Traffic Flow Estimation Research Articles

Toward Robust Car-Following Dynamics Modeling via Blackbox Models: Methodology, Analysis, and Recommendations

The selection of the target variable is critical for the performance of classical car-following (CF) models. There is a vast body of literature on which target variable is optimal for classical CF models, but there is no study that evaluates the selection of optimal target variables for black-box models prevalent in machine learning, which are increasingly being used to model CF behavior. This paper evaluates different target variables, for example acceleration, velocity, and headway, for three models: Gaussian processes (GP), kernel ridge regression, and long short-term memory (LSTM). These models have different objective functions and work in different vector spaces, for example, GP work in function space, and LSTM in parameter space. Furthermore, this paper evaluates the efficacy of black box and classical CF models across datasets, including diverse traffic scenarios and human versus automated control. Finally, this paper evaluates the coupling of design choices across selection of model type, target variable during model calibration, and dataset characteristics. The experiments show that the optimal target variable recommendations for black-box models differ from classical CF models, depending on the objective function and the vector space. Statistical analysis indicates that selection of models couples greatly with target variables, while recommended target variables do not depend on the datasets used during model calibration. These results provide a path toward more robust CF models, potentially resulting in more accurate and generalizable capacity and/or traffic flow estimates for roadways, even as driving behaviors change with the introduction of new types of automation.

Research on passenger flow control at metro transfer stations based on real-time flow calculation of streamlines

PurposeThe volume of passenger traffic at metro transfer stations serves as a pivotal metric for the orchestration of crowd flow management. Given the intricacies of crowd dynamics within these stations and the recurrent instances of substantial passenger influxes, a methodology predicated on stochastic processes and the principle of user equilibrium is introduced to facilitate real-time traffic flow estimation within transfer station streamlines.Design/methodology/approachThe synthesis of stochastic process theory with streamline analysis engenders a probabilistic model of intra-station pedestrian traffic dynamics. Leveraging real-time passenger flow data procured from monitoring systems within the transfer station, a gradient descent optimization technique is employed to minimize the cost function, thereby deducing the dynamic distribution of categorized passenger flows. Subsequently, adhering to the tenets of user equilibrium, the Frank–Wolfe algorithm is implemented to allocate the intra-station categorized passenger flows across various streamlines, ascertaining the traffic volume for each.FindingsUtilizing the Xiaozhai Station of the Xi’an Metro as a case study, the Anylogic simulation software is engaged to emulate the intra-station crowd dynamics, thereby substantiating the efficacy of the proposed passenger flow estimation model. The derived solutions are instrumental in formulating a crowd control strategy for Xiaozhai Station during the peak interval from 17:30 to 18:00 on a designated day, yielding crowd management interventions that offer insights for the orchestration of passenger flow and operational governance within metro stations.Originality/valueThe construction of an estimation methodology for the real-time streamline traffic flow augments the model’s dataset, supplanting estimated values derived from surveys or historical datasets with real-time computed traffic data, thereby enhancing the precision and immediacy of crowd flow management within metro stations.

Optimized demand-based charging networks for long-haul trucking in Europe

Abstract Battery electric trucks (BETs) are the most promising option for fast and large-scale CO2 emission reduction in road freight transport. Yet, the limited range and longer charging times compared to diesel trucks make long-haul BET applications challenging, so a comprehensive fast charging network for BETs is required. However, little is known about optimal truck charging locations for long-haul trucking in Europe. Here we derive optimized truck charging networks consisting of publicly accessible locations across the continent. Based on European truck traffic flow estimates for 2030 and actual truck stop locations we construct a long-term charging network that minimizes the total number of required locations. Our approach introduces an origin-destination pair sampling method and includes local capacity constraints to compute an optimized stepwise network expansion along the highest demand routes in Europe. For an electrification target of 15% BET share in long-haul and without depot charging, our results suggest that about 91% of electric long-haul truck traffic across Europe can be enabled already with a network of 1,000 locations, while 500 locations would suffice for about 50%. We furthermore show how the coverage of origin-destination flows scales with the number of locations and the size of the stations. Ideal locations to cover many truck trips are at highway intersections and along major European road freight corridors (TEN-T core network).

