Vehicle driving guidance method and system in the scenario of pedestrians crossing the road at a road section

Abstract

The present application relates to the technical field of traffic control, and discloses a vehicle driving guidance method and system in the context of pedestrians crossing the road on a road section. Among them, the method includes: responding to a preset warning line trigger signal, determining a target vehicle, and real-time obtaining its position, speed, and information on the behavior characteristics of pedestrians within the pedestrian crossing area of the road section; finding the target pedestrian closest to the warning line, and determining a potential intersection point in combination with the positions of both parties; respectively calculating the expected times for the target vehicle and the target pedestrian to reach the intersection point based on the relevant position and speed information, and determining a reserved safety time; judging whether the pedestrian's expected time is greater than the vehicle's expected time, if so, adopting a first strategy to obtain a first safe speed, and obtaining a first guidance speed to guide the vehicle; if not, adopting a second strategy to obtain a second safe speed, and obtaining a second guidance speed to guide the vehicle. This method can enable the vehicle and the pedestrian to pass smoothly without disturbing each other, ensure the safe and efficient passage of the vehicle and the pedestrian, and achieve efficient traffic control.

Description

Technical Field

[0001] The present disclosure relates to the technical field of traffic control, and in particular to a vehicle driving guidance method and system in a situation where pedestrians are crossing a road section. Background Art

[0002] With the rapid economic development, the urbanization process has significantly accelerated, the road network construction has made rapid progress, and at the same time, the number of cars has increased dramatically. Among them, the conflict between pedestrians and motor vehicles has become increasingly prominent, which has had a great impact on the travel safety and quality of life of urban residents and has become an important issue that needs to be solved urgently.

[0003] The dense population and high density of residential communities in cities make it very common for pedestrians to cross the street. It is difficult for pedestrians to accurately judge the traffic status when crossing the street, and drivers are less vigilant due to inertial thinking when driving on the road. These factors combined make the probability of traffic accidents when pedestrians cross the street higher, which is consistent with the statistics of traffic safety organizations that pedestrian traffic accidents account for a relatively high proportion of urban road traffic accidents.

[0004] In order to improve the safety of pedestrians crossing the road and reduce the occurrence of traffic accidents, many cities have taken a series of corresponding measures, such as setting up traffic infrastructure such as pedestrian overpasses and underground passages, and improving the setting of traffic lights. Summary of the invention

[0005] In view of this, the embodiments of the present disclosure provide a vehicle driving guidance method and system in a situation where pedestrians are crossing the street on a road section, which can solve the problems existing in the prior art that the installation of transportation infrastructure such as pedestrian overpasses and underground passages cannot be widely popularized due to economic and environmental factors, and the improvement of traffic signal settings is difficult to adapt to different road conditions and will reduce traffic efficiency, and cannot effectively guarantee the safety of pedestrians crossing the street on a large number of urban roads.

[0006] In a first aspect, an embodiment of the present disclosure provides a vehicle driving guidance method in a situation where pedestrians are crossing a road section, including:

[0007] In response to a preset warning line trigger signal, the vehicle that triggers the preset warning line is taken as a target vehicle, and the vehicle position, vehicle speed, and pedestrian behavior characteristic information in the pedestrian crossing area of the road section of the target vehicle are obtained in real time;

[0008] Based on the pedestrian behavior characteristic information, the pedestrian closest to the preset warning line is taken as the target pedestrian, and based on the vehicle position and the position of the target pedestrian, a potential intersection point is determined;

[0009] According to the vehicle position, the vehicle speed, the position of the target pedestrian, the speed of the target pedestrian, and the potential intersection point, respectively obtain the expected vehicle time and the expected pedestrian time for the target vehicle and the target pedestrian to reach the potential intersection point;

[0010] Based on the expected vehicle time and the expected pedestrian time, determine the safety time reserved for both to reach the potential intersection point;

[0011] Judge whether the expected pedestrian time is greater than the expected vehicle time. If so, obtain the first safe vehicle speed based on the first strategy, and dynamically obtain the first guiding vehicle speed of the target vehicle based on the first safe vehicle speed and the safety time, and guide the target vehicle;

[0012] If not, obtain the second safe vehicle speed based on the second strategy, and dynamically obtain the second guiding vehicle speed of the target vehicle based on the second safe vehicle speed and the safety time, and guide the target vehicle.

[0013] In a second aspect, the present application discloses a vehicle driving guidance system in a road section pedestrian crossing scenario. Based on the vehicle driving guidance method in the road section pedestrian crossing scenario, it includes:

[0014] A road layer for real-time display of associated lane information including a preset warning line and a road section pedestrian crossing area;

[0015] A vehicle layer for real-time display of target vehicle information triggering a preset warning line and information of a following vehicle located behind the target vehicle and at a preset distance from the target vehicle;

[0016] A prompt layer for forming a deceleration reminder layer in a first type of color in real time, or forming an acceleration reminder layer in a second type of color in real time, or forming a constant speed reminder layer in a third type of color in real time, or forming a stop reminder layer in a fourth type of color in real time;

[0017] An arrow layer for displaying the expected driving path corresponding to vehicle lane change in the form of an arrow

[0018] In a third aspect, an embodiment of the present disclosure further provides a computer device, adopting the following technical solution: The computer device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above vehicle driving guidance methods in a road section pedestrian crossing scenario.

[0019] Fourthly, embodiments of the present disclosure further provide a computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle driving guidance method in any of the above-mentioned road section pedestrian crossing scenarios.

[0020] Fifthly, embodiments of the present disclosure further provide a computer program product including a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps of the method in any of the above are implemented.

[0021] The vehicle driving guidance method in the road section pedestrian crossing scenario disclosed in this application can effectively avoid collisions between vehicles and pedestrians in the crossing area and reduce traffic accidents by real-time monitoring of vehicle and pedestrian information, predicting potential intersection points and arrival times in advance, and dynamically adjusting the driving speed of the vehicle according to the situation; on the premise of ensuring safety, reasonably adjusting the vehicle speed according to the actual situation, avoiding unnecessary sudden braking or long waiting of the vehicle, improving the road traffic efficiency and reducing traffic congestion; providing clear driving guidance vehicle speeds for drivers, enabling drivers to more calmly handle the situation of pedestrians crossing the road, reducing driving pressure, and enhancing driving comfort and convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0023] Figure 1 It is a schematic flowchart of the vehicle driving guidance method in the road section pedestrian crossing scenario provided by the embodiments of the present disclosure.

[0024] Figure 2 It is a schematic flowchart of the method for determining potential intersection points provided by the embodiments of the present disclosure.

[0025] Figure 3 It is a schematic flowchart of the method for obtaining the pedestrian expected time for the target pedestrian to reach the potential intersection point provided by the embodiments of the present disclosure.

[0026] Figure 4 It is a schematic flowchart of the method for obtaining the vehicle expected time for the target vehicle to reach the potential intersection point when the target vehicle needs to change lanes before reaching the road section pedestrian crossing area provided by the embodiments of the present disclosure.

[0027] Figure 5 It is a schematic flowchart of the method for guiding the target vehicle according to the first guidance vehicle speed provided by the embodiments of the present disclosure.

[0028] Figure 6 Flow chart of the method for guiding a target vehicle according to a second guiding vehicle speed provided by an embodiment of the present disclosure.

[0029] Figure 7 Flow chart of the guiding method when a target vehicle is located in a cooperative traffic flow provided by an embodiment of the present disclosure.

[0030] Figure 8 Flow chart of the road section pedestrian crossing position coordinate system and area division provided by an embodiment of the present disclosure.

[0031] Figure 9 Schematic diagram of vehicle driving in the context of a road section pedestrian crossing provided by an embodiment of the present disclosure.

[0032] Figure 10 Schematic diagram of the structure of a computer device provided by an embodiment of the present disclosure. Detailed implementation manners

[0033] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0034] Referring to Figure 1 , the present application discloses a vehicle driving guidance method in the context of a road section pedestrian crossing, including:

[0035] S100, in response to a preset warning line trigger signal, taking the vehicle that triggers the preset warning line as the target vehicle, and acquiring the vehicle position, vehicle speed, and pedestrian behavior characteristic information within the road section pedestrian crossing area of the target vehicle in real time.

[0036] Wherein, the preset warning line is a trigger line at a preset length from the road section pedestrian crossing area, and the trigger line is a straight line perpendicular to the lane driving direction.

[0037] The pedestrian behavior characteristic information includes the position information of pedestrians waiting to cross the street, the position information of pedestrians crossing the street, and the speed information of pedestrians crossing the street. Among them, the position information of pedestrians crossing the street includes the position information of pedestrians crossing the street in the forward direction and the position information of pedestrians crossing the street in the reverse direction, and the speed information of pedestrians crossing the street includes the speed information of pedestrians crossing the street in the forward direction and the speed information of pedestrians crossing the street in the reverse direction.

[0038] Wherein, the road section pedestrian crossing area includes a pedestrian waiting area for crossing the street, a pedestrian forward crossing area, and a pedestrian reverse crossing area.

[0039] A preset warning line is set at a certain distance in front of the pedestrian crossing area on the road. It can be detected whether a vehicle triggers the warning line through devices such as induction coils laid on the ground, lidar or cameras installed beside the road. When the vehicle passes through the induction coil, the induction coil will generate a change in the electrical signal, and this signal is used as the preset warning line trigger signal. For the position and speed of the target vehicle, they can be obtained in real time through the global positioning system (GPS) device installed on the vehicle and the vehicle-mounted speed sensor. For the pedestrian behavior characteristic information in the pedestrian crossing area of the road section, a high-definition camera installed above the road can be used to identify and analyze the behavior characteristics of pedestrians such as their position, walking direction, and whether they are running through computer vision technology.

[0040] Through this step, the target vehicle can be identified, providing a specific object for subsequent analysis and guidance, obtaining the relevant information of the vehicle and the pedestrian in real time, ensuring the timeliness and accuracy of the data, and providing a reliable basis for the decision-making in the subsequent steps.

[0041] S200, based on the pedestrian behavior characteristic information, the pedestrian closest to the preset warning line is taken as the target pedestrian, and based on the vehicle position and the position of the target pedestrian, a potential intersection point is determined.

[0042] Since the vehicle travels along the road and will surely pass through the crosswalk, and the pedestrian passes through the road along the crosswalk, there will definitely be an intersection point in the trajectories of the vehicle and the pedestrian, and this point is defined as the potential intersection point, that is, the point where the vehicle and the pedestrian will intersect in the future.

