Traffic signal notification method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a traffic signal notification method and device, equipment, a storage medium and a program product. The method is applied to an edge computing node, and comprises the following steps: screening at least two target vehicles to be notified of traffic signal information from a plurality of vehicles; obtaining vehicle positions of at least two target vehicles at multiple moments; predicting vehicle tracks of the at least two target vehicles at a plurality of future first moments according to the vehicle positions of the at least two target vehicles at the plurality of moments; according to the vehicle tracks and the vehicle sizes of the at least two target vehicles at the plurality of future first moments, predicting whether any target vehicle is shielded by another target vehicle at at least one future second moment in the plurality of future first moments so as to determine a shielded vehicle; and sending the traffic signal information to the shielded vehicle. According to the method provided by the embodiment of the invention, the accuracy of traffic signal notification and the information processing efficiency can be improved.

Description

Technical Field

[0001] This application belongs to the field of traffic safety technology, and in particular relates to a method, device, equipment, storage medium and program product for notifying traffic signals. Background Technology

[0002] Road traffic safety is a vital safeguard for people's lives and property. Therefore, accurately transmitting the real-time status of traffic lights to vehicles has become a key aspect of improving safety and traffic efficiency.

[0003] Current technology pushes traffic light information indiscriminately to all vehicles without assessing their actual needs. This not only creates unnecessary network load and information redundancy but also incurs unnecessary data processing overhead on the vehicle side, reducing the accuracy of traffic signal notification services. Furthermore, current technology does not address network latency during data transmission, resulting in significant delays in information transmission. Summary of the Invention

[0004] This invention provides a method, apparatus, device, storage medium, and program product for traffic signal notification, which can accurately identify obscured vehicles and accurately push information to obscured vehicles, thereby improving the accuracy of traffic signal notification services, avoiding information redundancy, and reducing information transmission latency.

[0005] In a first aspect, embodiments of the present invention provide a traffic signal notification method applied to an edge computing node, the method comprising: In response to multiple vehicles entering a target geographical area, at least two target vehicles to be notified of traffic signal information are selected from the multiple vehicles; The vehicle positions of the at least two target vehicles at multiple times are obtained from the on-board units of the at least two target vehicles, wherein the multiple times are the times after the at least two target vehicles enter the target geographical area; Based on the vehicle positions of the at least two target vehicles at multiple times, predict the vehicle trajectories of the at least two target vehicles at multiple future first moments; Based on the vehicle trajectories and vehicle sizes of the at least two target vehicles at multiple future first moments, predict whether any of the target vehicles will be occluded by another target vehicle at at least one future second moment in the multiple future first moments, so as to determine the occluded vehicle. The traffic signal information for at least one future second moment is sent to the obstructed vehicle, wherein the traffic signal information for the future first moment is determined based on the traffic light status information obtained from the roadside unit.

[0006] In one feasible implementation, the vehicle dimensions include vehicle length and vehicle width, the first target vehicle is one of the target vehicles, and the second target vehicle is one of the target vehicles that is different from the first target vehicle. The method further includes: Based on the vehicle position of the first target vehicle at the multiple future first moments and the length and width of the first target vehicle, determine the projection area of ​​the first target vehicle at the multiple future first moments; Based on the vehicle position of the second target vehicle at the plurality of future first moments and the projection area of ​​the first target vehicle at the plurality of future first moments, predict whether the second target vehicle will be occluded by the first target vehicle at at least one future second moment. If so, then the second target vehicle is determined to be the obscured vehicle.

[0007] In one feasible implementation, the projection region includes a first vertex, a second vertex, a third vertex, and a fourth vertex, and the method further includes: Subtract half the width of the target vehicle from the x-coordinate of the vehicle position of the first target vehicle at the multiple future first moments to obtain the x-coordinate of the first vertex and the x-coordinate of the third vertex. Add half the width of the target vehicle to the x-coordinate of the vehicle position of the first target vehicle at the multiple future first moments to obtain the x-coordinate of the second vertex and the x-coordinate of the fourth vertex. Add half the length of the target vehicle to the ordinate of the vehicle position of the first target vehicle at the multiple future first moments to obtain the ordinate of the first vertex and the ordinate of the second vertex. The ordinates of the first target vehicle at each of the multiple future first moments are subtracted by half the length of the target vehicle to obtain the ordinates of the third and fourth vertices.

[0008] In one feasible implementation, the method further includes: Determine whether the x-coordinate of the second target vehicle's position at at least one future second moment is greater than the x-coordinate of the first vertex and less than the x-coordinate of the second vertex, and whether the y-coordinate of the second target vehicle's position at at least one future second moment is greater than the y-coordinate of the third vertex and less than the y-coordinate of the first vertex.

[0009] In one feasible implementation, the method further includes: Geofencing technology is used to identify the multiple vehicles entering the target geographic area; Based on the driving direction and driving lane of the plurality of vehicles, at least two vehicles that require the traffic signal information are selected from the plurality of vehicles to obtain the at least two target vehicles.

[0010] In one feasible implementation, the method further includes: The vehicle trajectories of the at least two target vehicles are determined using the Kalman filter algorithm based on their vehicle positions at multiple times.

