Present study reviews simulation models available for signalised and unsignalised intersections using cellular automata (CA). CA models are discrete dynamic systems, through which it is possible to model traffic behaviour with ease and simplicity. Thus, CA was chosen for the study. Driver, seepage behaviour and type of traffic (homogeneous/heterogeneous) affect the capacity and safety of the intersections. These models can be either with open boundary (with continuous deletion and generation of vehicles) or closed/periodic boundary (with a fixed number of vehicles). The proposed study also investigates about the boundary conditions of simulation models as these change the results of simulations. Further, frequent acceleration/deceleration activity at the intersection causes more emissions. It was found that most of the traffic simulation models developed for intersections lack in modelling interaction between vehicles, seepage, driver behaviour and emission behaviour etc. Very few studies were found to model the emission behaviour with CA. Present study chronologically lists studies with methods adopted, advancements in those methods, traffic behaviours taken into consideration and missing gaps between studies. The composition and interaction of five different modes such as cars, buses, trucks, motorised three-wheelers and motorised two-wheelers were considered as mixed traffic. A new methodology is suggested based on this review.

The vision-based traffic flow parameter estimation is a challenging problem especially for dense traffic scenes, due to the difficulties of occlusion, small-size and dense traffic etc. Yet, previous methods mainly use detection and tracking methods to do vehicle counting in non-dense traffic scenes and few of them further estimate traffic flow parameters in dense traffic scenes. A framework is proposed to count vehicles and estimate traffic flow parameters in dense traffic scenes. First, a pyramid-YOLO network is proposed for detecting vehicles in dense scenes, which can effectively detect small-size and occluded vehicles. Second, the authors design a line of interest counting method based on restricted multi-tracking, which counts vehicles crossing a counting line at a certain time duration. The proposed tracking method tracks short-term vehicle trajectories near the counting line and analyses the trajectories, thus improving tracking and counting accuracy. Third, based on the detection and counting results, an estimation model is proposed to estimate traffic flow parameters of volume, speed and density. The evaluation experiments on the databases with dense traffic scenes show that the proposed framework can efficiently count vehicles and estimate traffic flow parameters with high accuracy and outperforms the representative estimation methods in comparison.

Examining the travel time variability (TTV) of buses, passenger cars and taxis is essential to obtain reliable travel time in urban daily trips. TTV analyses of three travel modes are conducted using travel time data collected on two urban arterial roads in Xi'an City. Firstly, the TTV is evaluated using statistical indexes. The results reveal that the TTV differs from vehicle to vehicle, period to period and site to site. Secondly, the finite mixture survival model is proposed to address the heterogeneity of travel time data by decomposing the population into several sub-populations. Wasserstein distance and Kolmogorov–Smirnov test are used to further compare the sub-populations of different vehicle types during different periods on different roads. Finally, based on the model analysis, it can be found that the finite mixture survival model is an accurate tool to examine the variability by capturing the heterogeneity of travel time data. The difference among the sub-populations suggests different travel behaviours. It concludes that more diverse travel behaviours result in higher TTV. An accurate investigation on TTV is valuable for travellers’ mode choices and transportation management agencies to obtain reliable travel time information and improve traffic efficiency.

To improve a parallel hybrid electric vehicle's (HEV's) fuel economy, this study develops a real-time optimisation strategy with a learning-based method that predicts the driver's power demand under the connected environment. This demand is strongly constrained by the total power generated by the energy sources. Therefore, a key issue of solving the energy management problem in real time by model-based predictive optimisation is to predict the power demand of each receding horizon. The proposed optimisation strategy consists of two layers. The upper layer provides the prediction of the driver's torque demand. Gaussian process regression (GPR) is used to predict the driver's demand with the uncertain and stochastic estimation between the traffic environment and torque demand. Vehicle-to-vehicle and vehicle-to-infrastructure data are used as the inputs of the GPR model. The lower layer performs finite-horizon optimisation based on the cost function of energy consumption. A receding horizon control (RHC) problem is formulated, and optimisation is achieved by a sequential quadratic programming algorithm. To validate the proposed optimisation strategy, a powertrain control co-simulation platform with a traffic-in-the-loop environment is constructed, and results validation with the platform is demonstrated. The comparisons with the dynamic programming and no-prediction RHC results show that the proposed strategy can improve fuel economy.