[0043] According to the pedestrian behavior characteristic information obtained in step S100, calculate the distance of each pedestrian to the preset warning line, select the pedestrian with the closest distance as the target pedestrian. When determining the potential intersection point, it can be assumed that the vehicle and the pedestrian continue to move according to the current driving or walking trajectories. In this step, selecting the pedestrian with the closest distance as the target pedestrian focuses on the pedestrian most likely to intersect with the vehicle, reducing unnecessary calculations and analyses, determining the potential intersection point, clarifying the possible meeting position of the vehicle and the pedestrian, and providing a key reference point for subsequent calculation of the arrival time and formulation of strategies.

[0044] S300, according to the vehicle position, vehicle speed, target pedestrian position, target pedestrian speed, and potential intersection point, respectively obtain the expected vehicle time and pedestrian expected time for the target vehicle and the target pedestrian to reach the potential intersection point.

[0045] In this step, by calculating the expected times for the vehicle and the pedestrian to reach the potential intersection point, the time difference between the two reaching the intersection point can be quantified, providing a direct basis for subsequent judgment of whether a conflict will occur and formulation of corresponding vehicle speed guidance strategies.

[0046] S400 determines the safety time reserved for both the vehicle and the pedestrian to reach the potential intersection point based on the expected time of the vehicle and the expected time of the pedestrian.

[0047] Among them, the safety time is the time reserved for the vehicle and the pedestrian to reach the intersection point successively without disturbing each other in order to achieve the purpose that the vehicle and the pedestrian can just pass smoothly without disturbing each other.

[0048] Specifically, the safety time is :

[0049] Or,

[0050] .

[0051] Among them, is the reaction time of the driver of the target vehicle (that is, the reaction time from when the driver of the target vehicle discovers a pedestrian ahead to making a reaction); is the preset buffer time, which is used to cope with emergencies, such as pedestrians suddenly decelerating or staying, and the vehicle being unable to achieve the expected deceleration effect due to road surface, weather, etc.; is the expected time of the vehicle when the target vehicle does not make an expected lane change, is the corresponding expected time of the pedestrian when the target vehicle does not make an expected lane change, is the expected time of the vehicle when the target vehicle makes an expected lane change, is the corresponding expected time of the pedestrian when the target vehicle makes an expected lane change.

[0052] In this step, reserving the safety time can provide a certain buffer for the vehicle and the pedestrian, avoiding collisions between the two at the intersection point due to calculation errors or minor changes in the actual situation, and improving the traffic safety factor.

[0053] S500 determines whether the expected time of the pedestrian is greater than the expected time of the vehicle. If so, obtain the first safe speed based on the first strategy, and dynamically obtain the first guiding speed of the target vehicle based on the first safe speed and the safety time, and guide the target vehicle;

[0054] If not, obtain the second safe speed based on the second strategy, and dynamically obtain the second guiding speed of the target vehicle based on the second safe speed and the safety time, and guide the target vehicle.

[0055] Among them, the first guiding speed or the second guiding speed represents the safe speed that the vehicle needs to adjust to avoid conflicts with pedestrians.

[0056] According to the time relationship between the vehicle and the pedestrian arriving at the potential intersection, different strategies are adopted to obtain the safe speed and the guiding speed, which can more flexibly respond to different traffic situations and ensure the safety of the vehicle and the pedestrian; dynamically adjusting the guiding speed can adapt to the real-time changing traffic environment and improve the practicability and effectiveness of the strategy.

[0057] The vehicle driving guidance method in the scenario of pedestrian crossing on the road section disclosed in this application can effectively avoid collisions between vehicles and pedestrians in the crossing area and reduce the occurrence of traffic accidents by real-time monitoring of vehicle and pedestrian information, predicting potential intersections and arrival times in advance, and dynamically adjusting the driving speed of the vehicle according to the situation; on the premise of ensuring safety, reasonably adjusting the vehicle speed according to the actual situation to avoid unnecessary sudden braking or long waiting of the vehicle, improving the road passing efficiency and reducing traffic congestion; providing clear guiding driving speed for the driver, enabling the driver to more calmly handle the situation of pedestrian crossing, reducing the driving pressure and enhancing the comfort and convenience of driving.

[0058] Refer to Figure 2 , for the method of S200 "Based on the pedestrian behavior characteristic information, taking the pedestrian closest to the preset warning line as the target pedestrian, and determining the potential intersection based on the vehicle position and the position of the target pedestrian", that is, the method for determining the potential intersection, specifically includes:

[0059] S210, determine the coordinate origin.

[0060] When the pedestrian crossing area on the road section is located in a one-way lane, take the intersection of the longitudinal central axis of the pedestrian crossing area on the road section and the left roadside of the one-way lane as the coordinate origin, take the driving direction of the target vehicle as the positive direction of the X-axis, and take the moving direction of the forward crossing pedestrian as the positive direction of the Y-axis.

[0061] When the pedestrian crossing area on the road section is located in a two-way lane, take the intersection of the longitudinal central axis of the pedestrian crossing area on the road section and the central axis of the two-way lane as the coordinate origin, take the driving direction of the target vehicle as the positive direction of the X-axis, and take the moving direction of the forward crossing pedestrian as the positive direction of the Y-axis.

[0062] When the pedestrian crossing area on the road section is located in a multi-lane two-way road, take the intersection of the longitudinal central axis of the pedestrian crossing area on the road section and the central axis of the multi-lane two-way road as the coordinate origin, take the driving direction of the target vehicle as the positive direction of the X-axis, and take the moving direction of the forward crossing pedestrian as the positive direction of the Y-axis.

[0063] Develop a unified method for determining the coordinate origin for different types of lanes (one-way lanes, two-way lanes, multi-lane two-way lanes), so as to have a standardized position reference system in various traffic scenarios. In this way, regardless of the road conditions, the positions of vehicles and pedestrians can be described conveniently and accurately. The clear coordinate origin and axis directions provide a basis for subsequent calculations of the positions of vehicles and pedestrians and potential intersection points, simplifying the mathematical model and calculation process.

[0064] S220. Determine the positions of the vehicle and the target pedestrian based on the coordinate origin.

[0065] After determining the coordinate origin and the positive directions of the X-axis and Y-axis, the position information of the vehicle and the target pedestrian can be obtained through the positioning sensors (such as GPS) installed on the vehicle and the pedestrian monitoring devices (such as cameras, radars, etc.) arranged in the crosswalk area.

[0066] Through advanced positioning and monitoring technologies, combined with the determined coordinate system, the position information of the vehicle and the target pedestrian can be accurately obtained. This provides key data for subsequent accurate judgment of vehicle-pedestrian intersection situations, improving the reliability and accuracy of the system. The position changes of the vehicle and the pedestrian can be tracked in real time to ensure that the latest position information can always be obtained during the movement of the vehicle and the pedestrian, and the safety strategy can be adjusted in a timely manner.

[0067] S230. Determine the potential intersection point based on the positions of the vehicle and the target pedestrian.

[0068] Among them, the x-coordinate of the potential intersection point is the x-coordinate of the target pedestrian, and the y-coordinate of the potential intersection point is the y-coordinate of the vehicle position.

[0069] For example: The position coordinates of the vehicle are , and the pedestrian coordinates are , then the coordinates of the potential intersection point are .

[0070] The potential intersection point can be quickly determined through simple coordinate operations, enabling the prediction of the possible collision position between vehicles and pedestrians in a short time, and gaining time for subsequent determination of safe speed and guidance of vehicle speed. The potential intersection point is presented in coordinate form, which is intuitive and clear, facilitating the system and the driver to understand the specific position of vehicle-pedestrian intersection, and thus better taking corresponding safety measures.

[0071] The method for determining potential intersection points disclosed in S210 - S230 can predict in advance the positions where vehicles and pedestrians may intersect. Then, it can dynamically adjust the driving speed of the vehicle according to the intersection situation, effectively avoiding collisions between vehicles and pedestrians at these positions and reducing the occurrence of traffic accidents. This solution provides a scientific and accurate method for traffic management departments to analyze the conflict situation between vehicles and pedestrians. By counting and analyzing potential intersection points, areas with large traffic flow and frequent conflicts can be found, so as to optimize traffic facilities and adjust traffic rules targeted. The unified coordinate system and standardized method for determining potential intersection points enable this solution to be better integrated with existing intelligent transportation systems and vehicle safety assistance systems, improving the compatibility and scalability of the system, and facilitating the popularization and application of intelligent transportation technologies.

[0072] The calculation method for the vehicle expected time when the target vehicle in S300 reaches the potential intersection point includes: determining the vehicle expected time based on the vehicle position, vehicle speed, and potential intersection point.

[0073] The vehicle expected time is , ,where is the x - coordinate of the potential intersection point, is the x - coordinate of the target vehicle, is the vehicle speed.

[0074] Referring to Figure 3 ,for the method of obtaining the pedestrian expected time when the target pedestrian in S300 reaches the potential intersection point includes:

[0075] S301, determine whether the target pedestrian is a pedestrian crossing the street. If so, determine the pedestrian expected time based on the obtained position of the target pedestrian, the speed of the target pedestrian, and the potential intersection point.

[0076] Among them, the pedestrian expected time is , ; is the y - coordinate of the target vehicle, is the y - coordinate of the target pedestrian, is the speed of the target pedestrian.

[0077] S302, if the target pedestrian is not a pedestrian crossing the street, obtain the average pedestrian speed from the preset dynamic information table of pedestrians crossing the street in the section, and use the average pedestrian speed as the speed of the target pedestrian, and determine the pedestrian expected time based on the obtained position of the target pedestrian, the speed of the target pedestrian, and the potential intersection point.

[0078] In this embodiment, when the target pedestrian is crossing the street, the expected pedestrian time is directly calculated based on their current position, speed, and potential intersection points. Since the real-time speed information of the pedestrian is used, it can accurately reflect the current movement state of the pedestrian. For example, a pedestrian may walk faster because they are in a hurry or walk slower because they are carrying something in their hand. The real-time speed can capture these dynamic changes, thus calculating a more realistic time to reach the potential intersection point. For vehicles, the accurate expected pedestrian time can help the vehicle system formulate a more precise driving strategy. For instance, if it is calculated that the pedestrian will reach the potential intersection point soon, the vehicle needs to decelerate or stop in advance to ensure the safety of the pedestrian. If the pedestrian takes a longer time to reach, the vehicle can appropriately maintain its speed and pass safely under safe circumstances, avoiding unnecessary deceleration and stopping and improving traffic efficiency. This method can adapt to the individual differences of different pedestrians. Different pedestrians have different walking speeds, and the acquisition of real-time speed enables the system to make accurate time predictions for each specific pedestrian instead of using a unified average speed, enhancing the adaptability of the system in complex actual scenarios.