[0011] Secondly, embodiments of the present invention provide a traffic signal notification device, the device comprising: A filtering module is used to filter out at least two target vehicles from the multiple vehicles to be notified of traffic signal information in response to multiple vehicles entering the target geographical area. The location acquisition module is used to acquire the vehicle locations of the at least two target vehicles at multiple times from the vehicle-mounted units of the at least two target vehicles, wherein the multiple times are the times after the at least two target vehicles enter the target geographical area; The trajectory prediction module is used to predict the vehicle trajectories of the at least two target vehicles at multiple future first moments based on the vehicle positions of the at least two target vehicles at multiple moments. An occlusion prediction module is used to predict, based on the vehicle trajectories and vehicle sizes of the at least two target vehicles at multiple future first moments, whether any of the target vehicles will be occluded by another target vehicle at at least one future second moment in the multiple future first moments, so as to determine the occluded vehicle. The transmitting module is used to transmit the traffic signal information of at least one future second moment to the obstructed vehicle, wherein the traffic signal information of the future first moment is determined based on the traffic light status information obtained from the roadside unit.

[0012] Thirdly, embodiments of the present invention provide a traffic signal notification device, the device comprising: The processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the traffic signal notification method as described in the first aspect.

[0013] Fourthly, embodiments of the present invention provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the traffic signal notification method as described in the first aspect.

[0014] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the traffic signal notification method as described in the first aspect.

[0015] The traffic signal notification method, apparatus, device, storage medium, and program product of this invention can predict whether any of the target vehicles will be obstructed by another target vehicle in a future first moment based on the vehicle trajectories and vehicle sizes of at least two target vehicles. This accurately predicts which vehicles may be obstructed in the future, thus identifying the obstructed vehicles that actually need traffic signal information. The traffic signal information for the future first moment is then sent to the obstructed vehicles, eliminating the need to send traffic signal information to all vehicles, improving the accuracy of traffic signal notification, reducing information redundancy, and further reducing resource waste in sending traffic signal information. Furthermore, the collaborative structure between edge computing nodes, on-board units, and roadside units improves the efficiency of information processing and transmission, and reduces the latency of traffic signal information transmission to vehicles. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a traffic signal notification method according to an embodiment of this application is shown; Figure 2 A schematic diagram of the process for determining an obstructed vehicle according to an embodiment of this application is shown; Figure 3 This illustration shows a flowchart of determining a projection area according to an embodiment of this application; Figure 4 This illustration shows a schematic diagram of a collaborative architecture provided in an embodiment of this application; Figure 5 A schematic diagram of the structure of a traffic signal notification device provided in an embodiment of this application is shown; Figure 6 A schematic diagram of the hardware structure of the traffic signal notification device provided in an embodiment of this application is shown. Detailed Implementation

[0018] The features and exemplary embodiments of various aspects of the present invention will now be described in detail. To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely intended to explain the present invention and not to limit the present invention. For those skilled in the art, the present invention can be practiced without some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present invention by illustrating examples of the invention.

[0019] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0020] For traffic signal notification services, existing technologies generally employ a "broadcast" push strategy, which sends a uniform set of signal data to every vehicle within the coverage area, regardless of the vehicle's specific location, route, or immediate needs. This extensive management model first leads to a significant waste of communication resources, causing the limited vehicle network channels to be filled with a large amount of redundant information that has no practical value to the receiving vehicles, resulting in unnecessary network load.

[0021] Furthermore, on the vehicle terminal side, the onboard system has to receive, decode, and process this signal data that is unrelated to the vehicle itself. This undoubtedly consumes valuable local computing power and storage resources, resulting in high overhead for invalid data processing. The direct consequence is that the accuracy and practicality of traffic signal notification services are greatly reduced, failing to provide truly personalized critical decision support for drivers or autonomous driving systems.

[0022] Furthermore, existing technical solutions are often based on ideal network models, neglecting the dynamically changing network conditions in real-world environments. In other words, existing solutions do not truly address network latency in information transmission, resulting in the inability to achieve stable and timely low-latency transmission of critical road status information. This significant information transmission latency, in high-speed traffic scenarios, severely weakens the effectiveness of information and may even lead to safety hazards.

[0023] To address the problems of the prior art, embodiments of the present invention provide a method, apparatus, device, storage medium, and program product for notifying traffic signals.

[0024] The traffic signal notification method provided in the embodiments of the present invention will be introduced first below.

[0025] Figure 1 A schematic flowchart of a traffic signal notification method according to an embodiment of this application is shown. Figure 1 As shown, this method is applied to an edge computing node and may include the following steps: S101 to S105.

[0026] S101, In response to multiple vehicles entering a target geographical area, select at least two target vehicles from the multiple vehicles to be notified of traffic signal information.

[0027] In this embodiment, the target geographic area refers to a geographic area on the road surface covered by a certain intersection or traffic light at that intersection. The target geographic area can be displayed on a map. The target geographic area is used to determine whether a vehicle is approaching the intersection or traffic light. If a vehicle enters the target geographic area, it means that the vehicle may receive information corresponding to the traffic light at that intersection. The shape of the target geographic area includes, but is not limited to, rectangles, circles, and any regular or irregular shape. For example, the target geographic area can be a circular area with the center of the intersection as the center and a preset distance as the radius. The "preset distance" can be set by the user.

[0028] In some embodiments, S101 may include: Using geofencing technology, multiple vehicles entering the target geographic area are identified; based on the driving direction and lane of the multiple vehicles, at least two vehicles requiring traffic signal information are selected from the multiple vehicles to determine whether any vehicles have entered the target geographic area.

