Bus shelter based on intelligent connected vehicle technology application

Abstract

Disclosed in the present invention is a bus shelter based on an intelligent connected vehicle technology application. In the prior art, the degree of association between buses and bus shelters is low, and prediction results of bus arrival time are inaccurate. In the present invention, a Gaussian plume model is used for simulating a driving process of a road vehicle between every two intersections, thereby accurately analyzing the impact of road traffic flow on the bus arrival time, and providing real-time bus information. By directly communicating with a nearby vehicle to perform information exchange, more accurate arrival and departure information can be provided compared with conventional positioning information-based stop announcement. Information interaction between a passenger and a bus system is realized, and travel experience is improved.

Description

A bus shelter based on intelligent connected technology Technical Field

[0001] This invention belongs to the field of intelligent public transportation facilities technology, and relates to a bus shelter based on intelligent network technology. Background Technology

[0002] Traditional bus shelters have a relatively simple function, providing only basic shelter from wind and rain, which is insufficient to meet the information and intelligent needs of modern urban public transportation systems. Modern intelligent bus shelters mainly focus on providing intelligent integration and information services such as bus stop information dissemination, multimedia information dissemination, passenger convenience services, and video surveillance, basically meeting the application requirements of current public transportation systems.

[0003] However, with the development of intelligent connected technologies and the increasing prospect of driverless vehicles, it is necessary to further integrate intelligent bus stops into future connected systems such as people, vehicles, roads, and cloud computing. This requires effectively connecting buses and bus shelters through networks to provide richer information and services, improve the travel experience for passengers, and enhance the efficiency of public transportation systems. Summary of the Invention

[0004] To address the problems existing in the background technology, this invention proposes a bus shelter based on intelligent connected vehicle technology.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] The data acquisition module collects images of vehicles entering the bus operating area based on time series data.

[0007] The data processing module identifies vehicle characteristics, marks vehicles, predicts the fuzzy location of vehicles, and updates the traffic flow within the bus operating area in real time when a vehicle leaves the bus operating area.

[0008] The bus timing module predicts the arrival time of buses based on the traffic flow within the bus's operating range.

[0009] The information display module shows the time required for the bus to arrive at the current stop, providing passengers with intuitive information;

[0010] The data transmission module coordinates and schedules the sending and receiving of information between various modules.

[0011] Furthermore, the data acquisition module collects images of vehicles entering the bus operating area based on time series data;

[0012] The data processing module identifies vehicle features and marks the vehicles;

[0013] The data processing module predicts the fuzzy position of the bus within its operating range based on time and spatial factors.

[0014] The data processing module determines the traffic flow within the bus operating zone based on the time it takes for a vehicle to enter and exit the bus operating zone.

[0015] The bus timing module simulates the driving process of road vehicles based on the Gaussian plume model to calculate the arrival time of buses.

[0016] The information display module shows the time required for the bus to arrive at the current stop.

[0017] Furthermore, the specific method by which the data processing module identifies vehicle features and marks the vehicle is as follows:

[0018] Edge detection is performed on the vehicle images collected by the data acquisition module to detect the location corresponding to the license plate;

[0019] Extract the corresponding position of the license plate and segment the area where the license plate is located according to a fixed ratio;

[0020] The segmented license plate area is compared with the existing character shapes to obtain the vehicle's license plate number mark;

[0021] Based on the license plate number, the nature of the vehicle, as well as its operating status and location information, can be extracted.

[0022] Furthermore, the data processing module predicts the fuzzy position of the bus within the bus's operating range, and uses the vehicle image acquisition time and location in historical time to calculate the speed changes and vehicle turning in different bus operating ranges.

[0023] Using the first deep learning model, based on vehicle speed and vehicle steering data from historical time data, the fuzzy position of any vehicle is predicted. In the prediction result, multiple position points are generated based on multiple steering opportunities.

[0024] Set the time it takes for a vehicle to reach the bus shelter corresponding to a certain turning opportunity at the predicted speed. If the vehicle does not pass the bus shelter corresponding to the turning opportunity after the predicted time has elapsed, then the predicted point is deleted.

