WO2023014311A1 - Traffic density estimation system and a method thereof - Google Patents

Traffic density estimation system and a method thereof Download PDF

Info

Publication number
WO2023014311A1
WO2023014311A1 PCT/TR2021/051098 TR2021051098W WO2023014311A1 WO 2023014311 A1 WO2023014311 A1 WO 2023014311A1 TR 2021051098 W TR2021051098 W TR 2021051098W WO 2023014311 A1 WO2023014311 A1 WO 2023014311A1
Authority
WO
WIPO (PCT)
Prior art keywords
traffic
routing
information
data
allows
Prior art date
Application number
PCT/TR2021/051098
Other languages
French (fr)
Inventor
Alper DEGIRMENCI
Berk SONMEZ
Taha TURK
Caner KAVAK
Emrah YILMAZ
Murat AKIN
Seref SAGIROGLU
Original Assignee
Basarsoft Bilgi Teknolojileri Anonim Sirketi
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Basarsoft Bilgi Teknolojileri Anonim Sirketi filed Critical Basarsoft Bilgi Teknolojileri Anonim Sirketi
Priority to EP21944417.1A priority Critical patent/EP4162464A4/en
Publication of WO2023014311A1 publication Critical patent/WO2023014311A1/en

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3691—Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions
    • G01C21/3694—Output thereof on a road map
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
    • G08G1/096716—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information does not generate an automatic action on the vehicle control
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096733—Systems involving transmission of highway information, e.g. weather, speed limits where a selection of the information might take place
    • G08G1/096758—Systems involving transmission of highway information, e.g. weather, speed limits where a selection of the information might take place where no selection takes place on the transmitted or the received information
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • G08G1/096775—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
    • G08G1/096805—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route
    • G08G1/096811—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route where the route is computed offboard
    • G08G1/096816—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route where the route is computed offboard where the complete route is transmitted to the vehicle at once
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
    • G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
    • G08G1/096844—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route where the complete route is dynamically recomputed based on new data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]