[0029] In this embodiment, geofencing is a location-based service technology that constructs a virtual area boundary, specifically using the boundary of the target geographic area as the virtual area boundary on the map. By using geofencing and the location of each vehicle, it can be determined whether a vehicle has entered the target geographic area. The location of each vehicle can be detected by a roadside unit and sent to the edge computing node, or the specific vehicle location can be sent to the edge computing node by an onboard unit within the vehicle. A "roadside unit" refers to a module deployed on infrastructure along both sides of a road or on a traffic light, used to collect traffic signal information. In some embodiments, the roadside unit can be deployed on the guardrail of a traffic light.

[0030] In this embodiment, "traffic signal information" refers to the collection of all data and states related to traffic lights. Traffic signal information may include the current directional indication state, the remaining time corresponding to the current directional indication state, the next directional indication state, and the duration of the next directional indication state. The directional indication state may include multiple indication states for different directions, such as straight ahead, left turn, right turn, and U-turn. The indication state may include red, green, and yellow lights. The current directional indication state refers to the indication state of the traffic light at the current moment. The remaining time corresponding to the current directional indication state refers to the remaining time the traffic light will maintain the current directional indication state; in other words, how much longer until the directional indication state changes. The next directional indication state refers to the directional indication state the traffic light will switch to after the current directional indication state. The duration of the next directional indication state refers to the total display time of the next directional indication state. It should be noted that traffic signal information can be switched at any time.

[0031] In some embodiments, the roadside unit can also be used to collect the location of individual vehicles.

[0032] In this embodiment, after identifying multiple vehicles entering the target geographical area, it is also necessary to identify at least two vehicles that require traffic signal information. This is because some vehicles have already moved in the direction of exiting the intersection or traffic light, so these vehicles do not need to obtain the traffic signal information corresponding to that intersection or traffic light. In this embodiment, it is also necessary to filter out at least two vehicles that require the traffic signal information from the multiple vehicles based on their travel direction and lane. Here, the at least two vehicles that require the traffic signal information from the multiple vehicles are referred to as target vehicles. For example, if a vehicle's travel direction is close to the intersection or traffic light, and the vehicle's lane is also close to the intersection or traffic light, then that vehicle is a target vehicle.

[0033] In other embodiments, at least two target vehicles can be identified based on the travel direction or lane of multiple vehicles. For example, if a vehicle is traveling towards an intersection or traffic light, then that vehicle is a target vehicle. If a vehicle is traveling in a lane close to an intersection or traffic light, then that vehicle is a target vehicle.

[0034] It should be noted that in some embodiments, assuming a road has driving lanes closer to intersections or traffic lights and driving lanes farther away from intersections or traffic lights, in an emergency, a vehicle that should be traveling in the driving lane closer to the intersection or traffic light might briefly travel in the driving lane farther away from the intersection or traffic light due to overtaking. In this case, the vehicle is identified as the target vehicle. The example shown in this embodiment avoids erroneously missing target vehicles based solely on driving lanes.

[0035] In this embodiment, the vehicle's driving direction and driving lane can be detected by the roadside unit and sent to the edge computing unit, or the driving direction and driving lane can be sent directly to the edge computing unit by the vehicle's on-board unit. The driving lane-related information can be pre-stored in the edge computing unit.

[0036] In this embodiment, the edge computing unit is essentially a small computer or server, typically deployed in an edge network along the road to execute the methods provided in this application. This edge computing unit is located close to vehicles and traffic lights and possesses powerful data processing capabilities. The edge computing unit enables the rapid implementation of the methods provided in this application and can quickly send traffic signal information to the vehicles that actually need it, thereby improving the service efficiency of traffic signals.

[0037] In this embodiment, the in-vehicle unit refers to a unit integrated into the vehicle, used to receive traffic signal information from the edge computing unit and intuitively display the information to the driver through augmented reality head-up display (AR-HUD), in-vehicle display screen, or voice broadcast. In this embodiment, the in-vehicle unit can support multimodal broadcasting methods such as voice and images, thereby providing the driver with a more intuitive and convenient way to obtain information and improving the driving experience.

[0038] S102. Obtain the vehicle positions of at least two target vehicles at multiple times from the on-board units of at least two target vehicles. The multiple times are the times after the at least two target vehicles enter the target geographical area.

[0039] In this embodiment, after determining at least two target vehicles in S101, it is also necessary to obtain the vehicle positions of at least two target vehicles after they enter the target geographical area, that is, the vehicle positions at multiple times. Here, multiple times refers to the times after the target vehicles enter the target geographical area.

[0040] In some embodiments, the vehicle position of the target vehicle at multiple times can be obtained by roadside unit detection or by the vehicle-mounted unit of the target vehicle. While obtaining the vehicle position of the target vehicle at multiple times, the roadside unit or the vehicle-mounted unit sends the vehicle position of the target vehicle at multiple times to the edge computing unit.

[0041] S103. Based on the vehicle positions of at least two target vehicles at multiple times, predict the vehicle trajectories of at least two target vehicles at multiple future first moments.

[0042] In some embodiments, S103 may include: using a Kalman filter algorithm to predict the vehicle trajectories of at least two target vehicles at multiple future first moments based on the vehicle positions of at least two target vehicles at multiple moments.

[0043] In this embodiment, the "first future moment" refers to a point in time after the "multiple moments" mentioned earlier. In other words, the first future moment can be a moment in the future that has not yet begun, i.e., a moment that has not yet arrived. The Kalman filter algorithm is a powerful algorithm used to extract the optimal and most accurate estimate from multiple information sources containing uncertainty. Specifically, in this application, the Kalman filter algorithm is used to predict the vehicle trajectories of at least two target vehicles at multiple future first moments based on their vehicle positions at multiple moments. The following section uses a single target vehicle as an example to illustrate how the Kalman filter algorithm can predict the vehicle trajectory of a target vehicle at multiple future first moments.