[0025] Furthermore, the method by which the bus timing module predicts bus arrival times is as follows:

[0026] A Gaussian plume model is established on the current bus route to simulate the traffic flow from the current intersection to the next nearest intersection. The specific formula is as follows:

[0027] ;

[0028] in The location of the next intersection. For the traffic flow at the next intersection, This represents the current traffic flow at the intersection. The average speed of the vehicle. This is the current location of the intersection. Let be the standard deviation of the diffusion of vehicles in the direction of travel on the road. Let $ be the standard deviation of the diffusion of vehicles in the direction perpendicular to the road lanes. The value is equal to the distance from the current intersection to the next nearest intersection. The value is equal to the number of lanes on the current road;

[0029] Based on the traffic light of the next nearest intersection, if the light is green, the Gaussian plume model will diffuse normally.

[0030] If the traffic light at the next nearest intersection is red, then add a constraint to stop the spread of vehicles that have already spread to the next nearest intersection in the Gaussian plume model and stack them at the next nearest intersection position.

[0031] Substitute the current position of the bus into the Gaussian plume model and record the time required for the bus to diffuse to the destination.

[0032] Furthermore, the data transmission module utilizes V2X communication mode to transmit data.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] It provides real-time bus information by communicating directly with nearby vehicles, offering more accurate arrival and departure information compared to traditional location-based announcements. This enables information interaction between passengers and the public transportation system, enhancing the travel experience. Attached Figure Description

[0035] Figure 1 is a system module architecture diagram of the present invention;

[0036] Figure 2 is a flowchart of the system operation of the present invention;

[0037] Figure 3 is a system module collaboration diagram of the present invention. Detailed Implementation

[0038] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Example 1

[0040] The technical solution adopted in this invention is as follows.

[0041] As shown in Figure 1, a bus shelter based on intelligent connected vehicle technology includes:

[0042] The data acquisition module uses vehicle-to-everything (V2X) technology to acquire road information in real time, including collecting images of vehicles entering the bus route, the number of vehicles, and traffic light information based on time series data.

[0043] The data processing module identifies vehicle characteristics, marks vehicles, predicts the fuzzy location of vehicles, and updates the traffic flow within the bus operating area in real time when a vehicle leaves the bus operating area.

[0044] The bus timing module predicts the arrival time of buses based on the traffic flow within the bus's operating range.

[0045] The information display module shows the time required for the bus to arrive at the current stop, providing passengers with intuitive information;

[0046] The data transmission module coordinates and schedules the sending and receiving of information between various modules.

[0047] As shown in Figure 2, the method for implementing the bus shelter based on intelligent connected vehicle technology includes:

[0048] The data acquisition module collects images of vehicles entering the bus operating area based on time series data.

[0049] The data processing module identifies vehicle features and marks the vehicles;

[0050] The data processing module predicts the fuzzy position of the bus within its operating range based on time and spatial factors.

[0051] The data processing module determines the traffic flow within the bus operating zone based on the time it takes for a vehicle to enter and exit the bus operating zone.

[0052] The bus timing module simulates the driving process of road vehicles based on the Gaussian plume model to calculate the arrival time of buses.

[0053] The information display module shows the time required for the bus to arrive at the current stop.

[0054] First, images of vehicles entering the bus operating area are collected based on time series data. Vehicle features are identified in the collected images, and each vehicle is uniquely identified. This solution extracts the vehicle license plate number, which ensures vehicle uniqueness and is not obscured, allowing for the complete extraction of the vehicle's unique identifier.

[0055] Edge detection is performed on the vehicle images collected by the data acquisition module to detect the location of the license plate. Edge detection can be performed in various ways, such as the Canny operator, gradient value extraction, dilation, and erosion. Any of these methods can be used to extract the edges of the vehicle.