Definitions

  • the invention relates to a system and a method that allows for determining the state of traffic density by processing and analyzing instant GPS information in big data architecture.
  • the present invention particularly relates to a system and a method that allows for estimating feature traffic density and detecting road characteristics.
  • This invention relates to a traffic planning system that detects the possible traffic density depending on the travel routes received from the users and provides a route recommendation to the users by taking into consideration the detected traffic density. It allows for determining the possible traffic density information based on date and time by periodically processing the data regarding the travel route information recorded therein and the date and time information of when these routes will be used.
  • the invention discloses a method for detecting an urban traffic congestion by using a density-based clustering algorithm.
  • the invention comprises performing clustering on the congestion point GPS data to obtain congestion area information and saving the information of urban traffic congestion state to a data warehouse.
  • the invention comprises being able to effectively find a traffic congestion area, classifying the urban traffic states and make suggestions for urban planning.
  • the invention relates to the field of transportation, in particular to a method for estimating traffic demand based on GPS navigation data. Based on the macro data characteristics presented by big data, a hierarchical clustering algorithm is used to divide the hotspot areas of residents' travel needs. The clustering section includes being able to analyze the travel needs of current residents and provide an effective basis for alleviating urban traffic.
  • the available data was used by instant processing due to the ineffectiveness of the storing cost and processability of the historical data. Since the traffic status differs on an hourly and daily basis specific to road and segment, making estimations for the next day with the data obtained only the day before causes a substantial change in the accuracy rate.
  • the size of the data amount plays an important role in determining the annual, monthly, weekly, daily, hourly, and minute characteristics of the road. There is no system that enables the value-added, multipurpose use of old and new data, and at the same time to be evaluated independently of data capacity.
  • the invention relates to a system and a method that allows for determining the state of traffic density by processing and analyzing instant GPS information in big data architecture.
  • Another object of the present invention is to detect the traffic density in the road network with instant GPS data.
  • Another object of the present invention is to determine the traffic that will occur in the road network in the future. Thus, it is ensured that users can make travel planning in a future time period.
  • Another object of the present invention is to extract data with higher added value from the real-time and historical data that occurs by increasing the amount of the data to be processed.
  • Another object of the present invention is to determine the time-focused region characteristic from GPS data.
  • Another object of the present invention is to minimize the action time from GPS tracks to changes in road networks (direction, open or close for traffic, new road).
  • Another object of the present invention is to ensure that data up-to-date is provided independently of the field teams.
  • Another object of the present invention is to allow for making the speed information that may exist on a road, not specific to users, but in the clustering that it creates algorithmically.
  • Another object of the present invention is to perform instantaneous and time-moving speed detection over an unpredictable route or path vector with big data architecture.
  • Another object of the present invention is to perform the estimation algorithm by using machine learning methods.
  • Another object of the present invention is to include external factors (weather conditions, special days, etc.) in estimation as a feature in machine learning model training in addition to GPS data.
  • t is ensured that the features that are used are more comprehensive while creating the machine learning model.
  • Another object of the present invention is to provide diversity in data size. Thus, the amount of data used in determining the accuracy success of the estimation algorithm is taken into consideration.
  • Another object of the present invention is to minimize the field operations that are costly and to ensure that problems to be experienced due to data interruption are continued with predictable systems.
  • Another object of the present invention is to form clusters by using vehicle flow direction, time, and speed information. In this way, inferences such as traffic density, congestion status, user movement trends can be made in intelligent zone analyzes with the cluster characteristics created.
  • Figure 1 illustrates a view of schematic flow diagram of the system according to the present invention.
  • the present invention allows for determining the state of traffic density by processing and analyzing instant GPS information in big data architecture.
  • the system of the present invention basically consists of data warehouse (10), vehicle management unit (20), application (30), and server (40).
  • the data warehouse (10) is stored in the cloud environment.
  • the data warehouse (10) records the vehicle location and direction information obtained by the server (40).
  • the data warehouse (10) stores historical and real-time road condition information obtained from contracted institutions.
  • the data warehouse (10) stores the analysis results made by the server (40).
  • the data warehouse (10) allows for performing three-dimensional index with geographical and temporal features by using Z3 index and geographic index while GPS data is being stored.
  • Data warehouse (10) allows for storing historical vehicle GPS points, weather information required for data enrichment, road network information, instant traffic information and predictive traffic information therein.
  • the data warehouse (10) meets the need for a data warehouse having geographic data storage, indexing and processing capacity or that can be provided with add-ons for the purpose of storing historical and increasingly advancing flowing data and then processing the data.
  • the Z3 index is a way of mapping a multidimensional space to a one-dimensional space. It acts like a thread going through each cell element (or pixel) in multidimensional space, thereby visiting each cell completely once.
  • a spacefilling curve imposes a linear arrangement of points in multidimensional space.
  • the D- dimensional space-filling curve in the N-cell (pixel) area of each dimension consists of N AD-1 segments, in which each segment connects two successive D-dimensional points. There is a great number of space-filling curves.
  • the vehicle management unit (20) communicates with the server (40) over any communication protocol.
  • the vehicle management unit (20) transmits the location information and direction information obtained via GPS (Global Positioning System) to the server (40).
  • the application (30) ensures that it can be run by any electronic device and that gps information can be sent to the server (40) via the electronic device.
  • the application (30) provides the arrival time and the optimal route to be drawn by obtaining the information of the place where the users desire to go.
  • the application (30) presents the traffic speed information analyzed by the server (40) to the users by coloring them on a map.
  • the application (30) provides the estimation information of the traffic density to the user, which may occur in the location where users desires to go in the future.
  • the application (30) comprises presenting the route and traffic density conditions to the users on a map. Thus, users can learn in which time period or through which route it will be more effective to go to the location they desire to go in the future.
  • the application (30) allows for providing the information of the areas with high probability of accident analyzed by the server (40), and how the social and economic circulation in the region is directed, to the user.
  • the server (40) is in communication with the data warehouse (10), the vehicle management unit (20), and the application (30). All data calculated by the server (40) are kept on the data warehouse (10).
  • the server (40) ensures that the historical and real-time gps information obtained from the field and contracted institutions are stored on the cloud system data warehouses (10).
  • the server (40) allows for determining the traffic density by performing analyzes on the big data.
  • the server (40) enables generating vector path data by means of grouping the gps location information with the clustering solutions.
  • the traffic service unit (41 ) works on the server (40) and calculates the historical traffic data by performing operations such as basic addition and averaging, which will be applied over the data set obtained by applying time-filtered geographic intersection to the raw GPS data in the data warehouse (10).
  • the traffic service unit (41 ) provides the calculation of instant traffic information in 5- m inute periods by feeding the existing area (road, region, etc.) with the flowing data.
  • the traffic service unit (41 ) uses geographic, H3, and OPTICS clustering methods in order to generate density and congestion information created by GPS points in a certain area by performing certain algorithmic and arithmetic matches according to usage scenarios in determining the region.
  • the traffic service unit (41 ) calculates the instant traffic information by taking the average speed of the GPS coordinates in the 5-minute time intervals that will be formed by geographically intersecting the flowing data with the road network in the geographical cluster method.