[0044] First, a motion model describing the target vehicle is established. In the embodiments of this application, trajectory prediction is performed on vehicles traveling towards intersections or traffic lights. It is understood that vehicles traveling towards intersections or traffic lights typically need to decelerate after entering the target geographical area to comply with relevant traffic safety regulations. They may also initially maintain a constant speed before decelerating. In congested traffic conditions, there may be multiple alternating accelerations and decelerations, or even intermittent stops. In some embodiments, a deceleration motion model, a model that initially maintains a constant speed before decelerating, and a composite model encompassing frequent acceleration / deceleration and stationary behavior can be used as the motion model describing the target vehicle. The choice of which motion model to describe the target vehicle is based on the actual conditions of a specific road segment can be determined by referring to the traffic flow information accumulated at that intersection in the past.

[0045] Next, after establishing a motion model describing the target vehicle, the vehicle position at the first of multiple time points is taken as the initial position. Here, any time point among these multiple time points is referred to as a known time point. It's easy to see that the first future time point will be a time point after the known time point. Based on the initial position, the following steps are iteratively executed: step one to step two, until the position of the last known time point is predicted. When initially executing steps one and two, the current position is the initial position.

[0046] The first step is to predict the vehicle's position at the next moment based on the motion model describing the target vehicle. Here, the predicted vehicle position at the next moment, based on the motion model, is called the predicted position, and the vehicle positions at multiple moments obtained earlier are called the actual positions. It is also necessary to determine the uncertainty of the motion model describing the target vehicle. In this embodiment, the speed at the current position can be obtained from the vehicle positions at multiple moments obtained earlier. Specifically, calculus can be used to calculate the speed of the target vehicle at multiple moments and the speed at each actual position, thereby obtaining the speed at the current position.

[0047] The second step involves comprehensively considering the uncertainty of the motion model describing the target vehicle, the noise in acquiring the actual position, fusing the actual position and the predicted position, to obtain the optimal predicted position for the next moment. The optimal predicted position is then used as the current position, and the process returns to the first step.

[0048] Then, based on the motion model describing the target vehicle, the vehicle position of the target vehicle at multiple future first moments is predicted.

[0049] S104. Based on the vehicle trajectories and vehicle sizes of at least two target vehicles at multiple future first moments, predict whether any target vehicle will be occluded by another target vehicle at at least one future second moment in the multiple future first moments, so as to determine the occluded vehicle.

[0050] In some embodiments, a vehicle traveling ahead may obstruct the view of a driver in a following vehicle due to its height, preventing the driver in the following vehicle from seeing traffic lights. Here, the target vehicle whose view is obstructed is called the "obstructed vehicle," and the vehicle causing the obstruction is called the "blocking vehicle." Multiple vehicles may exist between the blocking vehicle and the obstructed vehicle, or there may be no vehicles between them. It is clear that the obstructed vehicle is the one that truly needs traffic signal information. This embodiment of the application sends traffic signal information to the obstructed vehicle, allowing the driver in the obstructed vehicle to obtain traffic signal information in a timely manner, improving both the driving experience and driving safety.

[0051] In this embodiment, the future second moment refers to one of a plurality of future first moments, and the future second moment specifically refers to the moment when the driver's view of the target vehicle is obstructed, or the moment when the obstructed vehicle appears. Vehicle size refers to information related to the size or dimensions of the vehicle, specifically, vehicle size includes vehicle length, vehicle width, and vehicle height.

[0052] In S104, based on the vehicle trajectories and vehicle sizes of at least two target vehicles at multiple future first moments, it can be predicted whether any one of the at least two target vehicles will be occluded by the other target vehicle, thereby identifying the occluded vehicle.

[0053] Figure 2 A schematic diagram illustrating the process of determining an obscured vehicle according to an embodiment of this application is shown.

[0054] As shown in the figure, in some embodiments, S104 may include the following steps: S201 to S203.

[0055] S201. Based on the vehicle position of the first target vehicle at multiple future first moments and the length and width of the first target vehicle, determine the projection area of ​​the first target vehicle at multiple future first moments.

[0056] In this embodiment, the first target vehicle is one of at least two target vehicles, and the second target vehicle is one of the target vehicles that is different from the first target vehicle. In other words, the second target vehicle is the other of at least two target vehicles.

[0057] In some embodiments, the first target vehicle can be determined based on its vehicle height and a preset obstruction height. The preset obstruction height is a user-defined threshold used to determine whether the target vehicle might obstruct the view of the driver in a target vehicle traveling behind it. For example, the preset obstruction height can be set to 1.62 meters, and target vehicles with a height greater than 1.62 meters are designated as the first target vehicle. It is easy to see that the first target vehicle can be a relatively tall vehicle.

[0058] In this embodiment, the projection area refers to the area formed due to the occlusion of the first target vehicle. If a vehicle traveling behind the first target vehicle enters the projection area, it indicates that the first target vehicle has occluded the vehicle traveling behind it.

[0059] Figure 3 A schematic diagram of the process for determining the projection area provided in one embodiment of this application is shown.

[0060] As shown in the figure, in some embodiments, S201 may include the following steps: S301 to S304.