Challenges and opportunities in traffic flow prediction: review of machine learning and deep learning perspectives

In recent days, traffic prediction has been essential for modern transportation networks. Smart cities rely on traffic management and prediction systems. This study utilizes state-of-the-art deep learning and machine learning techniques to adjust to changing traffic conditions. Modern DL models, such as LSTM and GRU, are examined here to see whether they may enhance prediction accuracy and provide valuable insights. Repairing problems and errors connected to weather requires hybrid models that integrate deep learning with machine learning. These models need top-notch training data to be precise, flexible, and able to generalize. Researchers are continuously exploring new approaches, such as hybrid models, deep learning, and machine learning, to discover traffic flow data patterns that span several places and time periods. Our current traffic flow estimates need improvement. Some expected benefits are fewer pollutants, higher-quality air, and more straightforward urban transportation. With machine learning and deep learning, this study aims to improve traffic management in urban areas. Long Short-Term Memory (LSTM) models may reliably forecast traffic patterns.

Adaptive observer design for coupled ODE–hyperbolic PDE systems with application to traffic flow estimation

This paper studies the state estimation problem for a class of coupled linear ODE–hyperbolic PDE systems with unknown in-domain parameters. Based on the swapping transformation and the least squares parameter estimation method, a Luenberger-type adaptive boundary observer is designed to estimate the ODE–PDE states under the unknown parameters. The exponential convergence conditions w.r.t. the observer feedback gains are given by employing the Lyapunov technique. Finally, an application to traffic state estimation of the Aw–Rascle–Zhang (ARZ) model involving the unknown relaxation time and the boundary input speed deviation is provided to validate the theoretical result.

Data-driven traffic sensor location and path flow estimation using Wasserstein metric

This paper introduces link information value obtained by the traffic sensors and presents a traffic sensor location and flow estimation joint optimization model in an urban road network. In contrast to most previous studies, this paper adds new traffic sensors into the existing sensor network and proposes a data-driven path flow measurement method based on Wasserstein metric, which is utilized to measure the distance between the estimated traffic flow distribution and the actual distribution. Furthermore, this paper develops a customized greedy algorithm by combining a search strategy for the link information value to obtain the optimal sensor location scheme and perform traffic flow estimation under different budget conditions. Numerical experiments are conducted on Sioux-Falls test network and Eastern Massachusetts interstate highway subnetwork to verify the accuracy and effectiveness of the proposed model based on Wasserstein metric and the developed solution method. Computational results show that the sensor location scheme generated by the model based on Wasserstein metric can reduce the estimation error of the traffic flow compared with KL divergence model under the same deployment cost. Additionally, the customized greedy algorithm can achieve the better performance than the Brute force algorithm in terms of computing time and solution quality.

Optimal Placement of Sensors in Traffic Networks Using Global Search Optimization Techniques Oriented towards Traffic Flow Estimation and Pollutant Emission Evaluation

The relationship between estimating traffic flow and evaluating pollutant emissions lies in understanding how vehicular traffic patterns affect air quality. Traffic flow estimation is a complex field that involves a variety of analytical techniques to understand, predict, and manage the flow of vehicles on road networks. Different types of analyses commonly employed in this area are statistical analysis (e.g., descriptive statistics, inferential statistics, time series analysis), mathematical modeling (macroscopic models, microscopic models, mesoscopic models), computational methods (e.g., simulation modeling, machine learning, and AI techniques), geospatial analysis (e.g., geographic information systems (GISs), spatial data analysis), network analysis (e.g., graph theory and network flow models). In sensor network setups, the strategic placement of sensors is crucial, primarily due to the challenges posed by limited energy supplies, restricted storage capabilities, and the demands on processing and communication, all of which significantly impact maintenance costs and hardware limitations. To mitigate the burden on processing and communication, it is essential to deploy a limited number of sensors strategically. In practical applications, achieving an optimal layout of physical sensors (i.e., placing sensors within the network in such a way as to meet a specific optimality criterion, such as identifying the minimum number of sensors required to ensure the ability to design reliable state observers capable of reconstructing the network’s state based on the available data) is essential for the accurate monitoring of large-scale systems, including traffic flow or the distribution networks of water and gas. In the context of traffic systems, addressing the challenge of full link flow observability, that is, the ability to accurately monitor and assess the flow of entities (i.e., vehicles) across all the links or pathways within a network, entails selecting the smallest number of traffic sensors from a larger set to install. The goal is to choose a subset of p sensors, which may include redundancies, from a pool of n>>p potential sensors. This is conducted to maintain the structural observability of the entire traffic network. This concept pertains to deducing the complete internal state (traffic volume on each road link in the network) from external outputs and inputs (measurements from sensors). The traditional concept of system observability serves as a criterion for sensor placement. This article presents the development of a simulated annealing heuristic to address the selection problem. The selected sensors are then applied to construct a Luenberger observer, a mathematical construct used in control theory to accurately estimate the internal state of a dynamic system based on its inputs and outputs. Numerical simulations are carried out to demonstrate the effectiveness of this method, and a performance analysis using a digital twin of a transport network, designed using the Aimsun Next software, are also carried out to assess traffic flow and associated pollutant emissions. In particular, we examine a traffic network comprising 21 roads. We address the sensor selection problem by identifying an optimal set of six sensors, which facilitates the design of a Luenberger observer. This observer enables the reconstruction of traffic flow across the network with minimal estimation error. Furthermore, by integrating this observer with data from the Aimsun Next software, we assess the pollutant emissions related to traffic flow. The results indicate a high accuracy in estimating pollutant levels.