  • the traffic service unit (41 ) ensures that the average speed and the number of vehicles in the 5-minute stack are determined on each GPS coordinate that receives with the R-Tree (R-trees) index that will be geographically created over the road network, as a result of the matching to be performed according to the intersection and road directions by creating a 20-meter buffer (equal distance or simultaneous zone calculated around a map detail), which will also be created by taking into account the GPS deviation.
  • the traffic service unit (41 ) calculates the instant traffic information by taking the average speed of the GPS coordinates in 5-minute time intervals within the hexagonal area that will be formed at the resolution level determined by the H3 index, which is created by hexagonal division of the world plane independent of the road network of the flowing data in the H3 cluster method.
  • the traffic service unit (41 ) calculates the max-min average speed and the number of vehicles according to the 5 minutes vehicle type in the common hexagon in the H3 cluster method.
  • H3 Index is a geospatial indexing system that combines the benefits of the hexagonal grid system with the hierarchical subdivisions of S2, using a hexagonal grid that can be divided into (approximately) thinner and thinner hexagonal grids.
  • the traffic service unit (41 ) only classifies the geographical locations and directions of the objects, independent of the road network of the flowing data in the optical clustering method.
  • the traffic service unit (41 ) considers the distance of the objects from each other or the use of the minimum number of objects that should be in the class while clustering in the optical clustering method.
  • the traffic service unit (41 ) uses the OPTICS algorithm in the optical clustering method to ensure that the vehicles with the same characteristics staying in a certain area are included in the same groups and then the road congestion is calculated by calculating the density of the road network in these clusters.
  • the traffic service unit (41 ) calculates the possible traffic density for a certain road or region with 15-minute periods by anticipating the necessary conditions over time. Traffic service unit (41 ) calculates predictive traffic information with models that will be created by considering factors such as weather conditions and special days of cumulative data over time by means of using CNN (Convolutional Neural Networks) and LSTM (Long short-term memory) deep learning models. The traffic service unit (41 ) ensures that the traffic information that it calculates based on the past, instant and estimation is sent to the data warehouse (10) to be stored.
  • CNN Convolutional Neural Networks
  • LSTM Long short-term memory
  • the traffic service unit (41 ) allows for making data enrichment in order to increase the success rate of traffic density and routing data based on estimation by means of using meteorological information, road information, vehicle travel analyzes (vehicle max-min speed, acceleration, etc.), vehicle type, factors that will affect traffic flow, etc., which will be obtained from external sources, in addition to time, GPS and vehicle instant information, for the purpose of increasing the success rates of the analyzes to be made.
  • meteorological information road information
  • vehicle travel analyzes vehicle max-min speed, acceleration, etc.
  • vehicle type factors that will affect traffic flow, etc., which will be obtained from external sources, in addition to time, GPS and vehicle instant information, for the purpose of increasing the success rates of the analyzes to be made.
  • the traffic service unit (41 ) allows for producing new features for the classification of vehicle type as passenger vehicles, medium vehicles and heavy vehicles by using cumulative GPS information and virtually generated vehicle information, by analyzing the travel of the existing vehicle in certain time periods, by making travel analysis such as the roads passed during the travel, average speed, max speed, min speed, acceleration.
  • the traffic service unit (41 ) enables that the vehicle type is determined by using Convolutional Neural Networks (CNN-VC) method, which is the deep learning method.
  • CNN-VC Convolutional Neural Networks
  • Well-structured positioning tools such as GPS in vehicle classification are an alternative solution that records the spatio-temporal information of vehicles as they move in a traffic network.
  • the traffic service unit (41 ) ensures that GPS points with known vehicle classes within the existing cumulative data are marked and used as training data.
  • the traffic service unit (41 ) uses large-scaled marked GPS data to identify the classes of vehicles from trajectories thereof with a deep convolutional neural network. Previously prepared data enrichment information is used in order to obtain more accurate information regarding the travel time and distance between GPS coordinates.
  • a CNN-based deep learning model may be used in order to determine the class of the vehicle from the GPS point.
  • CNN-VC uses the CNN layer basic stack in order to extract abstract features from the GPS point. Capsulizing of the most important ones is used among the features extracted by the pooling process to be used. It also includes a softmax layer to perform the vehicle classification task.
  • the traffic service unit (41 ) ensures that the information related to the GPS point and the weather events that occur during the vehicle-specific travel period, as well as the special days, hours and situations are obtained over the relevant services and recorded in order to enrich the training and test data sets.
  • the temperature of the air, humidity, snow-rain precipitation, fog and wind conditions can be recorded in the weather information.
  • the traffic service unit (41 ) allows for calculating the Van Aerde traffic flow model in order to determine the maximum flow rate of the highways that may affect the traffic flow and the corresponding traffic quality.
  • c1 is the fixed distance headway constant [km]
  • c2 is the first variable distance headway constant [km2/h]
  • c3 is the second variable distance headway constant [h]
  • m is a constant [h/km] used for solving end headway constant
  • vf is free flow rate
  • vO is speed at capacity
  • qm is capacity
  • kj is traffic density. Equations for parameters are given in Equation-1 , Equation-2, Equation-3, Equation-4, Equation-5 and Equation-6.
  • c1 m*c2 Equation-1
  • c2 1/kj(m+1/vf) Equation-2
  • c3 (-c1 +v0/qm-c2/(vf-vo))/v0 Equation-3
  • k 1/(c1 +(c2/(vf-v))+c3*v) Equation-4
  • m (2*vO-vf)/(vf-vO)
  • q v/(c1 +c2/(vf-v)+c3*v) Equation-6
  • the routing unit (42) allows for providing routing service for users with the live traffic information, predictive traffic information, and intelligent zones, which will be created by running on the server (40)
  • the routing unit (42) enables making routing for the shortest road, routing for the shortest time, routing for least fuel, priority routing according to road types, dynamic routing, routing according to vehicle type, routing based on predictive traffic density, weather dependent routing, pedestrian travel routing, and public transportation routing depending on urban-interurban transportation vehicles.
  • the routing unit (42) allows for finding the most optimal solution globally by means of exploring all available solutions using Dijsktra algorithm, heuristic algorithms, and hybrid algorithms.
  • the routing unit (42) uses A*, tabu search, ant colony, and genetic algorithms from the heuristic algorithms that search a subset of available solutions and generally generate an approximate optimal solution with characteristics close to the global optimal one.
  • the routing unit (42) allows for routing that provides route length, travel time and travel convenience by means of using hybrid algorithms, which are routing algorithms created by combining heuristic approaches and optimal solutions.
  • the intelligent zone unit (43) works on the server (40) and provides filtering the constraints with the processed data over the data warehouse (10).
  • the system that is the subject of the present invention has a traffic density detection method. Said method comprises process steps in the following.
  • routing unit (42) Making routing for the shortest road, routing for the shortest time, routing for least fuel, priority routing according to road types, dynamic routing, routing according to vehicle type, routing based on predictive traffic density, weather dependent routing, pedestrian travel routing, and public transportation routing depending on urban-interurban transportation vehicles by means of the routing unit (42) working on the server (40),
  • the arrival time and optimal route calculated by the server (40) is provided to the user over the application (30) by receiving the information of the place where users desire to go.
  • the traffic speed information analyzed by the server (40) is transmitted to the user over the application (30) by coloring them on a map.
  • the estimation information of the possible traffic density calculated by the server (40) is provided to the user over the application (30) at the location where the users desire to go in the future.
  • clusters are made by using vehicle flow direction, time, and speed information. Therefore, inferences such as traffic density, congestion status, user movement trends can be made in intelligent zone analyzes with the cluster characteristics created. In addition to the detection of traffic congestion in a certain area with intelligent zones, information regarding how the social and economic circulation in the region is directed from the road network and the road network can be obtained from the combination of cluster segments. In the intelligent zone analysis, the areas with a high probability of accident are obtained with the detection of Accident - Black spots.