[0061] S301. Subtract half the width of the target vehicle from the x-coordinate of the vehicle position of the first target vehicle at multiple future first moments to obtain the x-coordinate of the first vertex at multiple future first moments and the x-coordinate of the third vertex at multiple future first moments.

[0062] S302. Add half the width of the target vehicle to the x-coordinate of the first target vehicle's position at multiple future first moments to obtain the x-coordinate of the second vertex at multiple future first moments and the x-coordinate of the fourth vertex at multiple future first moments.

[0063] S303. Add half the length of the target vehicle to the ordinate of the vehicle position of the first target vehicle at multiple future first moments to obtain the ordinate of the first vertex at multiple future first moments and the ordinate of the second vertex at multiple future first moments.

[0064] S304. Subtract half the length of the target vehicle from the ordinate of the vehicle position of the first target vehicle at multiple future first moments to obtain the ordinate of the third vertex at multiple future first moments and the ordinate of the fourth vertex at multiple future first moments.

[0065] In this embodiment, a Cartesian coordinate system is established on a map or road surface. The line containing the width of a target vehicle is used as the horizontal axis (X-axis), and the line containing the length of the target vehicle is used as the vertical axis (Y-axis). In other embodiments, the line containing the length of the target vehicle may be used as the horizontal axis, and the line containing the width of the target vehicle may be used as the vertical axis. The method of establishing the Cartesian coordinate system in this application is not limited in any way.

[0066] In this embodiment, the points and coordinates are defined by a Cartesian coordinate system established from the vertical top view of the target vehicle. In this Cartesian coordinate system, the positive X-axis points to the right side of the vehicle, and the positive Y-axis points to the front of the vehicle. The vertical top-view projection of the first target vehicle on the ground is taken as the projection area of ​​the first target vehicle, and the center point of the vertical top-view projection of the target vehicle on the ground is taken as the vehicle position. This yields the coordinates of the respective vehicle positions of the first and second target vehicles. In this embodiment, the projection area of ​​the first target vehicle is approximately rectangular, so it is considered a rectangle. A rectangle has four vertices; therefore, the upper left vertex of the projection area is called the first vertex, the upper right vertex is called the second vertex, the lower left vertex is called the third vertex, and the lower right vertex is called the fourth vertex. It should be noted that in this embodiment, "upper left," "upper right," "lower left," and "lower right" are all based on the vertical top view of the target vehicle.

[0067] In this embodiment, step S301 above can obtain the abscissas of the first and third vertices of the projection region at multiple future first moments. Specifically, the abscissas of the first and third vertices of the projection region at multiple future first moments are: . Represents any future first moment, The x-coordinate represents the position of the first target vehicle at the first future moment. Represents any future first moment, This indicates the width of the first target vehicle.

[0068] In this embodiment, step S302 above can obtain the abscissas of the second and fourth vertices of the projection region at multiple future first moments. Specifically, the abscissas of the first and third vertices of the projection region at multiple future first moments are: .

[0069] In this embodiment, step S303 above can obtain the ordinates of the first and second vertices of the projection region at multiple future first moments. Specifically, the ordinates of the first and second vertices of the projection region at multiple future first moments are: . The vertical coordinate represents the position of the first target vehicle at the first future moment. This indicates the length of the first target vehicle.

[0070] In this embodiment, S304 above can obtain the ordinates of the third and fourth vertices of the projection region at multiple future first moments. Specifically, the ordinates of the third and fourth vertices of the projection region at multiple future first moments are: .

[0071] Through steps S301 to S304 above, the coordinates of the first vertex, second vertex, third vertex, and fourth vertex at the first future moment can be obtained respectively, so as to subsequently determine the occluded vehicle based on the projection area. The coordinates of the first vertex at the first future moment are ( , The coordinates of the second vertex at the first future moment are ( , The coordinates of the third vertex at the first future moment are ( , The coordinates of the fourth vertex at the first future moment are ( , ).

[0072] S202. Based on the vehicle position of the second target vehicle at multiple future first moments and the projection area of ​​the first target vehicle at multiple future first moments, predict whether the second target vehicle will be occluded by the first target vehicle at at least one future second moment.

[0073] In this embodiment, it is determined whether there is at least one future second moment among multiple future first moments, at which time the second target vehicle is obscured by the first target vehicle.

[0074] In some embodiments, S202 may include: determining whether the abscissa of the second target vehicle's position at at least one future second moment is greater than the abscissa of the first vertex and less than the abscissa of the second vertex, and whether the ordinate of the second target vehicle's position at at least one future second moment is greater than the ordinate of the third vertex and less than the ordinate of the first vertex.

[0075] In this embodiment, the condition for determining or predicting occlusion is: whether there is a future second moment in time in which the vehicle position of the second target vehicle overlaps with the projection area of ​​the first target vehicle.

[0076] Specifically, if there exists at least one future second moment... At the same time satisfy and If the second target vehicle enters the projection area of ​​the first target vehicle, it is determined that the first target vehicle is obscuring the second target vehicle. Indicates any second future moment. The x-coordinate represents the position of the first target vehicle at the second future time. The vertical coordinate represents the position of the first target vehicle at the second future time. The x-coordinate represents the position of the first target vehicle at the second future time. The vertical coordinate represents the position of the first target vehicle at the second future moment.

[0077] In this embodiment, S201 to S203 will be executed cyclically at a preset frequency until at least one obscured vehicle and its corresponding future second moment are determined.