[0079] When the target pedestrian has not yet started crossing the street, it may not be possible to directly obtain their current walking speed. At this time, obtaining the average pedestrian speed from the preset dynamic information table of pedestrians crossing the street in a section is a feasible alternative method. Among them, the preset dynamic information table is obtained based on a large amount of historical data statistics and has a certain degree of representativeness and reliability. This can avoid getting stuck in a calculation dilemma when real-time speed cannot be obtained and ensure that the system can continue to calculate the expected pedestrian time. The average pedestrian speed reflects the general walking speed of pedestrians in this section. Using the average speed for calculation when there is no real-time speed information can enable the system to give a relatively reasonable expected pedestrian time in various situations. This method has generality and stability and will not cause the calculation result to deviate too much due to the special circumstances of individual pedestrians (such as suddenly running or walking slowly), ensuring the normal operation of the system in different scenarios. Measuring the speed of each non-crossing pedestrian in real time may require additional equipment and complex algorithms, increasing the cost and complexity of the system. However, by using the preset average pedestrian speed, only an information table needs to be maintained without real-time monitoring of each pedestrian, reducing the implementation cost and operation burden of the system.

[0080] Combining the methods of S301 and S302 can comprehensively cover the two different states of the target pedestrian, i.e., crossing the street and not crossing the street yet. Regardless of the state of the pedestrian, the system can effectively calculate the expected time for the pedestrian to reach the potential intersection point, improving the integrity and practicality of the system. By accurately calculating the expected time of the pedestrian, the vehicle can reasonably adjust its driving speed according to the arrival situation of the pedestrian, ensuring the safety of the pedestrian crossing the street and avoiding unnecessary long waiting times for the vehicle. On the premise of ensuring safety, the traffic operation efficiency is improved. This method of handling different situations makes the system have good scalability and maintainability. For pedestrians crossing the street, the method of obtaining real-time speed can be continuously optimized according to the development of subsequent technologies; for pedestrians not crossing the street yet, the dynamic information table of pedestrians crossing the street in the preset section can be updated regularly to adapt to changes in traffic flow, pedestrian behavior and other factors.

[0081] Furthermore, the vehicle driving guidance method in the scenario of pedestrian crossing in the road section disclosed in this application further includes: if the target vehicle needs to change lanes before reaching the road section pedestrian crossing area, set the y coordinate of the target vehicle after performing the expected lane change operation as the y coordinate corresponding to the longitudinal center axis of the lane after the lane change, and record it as the expected transformed y coordinate; at this time, the y coordinate of the potential intersection point is updated to the expected transformed y coordinate.

[0082] Refer to Figure 4 , the method for obtaining the vehicle's expected time to reach the potential intersection point when the target vehicle needs to change lanes before reaching the road section pedestrian crossing area includes:

[0083] A100, obtain the width of a single lane, the number of lanes involved in the vehicle lane change, and the lateral driving acceleration of the target vehicle.

[0084] The width of a single lane, the number of lanes involved in the vehicle lane change, and the lateral driving acceleration of the target vehicle are key parameters describing the vehicle lane change process. Accurately obtaining these parameters provides a basis for subsequent precise calculation of the time required for the vehicle to change lanes and the longitudinal moving distance during the lane change process. For different road designs, the lane width may be different; the number of lanes involved in the vehicle lane change reflects the complexity of the lane change operation; the lateral driving acceleration reflects the dynamic characteristics of the vehicle during lateral movement. By obtaining these parameters, various different traffic scenarios can be adapted. Whether it is frequent lane changes on urban roads or long-distance lane changes on highways, accurate calculations can be made according to the actual lane width, the number of lanes for lane change, and the vehicle acceleration, improving the versatility and applicability of the solution.

[0085] A200, determine the expected lateral lane change time of the target vehicle according to the lane width, the number of lanes, and the lateral driving acceleration.

[0086] Among them, the expected lateral lane change time is , , where is the number of lanes, is the lane width, is the lateral acceleration during driving.

[0087] By combining the lane width, the number of lanes, and the lateral acceleration through physical formulas, the lateral expected lane - change time required for a vehicle to complete a lane change is accurately calculated. This enables the vehicle system to predict in advance the time required for a lane - change operation, thereby reasonably arranging subsequent driving strategies. For example, if the calculated lane - change time is long, the vehicle can adjust its speed in advance to avoid affecting the normal driving of other vehicles during the lane - change process.

[0088] For A300, based on the vehicle speed and the lateral expected lane - change time, the longitudinal expected moving distance is obtained.

[0089] Among them, the longitudinal expected moving distance is , .

[0090] During the vehicle lane - change process, the vehicle not only moves laterally but also continues to move longitudinally. This step calculates the longitudinal expected moving distance of the vehicle during the lane - change process by multiplying the vehicle speed by the lateral expected lane - change time. This enables the system to comprehensively consider the movement of the vehicle during the lane - change process and accurately estimate the position of the vehicle after the lane - change. For example, on a busy urban road, when a vehicle changes lanes, it needs to consider the impact of the longitudinal moving distance on subsequent driving to avoid colliding with the vehicle in front. Understanding the longitudinal expected moving distance helps the vehicle system optimize the driving plan. If the longitudinal expected moving distance is large, the vehicle can adjust its speed in advance or choose a more appropriate time to change lanes to ensure the safety and efficiency of the lane - change operation.

[0091] For A400, based on the lateral expected lane - change time, the longitudinal expected moving distance, the vehicle speed, and the distance between the target vehicle and the potential intersection point, the vehicle expected time is determined.

[0092] Among them, the vehicle expected time is , .

[0093] This step comprehensively considers the lateral expected lane - change time of the vehicle, the longitudinal expected moving distance during the lane - change process, the vehicle speed, and the distance between the target vehicle and the potential intersection point, and comprehensively calculates the expected time for the vehicle to reach the potential intersection point. This comprehensive consideration can more accurately reflect the complex situation during the actual driving process of the vehicle and avoid calculation errors caused by only considering a single factor; the accurate vehicle expected time provides an important basis for the vehicle's safety decision - making. The vehicle system can compare this time with the pedestrian's expected time to determine whether there is a collision risk and take corresponding measures in a timely manner, such as adjusting the speed, stopping in advance, etc., so as to ensure the safety of pedestrians and vehicles.

[0094] The method disclosed in A100 - A400, by accurately calculating the expected time for the vehicle to reach the potential intersection point, the vehicle system can predict in advance the possibility of meeting with pedestrians and take corresponding safety measures, reducing the risk of collision between the vehicle and pedestrians in the pedestrian crossing area of the road section, and improving the traffic safety level; the reasonable calculation of the vehicle's expected time helps the vehicle to perform more efficient lane - change operations before reaching the pedestrian crossing area of the road section. The vehicle can reasonably adjust the speed and lane - change timing according to the expected time, avoiding unnecessary stops and waiting, improving the traffic operation efficiency, and reducing traffic congestion; this scheme considers various actual factors, such as lane width, the number of lane - change lanes, vehicle acceleration, etc., and can adapt to different road conditions and vehicle performances. This enables the system to accurately calculate the vehicle's expected time in various traffic scenarios, enhancing the adaptability and reliability of the system.

[0095] A method for obtaining the pedestrian's expected time when the target vehicle needs to change lanes before reaching the pedestrian crossing area of the road section includes the following two situations.

[0096] Situation 1: If the target pedestrian is a pedestrian crossing the road, based on the obtained position of the target pedestrian, the speed of the target pedestrian, and the expected y - coordinate transformation, determine the pedestrian's expected time.

[0097] The pedestrian's expected time is , ; is the expected y - coordinate transformation, is the y - coordinate of the target pedestrian, is the speed of the target pedestrian.

[0098] Situation 2: If the target pedestrian is not a pedestrian crossing the road, obtain the average pedestrian speed from the preset dynamic information table of road - crossing pedestrians, and use the average pedestrian speed as the speed of the target pedestrian. Based on the obtained position of the target pedestrian, the speed of the target pedestrian, and the expected y - coordinate transformation, determine the pedestrian's expected time.

[0099] By accurately calculating the expected time of pedestrians, the vehicle system can better judge the possibility of meeting pedestrians at potential intersection points, and thus take corresponding safety measures, such as decelerating in advance, stopping and waiting, etc., effectively reducing the risk of collisions between vehicles and pedestrians and ensuring the safety of pedestrians crossing the street; reasonable calculation of the expected time of pedestrians helps vehicles change lanes and drive more efficiently. Vehicles can reasonably arrange the timing of lane changes according to the arrival time of pedestrians, avoid unnecessary stops and waiting, reduce traffic congestion, and improve traffic operation efficiency. This method of handling different situations makes the system have good scalability and maintainability. For pedestrians who are crossing the street, the method of obtaining real-time speed can be continuously optimized according to the development of subsequent technologies; for pedestrians who have not crossed the street, the dynamic information table of pedestrians crossing the street in the preset section can be updated regularly to adapt to changes in traffic flow, pedestrian behavior and other factors.

[0100] Referring to Figure 5 , for the method of "obtaining the first safe vehicle speed based on the first strategy, and dynamically obtaining the first guiding vehicle speed of the target vehicle based on the first safe vehicle speed and the safety time and guiding the target vehicle" in S500, that is, the method of guiding the target vehicle according to the first guiding vehicle speed, includes:

[0101] B100. Determine the target distance according to the x coordinate of the vehicle position and the x coordinate of the position of the target pedestrian.

[0102] Wherein, the target distance is , .

[0103] B200. Obtain the first safe vehicle speed based on the target distance, the vehicle expected time, and the safety time.

[0104] Wherein, the first safe vehicle speed is , , or, .

[0105] B300. Dynamically obtain the first guiding vehicle speed of the target vehicle based on the first safe vehicle speed and the safety time.

[0106] Wherein, the first guiding vehicle speed is , ≥ .

[0107] B400. Issue an instruction with an average vehicle speed not less than the first guiding vehicle speed to the target vehicle based on the first guiding vehicle speed, and the target vehicle executes driving operations according to this instruction.

[0108] The method disclosed in this embodiment is used to guide the target vehicle to accelerate; in step B100, the target distance is determined by calculating the difference between the x coordinate of the vehicle position and the x coordinate of the target pedestrian position, which provides basic data for the subsequent calculation of the safe speed. An accurate target distance can reflect the relative position relationship between the vehicle and the pedestrian in the lateral space; in step B200, the first safe speed is calculated by combining the vehicle's expected time and the safety time, taking into account both the time for the vehicle to reach the potential intersection point and the reserved safety buffer time. Through this dynamic evaluation method, the vehicle speed can be adjusted according to different scenarios and real-time situations, ensuring that there is enough safety margin during the vehicle's driving process and reducing the risk of collision with pedestrians. Calculate the first safe speed in advance based on the target distance, the vehicle's expected time, and the safety time, and further obtain the first guidance speed to guide the vehicle to accelerate. This can avoid the situation where the vehicle needs to suddenly brake urgently when approaching the pedestrian because the speed is too slow. Sudden braking not only brings an uncomfortable experience to the passengers in the vehicle but may also trigger a chain reaction such as a rear-end collision by the following vehicle. Through reasonable acceleration guidance, such dangerous situations can be effectively reduced.