Abstract

The present invention relates to a system that allows for determining the traffic density status, estimating future traffic density and detecting the road characteristics by processing and analyzing instant GPS information in big data architecture.

Description

TRAFFIC DENSITY ESTIMATION SYSTEM AND A METHOD THEREOF
Technical Field of the Invention
The invention relates to a system and a method that allows for determining the state of traffic density by processing and analyzing instant GPS information in big data architecture.
The present invention particularly relates to a system and a method that allows for estimating feature traffic density and detecting road characteristics.
State of the Art
Increasing number of vehicles in cities becoming crowded causes traffic density problem. When users encounter this problem, they avoid traffic by not using certain roads during rush hour. However, although these solutions are valid for certain time intervals, traffic density may occur at times and courses that are unpredictable. In such cases, people lose time and can reach the places by consuming much more time and fuel where they could otherwise reach in a very short time by consuming much less fuel.
Today, instant traffic density data is processed by means of the traffic measurement systems in the field and presented through the traffic density map. This map created is published on the web, and it enables that the drivers and passengers are directed to alternative courses for an economical and comfortable travel and planning their travels.
In the state of the art, the patent document numbered “TR201620063” was examined. This invention relates to a traffic planning system that detects the possible traffic density depending on the travel routes received from the users and provides a route recommendation to the users by taking into consideration the detected traffic density. It allows for determining the possible traffic density information based on date and time by periodically processing the data regarding the travel route information recorded therein and the date and time information of when these routes will be used.
In the state of the art, the patent document numbered “CN105261217” was examined. The invention discloses a method for detecting an urban traffic congestion by using a density-based clustering algorithm. The invention comprises performing clustering on the congestion point GPS data to obtain congestion area information and saving the information of urban traffic congestion state to a data warehouse. The invention comprises being able to effectively find a traffic congestion area, classifying the urban traffic states and make suggestions for urban planning.
In the state of the art, the patent document numbered “CN110555544” was examined. The invention relates to the field of transportation, in particular to a method for estimating traffic demand based on GPS navigation data. Based on the macro data characteristics presented by big data, a hierarchical clustering algorithm is used to divide the hotspot areas of residents' travel needs. The clustering section includes being able to analyze the travel needs of current residents and provide an effective basis for alleviating urban traffic.
In the state of the art, the available data was used by instant processing due to the ineffectiveness of the storing cost and processability of the historical data. Since the traffic status differs on an hourly and daily basis specific to road and segment, making estimations for the next day with the data obtained only the day before causes a substantial change in the accuracy rate. The size of the data amount plays an important role in determining the annual, monthly, weekly, daily, hourly, and minute characteristics of the road. There is no system that enables the value-added, multipurpose use of old and new data, and at the same time to be evaluated independently of data capacity.
Consequently, the disadvantages disclosed above and the inadequacy of available solutions in this regard necessitated making an improvement in the relevant technical field. Objects of the Invention
The invention relates to a system and a method that allows for determining the state of traffic density by processing and analyzing instant GPS information in big data architecture.
Another object of the present invention is to detect the traffic density in the road network with instant GPS data.
Another object of the present invention is to determine the traffic that will occur in the road network in the future. Thus, it is ensured that users can make travel planning in a future time period.
Another object of the present invention is to extract data with higher added value from the real-time and historical data that occurs by increasing the amount of the data to be processed.
Another object of the present invention is to determine the time-focused region characteristic from GPS data.
Another object of the present invention is to minimize the action time from GPS tracks to changes in road networks (direction, open or close for traffic, new road).
Another object of the present invention is to ensure that data up-to-date is provided independently of the field teams.
Another object of the present invention is to allow for making the speed information that may exist on a road, not specific to users, but in the clustering that it creates algorithmically.
Another object of the present invention is to perform instantaneous and time-moving speed detection over an unpredictable route or path vector with big data architecture.
Another object of the present invention is to perform the estimation algorithm by using machine learning methods.
Another object of the present invention is to include external factors (weather conditions, special days, etc.) in estimation as a feature in machine learning model training in addition to GPS data. Thus, t is ensured that the features that are used are more comprehensive while creating the machine learning model.
Another object of the present invention is to provide diversity in data size. Thus, the amount of data used in determining the accuracy success of the estimation algorithm is taken into consideration.
Another object of the present invention is to minimize the field operations that are costly and to ensure that problems to be experienced due to data interruption are continued with predictable systems.
Another object of the present invention is to form clusters by using vehicle flow direction, time, and speed information. In this way, inferences such as traffic density, congestion status, user movement trends can be made in intelligent zone analyzes with the cluster characteristics created.
Structural and characteristic features of the present invention as well as all advantages thereof will be understood more clearly from figures disclosed below and the detailed description written by making references to these figures. Therefore, the assessment should be made by taking these figures and the detailed description into consideration.
Description of the Figures
Figure 1 illustrates a view of schematic flow diagram of the system according to the present invention.
Reference Numerals
10. Data warehouse
20. Vehicle management unit
30. Application
40. Server
41. Traffic service unit 42. Routing Unit
43. intelligent zone unit
Description of the Invention
The present invention allows for determining the state of traffic density by processing and analyzing instant GPS information in big data architecture.
The system of the present invention basically consists of data warehouse (10), vehicle management unit (20), application (30), and server (40).
The data warehouse (10) is stored in the cloud environment. The data warehouse (10) records the vehicle location and direction information obtained by the server (40). The data warehouse (10) stores historical and real-time road condition information obtained from contracted institutions. The data warehouse (10) stores the analysis results made by the server (40). The data warehouse (10) allows for performing three-dimensional index with geographical and temporal features by using Z3 index and geographic index while GPS data is being stored. Data warehouse (10) allows for storing historical vehicle GPS points, weather information required for data enrichment, road network information, instant traffic information and predictive traffic information therein. The data warehouse (10) meets the need for a data warehouse having geographic data storage, indexing and processing capacity or that can be provided with add-ons for the purpose of storing historical and increasingly advancing flowing data and then processing the data.