[0078] S203. If so, determine that the second target vehicle is the obscured vehicle.

[0079] In this example, if it is determined in S202 that the second target vehicle will be obscured at a second time in the future, then the second target vehicle is determined to be the obscured vehicle.

[0080] It should be noted that S103 is used to predict the trajectory of vehicles that are obscured, while the driver or autonomous driving technology of vehicles that are not obscured can directly obtain traffic signal information through the naked eye or roadside units. Therefore, for vehicles that are not obscured, it is not necessary to predict their trajectory.

[0081] S105. At least one future second moment of traffic signal information is sent to the obstructed vehicle, and the future first moment of traffic signal information is determined based on the traffic light status information obtained from the roadside unit.

[0082] In this embodiment, after identifying the obscured vehicle, at least one future second-time traffic signal message needs to be sent to the obscured vehicle. This ensures that the driver or autonomous driving system in the obscured vehicle can still be aware of the traffic signal information at the time of obstruction, improving the driving experience and safety. This embodiment accurately predicts potentially obscured vehicles and sends the corresponding traffic signal information to them, eliminating the need to send traffic signal information to all vehicles at the intersection or near traffic lights. This improves the accuracy of traffic signal notification, reduces information redundancy, and further minimizes the waste of resources in sending traffic signal information.

[0083] Through steps S101 to S105, based on the vehicle trajectories and dimensions of the at least two target vehicles, it is possible to predict whether any of the target vehicles will be obstructed by the other target vehicle at a future first moment. This accurately predicts which vehicles may be obstructed in the future, thus identifying the obstructed vehicles that actually require traffic signal information. The traffic signal information for the future first moment is then sent to the obstructed vehicles, eliminating the need to send traffic signal information to all vehicles, improving the accuracy of traffic signal notification, reducing information redundancy, and further reducing the waste of resources in sending traffic signal information. Furthermore, the collaborative structure between edge computing nodes, on-board units, and roadside units improves the efficiency of information processing and transmission, and reduces the latency of traffic signal information transmission to vehicles.

[0084] Figure 4 A schematic diagram of a collaborative architecture provided in an embodiment of this application is shown.

[0085] As shown in the figure, edge computing units, vehicle-mounted units, and roadside units work together to form a vehicle-edge collaborative architecture. In this "vehicle-edge collaborative architecture," "vehicle" refers to the vehicle-mounted unit, and "edge" refers to the edge computing unit and roadside unit. In this embodiment, the roadside unit may include a camera device for recognizing traffic signal information, specifically the state of traffic lights at various times. The roadside unit can send the traffic signal information to the edge computing node. The edge computing node can receive vehicle information and map information. Vehicle information may include the vehicle's size and its position, speed, and direction at various times. It should be noted that "various vehicles" may include larger vehicles. Map information may include lane lines and various road information on the target geographic area. After receiving the vehicle size, position, speed, and direction at various times, and map information, the edge computing node can use geofencing technology to identify multiple vehicles entering the target geographic area. It can also predict whether any target vehicle will be occluded by another target vehicle at at least in one of the multiple future first moments based on the vehicle trajectories and vehicle sizes of at least two target vehicles at multiple future first moments, thus identifying the occluded vehicle. Edge computing nodes can filter information and predict occlusion using geofencing technology and occlusion prediction. They can then push traffic signal information for the time the vehicle is blocked to the blocked vehicle, thus achieving information push.

[0086] After receiving traffic signal information pushed by the edge computing node, the vehicle-mounted unit will intuitively display the information to the driver through augmented reality head-up display (AR-HUD), in-vehicle display screen, or voice broadcast. The data transmission and respective functions between the edge computing unit, the vehicle-mounted unit, and the roadside unit are described in the various embodiments above, and will not be repeated here.

[0087] It should also be noted that in this embodiment, the edge computing unit, vehicle-mounted unit, and roadside unit transmit data to each other via a 5G-Advanced (5G-A) network. The high bandwidth and low latency of the 5G-A network ensure real-time transmission and reliable delivery of traffic signal information, further reducing transmission latency. The 5G-A network can "sleep deeply" under low load and operate efficiently under high load, thereby significantly reducing carbon emissions and achieving deep energy savings.

[0088] Figure 5 A schematic diagram of a traffic signal notification device according to an embodiment of this application is shown. As shown, the traffic signal notification device 500 may include a filtering module 510, a location acquisition module 520, a trajectory prediction module 530, an occlusion prediction module 540, and a sending module 550.

[0089] The filtering module 510 is used to filter out at least two target vehicles from the multiple vehicles to be notified of traffic signal information in response to multiple vehicles entering the target geographical area.

[0090] The location acquisition module 520 is used to acquire the vehicle positions of the at least two target vehicles at multiple times from the vehicle-mounted units of the at least two target vehicles, wherein the multiple times are the times after the at least two target vehicles enter the target geographical area.

[0091] The trajectory prediction module 530 is used to predict the vehicle trajectories of the at least two target vehicles at multiple future first moments based on the vehicle positions of the at least two target vehicles at multiple moments.

[0092] The occlusion prediction module 540 is used to predict, based on the vehicle trajectories and vehicle sizes of the at least two target vehicles at multiple future first moments, whether any of the target vehicles will be occluded by another target vehicle at at least one future second moment in the multiple future first moments, so as to determine the occluded vehicle.

[0093] The transmitting module 550 is used to transmit the traffic signal information of at least one future second moment to the obstructed vehicle, wherein the traffic signal information of the future first moment is determined based on the traffic light status information obtained from the roadside unit.