EVALUATION OF TRANSPORT FLOW USING DEEP LEARNING METHODS OF SATELLITE IMAGES

The exponential growth of urbanization has led to increasing problems in traffic management, which require innovative solutions for efficient estimation of traffic flow. Deep learning methods are emerging as a powerful tool for processing and analyzing satellite images, and are being used for traffic flow estimation. This paper describes deep learning-based methods for traffic flow estimation using satellite imagery.

Computational Architecture of an Integrated Urban Model Considering Physical-Virtual Activity Spaces

This study presents the computational architecture of the integrated transport, land-use, and emission (iTLE) modeling system. It incorporates the effects of physical-virtual activity-space interactions within the microsimulation framework, making it a comprehensive tool for predicting travel demand and evaluating the impacts of evolving activity-travel behavior on transport and land-use systems. The model systematically integrates households’ and individuals’ long-term, medium-term, and short-term travel related decisions, and traffic assignment allowing for more reliable estimates of travel demand. Application of the iTLE prototype in the Halifax Regional Municipality (HRM), Canada reveals notable trends, including a reduction in travel time for work activities, highlighting the potential of teleworking as a pragmatic strategy for traffic management. The model’s flexibility is demonstrated through its ability to capture the trade-offs between physical and virtual activity environments, aligning with the intricacies of modern digitalized societies. Integration of iTLE with the traffic assignment system enhances its applicability across diverse urban contexts, streamlining the process of setting origin-destination trip matrices and significantly improving computational efficiency. By systematically coupling the micro-behavioral decision processes, iTLE generates robust estimates of traffic flow, emissions, and energy use, providing reliable insights for sustainable and efficient transportation planning. This study contributes to advancing integrated urban modeling, offering a valuable tool that can be replicable for multiple cities in Canada and beyond.

Adaptive Boundary Observers for Hyperbolic PDEs With Application to Traffic Flow Estimation

Adaptive Boundary Observers for Hyperbolic PDEs With Application to Traffic Flow Estimation

A Deep Graph Neural Network Approach for Assessing Origin Destination Traffic Flow Estimates Based on COVID-19 Data

A Deep Graph Neural Network Approach for Assessing Origin Destination Traffic Flow Estimates Based on COVID-19 Data

Prediction of Traffic Flow by Sequencing Spatial–Temporal Traffic Dependency on Highways

Traffic flow on highways is a dynamic process in which characteristics of road segments vary in time and space. Traffic congestion is the adverse effect caused dby an increase in travel time which is unprecedented by time and space. Temporal and spatial information of traffic flow is an integral component in the assessment of highway traffic flow. The spatial–temporal traffic flow dependency on highways can be well assessed when temporal traffic information in preceding time instances is sequenced. Thus, the SCAE-LSTM network is proposed considering time and space. This study investigates the estimation of traffic flow on highways based on spatial and temporal traffic sequences. Sequencing highway traffic information has motivated the authors to propose the method. The performance of the method is experimented on State Highways SH 49 and SH 49-A of Chennai Metropolitan City, Tamil Nadu, India. The computational complexity of the method is analyzed empirically. The significant outcome of the proposed method is reported in the experimental study. The traffic flow estimated using the proposed method has shown reduced complexity compared to other baseline methods. Finally, research directions to work in future are presented towards the end.