The Z3 index, a space-filling curve, is a way of mapping a multidimensional space to a one-dimensional space. It acts like a thread going through each cell element (or pixel) in multidimensional space, thereby visiting each cell completely once. Thus, a spacefilling curve imposes a linear arrangement of points in multidimensional space. The D- dimensional space-filling curve in the N-cell (pixel) area of each dimension consists of NAD-1 segments, in which each segment connects two successive D-dimensional points. There is a great number of space-filling curves. The vehicle management unit (20) communicates with the server (40) over any communication protocol. The vehicle management unit (20) transmits the location information and direction information obtained via GPS (Global Positioning System) to the server (40).
The application (30) ensures that it can be run by any electronic device and that gps information can be sent to the server (40) via the electronic device. The application (30) provides the arrival time and the optimal route to be drawn by obtaining the information of the place where the users desire to go. The application (30) presents the traffic speed information analyzed by the server (40) to the users by coloring them on a map. The application (30) provides the estimation information of the traffic density to the user, which may occur in the location where users desires to go in the future. The application (30) comprises presenting the route and traffic density conditions to the users on a map. Thus, users can learn in which time period or through which route it will be more effective to go to the location they desire to go in the future.
The application (30) allows for providing the information of the areas with high probability of accident analyzed by the server (40), and how the social and economic circulation in the region is directed, to the user.
The server (40) is in communication with the data warehouse (10), the vehicle management unit (20), and the application (30). All data calculated by the server (40) are kept on the data warehouse (10). The server (40) ensures that the historical and real-time gps information obtained from the field and contracted institutions are stored on the cloud system data warehouses (10). The server (40) allows for determining the traffic density by performing analyzes on the big data. The server (40) enables generating vector path data by means of grouping the gps location information with the clustering solutions.
The traffic service unit (41 ) works on the server (40) and calculates the historical traffic data by performing operations such as basic addition and averaging, which will be applied over the data set obtained by applying time-filtered geographic intersection to the raw GPS data in the data warehouse (10). The traffic service unit (41 ) provides the calculation of instant traffic information in 5- m inute periods by feeding the existing area (road, region, etc.) with the flowing data. The traffic service unit (41 ) uses geographic, H3, and OPTICS clustering methods in order to generate density and congestion information created by GPS points in a certain area by performing certain algorithmic and arithmetic matches according to usage scenarios in determining the region.
The traffic service unit (41 ) calculates the instant traffic information by taking the average speed of the GPS coordinates in the 5-minute time intervals that will be formed by geographically intersecting the flowing data with the road network in the geographical cluster method. The traffic service unit (41 ) ensures that the average speed and the number of vehicles in the 5-minute stack are determined on each GPS coordinate that receives with the R-Tree (R-trees) index that will be geographically created over the road network, as a result of the matching to be performed according to the intersection and road directions by creating a 20-meter buffer (equal distance or simultaneous zone calculated around a map detail), which will also be created by taking into account the GPS deviation.
The traffic service unit (41 ) calculates the instant traffic information by taking the average speed of the GPS coordinates in 5-minute time intervals within the hexagonal area that will be formed at the resolution level determined by the H3 index, which is created by hexagonal division of the world plane independent of the road network of the flowing data in the H3 cluster method. The traffic service unit (41 ) calculates the max-min average speed and the number of vehicles according to the 5 minutes vehicle type in the common hexagon in the H3 cluster method. H3 Index is a geospatial indexing system that combines the benefits of the hexagonal grid system with the hierarchical subdivisions of S2, using a hexagonal grid that can be divided into (approximately) thinner and thinner hexagonal grids.
The traffic service unit (41 ) only classifies the geographical locations and directions of the objects, independent of the road network of the flowing data in the optical clustering method. The traffic service unit (41 ) considers the distance of the objects from each other or the use of the minimum number of objects that should be in the class while clustering in the optical clustering method. The traffic service unit (41 ) uses the OPTICS algorithm in the optical clustering method to ensure that the vehicles with the same characteristics staying in a certain area are included in the same groups and then the road congestion is calculated by calculating the density of the road network in these clusters.
The traffic service unit (41 ) calculates the possible traffic density for a certain road or region with 15-minute periods by anticipating the necessary conditions over time. Traffic service unit (41 ) calculates predictive traffic information with models that will be created by considering factors such as weather conditions and special days of cumulative data over time by means of using CNN (Convolutional Neural Networks) and LSTM (Long short-term memory) deep learning models. The traffic service unit (41 ) ensures that the traffic information that it calculates based on the past, instant and estimation is sent to the data warehouse (10) to be stored.
The traffic service unit (41 ) allows for making data enrichment in order to increase the success rate of traffic density and routing data based on estimation by means of using meteorological information, road information, vehicle travel analyzes (vehicle max-min speed, acceleration, etc.), vehicle type, factors that will affect traffic flow, etc., which will be obtained from external sources, in addition to time, GPS and vehicle instant information, for the purpose of increasing the success rates of the analyzes to be made.
The traffic service unit (41 ) allows for producing new features for the classification of vehicle type as passenger vehicles, medium vehicles and heavy vehicles by using cumulative GPS information and virtually generated vehicle information, by analyzing the travel of the existing vehicle in certain time periods, by making travel analysis such as the roads passed during the travel, average speed, max speed, min speed, acceleration.
Knowing the class of the vehicle from which the GPS data is generated varies in some cases according to the status of the dominant vehicle class for the shortest time and traffic routing in order to converge the effect of instant and historical data on the average region and road speeds of the instant and historical data among the cumulative data. The traffic service unit (41 ) enables that the vehicle type is determined by using Convolutional Neural Networks (CNN-VC) method, which is the deep learning method. Well-structured positioning tools such as GPS in vehicle classification are an alternative solution that records the spatio-temporal information of vehicles as they move in a traffic network. The traffic service unit (41 ) ensures that GPS points with known vehicle classes within the existing cumulative data are marked and used as training data. The traffic service unit (41 ) uses large-scaled marked GPS data to identify the classes of vehicles from trajectories thereof with a deep convolutional neural network. Previously prepared data enrichment information is used in order to obtain more accurate information regarding the travel time and distance between GPS coordinates.
A CNN-based deep learning model may be used in order to determine the class of the vehicle from the GPS point. CNN-VC uses the CNN layer basic stack in order to extract abstract features from the GPS point. Capsulizing of the most important ones is used among the features extracted by the pooling process to be used. It also includes a softmax layer to perform the vehicle classification task.