[0109] When the vehicle accelerates according to the first guidance speed, it can pass through the pedestrian crossing area of the road section more efficiently. If the vehicle has been driving at a low speed, it will affect the passing of subsequent vehicles and cause road congestion. By accelerating reasonably, the vehicle can quickly pass through this area, improve the overall passing capacity of the road, and reduce the occurrence of traffic congestion. This method helps to optimize the entire traffic flow. In the interaction scenario between the vehicle and the pedestrian, reasonable vehicle speed control can make the traffic more orderly. The vehicle can smoothly accelerate according to the calculated first guidance speed, avoiding unnecessary stops and starts, making the traffic flow smoother, and improving the operation efficiency of the entire traffic system.

[0110] This method can adapt to different traffic scenarios. Different factors such as road conditions, pedestrian flow, and vehicle speed will affect the interaction between vehicles and pedestrians. By calculating the target distance, vehicle expected time, and safety time in real-time and dynamically adjusting the first safe speed and the first guiding speed, flexible speed guidance can be provided according to specific scenarios. For example, on busy streets with a large pedestrian flow and remote sections with fewer pedestrians, the system can give appropriate acceleration instructions based on the actual situation. During the calculation of the first safe speed and the first guiding speed, the variable of safety time is introduced. The safety time can be dynamically adjusted according to the actual situation. For example, in bad weather or poor road conditions, the safety time can be appropriately increased, thereby reducing the first safe speed and the first guiding speed to ensure the safety of vehicle driving. This dynamic adjustment mechanism makes the system more adaptable and flexible. Guiding the vehicle to accelerate is carried out on the premise of ensuring safety, which meets the requirements of traffic rules regarding safe driving and reasonable speed. When there is sufficient safety distance and time, appropriately accelerating can improve the traffic efficiency of the road without violating traffic regulations. Compared with sudden hard braking or long-term low-speed driving, accelerating smoothly according to the first guiding speed is more in line with the driving habits of most drivers, which can reduce the operation burden of drivers, improve driving comfort and safety; at the same time, the instructions of the system are easier to be accepted and executed by drivers, which is conducive to improving the coordination of the entire traffic system.

[0111] Referring to Figure 6 , for the "obtaining the second safe speed based on the second strategy, and dynamically obtaining the second guiding speed of the target vehicle based on the second safe speed and the safety time and guiding the target vehicle" in S500, that is, the method of guiding the target vehicle according to the second guiding speed, includes: includes:

[0112] C100, determining the target distance according to the x coordinate of the vehicle position and the x coordinate of the position of the target pedestrian.

[0113] Wherein, the target distance is , .

[0114] C200, obtaining the second safe speed based on the target distance, vehicle expected time, and safety time.

[0115] The second safe speed is , , or, .

[0116] C300, dynamically obtaining the second guiding speed of the target vehicle based on the second safe speed and the safety time.

[0117] Wherein, the second guiding speed is , ≤ 。

[0118] C400, issue an instruction to the target vehicle that the average speed is not greater than the second guiding speed based on the second guiding speed, and the target vehicle performs driving operations according to this instruction.

[0119] The method disclosed in this embodiment is used to guide the target vehicle to decelerate. In step C100, the target distance between the vehicle and the target pedestrian is accurately calculated, which is the basis for subsequent safety decisions. Combining the vehicle's expected time and safety time considered in step C200 to determine the second safety speed enables the vehicle to reasonably control its speed according to the actual situation when approaching a potential intersection point; when the second guiding speed limits the average speed of the vehicle to not be greater than this value, the vehicle has more time to handle unexpected situations, such as pedestrians suddenly changing their walking routes, etc., greatly reducing the possibility of collisions between the vehicle and pedestrians and ensuring the safety of pedestrians and vehicles; by calculating and giving an instruction not greater than the second guiding speed in advance based on various parameters, the vehicle can decelerate smoothly. Compared with suddenly braking sharply when approaching the pedestrian, this early speed control method can avoid the risk of rear-end collisions caused by sudden braking of the vehicle. Especially in sections with heavy traffic flow, it is of great significance to the stability and safety of the entire traffic order. When the vehicle travels at a speed not greater than the second guiding speed, it can better integrate with the surrounding traffic flow. In the pedestrian crossing area of the section, reasonable speed control can avoid large fluctuations in the vehicle speed and make the traffic flow more stable and orderly. For example, in scenarios with multiple pedestrians crossing the street, the vehicle decelerating in an orderly manner allows pedestrians to cross the street safely and at the same time does not cause congestion and chaos to the vehicles behind. Although the vehicle speed decreases, this orderly deceleration avoids unnecessary stopping and restarting processes, which actually helps to improve the traffic efficiency of the entire section. The vehicle can pass through the pedestrian crossing area at a relatively stable low speed, reducing the formation of traffic jams and enabling more vehicles and pedestrians to pass through this area within a reasonable time.

[0120] This method can be flexibly adjusted according to different actual scenarios. For example, in situations where there is a large pedestrian flow, pedestrians walk at a slow speed, or the weather conditions are poor, by adjusting parameters such as the safety time, the second safety speed and the second guiding speed can be correspondingly reduced to make the vehicle travel at a slower speed to ensure traffic safety; while in situations where there are fewer pedestrians and the visibility is good, the speed limit can be appropriately increased to ensure traffic efficiency; the entire method is calculated based on real-time obtained data such as the vehicle position, pedestrian position, and vehicle expected time. This enables the system to dynamically adjust the second guiding speed according to the real-time changes in traffic conditions, with strong adaptability and flexibility. Whether it is during peak hours or off-peak hours, it can provide appropriate speed guidance for vehicles.

[0121] Driving at a steady deceleration not greater than the second guiding vehicle speed avoids sudden braking and frequent acceleration and deceleration operations, bringing a more comfortable driving experience to the driver and passengers. The driver does not need to constantly worry about suddenly appearing pedestrians and perform nervous operations, and can drive the vehicle more easily. It provides clear speed guidance for the driver, and the driver only needs to drive according to the instructions. This reduces the decision-making burden of the driver in complex traffic scenarios, reduces driving pressure, and makes the driving process easier and safer.

[0122] The vehicle driving guidance method in the scenario of pedestrian crossing on the road section disclosed in this application further includes: judging whether the target vehicle is in the coordinated traffic flow. If so, the guiding vehicle speed of the target vehicle is used as the guiding vehicle speed of other vehicles in the coordinated traffic flow. Among them, the coordinated traffic flow refers to the same traffic flow.

[0123] Refer to Figure 7 , the guiding method when the target vehicle is in the coordinated traffic flow includes:

[0124] D100, in response to the preset warning line trigger signal, taking the vehicle that triggers the preset warning line as the target vehicle, and obtaining the vehicle position, vehicle speed of the target vehicle, and the rear vehicle position and rear vehicle speed of the vehicle behind the target vehicle in real time.

[0125] D200, determining the real-time distance based on the vehicle position of the target vehicle and the rear vehicle position.

[0126] Among them, the real-time distance is : ; the position of the leading vehicle is , the position of the rear vehicle is , is the rear vehicle speed.

[0127] D300, determining the dynamic safety distance according to the rear vehicle speed, preset buffer distance, and safety time.

[0128] Among them, the dynamic safety distance is ; , is the preset buffer distance.

[0129] D400, if the real-time distance is not greater than the dynamic safety distance, determining that the target vehicle is in the coordinated traffic flow, and the target vehicle and the corresponding rear vehicle are in the same coordinated traffic flow.

[0130] D500, taking the guiding vehicle speed of the target vehicle as the guiding vehicle speed of other vehicles in the coordinated traffic flow, and the driving directions of other vehicles in the coordinated traffic flow are the same as that of the target vehicle.

[0131] Specifically, if the vehicle flow needs to decelerate or change lanes, the speeds and driving directions of all vehicles within the vehicle flow are uniformly adjusted.

[0132] In this embodiment, by obtaining the position and speed information of the target vehicle and the following vehicle in real time, calculating the real-time distance and the dynamic safety distance, and comparing the magnitudes of the two, the safety condition between vehicles can be judged in a timely manner; when the real-time distance is not greater than the dynamic safety distance, it indicates that the distance between vehicles is too close and there is a risk of rear-end collision. At this time, it is determined that the target vehicle and the following vehicle are in the same cooperative vehicle flow, and a unified speed guidance is adopted, which can keep the vehicle speeds of the entire cooperative vehicle flow consistent, avoid the following vehicle from rear-ending the leading vehicle due to excessive speed, and effectively reduce the occurrence probability of rear-end collision accidents. Uniformly guiding the vehicle speeds in the cooperative vehicle flow can make the relative positions and speed relationships between vehicles more stable. Vehicles travel at the same speed, reducing the frequent acceleration, deceleration, and lane-changing behaviors between vehicles, reducing the volatility of the traffic flow, making the entire traffic system more stable, and reducing traffic accidents caused by mutual interference between vehicles.

[0133] When the vehicles in the cooperative vehicle flow travel at a unified guided vehicle speed, the distances between vehicles are more reasonable and the traffic flow is smoother. This can avoid traffic congestion caused by excessive differences in vehicle speeds and improve the overall traffic capacity of the road. For example, on a highway, the orderly travel of the cooperative vehicle flow can enable more vehicles to pass through a specific section within a unit time, reducing the delay time of vehicles.

[0134] The unified speed guidance helps to optimize the distribution of the traffic flow. Vehicles maintain a consistent driving speed in the cooperative vehicle flow, avoiding congestion and chaos in local traffic, and making the traffic flow more evenly distributed on the road. This not only improves the utilization efficiency of the road but also reduces the emergence of traffic bottlenecks, enabling the entire traffic network to operate more efficiently.