[0094] In some embodiments, the vehicle dimensions include vehicle length and vehicle width, the first target vehicle is one of the target vehicles, the second target vehicle is one of the target vehicles that is different from the first target vehicle, and the occlusion prediction module 540 can also be used for: Based on the vehicle position of the first target vehicle at the multiple future first moments and the length and width of the first target vehicle, determine the projection area of ​​the first target vehicle at the multiple future first moments; Based on the vehicle position of the second target vehicle at the plurality of future first moments and the projection area of ​​the first target vehicle at the plurality of future first moments, predict whether the second target vehicle will be occluded by the first target vehicle at at least one future second moment. If so, then the second target vehicle is determined to be the obscured vehicle.

[0095] In some embodiments, the projection region includes a first vertex, a second vertex, a third vertex, and a fourth vertex, and the occlusion prediction module 540 can also be used for: Subtract half the width of the target vehicle from the x-coordinate of the vehicle position of the first target vehicle at the multiple future first moments to obtain the x-coordinate of the first vertex at the multiple future first moments and the x-coordinate of the third vertex at the multiple future first moments. Add half the width of the target vehicle to the x-coordinate of the vehicle position of the first target vehicle at the multiple future first moments to obtain the x-coordinate of the second vertex at the multiple future first moments and the x-coordinate of the fourth vertex at the multiple future first moments. Add half the length of the target vehicle to the ordinate of the vehicle position of the first target vehicle at the multiple future first moments to obtain the ordinate of the first vertex at the multiple future first moments and the ordinate of the second vertex at the multiple future first moments. The vertical coordinates of the first target vehicle at the vehicle position at the multiple future first moments are obtained by subtracting half the length of the target vehicle from the vertical coordinates of the vehicle position at the multiple future first moments, and the vertical coordinates of the third vertex at the multiple future first moments.

[0096] In some embodiments, the occlusion prediction module 540 can also be used for: Determine whether the x-coordinate of the second target vehicle's position at at least one future second moment is greater than the x-coordinate of the first vertex and less than the x-coordinate of the second vertex, and whether the y-coordinate of the second target vehicle's position at at least one future second moment is greater than the y-coordinate of the third vertex and less than the y-coordinate of the first vertex.

[0097] In some embodiments, the filtering module 510 can also be used for: Geofencing technology is used to identify the multiple vehicles entering the target geographic area; Based on the driving direction and driving lane of the plurality of vehicles, at least two vehicles that require the traffic signal information are selected from the plurality of vehicles to obtain the at least two target vehicles.

[0098] In some embodiments, the trajectory prediction module 530 can also be used for: The Kalman filter algorithm is used to predict the vehicle trajectories of the at least two target vehicles at multiple future first moments based on their vehicle positions at multiple times.

[0099] Figure 6 A schematic diagram of the hardware structure of the traffic signal notification device provided in an embodiment of this application is shown.

[0100] The traffic signal notification device may include a processor 601 and a memory 602 storing computer program instructions.

[0101] Specifically, the processor 601 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0102] Memory 602 may include mass storage for data or instructions. For example, and not limitingly, memory 602 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 602 may include removable or non-removable (or fixed) media, or memory 602 may be non-volatile solid-state memory. Memory 602 may be internal or external to the integrated gateway disaster recovery device.

[0103] Memory 602 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0104] The processor 601 reads and executes computer program instructions stored in the memory 602 to achieve... Figure 1 The traffic signal notification method in the illustrated embodiment.

[0105] In one example, the traffic signal notification device may also include a communication interface 603 and a bus 604. As shown in the figure, the processor 601, memory 602, and communication interface 603 are connected via the bus 604 and communicate with each other.

[0106] The communication interface 603 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of the present invention.

[0107] Bus 604 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 604 may include one or more buses. While specific buses are described and illustrated in embodiments of the invention, the invention contemplates any suitable bus or interconnect.

[0108] The traffic signal notification device can execute the online data traffic billing method in this embodiment of the invention based on currently blocked spam text messages and text messages reported by users, thereby achieving a combination of... Figure 1 and Figure 2 Describes the methods for notifying traffic signals.

[0109] Furthermore, in conjunction with the traffic signal notification methods in the above embodiments, this invention can be implemented using a computer storage medium. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the traffic signal notification methods in the above embodiments.

[0110] This application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the traffic signal notification methods described in the above embodiments.

[0111] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0112] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0113] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0114] The aspects of this disclosure have been described above 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 in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer 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 these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0115] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A traffic signal notification method characterized by, The method is applied to an edge computing node, and the method comprises: In response to a plurality of vehicles entering a target geographical area, screening at least two target vehicles to be notified of traffic signal information from the plurality of vehicles; Obtaining vehicle positions of the at least two target vehicles at a plurality of time instants from on-board units of the at least two target vehicles, the plurality of time instants being time instants after the at least two target vehicles enter the target geographical area; Predicting vehicle trajectories of the at least two target vehicles at a plurality of future first time instants according to the vehicle positions of the at least two target vehicles at the plurality of time instants; Predicting whether any of the target vehicles is blocked by another of the target vehicles at at least one future second time instant in the plurality of future first time instants according to the vehicle trajectories of the at least two target vehicles at the plurality of future first time instants and vehicle sizes, to determine a blocked vehicle; Sending traffic signal information of the at least one future second time instant to the blocked vehicle, the traffic signal information of the future first time instant being determined based on signal light state information obtained from a road side unit.