The traffic service unit (41 ) ensures that the information related to the GPS point and the weather events that occur during the vehicle-specific travel period, as well as the special days, hours and situations are obtained over the relevant services and recorded in order to enrich the training and test data sets. In a preferred embodiment of the present invention, the temperature of the air, humidity, snow-rain precipitation, fog and wind conditions can be recorded in the weather information. The traffic service unit (41 ) allows for calculating the Van Aerde traffic flow model in order to determine the maximum flow rate of the highways that may affect the traffic flow and the corresponding traffic quality. In the Van Aerde traffic flow model, c1 : is the fixed distance headway constant [km], c2: is the first variable distance headway constant [km2/h] c3: is the second variable distance headway constant [h], and m: is a constant [h/km] used for solving end headway constant, vf: is free flow rate, vO: is speed at capacity, qm: is capacity, and kj: is traffic density. Equations for parameters are given in Equation-1 , Equation-2, Equation-3, Equation-4, Equation-5 and Equation-6. c1 = m*c2 Equation-1 c2=1/kj(m+1/vf) Equation-2 c3=(-c1 +v0/qm-c2/(vf-vo))/v0 Equation-3 k=1/(c1 +(c2/(vf-v))+c3*v) Equation-4 m=(2*vO-vf)/(vf-vO)A2 Equation-5 q=v/(c1 +c2/(vf-v)+c3*v) Equation-6
The routing unit (42) allows for providing routing service for users with the live traffic information, predictive traffic information, and intelligent zones, which will be created by running on the server (40) The routing unit (42) enables making routing for the shortest road, routing for the shortest time, routing for least fuel, priority routing according to road types, dynamic routing, routing according to vehicle type, routing based on predictive traffic density, weather dependent routing, pedestrian travel routing, and public transportation routing depending on urban-interurban transportation vehicles. The routing unit (42) allows for finding the most optimal solution globally by means of exploring all available solutions using Dijsktra algorithm, heuristic algorithms, and hybrid algorithms. The routing unit (42) uses A*, tabu search, ant colony, and genetic algorithms from the heuristic algorithms that search a subset of available solutions and generally generate an approximate optimal solution with characteristics close to the global optimal one. The routing unit (42) allows for routing that provides route length, travel time and travel convenience by means of using hybrid algorithms, which are routing algorithms created by combining heuristic approaches and optimal solutions. The intelligent zone unit (43) works on the server (40) and provides filtering the constraints with the processed data over the data warehouse (10).
The system that is the subject of the present invention has a traffic density detection method. Said method comprises process steps in the following.
• Recording the location information and direction information obtained via GPS by the vehicle management unit (20) to the data warehouse (10),
• Calculating the historical traffic data by the traffic service unit working on the server (40) by performing operations such as basic addition and averaging to be applied on the data set obtained by applying time-filtered geographical intersection in the raw GPS data on the data warehouse (10), • Calculating the instant traffic information in certain time periods by the traffic service unit (41 ) working on the server (40) by feeding the road and region determined by the user with the flowing data,
• Calculating the possible traffic density by the traffic service unit (41 ) working on the server (40) in time periods determined by anticipating the necessary conditions for a particular road or region,
• Making data enrichment in order to increase the success rate of predictive traffic density and routing data to be made by using GPS, vehicle instantaneous information, meteorological information to be obtained from external sources, road information, vehicle travel analyzes, vehicle type, factors that will affect traffic flow by means of the traffic service unit (41 ) working on the server (40),
• Routing for users with live traffic information, predictive traffic information and intelligent zones to be created by the routing unit (42) working on the server (40),
• Making routing for the shortest road, routing for the shortest time, routing for least fuel, priority routing according to road types, dynamic routing, routing according to vehicle type, routing based on predictive traffic density, weather dependent routing, pedestrian travel routing, and public transportation routing depending on urban-interurban transportation vehicles by means of the routing unit (42) working on the server (40),
• Finding the most optimal solution globally by exploring all available solutions by using Dijsktra algorithm, heuristic algorithms, and hybrid algorithms, by means of the routing unit (42) working on the server (40),
• Making routing that provides route length, travel time and travel convenience by using hybrid algorithms, which are routing algorithms created by combining heuristic approaches and optimal solutions, by means of the routing unit (42) working on the server (40), • filtering the constraints with the processed data over the data warehouse (10) by means of the intelligent zone unit (43) working on the server (40),
• Generating vector road data by the server (40) by taking historical and real-time road state information obtained from contracted institutions from the data warehouse (10) by grouping them with clustering solutions,
• Clustering data in different neighborhood values by using optical clustering algorithm, and performing productivity analysis by the server (40) in order for clustering the vehicles at the desired distance,
• Grouping the vehicles at any scale independent of road information, and calculating the road condition coloring and traffic flow estimation by calculating the average speed of these vehicles by means of the server (40),
• Determining the traffic density that may occur in the road network in the future with machine learning on the big data collected by considering the data in the past years and the side factors that may affect the traffic flow by means of the server (40),
• Extracting the time-focused region characteristic from the GPS data kept in the data warehouse (10) by the server (40) and recording it to the data warehouse (10),
• Extracting the areas with a high probability of accident from the region characteristic by the server (40) and recording them to the data warehouse (10),
• Calculating the information extraction regarding how the social and economic circulation in the region is directed from the road network and the road network from the combination of the cluster segments by means of the server (40) and recording it to the data warehouse (10)
• Providing the arrival time and optimal route calculated by the server (40) over the application (30) to the user by receiving the information of the place where users desire to go, • Transmitting the traffic speed information analyzed by the server (40) to the user over the application (30) by coloring them on a map,
• providing the estimation information of the possible traffic density calculated by the server (40) at the location where the users desire to go in the future, to the user over the application (30).
The arrival time and optimal route calculated by the server (40) is provided to the user over the application (30) by receiving the information of the place where users desire to go. The traffic speed information analyzed by the server (40) is transmitted to the user over the application (30) by coloring them on a map. The estimation information of the possible traffic density calculated by the server (40) is provided to the user over the application (30) at the location where the users desire to go in the future.
In the method of the present invention, clusters are made by using vehicle flow direction, time, and speed information. Therefore, inferences such as traffic density, congestion status, user movement trends can be made in intelligent zone analyzes with the cluster characteristics created. In addition to the detection of traffic congestion in a certain area with intelligent zones, information regarding how the social and economic circulation in the region is directed from the road network and the road network can be obtained from the combination of cluster segments. In the intelligent zone analysis, the areas with a high probability of accident are obtained with the detection of Accident - Black spots.