[0135] This method applies the guided vehicle speed of the target vehicle to other vehicles in the cooperative vehicle flow, greatly simplifying the difficulty of traffic management. The traffic management department or the intelligent transportation system only needs to conduct speed guidance on the target vehicle to achieve unified management of the entire cooperative vehicle flow, reducing the workload of individually controlling and guiding each vehicle and improving the management efficiency; adopting unified speed guidance in the cooperative vehicle flow is conducive to information sharing and cooperation between vehicles. Vehicles can travel according to the unified speed requirements and can also share information such as the position and speed of the vehicle in real time through vehicle-to-vehicle communication and other technologies, further improving the safety and efficiency of the cooperative vehicle flow. This information sharing and cooperation mechanism helps to achieve more intelligent traffic management and improve the operation level of the entire traffic system.

[0136] For drivers, driving at a unified guiding speed in a coordinated traffic flow eliminates the need for frequent speed adjustments and constant monitoring of the vehicles ahead and behind. This reduces the complexity and stress of driving, allowing drivers to operate their vehicles more easily, minimizing the risk of fatigue driving, and enhancing driving comfort and safety. The unified speed guidance also makes vehicle movement more predictable, enabling drivers to better anticipate the driving behavior of surrounding vehicles and prepare in advance, thereby reducing tension and panic caused by unexpected situations and improving driving stability and confidence.

[0137] If there are multiple target vehicles triggering the preset warning line, simultaneous calculation and analysis of multiple vehicles can be performed to obtain the guidance plans for the corresponding vehicles.

[0138] Furthermore, referring to Figure 8 , in the vehicle driving guidance method for the scenario of pedestrians crossing the road on the section disclosed in this application, to more effectively and accurately identify pedestrians crossing the road on the section, the pedestrian crossing area on the section needs to be divided. The pedestrian crossing area on the section involves the pedestrian crossing section within the zebra crossing and the extended areas at both ends. At the same time, considering the pedestrian crossing status, the pedestrian crossing area on the section is divided into a pedestrian waiting area and a pedestrian crossing area, and the pedestrian waiting area is further divided into a forward pedestrian waiting area and a reverse pedestrian waiting area.

[0139] To more accurately describe and analyze the data of the pedestrian crossing area on the section, a two-dimensional rectangular coordinate system based on the road, namely the pedestrian crossing position coordinate system on the section, is established as follows: 1) Coordinate axis origin: The reference point of the pedestrian crossing coordinate system, that is, the origin O of the coordinate system, is defined as the intersection of the center line of the vehicle lane and the center line of the crosswalk. This point is not only the intersection of the vehicle driving area and the pedestrian crossing area but also the core position of the pedestrian activity range, facilitating the calculation of the relative positions between pedestrians and vehicles. 2) Coordinate axis y direction: The y-axis is perpendicular to the center line of the vehicle lane and extends along the crosswalk direction, representing the longitudinal direction of pedestrian crossing. Taking the camera monitoring perspective as a reference, the upper direction in the camera-captured image is defined as the positive direction of the y-axis, and its opposite direction is defined as the negative direction of the y-axis. The y-axis is used to describe the pedestrian crossing process, reflecting the crossing direction and progress. 3) Coordinate axis x direction: The x-axis extends along the center line of the vehicle lane, which is the horizontal direction of the road, representing the lateral direction of pedestrian crossing. The positive direction of the x-axis is defined as the direction obtained by rotating the positive direction of the y-axis clockwise by 90°, and the negative direction of the x-axis is defined as the direction obtained by rotating the positive direction of the y-axis counterclockwise by 90°. The x-axis is used to reflect the lateral position of pedestrians, such as their specific lateral position in the waiting area or within the zebra crossing.

[0140] According to the established coordinate axes, it is stipulated that when a pedestrian walks in the positive direction of the y-axis, it is a forward cross-street, and vice versa for a reverse cross-street. Based on this, the position expressions of the forward pedestrian cross-street waiting area, the pedestrian cross-street area, and the reverse pedestrian cross-street waiting area are obtained. Forward pedestrian cross-street waiting area (Area I): The area outside the lane near the zebra crossing for pedestrians to wait for a forward cross-street, specifically ranging from 1 to 2 meters outward from the lane edge along the zebra crossing. Pedestrian cross-street area (Area II): The area covered by the zebra crossing, which is the area for pedestrians to cross the street, and this area is the pedestrian cross-street passage area. Reverse pedestrian cross-street waiting area (Area III): The area outside the lane near the zebra crossing for pedestrians to wait for a reverse cross-street, specifically ranging from 1 to 2 meters outward from the lane edge along the zebra crossing.

[0141] For the cross-street pedestrians on the road section, information such as their quantity and location needs to be collected. These information only consider the behavioral characteristics of pedestrians and do not involve the personal information of pedestrians. The cross-street pedestrian information on the road section is stored in the form of a dynamic information table, which specifically includes time, pedestrian number, area, location, speed, and remarks. For example, when a pedestrian is in the waiting area, the speed is recorded as 0.

[0142] In this application, the detection of cross-street pedestrians on the road section is completed by the cross-street pedestrian detection subsystem set on the road section. This subsystem uses video surveillance cameras for pedestrian detection, can capture real-time and high-resolution video images of pedestrians on the road section, and uses the deep learning method YOLOv5 to identify pedestrians. Finally, the boundary boxes of the identified cross-street pedestrians and the boundary box coordinates of the pedestrians are obtained. The specific process includes: ① Preprocessing of cross-street pedestrian images. The purpose of image preprocessing is to meet the requirements of the YOLOv5 algorithm for image size, and improve the image quality and the accuracy of algorithm recognition. The preprocessing operations specifically include resizing the image, normalizing, and adjusting the channel format. First, uniformly adjust the image size input to the YOLOv5 neural network to the required fixed input size. Here, the bilinear interpolation method is used for image processing, and the linear weighted average is calculated within the neighborhood of the target pixel to calculate the new pixel value. This method can retain better image details and continuity when enlarging and reducing. If the position of the target pixel is , and its corresponding floating-point coordinates in the original image are , the original image neighborhood pixel values are respectively the upper left , the lower left , the upper right , the lower right , then the formula for calculating the target pixel value is:

[0143] ; where: (weight in the horizontal direction), (weight in the vertical direction).

[0144] Secondly, perform a normalization operation on the resized image. The pixel values of the image before the normalization operation are in the range of [0, 255]. Directly inputting these values will result in overly large numerical values, causing unstable gradient calculation and making it difficult for the model to converge. After normalization, the pixel values (which are floating-point numbers) fall into the range of [0, 1], which is more suitable for the weight update of the neural network and makes the gradient calculation stable.

[0145] Specifically, , where x is the original pixel value, is the pixel value after normalization.

[0146] Finally, perform a channel format adjustment on the normalized image, changing the channel order of the image from HW (Height * Width * Channel) to CHW (Channel * Height * Width). In computer vision, the storage format of an image is usually HWC (i.e., pixel values are arranged by height, width, and color channels), but deep learning frameworks require the input format of data to be CHW, which necessitates a channel format adjustment for the image. After the channel is adjusted to the CHW format, the image data can be matrix-operated in a more efficient manner, optimizing the computing performance. After adjustment, the image data will be arranged in the following order: the first dimension: channels (C), representing the R, G, and B channels respectively; the second dimension: height (H); the third dimension: width (W).

[0147] ② Feature extraction and object detection. Specifically, after the image of the street-crossing pedestrians captured by the camera undergoes preprocessing, it is input into the YOLOv5 model for feature extraction and object detection. Through learning a large amount of labeled data, YOLOv5 can automatically extract features related to pedestrians from the image, and these features can accurately locate the target and identify pedestrians during the pedestrian detection process.

[0148] The feature extraction process of YOLOv5 is divided into three main modules: Backbone, Neck, and Head. First, the image undergoes feature extraction through the Backbone (such as CSPDarknet), extracting multi-level high-dimensional feature maps. Then, these features are fused and optimized through the Neck module (such as PANet) to generate multi-scale feature maps for detecting targets at different scales. Finally, the Head module uses these feature maps for prediction, outputting the bounding box coordinates, confidence scores, and object categories of each target.

[0149] After feature extraction, non-maximum suppression (NMS) is used to screen the multiple detected bounding boxes of road-crossing pedestrians generated above, and the optimal bounding box is selected to avoid repeated prediction of the same target, that is, each bounding box uniquely corresponds to a pedestrian target. Finally, the detection result is the bounding box containing the road-crossing pedestrian and its coordinates, and the coordinates of the bounding box include the coordinates of the upper left corner point and the coordinates of the lower right corner point .

[0150] Calculation of pedestrian position coordinates: After feature extraction and target detection by the YOLOv5 model, the coordinates of the rectangular bounding box of the pedestrian can be obtained, that is, the upper left corner and the lower right corner . It is stipulated that the center point at the bottom of the rectangular box ( ) is used as the position coordinates of the pedestrian.

[0151] Calculation of the coordinates of the center point at the bottom of the rectangular box: .

[0152] Furthermore, the position coordinates of the pedestrian need to be mapped to the coordinate system of the road-crossing position of pedestrians on the road section to obtain the pedestrian position : ; where , is the position coordinate in the coordinate system of the road-crossing position of pedestrians on the road section, , is the position of the origin of the coordinate system of the road-crossing position of pedestrians on the road section in pixel coordinates, and S is the ratio of image pixels to the real distance. For example, 100 pixels = 1 meter, then S = 100.

[0153] ④ Calculation of the speed of road-crossing pedestrians: The speed of road-crossing pedestrians can be calculated by the change in position within a time interval. Assume that at time , the pedestrian coordinates are ; at time , the pedestrian coordinates are . Then, the speed of the pedestrian within the time interval can be calculated by the following formula: ; where: is the speed of the pedestrian, and the unit is meters per second (m / s).

[0154] Refer to Figure 9, shown as the vehicle driving schematic diagram in the scenario of pedestrians crossing the road at a road section. In this figure, the preset warning line (i.e., the vehicle warning line, which can also be understood as the vehicle-pedestrian position prediction line) is a virtual trigger line set in the pedestrian crossing section of the road. When the vehicle reaches this line, based on the vehicle's current position, speed and other information, the relative position between the vehicle and the pedestrian and the time difference to reach the intersection point will be calculated in real time, and the vehicle driving guidance process will be started.

[0155] A vehicle warning window is formed between the preset warning line and the target pedestrian. It can be used to monitor and analyze the position relationship between the vehicle and the pedestrian in real time. That is, this window starts from the vehicle-pedestrian position prediction line and extends to before the first crossing pedestrian encountered by the vehicle, covering the range where the vehicle may intersect with the pedestrian.

[0156] When the vehicle enters the pedestrian crossing section, at the moment of passing through the vehicle warning line, it is selected as the target vehicle. Based on its current position, speed and other information, it is analyzed to calculate the distance between the target vehicle and the pedestrian and the time for each to reach the intersection point, determine whether an intersection will occur, and give specific guidance to it.