[0056] The license plate's corresponding positions are extracted, and the area containing the license plate is segmented according to a fixed ratio. The extraction of the license plate's corresponding positions can be achieved using deep learning models, convolutional neural networks, or feature classifiers. After extraction, based on a fixed ratio, each character on the license plate is 45mm wide, with space including left and right margins. The stroke width of each character is 10mm, the gap between the second and third characters from the left is 34mm, and the gap between other characters is 12mm. There are a total of 7 characters, and the width of each character is approximately 10% of the license plate's width. The character area of ​​the license plate is then segmented using a fixed ratio.

[0057] The segmented license plate area is compared with the existing character shapes to obtain the vehicle's license plate number mark.

[0058] After obtaining the vehicle's license plate number, a network query is performed using connected technology to extract the vehicle's nature, operating status, and location information. When a vehicle passes through multiple bus shelters, information about the same vehicle can be analyzed across multiple shelters to obtain details such as the vehicle's operating status.

[0059] The data processing module predicts the ambiguous position of buses within their operating range based on time and spatial factors. It calculates speed variations and turning patterns for different bus operating ranges by utilizing historical vehicle image acquisition times and locations.

[0060] Set the time it takes for a vehicle to reach the bus shelter corresponding to a certain turning opportunity at the predicted speed. If the vehicle does not pass the bus shelter corresponding to the turning opportunity after the predicted time has elapsed, then the predicted point is deleted.

[0061] In historical time, vehicle images should be collected in groups of time and location. For example, if vehicle A enters the first bus route, it may not leave the first bus route and instead turns to enter the second bus route. If vehicle A is captured in the second bus route, it means that vehicle A has left the first bus route.

[0062] The first deep learning model predicts the fuzzy position of any vehicle based on historical data of vehicle speed and steering. This includes predicting vehicle speed and the probability of steering during the journey. Multiple position points are generated based on these multiple steering opportunities. Since the vehicle's steering record is not fixed during its journey, multiple predictions need to be generated until the vehicle leaves the bus's operating area.

[0063] Based on traffic flow factors, bus arrival times are simulated. A Gaussian plume model is established on the current bus route to simulate the traffic flow from the current intersection to the next nearest intersection. The specific formula is as follows:

[0064] ;

[0065] in The location of the next intersection. For the traffic flow at the next intersection, This represents the current traffic flow at the intersection. The average speed of the vehicle. This is the current location of the intersection. Let be the standard deviation of the diffusion of vehicles in the direction of travel on the road. Let $ be the standard deviation of the diffusion of vehicles in the direction perpendicular to the road lanes. The value is equal to the distance from the current intersection to the next nearest intersection. The value is equal to the number of lanes on the current road.

[0066] Based on the traffic light at the next nearest intersection, if the light is green, the Gaussian plume model will diffuse normally.

[0067] If the traffic light at the next nearest intersection is red, then add a constraint to stop the spread of vehicles that have already spread to the next nearest intersection in the Gaussian plume model, and stack them at the next nearest intersection position.

[0068] Substitute the current position of the bus into the Gaussian plume model and record the time required for the bus to diffuse to the destination.

[0069] The Gaussian plume model was originally an algorithm for simulating the propagation of pollutants in the air. Based on the orderliness and directionality of vehicle movement on the road, it can treat intersections as pollution sources. The Gaussian plume model was modified based on the actual road conditions, and traffic light constraints were added to effectively simulate the position of vehicles on the road.

[0070] To verify the practicality of the present invention, experiments were conducted on the same bus traveling from the monitored intersection to the designated bus stop under different traffic flow conditions, as shown in the table below.

[0071]

[0072] Based on the simulation results above, it can be seen that the Gaussian plume model shows a clear linear correlation between the calculated bus arrival time and the traffic volume, which is in line with objective laws. Furthermore, the simulation results of bus arrival time are consistent with objective conditions. Therefore, simulating road traffic flow and extracting the bus points in the traffic flow using the Gaussian plume model can meet the requirements for high-precision prediction of bus arrival time.