2. The traffic signal notification method according to claim 1, characterized by, The vehicle sizes comprise a vehicle length and a vehicle width, a first target vehicle is one of the target vehicles, a second target vehicle is one of the target vehicles and different from the first target vehicle, and the predicting whether any of the target vehicles is blocked by another of the target vehicles at at least one future second time instant in the plurality of future first time instants according to the vehicle trajectories of the at least two target vehicles at the plurality of future first time instants and vehicle sizes, to determine a blocked vehicle comprises: Determining projection areas of the first target vehicle at the plurality of future first time instants according to the vehicle positions of the first target vehicle at the plurality of future first time instants and the vehicle length and the vehicle width of the first target vehicle; Predicting whether the second target vehicle is blocked by the first target vehicle at the at least one future second time instant according to the vehicle positions of the second target vehicle at the plurality of future first time instants and the projection areas of the first target vehicle at the plurality of future first time instants; If yes, determining that the second target vehicle is the blocked vehicle.

3. The traffic signal notification method according to claim 2, characterized by, The projection areas comprise a first vertex, a second vertex, a third vertex and a fourth vertex, and the determining the projection areas of the first target vehicle at the plurality of future first time instants according to the vehicle positions of the first target vehicle at the plurality of future first time instants and the vehicle length and the vehicle width of the first target vehicle comprises: Subtracting half of the vehicle width of the target vehicle from the abscissa of the vehicle position of the first target vehicle at the plurality of future first time instants to obtain the abscissa of the first vertex at the plurality of future first time instants and the abscissa of the third vertex at the plurality of future first time instants; Adding half of the vehicle width of the target vehicle to the abscissa of the vehicle position of the first target vehicle at the plurality of future first time instants to obtain the abscissa of the second vertex at the plurality of future first time instants and the abscissa of the fourth vertex at the plurality of future first time instants; adding the longitudinal coordinate of the vehicle position of the first target vehicle at the plurality of future first time instants to half of the length of the target vehicle to obtain the longitudinal coordinate of the first vertex at the plurality of future first time instants and the longitudinal coordinate of the second vertex at the plurality of future first time instants; subtracting the longitudinal coordinate of the vehicle position of the first target vehicle at the plurality of future first time instants from half of the length of the target vehicle to obtain the longitudinal coordinate of the third vertex at the plurality of future first time instants and the longitudinal coordinate of the fourth vertex at the plurality of future first time instants.

4. The traffic signal notification method according to claim 3, characterized by, The predicting whether the second target vehicle is occluded by the first target vehicle at the at least one future second time instant according to the vehicle position of the second target vehicle at the plurality of future first time instants and the projection area of the first target vehicle at the plurality of future first time instants comprises: judging whether the horizontal coordinate of the vehicle position of the second target vehicle at the at least one future second time instant is greater than the horizontal coordinate of the first vertex and less than the horizontal coordinate of the second vertex, and the longitudinal coordinate of the vehicle position of the second target vehicle at the at least one future second time instant is greater than the longitudinal coordinate of the third vertex and less than the longitudinal coordinate of the first vertex.

5. The traffic signal notification method according to claim 1, wherein The screening at least two target vehicles to be notified of traffic signal information from a plurality of vehicles in response to the plurality of vehicles entering a target geographic area comprises: determining the plurality of vehicles entering the target geographic area by a geofencing technology; screening at least two vehicles needing the traffic signal information from the plurality of vehicles according to the driving direction and driving lane of the plurality of vehicles to obtain the at least two target vehicles.

6. The traffic signal notification method according to claim 1, wherein The predicting vehicle trajectories of the at least two target vehicles at a plurality of future first time instants according to vehicle positions of the at least two target vehicles at a plurality of time instants comprises: predicting the vehicle trajectories of the at least two target vehicles at the plurality of future first time instants by a Kalman filtering algorithm according to the vehicle positions of the at least two target vehicles at the plurality of time instants.

7. A traffic signal notification device, characterized by The device comprises: a screening module configured to screen at least two target vehicles to be notified of traffic signal information from a plurality of vehicles in response to the plurality of vehicles entering a target geographic area; a position acquisition module configured to acquire vehicle positions of the at least two target vehicles at a plurality of time instants from vehicle-mounted units of the at least two target vehicles, the plurality of time instants being time instants after the at least two target vehicles enter the target geographic area; a trajectory prediction module configured to predict vehicle trajectories of the at least two target vehicles at a plurality of future first time instants according to the vehicle positions of the at least two target vehicles at the plurality of time instants; an occlusion prediction module configured to predict whether any of the target vehicles is occluded by another of the target vehicles at at least one future second time instant of the plurality of future first time instants according to the vehicle trajectories of the at least two target vehicles at the plurality of future first time instants and vehicle sizes to determine an occluded vehicle. The sending module is configured to send the traffic signal information of the at least one future second time to the blocked vehicle, and the traffic signal information of the future first time is determined based on signal lamp state information obtained from a road side unit.

8. A traffic signal notification device, characterized by, The device comprises a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the traffic signal notification method according to any one of claims 1-7.

9. A computer storage medium, characterized in that The computer storage medium stores computer program instructions, and the computer program instructions are executed by the processor to implement the traffic signal notification method according to any one of claims 1-7.

10. A computer program product, characterised in that, The computer program is executed by the processor to implement the traffic signal notification method according to any one of claims 1-7.

Images