[0157] In this embodiment, the position of the target vehicle can be obtained from the longitude and latitude coordinates of the vehicle transmitted by the collected vehicle, denoted as , since the vehicle position and the pedestrian position are not in the same coordinate system, it needs to be converted to the same rectangular coordinate system as the pedestrian position coordinate The specific process is as follows: 1) Determine the longitude and latitude coordinates of the reference point (i.e., the origin) of the pedestrian crossing coordinate system, denoted as , where is the latitude of the reference point, is the longitude of the reference point. 2) Calculate the longitude and latitude differences between the target vehicle and the reference point; for the longitude and latitude of the vehicle, the longitude difference between the two is: ; the latitude difference is: ; Convert the longitude and latitude differences to radian units, and the radian calculation formula is: ; . 3) Project the longitude and latitude differences onto the plane rectangular coordinate system. Here, it is necessary to first calculate the conversion to the plane rectangular coordinates based on due north and due east; latitude direction (north / south direction, Y-axis): ; longitude direction (east / west direction, X-axis): , and the at this time is the coordinate relative to the due north and due east directions. However, in reality, the coordinate system is not always based on the due north and due east directions, so coordinate rotation is required.

[0158] It is stipulated that the deflection angle is , and the deflection direction is counterclockwise. Use the rotation matrix for transformation:

[0159] 。

[0160] 4) The position of the vehicle in the same rectangular coordinate system as the pedestrian can be obtained, i.e.: , namely: ; . Among them, also needs to be converted to radians for calculation: .

[0161] The vehicle driving guidance method in the scenario of pedestrian crossing on the road section disclosed in this application can, by responding to a preset warning line trigger signal, obtain the position, speed of the target vehicle and the behavior characteristic information of pedestrians in the pedestrian crossing area of the road section in real time, which enables the system to perceive in advance the scenarios where vehicle-pedestrian conflicts may occur and provides an accurate data basis for subsequent safety decisions. For example, when the vehicle approaches the preset warning line, the system starts to collect relevant information and anticipates in advance the possible pedestrian crossing situations, greatly increasing the time and preparation for dealing with emergencies; determines the target pedestrian based on the pedestrian behavior characteristic information, and combines the positions of the vehicle and the pedestrian to determine the potential intersection point. This precise positioning enables the system to clearly identify in advance the specific positions where vehicle-pedestrian collisions may occur, so as to take targeted measures; for example, in complex urban road sections, the pedestrian crossing routes may be diverse. By determining the potential intersection point, the risk level can be more accurately evaluated; calculates respectively the expected times for the target vehicle and the target pedestrian to reach the potential intersection point, and determines the safety time reserved for their arrivals. This measure further ensures the safety when the vehicle and the pedestrian meet. Even if the driving speeds and routes of the vehicle and the pedestrian change, due to the reserved safety time, the risk of collision can be reduced; according to the magnitude relationship between the vehicle expected time and the pedestrian expected time, different strategies are adopted to obtain the safe speed and the guiding speed. When the pedestrian expected time is greater than the vehicle expected time, the first strategy is adopted to obtain the first safe speed and the first guiding speed; otherwise, the second strategy is adopted. This differential processing method can more flexibly respond to different traffic situations, effectively avoid collisions between vehicles and pedestrians in the crossing area, reduce the occurrence of traffic accidents, and effectively ensure the safety of pedestrians and vehicles.

[0162] This solution dynamically adjusts the driving speed of the vehicle according to the actual vehicle-pedestrian arrival time relationship, rather than adopting fixed rules like traditional signal lights. On the premise of ensuring safety, it avoids unnecessary sudden braking or long waiting of the vehicle; for example, when the impact of pedestrian crossing on vehicle driving is small, the vehicle can continue to drive at a reasonable speed without being forced to stop and wait due to fixed signal light settings, thereby improving the road traffic efficiency and reducing traffic congestion.

[0163] Compared with the problem that it is difficult for traditional signal lights to adapt to different road conditions, this solution can be adjusted in real time according to the specific conditions of vehicles and pedestrians. Whether in sections with dense population and frequent pedestrian crossings or in sections with relatively small pedestrian flow, it can flexibly give appropriate guiding vehicle speeds, making the traffic flow smoother and improving the adaptability and operation efficiency of the overall traffic system.

[0164] Due to the limitations in aspects such as economy and environment in many cities, it is difficult to popularize the construction of traffic infrastructure (such as pedestrian overpasses and underground passages) on a large scale. This solution realizes the guidance of vehicle driving through technical means without the need for large-scale construction of additional infrastructure, reducing the cost and difficulty of urban traffic construction to a certain extent. At the same time, it also avoids problems such as environmental impacts caused by the construction of infrastructure. At the same time, it provides drivers with clear guiding vehicle speeds, enabling drivers to respond more calmly when facing pedestrian crossing situations. Drivers do not need to judge complex traffic conditions and pedestrian behaviors by themselves, but only need to drive according to the guiding vehicle speeds given by the system, reducing driving pressure and improving driving comfort and convenience. For example, in busy urban sections, drivers can focus more on the basic operations of the vehicle without worrying about collisions with pedestrians.

[0165] In the second aspect, the present application discloses a vehicle driving guidance system in the context of pedestrian crossing on a road section. Based on the vehicle driving guidance method in the context of pedestrian crossing on a road section disclosed in the first aspect of the present application, it specifically includes: a road layer for real-time display of associated lane information including preset warning lines and pedestrian crossing areas on the road section; a vehicle layer for real-time display of target vehicle information triggering the preset warning line and information of the vehicle behind the target vehicle and at a preset distance from the target vehicle; a prompt layer for forming a deceleration reminder layer in a first type of color in real time, or forming an acceleration reminder layer in a second type of color in real time, or forming a constant speed reminder layer in a third type of color in real time, or forming a stop reminder layer in a fourth type of color in real time; an arrow layer for displaying the expected driving path corresponding to vehicle lane change in the form of an arrow. Among them, the preset distance can be a distance flexibly set according to actual needs.

[0166] Furthermore, the vehicle driving guidance system in the context of pedestrian crossing on a road section disclosed in this application further includes a road section pedestrian crossing detection subsystem, a road section traffic flow detection subsystem, a road section vehicle driving guidance subsystem, and a road section pedestrian crossing guidance subsystem. The road section pedestrian crossing detection subsystem can identify and detect the number and location of pedestrians. The road section traffic flow detection subsystem can collect information such as the speed, location, and number of the traffic flow on this road section. The road section pedestrian crossing detection subsystem and the road section traffic flow detection subsystem can transmit all the collected information to the road section vehicle driving guidance subsystem. The road section vehicle driving guidance subsystem can combine in-vehicle sensor data, evaluate the relative position and speed of the vehicle and the pedestrian, and through the calculation and analysis of the built-in modules of the system, obtain a safe vehicle speed and conduct real-time guidance on the vehicle speed and lane. With the assistance of the road section pedestrian crossing guidance subsystem, the vehicle and the pedestrian can just pass smoothly without disturbing each other, ensuring the safe and efficient passage of the vehicle and the pedestrian.

[0167] Specifically, the road section pedestrian crossing detection subsystem includes a microcontroller, a pedestrian detection sensor module, a data storage module, a communication module, and a power supply module. Its main function is to identify the pedestrians waiting to cross the road and the pedestrians who are crossing the road on the road section, obtain information such as their number, distribution, speed, and status, conduct real-time processing and analysis, and transmit the information to other modules. Among them, the microcontroller is the core of the road section pedestrian crossing detection subsystem and is responsible for the operation of the entire system. It is responsible for analyzing and processing the images obtained by the pedestrian detection sensor, screening out the pedestrian data, and using various image processing methods for enhancement and tracking to ensure the accuracy of subsequent image processing. At the same time, this module can integrate the results from the image processing module and the data of each sensor module, conduct analysis of pedestrian behavior characteristics, and obtain information such as the traffic flow characteristics, speed, and location of the pedestrians crossing the road, so as to facilitate the precise control and guidance of pedestrian crossing behavior and vehicle driving behavior in the future.

[0168] The pedestrian detection sensor module includes a detection module based on a video surveillance camera. The video surveillance camera can capture real-time, high-resolution video images on the road section and use computer vision and deep learning technologies to identify and track pedestrians for subsequent detection and analysis.

[0169] The data storage module is mainly used to store pedestrian crossing data collected by the video surveillance camera, etc. The communication module can wirelessly transmit the collected pedestrian data to the microcontroller via 5G technology for system analysis and processing. The power supply module is the power supply module of the entire road section pedestrian crossing detection subsystem, which uses a solar cell for power supply, practicing the concept of environmental protection and green while ensuring sufficient power supply for the module.

[0170] The road traffic flow detection subsystem consists of a microcontroller module, a communication and transmission module, a data storage module, and a power module. Its main function is to capture information such as the position, speed, and acceleration of the traffic flow on the road section, process and analyze this data in real time, and transmit it to other modules through the communication module. Among them, the microcontroller module is the core module of the road traffic flow detection subsystem, and its main role is to integrate, process, and analyze the traffic flow information collected by the communication and transmission module; the main role of the communication and transmission module is to receive the speed and position information from the road vehicles themselves and transmit it to the microcontroller module for unified analysis and processing. The data between this module and the traffic flow is wirelessly communicated through 5G technology, and it communicates with the microcontroller in a wired manner, ensuring the rapid and secure transmission of data; the data storage module is used to store data such as traffic flow, speed, and vehicle type, and can manage a large amount of traffic flow information; save historical traffic data for retrospective analysis when needed, and support querying and analyzing the traffic flow conditions of different time periods and road sections; the main function of the power module is to provide electrical energy for the entire road traffic flow detection subsystem, and solar cells are applied for power supply.

[0171] The road vehicle driving guidance subsystem includes a microcontroller module, a vehicle information collection module, an in-vehicle communication module, a display module, a voice module, a storage module, and a power module. The main function of this subsystem is to receive traffic flow and pedestrian information from the road traffic flow detection subsystem and the road crosswalk pedestrian detection subsystem, and based on its own speed and position, calculate the safe speed and appropriate lane, and issue guidance to the driver through the voice module; among them, the microcontroller module is the core module of the road vehicle driving guidance subsystem. It is responsible for summarizing and analyzing various types of information collected by the vehicle information collection module, calculating the appropriate speed range, and combining the lane occupancy, the current position of the vehicle, and the pedestrian information to recommend whether a lane change is needed, and judge whether to stop and give way if necessary. The vehicle information collection module is built into the road vehicle and can collect the status data of the vehicle in real time, mainly including the vehicle's speed, position, acceleration, braking state, steering wheel angle, etc., to ensure that the system can make reasonable decisions based on the dynamic information of the vehicle.