[0073] In the above method, data transmission utilizes the V2X communication mode. V2X encompasses various application communication scenarios, including vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), vehicle-to-pedestrian (V2P), and vehicle-to-external network (V2N). In bus shelters where intelligent connected vehicle technology is applied, the data sharing efficiency of V2X should be maximized.

[0074] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A bus shelter based on intelligent connected vehicle technology, characterized in that, The methods include the following: The data acquisition module acquires road information in real time based on vehicle connectivity technology; The data processing module identifies vehicle characteristics, marks vehicles, predicts the fuzzy location of vehicles, and updates the traffic flow within the bus operating area in real time when a vehicle leaves the bus operating area. The bus timing module predicts the arrival time of buses based on the traffic flow within the bus's operating range. The information display module shows the time required for the bus to arrive at the current stop, providing passengers with intuitive information; The data transmission module coordinates and schedules the sending and receiving of information between various modules.

2. A bus shelter based on intelligent network technology according to claim 1, characterized in that... , The data acquisition module collects images of vehicles entering the bus operating area based on time series data. The data processing module identifies vehicle features and marks the vehicles; The data processing module predicts the fuzzy position of the bus within its operating range based on time and spatial factors. The data processing module determines the traffic flow within the bus operating zone based on the time it takes for a vehicle to enter and exit the bus operating zone. The bus timing module simulates the driving process of road vehicles based on the Gaussian plume model to calculate the arrival time of buses. The information display module shows the time required for the bus to arrive at the current stop.

3. A bus shelter based on intelligent network technology according to claim 1, characterized in that... The specific method by which the data processing module identifies vehicle features and marks vehicles is as follows: Edge detection is performed on the vehicle images collected by the data acquisition module to detect the location corresponding to the license plate; Extract the corresponding position of the license plate and segment the area where the license plate is located according to a fixed ratio; The segmented license plate area is compared with the existing character shapes to obtain the vehicle's license plate number mark; Based on the license plate number, the nature of the vehicle, as well as its operating status and location information, can be extracted.

4. A bus shelter based on intelligent connected technology as described in claim 1, characterized in that... The data processing module predicts the fuzzy position of the bus within its operating range. It uses the vehicle image acquisition time and location in historical time to calculate the speed changes and vehicle turning in different operating ranges of the bus. Using the first deep learning model, based on vehicle speed and vehicle steering data from historical time data, the fuzzy position of any vehicle is predicted. In the prediction results, multiple position points are generated based on multiple steering opportunities. And the vehicle is in a certain predicted turning position, Set the time it takes for a vehicle to reach the bus shelter corresponding to a certain turning opportunity at the predicted speed. If the vehicle does not pass the bus shelter corresponding to the turning opportunity after the predicted time has elapsed, then the predicted point is deleted.

5. A bus shelter based on intelligent network technology according to claim 1, characterized in that... The method used by the bus timing module to predict bus arrival times is as follows: A Gaussian plume model is established on the current bus route to simulate the traffic flow from the current intersection to the next nearest intersection. The specific formula is as follows: ； in The location of the next intersection. For the traffic flow at the next intersection, This represents the current traffic flow at the intersection. The average speed of the vehicle. This is the current location of the intersection. Let be the standard deviation of the diffusion of vehicles in the direction of travel on the road. Let be the standard deviation of the diffusion of vehicles in the direction perpendicular to the road lanes. The value is equal to the distance from the current intersection to the next nearest intersection. The value is equal to the number of lanes on the current road; Based on the traffic light of the next nearest intersection, if the light is green, the Gaussian plume model will diffuse normally. If the traffic light at the next nearest intersection is red, then add a constraint to stop the spread of vehicles that have already spread to the next nearest intersection in the Gaussian plume model and stack them at the next nearest intersection position. Substitute the current position of the bus into the Gaussian plume model and record the time required for the bus to diffuse to the destination.

6. A bus shelter based on intelligent connected technology according to claim 1, characterized in that... The data transmission module uses V2X communication mode to transmit data.

Images