Claims

1. A system that allows for determining the state of traffic density, characterized in that, it comprises;
• at least one data warehouse (10) that allows for storing historical and real-time road condition information obtained from the field and contracted institutions, stored in the cloud environment, and three-dimensional indexing with geographic and temporal features by using Z3 index and geographical index while GPS data is being stored,
• at least one vehicle management unit (20) that allows for transmitting the location information and direction information obtained via GPS to the server (40),
• at least one application (30) that provides the user the estimation information of the traffic density that may occur in the location where the users desire to go in the future and showing them the route and traffic density status to the users on a map,
• at least one server (40) enabling the determination of traffic density by analyzing large data, generating vector road data by grouping gps location information with clustering solutions, and determining the density of traffic that may occur in the road network in the future, comprising a traffic service unit (41 ) that works on th server (40) and that allows for calculating the historical traffic data by performing operations such as basic addition and averaging, which will be applied over the data set obtained by applying time-filtered geographic intersection to the raw GPS data in the data warehouse (10), a routing unit (42) that enables the routing service to be provided for users with live traffic information, predictive traffic information and intelligent zones to be created by working on the server (40), an intelligent zone unit (43) that allows for filtering the constraints with the processed data over the data warehouse (10) by working on the server (40).
2. Operation method of the system that allows for determining the state of traffic density according to Claim 1 , characterized in that, it comprises the process steps of; • Recording the location information and direction information obtained via GPS by the vehicle management unit (20) to the data warehouse (10),
• Calculating the historical traffic data by the traffic service unit working on the server (40) by performing operations such as basic addition and averaging to be applied on the data set obtained by applying time-filtered geographical intersection in the raw GPS data on the data warehouse (10),
• Calculating the instant traffic information in certain time periods by the traffic service unit (41 ) working on the server (40) by feeding the road and region determined by the user with the flowing data,
• Calculating the possible traffic density by the traffic service unit (41 ) working on the server (40) in time periods determined by anticipating the necessary conditions for a certain road or region,
• Making data enrichment in order to increase the success rate of predictive traffic density and routing data to be made by using GPS, vehicle instantaneous information, meteorological information to be obtained from external sources, road information, vehicle travel analyzes, vehicle type, factors that will affect traffic flow by means of the traffic service unit (41 ) working on the server (40),
• Routing for users with live traffic information, predictive traffic information and intelligent zones to be created by the routing unit (42) working on the server (40),
• Making routing for the shortest road, routing for the shortest time, routing for least fuel, priority routing according to road types, dynamic routing, routing according to vehicle type, routing based on predictive traffic density, weather dependent routing, pedestrian travel routing, and public transportation routing depending on urban-interurban transportation vehicles by means of the routing unit (42) working on the server (40),
• Finding the most optimal solution globally by exploring all available solutions by using Dijsktra algorithm, heuristic algorithms, and hybrid algorithms, by means of the routing unit (42) working on the server (40),
• Making routing that provides route length, travel time and travel convenience by using hybrid algorithms, which are routing algorithms created by combining heuristic approaches and optimal solutions, by means of the routing unit (42) working on the server (40),
• Filtering the constraints with the processed data over the data warehouse (10) by means of the intelligent zone unit (43) working on the server (40),
• Providing the arrival time and optimal route calculated by the server (40) over the application (30) to the user by receiving the information of the place where users desire to go,
• Transmitting the traffic speed information analyzed by the server (40) to the user over the application (30) by coloring them on a map,
• Providing the estimation information of the possible traffic density calculated by the server (40) at the location where the users desire to go in the future, to the user over the application (30).
3. Traffic density system according to Claim 1 , characterized in that, it comprises data warehouse (10) that allows for recording the vehicle location and direction information obtained by the server (40).
4. Traffic density system according to Claim 1 , characterized in that, it comprises data warehouse (10) that allows for recording the vehicle location and direction information obtained by the server (40).
5. Traffic density system according to Claim 1 , characterized in that, it comprises data warehouse (10) that allows for storing historical vehicle GPS points, weather information required for data enrichment, road network information, instant traffic information and predictive traffic information therein.
6. Traffic density system according to Claim 1 , characterized in that, it comprises application (30) that allows for running by any electronic device and sending the gps information to the server (40) via the electronic device.
7. Traffic density system according to Claim 1 , characterized in that, it comprises application (30) that provides the arrival time and the optimal route to be drawn by obtaining the information of the place where the users desire to go.
16 Traffic density system according to Claim 1 , characterized in that, it comprises application (30) that allows for providing the traffic speed information analyzed by the server (40) to the users by coloring them on a map. Traffic density system according to Claim 1 , characterized in that, it comprises application (30) that allows for providing user the information of the areas with high probability of accident analyzed by the server (40), and how the social and economic circulation in the region is directed. Traffic density system according to Claim 1 , characterized in that, it comprises server (40) that is in communication with he data warehouse (10), the vehicle management unit (20), and the application (30). Traffic density system according to Claim 1 , characterized in that, it comprises server (40) that allows for storing the historical and real-time gps information obtained from the field and contracted institutions on the data warehouse (10) with cloud system. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for calculating instant traffic information in determined periods by feeding the flowing data of the road and region areas determined by the user. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that uses geographic, H3, and OPTICS clustering methods in order to generate density and congestion information created by GPS points in a certain area by performing certain algorithmic and arithmetic matches according to usage scenarios in determining the region. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for calculating the instant traffic information by taking the average speed of the GPS coordinates in the certain time intervals that will be formed by geographically intersecting the flowing data with the road network in the geographical cluster method. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that ensures the average speed and the number of
17 vehicles in the stack to be determined on each GPS coordinate that comes with the R-Tree (R-trees) index that will be geographically created over the road network and in the period to be determined a result of the matching to be performed according to the intersection and road directions by creating a certain meter buffer, which will be created by taking into account the GPS deviation. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for calculating the instant traffic information by taking the average speed of the GPS coordinates in the certain time intervals within the hexagonal area that will be formed at the resolution level determined by the H3 index, which is created by hexagonal division of the world plane independent of the road network of the flowing data with the H3 clustering method. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for calculating the maximum-minimum average speed and the number of vehicles according to the vehicle type in the certain time intervals in the common hexagon with the H3 clustering. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for classifying only the geographical locations and directions of the objects, independent of the road network of the flowing data with the optical clustering. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that ensures the vehicles with the same characteristics staying in a certain area to be included in the same groups, and then the road congestion to be calculated by calculating the density of the road network in these clusters by means of using the OPTICS algorithm in the optical clustering method. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for calculating the possible traffic density for a certain road or region with determined time periods by anticipating the necessary conditions over time.
18
21. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for calculating predictive traffic information with models that will be created by considering factors such as weather conditions and special days of cumulative data over time by means of using CNN and LSTM deep learning models.
22.Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for making data enrichment in order to increase the success rate of predictive traffic density and routing data to be made by using GPS, vehicle instantaneous information, meteorological information to be obtained from external sources, road information, vehicle travel analyzes, vehicle type, factors that will affect traffic flow for increasing the success rate of analyzes to be made.
23.Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for producing new features for the classification of vehicle type as passenger vehicles, medium vehicles and heavy vehicles by using cumulative GPS information and virtually generated vehicle information, by analyzing the travel of the existing vehicle in certain time periods, by making travel analysis such as the roads passed during the travel, average speed, maximum speed, minimum speed, acceleration.
24.Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for determining the vehicle type by using CNN- VC, which is the deep learning method.
25.Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows the marking of GPS points the vehicle classes of which are known among the existing cumulative data in order to be used as the training data.
26.Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for identifying the classes of vehicles from trajectories thereof with a deep convolutional neural network by using large- scaled marked GPS data.
19 Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for obtaining information related to the GPS point and the weather events that occur during the vehicle-specific travel period, as well as the special days, hours and situations over the relevant services and recording them in order to enrich the training and test data sets. Traffic density system according to Claim 1 , characterized in that, it comprises traffic service unit (41 ) that allows for calculating the Van Aerde traffic flow model in order to determine the maximum flow rate of the highways that may affect the traffic flow and the corresponding traffic quality. . Traffic density system according to Claim 1 and Claim 28, characterized in that, the Van Aerde traffic flow model is calculated by means of the equations of; c1 = m*c2, c2=1/kj(m+1/vf), c3=(-c1 +v0/qm-c2/(vf-vo))/v0, k=1/(c1 +(c2/(vf-v))+c3*v), m=(2*vO-vf)/(vf-vO)A2, q=v/(c1 +c2/(vf-v)+c3*v). Traffic density system according to Claim 1 , characterized in that, it comprises routing unit (42) that allows for routing for the shortest road, routing for the shortest time, routing for least fuel, priority routing according to road types, dynamic routing, routing according to vehicle type, routing based on predictive traffic density, weather dependent routing, pedestrian travel routing, and public transportation routing depending on urban-interurban transportation vehicles. Traffic density system according to Claim 1 , characterized in that, it comprises routing unit (42) that searches a subset of existing solutions using heuristic algorithms A*, tabu search, ant colony and genetic algorithms, and provides an approximate optimal solution with characteristics close to the global optimal one.
20 Traffic density system according to Claim 1 , characterized in that, it comprises routing unit (42) that allows for routing that provides route length, travel time and travel convenience by means of using hybrid algorithms, which are routing algorithms created by combining heuristic approaches and optimal solutions.
21
PCT/TR2021/051098 2021-08-06 2021-10-26 Traffic density estimation system and a method thereof WO2023014311A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP21944417.1A EP4162464A4 (en) 2021-08-06 2021-10-26 Traffic density estimation system and a method thereof