[0172] The in-vehicle communication module applies 5G communication technology and sends the obtained real-time vehicle speed, the location and lane of the vehicle to the communication and transmission module of the road traffic flow detection subsystem via wireless communication to achieve the effect of vehicle-road coordination for the analysis and application of the overall traffic flow. The display module is built into the vehicle, which can display the road conditions in real time, highlight the lanes with different colors, and prompt the driver to accelerate, decelerate or change lanes, providing more intuitive guidance to the driver. The voice module and the display module are both built into the vehicle. The voice module broadcasts to remind the driver of the pedestrian situation ahead and gives real-time voice guidance, providing real-time suggestions such as safe vehicle speed, lane selection, and pedestrian warning. The main function of the storage module is to store the vehicle speed and location data; the power supply module is used to provide stable power supply for the subsystem to ensure the normal operation of the system under various conditions.

[0173] The road pedestrian crossing guidance subsystem includes a microcontroller, an LED display screen, a communication module, a storage module, a voice module, and a power supply module. The main function of this subsystem is to combine the traffic flow situation and the guidance information for vehicle driving behavior to provide some intelligent instructions and reminders for the pedestrians crossing the road section, helping pedestrians choose a more appropriate time to cross the road, thereby improving the safety of pedestrians crossing the road. Among them, the microcontroller is the core module of the road pedestrian crossing guidance subsystem. It is responsible for processing the information transmitted by the communication module and converting it into display information for the other modules. The LED display screen is set at the road section, which can display the current traffic flow situation of the road section in real time and highlight the lanes where pedestrians can safely pass and the lanes where they need to stop and wait with high brightness. The communication module is used to collect the vehicle information and pedestrian information transmitted by the other subsystems and transmit them to the microcontroller by wire for further analysis and processing. The storage module is used to store the traffic flow and pedestrian information obtained by the communication module. The power supply module is used to provide stable power supply for the subsystem to ensure the normal operation of the system under various conditions.

[0174] Specifically, when there are no vehicles or pedestrians in the vehicle warning window, at this time, there will be no intersection between the vehicle and the pedestrian, and the vehicle and the pedestrian can be guided to directly pass through the warning window. The guiding voice is broadcast in the voice module of the road vehicle driving behavior guidance subsystem: "There are no pedestrians ahead, and you can keep the current vehicle speed and pass through." At the same time, an electronic map with the vehicle's forward area marked in light green is displayed in the display module of the road vehicle driving behavior guidance subsystem. At the same time, the LED display screen in the road pedestrian crossing guidance subsystem displays a light green area for pedestrian passage guidance, where the light green area represents that pedestrians can safely pass through this lane.

[0175] When guiding the target vehicle to pass through the upcoming pedestrian crossing section at the current vehicle speed, the guiding voice is broadcast in the voice module of the section vehicle driving behavior guiding subsystem as: "There is an upcoming pedestrian crossing section. You can maintain the current vehicle speed to pass through." At the same time, an electronic map of the vehicle's forward area marked in light green is displayed on the display module of the section vehicle driving behavior guiding subsystem.

[0176] When guiding the target vehicle to decelerate to the guiding vehicle speed to pass through the upcoming pedestrian crossing section, the guiding voice is broadcast in the voice module of the section vehicle driving behavior guiding subsystem as: "There is an upcoming pedestrian crossing section. Please decelerate to a safe vehicle speed to pass through." At the same time, an electronic map of the vehicle's forward area marked in light orange is displayed on the display module of the section vehicle driving behavior guiding subsystem to remind the vehicle to decelerate.

[0177] When guiding the target vehicle to accelerate to the guiding vehicle speed to pass through the upcoming pedestrian crossing section, the guiding voice is broadcast in the voice module of the section vehicle driving behavior guiding subsystem as: "Attention, pedestrians are about to arrive ahead. Please accelerate to to pass through." At the same time, an electronic map of the vehicle's forward area marked in light blue is displayed on the display module of the section vehicle driving behavior guiding subsystem.

[0178] When the target vehicle needs to change lanes before reaching the pedestrian crossing area of the section, the following conditions need to be met: a. Multi-lane road: The section needs to be a multi-lane road section to meet the conditions for changing lanes; b. Safety of lane change: The target lane is empty before the lane change and does not obstruct the driving of other vehicles; c. There are no pedestrians passing in front of the lane, and the lane change does not affect the passage of pedestrians; d. After changing lanes, it can meet the conditions.

[0179] Considering the safety of pedestrian crossing, it is stipulated here that the default lane change is to the right lane, and only one lane can be changed at a time. If the above conditions are not met, no lane change guidance will be taken, and the vehicle will be guided to stop and give way.

[0180] When the above conditions are met, the system will start the lane change guidance. The guiding voice is broadcast in the voice module of the section vehicle driving behavior guiding subsystem as: "Attention, there are pedestrians crossing ahead. Please change to the right lane to give way." At the same time, an electronic map of the lane that the vehicle needs to change to, marked in yellow, is displayed on the display module of the section vehicle driving behavior guiding subsystem. If the current situation does not meet the above lane change conditions, the vehicle will be guided to stop and wait for the pedestrians to pass. The guiding voice is broadcast in the voice module of the section vehicle driving behavior guiding subsystem as: "Attention, there are pedestrians crossing ahead. Please stop and give way"; at the same time, an electronic map using a red area and a stop symbol to prompt the vehicle to stop and give way is displayed on the display module of the section vehicle driving behavior guiding subsystem.

[0181] For the coordinated vehicle flow that can pass at a constant speed, decelerate or accelerate, the guiding voice for each vehicle is broadcast in the voice module of the road section vehicle driving behavior guiding subsystem: "In the upcoming pedestrian crossing section, you can pass at the current speed, need to decelerate to the guiding speed, or need to accelerate to the guiding speed." At the same time, an electronic map with the vehicle's forward area marked in the corresponding color is displayed in the display module of the road section vehicle driving behavior guiding subsystem.

[0182] When there are multiple lanes in the road section and there is a single vehicle in each lane, number the lanes with vehicles from the outside to the inside of the road, denoted as , i = 1, 2, 3, …, n, calculate the time for the vehicle in each lane to reach the intersection and the time for the pedestrian to reach the intersection of each lane .

[0183] Calculate in sequence from the outermost lane to the innermost lane. If the time for the vehicle in the outermost lane to reach the intersection , that is, the outermost vehicle arrives first, then guide the vehicle to maintain its speed or accelerate to to pass. The guiding method is the same as in Scenario 1, "When the vehicle arrives at the intersection earlier than the pedestrian", and guide the pedestrian to stop waiting. At this time, recalculate the time for the pedestrian to reach the remaining lanes, and the vehicle in the inner lane recalculates the difference between the time to reach the intersection and the time for the pedestrian to reach the intersection, and determines whether the pedestrian or the vehicle should give way.

[0184] If the time for the vehicle in the outermost lane to reach the intersection , that is, the pedestrian arrives first or they arrive almost at the same time, then guide the vehicle to maintain its speed, decelerate to to pass, or stop and wait. The guiding method is the same as in Scenario 1, "When the pedestrian approaches the intersection while the vehicle is far from the intersection", and guide the pedestrian to pass through the first lane.

[0185] And so on, calculate up to the innermost lane to obtain the guiding method for each single vehicle in each lane, and remind with the voice system and the electronic map. At the same time, conduct traffic guidance for pedestrians through the LED display screen in the road section pedestrian crossing guiding subsystem. Among them, light green can represent that pedestrians can safely pass through this lane, and red can represent that pedestrians need to stop and wait for the vehicle to pass before passing through this lane.

[0186] A computer device according to an embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-transitory computer-readable instructions. Specifically, the memory may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the computer device to perform desired functions. In an embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory, so that the computer device executes all or part of the steps of the vehicle driving guidance method in the scenario of road section pedestrian crossing according to the foregoing embodiments of the present disclosure. Those skilled in the art should understand that, in order to solve the technical problem of how to obtain a good user experience effect, this embodiment may also include well-known structures such as communication buses and interfaces, and these well-known structures should also be included in the protection scope of the present disclosure.

[0187] As Figure 10 FIG. is a schematic structural diagram of a computer device provided by an embodiment of the present disclosure. It shows a schematic structural diagram of a computer device suitable for implementing the computer device in the embodiment of the present disclosure. Figure 10 The computer device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0188] As Figure 10 As shown, the computer device may include a processor (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in read-only memory (ROM) or a program loaded from a storage device into random access memory (RAM). In the RAM, various programs and data required for the operation of the computer device are also stored. The processor, ROM, and RAM are connected to each other through a bus. The input / output (I / O) interface is also connected to the bus.

[0189] Generally, the following devices may be connected to the I / O interface: an input device including, for example, a sensor or a visual information acquisition device, etc.; an output device including, for example, a display screen, etc.; a storage device including, for example, a magnetic tape, a hard disk, etc.; and a communication device. The communication device may allow the computer device to communicate with other devices (such as edge computing devices) wirelessly or wiredly to exchange data. Although Figure 10A computer device having various devices is shown, but it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0190] The above computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or removable hard disk), media having built-in rewritable non-volatile memory (e.g., memory card), and media having built-in ROM (e.g., ROM cartridge). For a detailed description of this embodiment, reference may be made to the corresponding descriptions in the foregoing embodiments, which will not be elaborated herein.

[0191] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present disclosure. In addition, the above specific details are only for illustrative and facilitating understanding purposes and are not limitations. The above details do not limit the present disclosure to necessarily adopt the above specific details for implementation.

Claims

1. A vehicle driving guidance method in the context of pedestrians crossing the road at a section, characterized in that, Including: In response to a preset warning line trigger signal, the vehicle that triggers the preset warning line is used as the target vehicle, and the vehicle position, vehicle speed, and pedestrian behavior characteristic information within the pedestrian crossing area of the road section of the target vehicle are obtained in real time; Based on the pedestrian behavior characteristic information, the pedestrian closest to the preset warning line is used as the target pedestrian, and based on the vehicle position and the position of the target pedestrian, a potential intersection point is determined; According to the vehicle position, the vehicle speed, the position of the target pedestrian, the speed of the target pedestrian, and the potential intersection point, the expected vehicle time and pedestrian expected time for the target vehicle and the target pedestrian to reach the potential intersection point are respectively obtained; According to the vehicle expected time and the pedestrian expected time, the safety time reserved for both to reach the potential intersection point is determined; Judge whether the pedestrian expected time is greater than the vehicle expected time. If so, obtain the first safe vehicle speed based on the first strategy, and dynamically obtain the first guiding vehicle speed of the target vehicle based on the first safe vehicle speed and the safety time, and guide the target vehicle; If not, obtain the second safe vehicle speed based on the second strategy, and dynamically obtain the second guiding vehicle speed of the target vehicle based on the second safe vehicle speed and the safety time, and guide the target vehicle.