The effects of operational characteristics of the public transport system on the performance of the urban network traffic flow and the public transport system have been widely investigated at the local level. However, to the best of authors' knowledge, there is no attempt to investigate these characteristics at the network level. This study bridges this gap through the notion of network macroscopic fundamental diagram. In particular, the effects of the bus stop location (i.e. far-side and near-side) and berth number are discussed at the network level through simulating different scenarios in the central business district of the city of Christchurch, New Zealand. In consistent with the local level studies, the outputs show that the far-side bus stops result in better network performance (i.e. larger capacity and critical density range) and a lower median for the network average delay of car traffic. The near-side bus stops instead lead to a lower median for the public transport system. The results reveal that increasing the berth number improves the network capacity and median of the network average delay for both modes. Finally, the impacts of the combination of the far-side and near-side bus stop on network performance have been discussed.

Detecting traffic signs is an essential task for intelligent and connected vehicles. In this study, a modified model based on the method of You Only Look Once (YOLO) is proposed for detecting different types of Chinese signs, including mandatory, prohibitory, danger warning, guide, and tourist signs. Images of Chinese traffic signs are collected in real scenes and a new dataset is established. The modified model combines the DenseNet method with the YOLOv3 network. Dense blocks are used to strengthen feature propagation and promote feature reuse in those feature layers with low resolution in the YOLOv3 network. Experimental results on the test dataset reveal that the average precision of the modified model, the original YOLOv3, and the YOLOv2 networks are 95.92, 94.59, and 89.39%, respectively. Further comparative analyses that give more detailed experimental evaluation results are conducted on the designed model, including (i) the performance of the designed model based on five categories; (ii) the influence of training set size on the designed model; (iii) the performance of the designed model on occlusion and no object conditions in real scenes. The experimental results show that the modified model is effective at fast and accurate Chinese traffic sign detection in real scenes.

The intersection with special width approach lane (SWAL) is a newly proposed unconventional intersection design. A microscopic traffic flow model was proposed for describing the operation of vehicles at signalised intersections with SWAL. The operation process of driving on the SWAL was divided into four segments, including entering segment, transition segment, special width lane segment, and exiting segment. The car-following and lane selection behaviours of vehicles in these segments are analysed. The parameters used in the model were calibrated using the field data collected in Germany. The proposed model was realised in a time-discretised simulation. The sensitivity analyses of geometric, traffic, and signal factors were conducted. The results show that for the car-following behaviour, the passenger cars on the narrowed lanes cannot drive as efficient as on the normal width lane. For lane selection behaviour, it mainly depends on the distance between the two nearest vehicles in front of the two narrow lanes. The effectiveness of the SWAL depends on whether it is long enough to accommodate the queuing vehicles, which is a combined result of the layout design and the signal timing.

This study illustrates the early results of on-going research started under a recent project sponsored by the United Kingdom Government Transport Department to investigate the principal factors influencing road accidents as well as develop an internet application for the prediction of road accident-related effects at different scales. In particular, accident modelling, analysis of socio–economic, land use, infrastructural and contextual factors of road safety, as well as decision-making support are the focus of this work. In particular, an application in the United Kingdom of a model framework potentially transferable to other contexts is described. This application resulted in an extensive analysis of road safety factors as well as the development of a simulation web-based platform that uses microeconometric models to estimate the frequency of road accident along with the number and severity of injuries. These models proved considerable accuracy at the national level. In the end, the potential benefit of the simulation platform for road safety decision-making is showcased on a micro-scale with an application to a medium-sized town in South East England.

Due to the limited sensing ability with the single-view camera and the real-time requirement for multi-view scenarios or deep learning-based methods in complex scenes, the output of lane detection is not applicable for the actual lane departure warning system. To tackle this challenge, the authors propose a fast and robust approach for lane detection based on well-designed multi-camera fusion, integrating vanishing point estimation, and specified feature fitting strategies. To meet real-time demand, several simple but effective image processing means are introduced and improved. Concretely, on account of statistical information, the authors’ method carries out an improved region of interest selection to speed up the detection. Afterwards, they used the B-spline fitting lane line on the strength of the RANdom SAmple consensus algorithm for the front view image detection and improved the Hough algorithm for the two rear-view images correspondingly. Using coordinate conversion and self-designed fusion strategy, they get the robust lane information based on symmetrical lane detection from the left/right sides of both front and side views. Experimental results in newly introduced multi-camera scenarios show that their multi-camera fusion framework contributes to significant improvement in accuracy and robustness in comparison with traditional methods.