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
TR2021/012500A TR2021012500A2 (en) 2021-08-06 2021-08-06 Traffic density estimation system and its method.
TR2021/012500 2021-08-06

Publications (1)

Publication Number Publication Date
WO2023014311A1 true WO2023014311A1 (en) 2023-02-09

Family

ID=84603560

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/TR2021/051098 WO2023014311A1 (en) 2021-08-06 2021-10-26 Traffic density estimation system and a method thereof

Country Status (2)

Country Link
TR (1) TR2021012500A2 (en)
WO (1) WO2023014311A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116580565A (en) * 2023-07-12 2023-08-11 深圳比特耐特信息技术股份有限公司 Government affair big data analysis system based on cloud computing
CN116599697A (en) * 2023-04-14 2023-08-15 深圳市显科科技有限公司 Information board information transmission hard encryption method and system based on bidirectional identity authentication

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6480783B1 (en) * 2000-03-17 2002-11-12 Makor Issues And Rights Ltd. Real time vehicle guidance and forecasting system under traffic jam conditions
KR101638368B1 (en) * 2015-01-02 2016-07-11 경희대학교 산학협력단 Prediction System And Method of Urban Traffic Flow Using Multifactor Pattern Recognition Model
US20190172344A1 (en) * 2017-12-04 2019-06-06 Bluesignal Corporation System for forecasting traffic condition pattern by analysis of traffic data and forecasting method thereof

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6480783B1 (en) * 2000-03-17 2002-11-12 Makor Issues And Rights Ltd. Real time vehicle guidance and forecasting system under traffic jam conditions
KR101638368B1 (en) * 2015-01-02 2016-07-11 경희대학교 산학협력단 Prediction System And Method of Urban Traffic Flow Using Multifactor Pattern Recognition Model
US20190172344A1 (en) * 2017-12-04 2019-06-06 Bluesignal Corporation System for forecasting traffic condition pattern by analysis of traffic data and forecasting method thereof

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116599697A (en) * 2023-04-14 2023-08-15 深圳市显科科技有限公司 Information board information transmission hard encryption method and system based on bidirectional identity authentication
CN116599697B (en) * 2023-04-14 2024-03-26 深圳市显科科技有限公司 Information board information transmission hard encryption method and system based on bidirectional identity authentication
CN116580565A (en) * 2023-07-12 2023-08-11 深圳比特耐特信息技术股份有限公司 Government affair big data analysis system based on cloud computing
CN116580565B (en) * 2023-07-12 2023-10-27 深圳比特耐特信息技术股份有限公司 Government affair big data analysis system based on cloud computing

Also Published As

Publication number Publication date
TR2021012500A2 (en) 2022-09-21

Similar Documents

Publication Publication Date Title
CN107766808B (en) Method and system for clustering moving tracks of vehicle objects in road network space
CN110516708B (en) Path prediction method based on track and road network matching
CN108109382B (en) Congestion point, congestion line and congestion area discovery method based on composite network
Castro et al. Urban traffic modelling and prediction using large scale taxi GPS traces
CN102394008B (en) Assessing road traffic conditions using data from mobile data sources
JP5291935B2 (en) Apparatus and method for predicting future movement of an object
CN110555544B (en) Traffic demand estimation method based on GPS navigation data
WO2023014311A1 (en) Traffic density estimation system and a method thereof
CN109615851B (en) Sensing node selection method based on key road section in crowd sensing system
CN107270925B (en) User vehicle navigation system, device and method
CN110880238B (en) Road congestion monitoring method based on mobile phone communication big data
CN110598917B (en) Destination prediction method, system and storage medium based on path track
CN106931981A (en) A kind of generation method and device of remaining time of navigating
CN106899306A (en) A kind of track of vehicle line data compression method of holding moving characteristic
CN110362576A (en) A kind of bayonet traffic flow forecasting method
CN104006818A (en) Navigation system and method
CN114530038B (en) Travel interest area extraction method and system based on space-time data clustering
Stenneth et al. Monitoring and mining GPS traces in transit space
Pfoser et al. Dynamic travel time maps-enabling efficient navigation
Hu et al. A comprehensive survey of recommendation system based on taxi GPS trajectory
Abbar et al. STAD: Spatio-temporal adjustment of traffic-oblivious travel-time estimation
Kyriakou et al. Analysis of spatiotemporal data to predict traffic conditions aiming at a smart navigation system for sustainable urban mobility
Wu et al. Travel time estimation using spatio-temporal index based on Cassandra
EP4162464A1 (en) Traffic density estimation system and a method thereof
CN109448379A (en) A kind of identification of sporadic traffic events of social media data and localization method

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021944417

Country of ref document: EP

Effective date: 20230109

NENP Non-entry into the national phase

Ref country code: DE