A fundamental diagram based hybrid framework for traffic flow estimation and prediction by combining a Markovian model with deep learning

Accurate traffic congestion estimation and prediction are critical building blocks for smart trip planning and rerouting decisions in transportation systems. Over the decades, there have been many studies focusing on traffic congestion estimation and prediction with different statistical approaches (e.g., Markov chain) and machine learning models (e.g., clustering, Bayesian networks, and artificial neural networks). However, there is a lack of a unified framework to address the mechanisms of different models and integrate the advantages of different methods through combinations. This paper introduces the FD-Markov-LSTM model, a hybrid interpretable approach that combines the fundamental diagram (FD), Markov chain, and long short-term memory (LSTM). The aim is to estimate and predict traffic states by integrating statistical data in both congested and uncongested scenarios. The FD-Markov-LSTM model leverages the FD to identify hierarchical traffic states and utilizes the Markov process to capture the probabilistic transitions between these states. We employ the LSTM model to further capture the residual time series produced by the Markov chain model (assuming a memoryless property) to enhance the estimation and prediction performance. The proposed model's accuracy in estimating and predicting traffic flow is evaluated using empirical data from three case studies conducted in Beijing and Los Angeles. The results highlight a significant improvement in accuracy compared to classical benchmark models such as the Markov model, ARIMA model, k-Nearest Neighbor model, Random Forest model, and LSTM. Specifically, the FD-Markov-LSTM model achieves reductions of over 39% in mean absolute error, 35% in root mean squared error, and 7.4% in mean absolute percentage error. These results clearly demonstrate that the FD-Markov-LSTM model outperforms the benchmark models, enabling more precise predictions of traffic flow.

Models, algorithms, and equilibrium conditions for the simulation of autonomous vehicles in exclusive and mixed traffic

This paper proposes models and algorithms for the estimation of traffic flows generated by the centralised management of autonomous vehicles under exclusive and mixed traffic conditions. It is assumed that the autonomous vehicle manager wants to obtain the system optimum that minimises the total travel time on the network, of autonomous vehicles in the case of exclusive traffic, and of all flows in the case of mixed traffic. In the case of mixed traffic, the drivers of the human-guided vehicles choose their routes from a user-optimal perspective; in this case, a fixed-point problem has to be solved, which represents a state of equilibrium between the flows of human-guided vehicles, the flows of autonomous vehicles, which follow paths aimed at the system optimum, and the link costs. The proposed models and algorithms are tested on a small network with a single origin-destination pair, and on the Sioux Falls network, with different levels of congestion and different percentages of autonomous vehicles. The results show the validity of the proposed methods and the impact of autonomous vehicles on network performance. The proposed static/equilibrium approach is necessary to evaluate transport planning, design or policy interventions that include the presence of autonomous vehicles in traffic flows.

Toward a deep CNN and RS‐GOA framework for vehicle detection, traffic flow estimation, and optimal path selection from surveillance videos

SummarySeveral autonomous traffic monitoring systems have been created as a result of the growing number of vehicles in urban areas. Traffic surveillance systems that use roadside cameras, in particular, are becoming widely used for traffic management. For an efficient traffic control and vehicle navigation system, accurate traffic flow information must be obtained based on the vehicles detected in surveillance videos. However, vehicles of various scales are difficult to spot in traffic surveillance videos due to the presence of barricades, other vehicles, and the impact of poor lighting. Also, adverse weather conditions like snow, fog, and heavy rain diminish the visual quality of the surveillance footage. This paper proposes multi‐scale dense nested deep CNN (MSDN‐DCNN) and regional search grasshopper optimization algorithm (RS‐GOA) framework to accurately detect the vehicles, estimate the traffic flow, and find the optimal path with less travel time. First, the surveillance videos are pre‐processed, which includes frame conversion, redundancy removal, and image enhancement. The pre‐processed frames are given as input to the MSDN‐DCNN for multi‐scale vehicle detection. The detected results are used for vehicle counting and estimating the traffic flow. Finally, the optimal path is chosen based on the traffic flow information by using the RS‐GOA algorithm. The performance of the proposed method is compared with the existing vehicle detection and path selection techniques. The results illustrate that the proposed Deep CNN‐RS‐GOA framework has improved performance with high detection accuracy (91.03%), high speed (53.9 fps), less running time (1,000 ms), less travel time, and faster convergence.

