory and a staying trajectory of a sample vehicle for a target traffic light within the target time period; A position distribution map within a cycle is formed for the sample data; and the red light duration of the target traffic light intersection within a specified time is determined based on the position distribution map within the cycle.

2. The method according to claim 1, wherein forming a periodic position distribution information graph for the sample data comprises: The time difference between the timestamp of each track and the moment when the red light of the traffic light wave to which it belongs switches to green light is used to generate a position distribution diagram within the cycle, wherein the horizontal axis of the position distribution diagram within the cycle is the time offset and the vertical axis is the number of tracks.

3. The method according to claim 1 determines the red light duration of the target traffic light intersection within a specified time based on the data sufficiency and time resolution of the position distribution map within the period.

4. According to the method of claim 3, the data sufficiency is used to represent the proportion of statistical intervals of non-zero trajectories in the total number of statistical intervals under a specific interval statistical length, and the time resolution is the maximum time difference of trajectories that can be counted in the same interval.

5. The method according to claim 4, wherein the data sufficiency is proportional to the statistical interval width, and the time resolution is inversely proportional to the statistical interval width.

6. The method according to claim 3, wherein determining the red light duration of the target traffic light intersection within a specified time based on the data sufficiency and time resolution of the position distribution map within the period comprises traversing the statistical interval and determining the red light duration of the target traffic light intersection within the specified time based on the number of passing trajectories and the number of resident trajectories in the statistical interval.

7. The method according to claim 6, wherein determining the red light duration of the target traffic light intersection within a specified time based on the number of trajectories comprises: According to the number of passing trajectories and the number of staying trajectories, it is determined whether the interval is a mainstream passing interval or a mainstream staying interval, and the boundary interval between passing and staying is determined, and the red and green durations within the interval are proportionally allocated to obtain the red light duration of the target traffic light intersection within the specified time.

8. The method according to claim 7, if the time resolution is not 1, then after determining the boundary interval between the passing and the staying, the proportional relationship between the two trajectories in the boundary interval is compared.

9. An electronic device, wherein: The method comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 8.

10. A computer program product comprising computer instructions, wherein: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images