Bus scheduling is a well-known NP-hard problem, and it is addressed with the use of heuristic solution methods or graphical approaches. In this study, the author proposes an improved formulation of the bus scheduling problem that considers the vehicle availability, the vehicle capacity and the allowed headway variability among successive trip dispatches. His formulation expands the classic bus scheduling model formulation by including the aforementioned features. In his study, the bus scheduling problem is understood as the problem of setting the optimal dispatching times for a set of pre-determined daily trips of a particular bus line. His model facilitates the search of solutions that can improve the waiting times of passengers while meeting the operational requirements and avoiding overcrowding. His proposed mathematical program is proved to be non-convex, and it is solved with heuristic solution methods because numerical optimisation approaches cannot guarantee a globally optimal solution. The performance of his approach is tested in a case study using real operational data from bus line 302 in Singapore. A simulation-based evaluation demonstrates potential gains of up to 20% on average passenger waiting times and a major reduction in refused passenger boardings because of overcrowding.

To improve the accessibility of bus rapid transit (BRT) systems, the median stations are usually located beside intersections. However, due to the limited storage space at the stations, high bus volumes and fluctuant bus arrival patterns may cause queue spillbacks and consequently block the intersections. Traditional transit signal priority control could deteriorate such situations when a green extension or a red truncation is activated. Hence, it is essential to develop a new operational framework that is capable of both reducing bus travel time and preventing queue spillbacks at the median stations. This study presents a novel signal control scheme to integrate both priority (i.e. green extension and red truncation) and suppression strategies (i.e. green truncation and red extension) for approaching buses. Notably, the suppression control is only implemented to the farside directional traffic. To evaluate the proposed signal control system, this study tests the algorithms on a real BRT network in Jinan, China. Simulation results of multiple experiments show that the developed method has great promise in bus delay reduction and spillback avoidance in the station area. Other further explorations with sensitivity analysis find that the proposed control will be more effective when the signal is able to provide longer priority and suppression durations.

A real-time responsive customised bus (RTRCB) provides demand-oriented and shared-ride service for passengers with random travel demands. Unlike other works in the literature, the authors developed a hierarchical methodology to optimise the RTRCB schedule. It involves a trade-off between the interests of the transporter and those of the passengers. After minimising the initial travel distance while maintaining a wide service range, the bus routes are planned holistically based on the main travel locations. Based on the initial routes, the buses are dispatched to satisfy the real-time travel demands. The procedure for solving the proposed problem is developed by modifying the genetic algorithm (GA) and non-dominated sorting GA with elite strategy. The proposed method is applied to a real-life problem in the city of Shenzhen, and certain extensional analyses are performed to demonstrate their feasibility. The computational results show that: (i) the travel distance limitation and tortuosity ratio of the bus route play the most important roles in planning bus routes; (ii) the designation of all the initial bus stops as the control stops results in comparatively stable service for more passengers; and (iii) a better service performance can be achieved by introducing the soft time window strategy with an acceptable delivery delay.

A novel adaptive coordinated platoon control of connected autonomous distributed electric vehicles (CADEVs) on curved roads is proposed to increase traffic security. The nonlinear vehicle dynamic model that can precisely reflect the driving behaviours of CADEVs on curved roads is deduced by the Newton–Euler method. Owing to the fact that CADEVs have the strong coupled, uncertain non-linear and over-actuated features, a novel disturbance observer-based adaptive coordinated optimal dynamic platoon control strategy is presented to supervise the lateral and longitudinal coupled motions of CADEVs on curved roads, in which the switching gains of backstepping sliding mode control term are precisely adjusted by the neural-network technique, and the uniform ultimate boundedness of closed-loop high-level control system is guaranteed through the Lyapunov stability theory. Then, a sequential quadratic programming (SQP) tire distributor is the basic component of the low-level control law, which can realise the dynamic control distribution of over-actuated tire actuators of CADEVs. Finally, the results manifest the effectiveness of the proposed adaptive coordinated platoon control strategy.