A Vision-Based Method for Real-Time Traffic Flow Estimation on Edge Devices

Traffic flow estimation is an essential task in modern intelligent transportation systems. Many types of information, including vehicle type, vehicle totals, and movement direction, are vital for mitigating transportation-related tasks and effective traffic control strategies. With the development of embedded devices, systems can process captured video at the edge instead of transferring data to centralized processing servers. This paper proposes a real-time and edge-based traffic flow estimation system. The proposed system follows a detect-and-track mechanism where lightweight deep learning models perform vehicle detection. A novel scenario-based tracking and counting technique is developed to provide multi-class, multi-movement vehicle counting. The method uses predefined regions to assign the movement for each vehicle initially detected. It then performs spatial-temporal trajectory matching between the vehicle trajectory and the movement path throughout the whole video. Extensive experiments have shown that the proposed method achieves high effectiveness with multiple camera types and viewpoints.

Traffic Flow Video Image Recognition and Analysis Based on Multi-Target Tracking Algorithm and Deep Learning

Traffic flow parameters are an important data support for the research and development of several technologies in the intelligent transportation system. Therefore, accurate and real-time estimation of traffic flow is particularly important for urban traffic. In this study, a real-time traffic flow detection system framework was constructed based on video image collection and analysis. According to the vehicle detection and tracking results, a traffic flow parameter estimation model and an improved LSTM network are proposed for spatiotemporal counting feature recognition. The results conclude that the developed framework can estimate the traffic flow density and count vehicles, as well as estimate the traffic flow velocity and traffic volume to estimate and optimize traffic flow, respectively. Additionally, the simulation results show that the proposed method can not only counts the two-way traffic vehicles quickly and accurately, but also avoids the use of the complex multi-target tracking method to spatiotemporal correlation of a single target, increases the speed and accuracy of the spatiotemporal information processing procedure, and has stronger scene adaptability.

СТАТИСТИЧЕСКИЕ МЕТОДЫ ОЦЕНКИ МАТРИЦЫ КОРРЕСПОНДЕНЦИЙ НА ОСНОВЕ ПОДСЧЕТА ТРАНСПОРТНОГО ПОТОКА

This paper provides a brief overview of the statistical methods used in transport research in recent years to find the relationship between traffic flow estimates and the demand that generates these data. This problem is formulated within the framework of the general task of evaluating the correspondence matrix

Quality Assurance Methods for Hourly Nonmotorized Traffic Counts

Growing numbers of public transportation and recreation agencies have implemented automated bicycle and pedestrian traffic monitoring programs. To support these initiatives, researchers and agency analysts have developed programs, methods, and measures to ensure data quality. These methods include statistical tests for identifying and flagging outliers and other invalid counts and procedures for imputing or managing missing and censored counts. Because statistics such as annual average daily bicyclists are used frequently in planning and engineering, analysts have focused on validation of daily counts using data from permanent monitors. Procedures for ensuring the validity of hourly counts have not been standardized. This paper presents quality assurance (QA) methods for hourly nonmotorized traffic counts at 115 short-duration and nine permanent monitoring sites on multiuse trails monitored by the Minnesota Department of Natural Resources (MnDNR) and the Minnesota Department of Transportation (MnDOT) between 2016 and 2021. These methods include statistical tests for flagging and censoring invalid hourly counts and procedures for imputing estimates for censored or missing counts. Differences in traffic flow estimates with and without QA are documented, and hourly patterns and factors are presented. Use of quality assurance methods for hourly counts can increase the validity of estimates of nonmotorized traffic.

Use of Machine Learning in Traffic flow Estimation through DB Network and RF

Use of Machine Learning in Traffic flow Estimation through DB Network and RF