2. The vehicle driving guidance method in the scenario of pedestrians crossing the road on a road section according to claim 1, wherein, The preset warning line is a trigger line with a preset length from the pedestrian crossing area of the road section, and the trigger line is a straight line perpendicular to the lane driving direction; The pedestrian behavior characteristic information includes the position information of pedestrians waiting to cross the street, the position information of pedestrians crossing the street, and the speed information of pedestrians crossing the street. Among them, the position information of pedestrians crossing the street includes the position information of pedestrians crossing the street in the forward direction and the position information of pedestrians crossing the street in the reverse direction, and the speed information of pedestrians crossing the street includes the speed information of pedestrians crossing the street in the forward direction and the speed information of pedestrians crossing the street in the reverse direction; The pedestrian crossing area of the road section includes a pedestrian waiting area for crossing the street, a pedestrian forward crossing area, and a pedestrian reverse crossing area.

3. The vehicle driving guidance method in the scenario of pedestrians crossing the road on a road section according to claim 2, wherein, The step of, based on the pedestrian behavior characteristic information, using the pedestrian closest to the preset warning line as the target pedestrian, and determining a potential intersection point based on the vehicle position and the position of the target pedestrian, includes: Determine the coordinate origin; When the pedestrian crossing area of the road section is located in a one-way lane, the intersection of the longitudinal central axis of the pedestrian crossing area of the road section and the left roadside of the one-way lane is used as the coordinate origin, the driving direction of the target vehicle is used as the positive direction of the X axis, and the moving direction of the pedestrian crossing the street in the forward direction is used as the positive direction of the Y axis; When the pedestrian crossing area of the road section is located in a two-way lane, the intersection of the longitudinal central axis of the pedestrian crossing area of the road section and the central axis of the two-way lane is used as the coordinate origin, the driving direction of the target vehicle is used as the positive direction of the X axis, and the moving direction of the pedestrian crossing the street in the forward direction is used as the positive direction of the Y axis; When the pedestrian crossing area of the road section is located in a multi-lane two-way road, the intersection of the longitudinal central axis of the pedestrian crossing area of the road section and the central axis of the multi-lane two-way road is used as the coordinate origin, the driving direction of the target vehicle is used as the positive direction of the X axis, and the moving direction of the pedestrian crossing the street in the forward direction is used as the positive direction of the Y axis; Determine the position of the vehicle and the position of the target pedestrian based on the coordinate origin; Determine potential intersection points based on the position of the vehicle and the position of the target pedestrian; The x coordinate of the potential intersection point is the x coordinate of the target pedestrian, and the y coordinate of the potential intersection point is the y coordinate of the vehicle position.

4. The vehicle driving guidance method in the scenario of pedestrians crossing the road on a road section according to claim 3, wherein The vehicle expected time and pedestrian expected time for the target vehicle and the target pedestrian to reach the potential intersection point are respectively obtained according to the vehicle position, the vehicle speed, the position of the target pedestrian, the speed of the target pedestrian, and the potential intersection point, including: Determine the vehicle expected time based on the vehicle position, the vehicle speed, and the potential intersection point; The expected time of the vehicle is , , where is the x-coordinate of the potential intersection point, is the x-coordinate of the target vehicle, is the vehicle speed; Judge whether the target pedestrian is a pedestrian crossing the street. If so, determine the pedestrian expected time based on the obtained position of the target pedestrian, the speed of the target pedestrian, and the potential intersection point; The pedestrian expected time is , ; is the y coordinate of the target vehicle, is the y coordinate of the target pedestrian, is the speed of the target pedestrian; If the target pedestrian is not a pedestrian crossing the street, obtain the average pedestrian speed from the preset dynamic information table of street-crossing pedestrians in the section, and use the average pedestrian speed as the speed of the target pedestrian, and determine the pedestrian expected time based on the obtained position of the target pedestrian, the speed of the target pedestrian, and the potential intersection point.

5. The vehicle driving guidance method in the scenario of pedestrians crossing the road on a road section according to claim 4, wherein, If the target vehicle needs to change lanes before reaching the pedestrian crossing area of the section, set the y coordinate of the target vehicle after performing the expected lane change operation to the y coordinate corresponding to the longitudinal center axis of the lane after the lane change, and record it as the expected transformed y coordinate; Update the y coordinate of the potential intersection point to the expected transformed y coordinate; The vehicle expected time and pedestrian expected time for the target vehicle and the target pedestrian to reach the potential intersection point are respectively obtained according to the vehicle position, the vehicle speed, the position of the target pedestrian, the speed of the target pedestrian, and the potential intersection point, including: Obtain the width of a single lane, the number of lanes involved in the vehicle lane change, and the lateral driving acceleration of the target vehicle; Determine the expected lateral lane change time of the target vehicle according to the lane width, the number of lanes, and the lateral driving acceleration; The lateral expected lane change time is , , where is the number of lanes is the lane width is the lateral driving acceleration; Obtain the expected longitudinal moving distance according to the vehicle speed and the expected lateral lane change time; The longitudinal expected movement distance is , ; Determine the vehicle expected time according to the expected lateral lane change time, the expected longitudinal moving distance, the vehicle speed, and the distance between the target vehicle and the potential intersection point; The expected time of the vehicle is , ; If the target pedestrian is a pedestrian crossing the street, determine the pedestrian expected time based on the obtained position of the target pedestrian, the speed of the target pedestrian, and the expected transformed y coordinate; The pedestrian expected time is , ; is the expected transformed y coordinate, is the y coordinate of the target pedestrian, is the speed of the target pedestrian; If the target pedestrian is not a pedestrian crossing the street, obtain the average pedestrian speed from the preset dynamic information table of street-crossing pedestrians in the section, and use the average pedestrian speed as the speed of the target pedestrian, and determine the pedestrian expected time based on the obtained position of the target pedestrian, the speed of the target pedestrian, and the expected transformed y coordinate.

6. The vehicle driving guidance method in the pedestrian crossing situation of a road section according to claim 5, characterized in that, The safety time is : , or ； Among them, is the reaction time of the driver of the target vehicle, is the preset buffer time, is the vehicle expected time when the target vehicle does not perform the expected lane change, is the pedestrian expected time corresponding to when the target vehicle does not perform the expected lane change, is the vehicle expected time when the target vehicle performs the expected lane change, is the pedestrian expected time corresponding to when the target vehicle performs the expected lane change.

7. The vehicle driving guidance method in the scenario of pedestrians crossing the road on a road section according to claim 6, wherein, Obtain the first safe vehicle speed based on the first strategy, and dynamically obtain the first guiding vehicle speed of the target vehicle based on the first safe vehicle speed and the safety time, and guide the target vehicle, including: Determine a target distance based on the x - coordinate of the vehicle position and the x - coordinate of the target pedestrian's position; The target distance is , ; Obtain a first safe vehicle speed based on the target distance, the vehicle's expected time, and the safety time; The first safe vehicle speed is , , or ; Dynamically obtain a first guidance vehicle speed of a target vehicle based on the first safe vehicle speed and the safe time; the first guidance vehicle speed is , ≥ ; Issue an instruction with an average vehicle speed not less than the first guidance vehicle speed to the target vehicle based on the first guidance vehicle speed, and the target vehicle performs driving operations according to this instruction.

8. The vehicle driving guidance method in the scenario of pedestrians crossing the road on a road section according to claim 6, characterized in that, The obtaining the second safe vehicle speed based on the second strategy and dynamically obtaining the second guidance vehicle speed of the target vehicle based on the second safe vehicle speed and the safety time and guiding the target vehicle includes: Determine a target distance based on the x - coordinate of the vehicle position and the x - coordinate of the target pedestrian's position; The target distance is , ; Obtain a second safe vehicle speed based on the target distance, the vehicle's expected time, and the safety time; The second safe vehicle speed is , , or ; Dynamically obtain a second guidance speed of a target vehicle based on the second safe speed and the safe time; the second guidance speed is , ≤ ; Issue an instruction with an average vehicle speed not greater than the second guidance vehicle speed to the target vehicle based on the second guidance vehicle speed, and the target vehicle performs driving operations according to this instruction.

9. The vehicle driving guidance method in the scenario of pedestrians crossing the road on a road section according to claim 6, characterized in that, Further includes: Judge whether the target vehicle is located in a coordinated traffic flow. If so, use the guidance vehicle speed of the target vehicle as the guidance vehicle speed of other vehicles in the coordinated traffic flow; The judging whether the target vehicle is located in a coordinated traffic flow. If so, using the guidance vehicle speed of the target vehicle as the guidance vehicle speed of other vehicles in the coordinated traffic flow includes: In response to a preset warning line trigger signal, use the vehicle that triggers the preset warning line as the target vehicle, and real - time obtain the vehicle position, vehicle speed of the target vehicle, and the rear - vehicle position and rear - vehicle speed of the vehicle behind the target vehicle; Determine the real - time distance based on the vehicle position of the target vehicle and the rear - vehicle position; Determine the dynamic safety distance according to the rear - vehicle speed, the preset buffer distance, and the safety time; If the real - time distance is not greater than the dynamic safety distance, determine that the target vehicle is located in a coordinated traffic flow, and the target vehicle and the corresponding rear vehicle are in the same coordinated traffic flow; Use the guidance vehicle speed of the target vehicle as the guidance vehicle speed of other vehicles in the coordinated traffic flow, and the driving directions of other vehicles in the coordinated traffic flow are the same as that of the target vehicle.

10. A vehicle driving guidance system in the context of pedestrians crossing the road at a section, characterized in that, Based on the vehicle driving guidance method in the scenario of pedestrian crossing on a road section according to any one of claims 1 - 9, includes: The road layer is used to display in real - time the associated lane information including the preset warning line and the road - section pedestrian crossing area; The vehicle layer is used to display in real - time the target vehicle information that triggers the preset warning line and the rear - vehicle information of the vehicle behind the target vehicle and at a preset distance from the target vehicle; The prompt layer is used to form a deceleration reminder layer in a first - type color in real - time, or form an acceleration reminder layer in a second - type color in real - time, or form a constant - speed reminder layer in a third - type color in real - time, or form a stop reminder layer in a fourth - type color in real - time; The arrow layer is used to display the expected driving path corresponding to the vehicle lane change in the form of an arrow.

Images