Monitoring operations at freight intermodal terminals are useful for estimating their performance, while collecting traffic data allows them to properly manage and control truck flows. Nevertheless, the key role of observation can be in contrast with users’ privacy. A valuable solution to obtain traffic information preserving players’ anonymity may be provided by scanning radio signals emitted by commonly used on-board devices, which can be locally identified by their unique media access control address. In this solution, no personal, freight or vehicle information is collected. An uncommon application of bluetooth scanners for monitoring operation of truck flows inside terminals is presented, based on a simple methodology for data processing. The algorithm starts from the data collection and the selection of information at relevant points of the terminal, then the network observation is composed by matching the data recorded in connected points. Finally, key performance indicators are estimated, starting from vehicle trajectories, node by node, and their travel time. The method is applied with on-field tests in a large-size rail–road terminal, where the detected counting results are lower than the ground truth, being not all the users equipped with bluetooth devices; however, the pioneering application results replicable in other contexts related to logistics.

Dockless bike-sharing (DBS) is a novel and prevalent bike-sharing system without stations or docks. DBS has the advantages of convenience and real-time positioning, whereas it brings about some problems such as bike over-supply, disordered parking, and inefficient rebalancing. Forecasting usage and bike distribution are critical in the rebalancing operation for maintaining DBS inventory. By dividing the virtual stations through K-means clustering and processing the four-week Mobike journey data of Nanjing, China, the data of usage and bike count in the 4000 virtual stations are identified. Random forest (RF) is developed to predict the real-time passenger departure, passenger arrival and bike count in the virtual stations. The operation analyses indicate that there is a positive correlation between bike count and usage. RF provides accurate predictions of usage and bike distribution, and almost outperforms five benchmark methods. Forecasting bike distribution is more challenging than forecasting usage because of the volatility of many factors. The results also suggest that bike distribution forecasting based on the usage gap prediction is better than that based on the departure and arrival prediction. This study can help DBS companies in dynamically rebalancing bikes from over-supply regions to over-demand regions in a better way.

In the current practice of bus rapid transit (BRT) system, under-utilized exclusive bus lanes (EBL) could negatively impact the system efficiency, particularly when traffic congestion occurs on regular vehicle lanes during peak period. In this paper, we propose an EBL sharing scheme to dynamically control the usage of the EBL by regular vehicles based on connected vehicle technologies without disturbing normal operation of the BRT system. An enhanced cell transmission model (CTM)-based approach and a simulation-based approach are proposed to model the traffic dynamics of a BRT section currently running in Chengdu, China. The optimal entry/exit proportion of regular vehicles are derived by minimizing total car delay on both the EBL and regular lanes given fixed bus service. The performance of the proposed dynamic sharing control scheme is evaluated under-saturated and over-saturated conditions. The sensitivity of the BRT service frequency and the average bus waiting time on the performance of the control scheme is also analysed. The results show that when traffic becomes over-saturated, delays on regular lanes can be significantly reduced by allowing optimized proportion of regular vehicles to use the EBL. However, it is unnecessary to use the EBL where traffic demand on regular lanes is low.

It is becoming increasingly important to gain real-life insights into the effects of vehicle automation with the continued introduction of cooperative and automated vehicles (CAV). This study reports on the findings of a field operational test (FOT) of cooperative adaptive cruise control (CACC) vehicles on an arterial corridor with other traffic. The FOT demonstrated that that CACC vehicles can operate well under such conditions and can operate in platoons at lower time-headways than human driven vehicles. Platoon disengagement and cut-ins were analysed and showed that although many platoon break-ups are unavoidable, CACC operation was carried out without incident with frequent recoupling of platoons occurring. Most cut-ins occurred near to intersections, where vehicles are required to merge or need to change lanes to turn off the main corridor. It was not possible to derive potential traffic flow improvements from the FOT, due to a limited overall penetration rate and limitations of the intelligent traffic signals. The findings offer greater insights into the performance of CAV technology in a suburban environment and can aid road authorities to prepare infrastructure for the broader introduction of CAVs as well as the development of modelling tools to improve impact analysis of CAVs in urban environments.

Vehicle visual tracking is a challenging issue in intelligent transportation systems. The tracking gets more challenging when vehicles change direction at intersections. Undetermined motion flows, occlusion, and congestion are the potential issues of vehicle tracking at intersections. In this study, a new method for tracking multiple vehicles from a multi-view is proposed to overcome occlusion caused at the intersections with undetermined motion flows. In the authors’ method, a multilayer graph is presented that assigns motion flows to distinct layers with different neighbourhoods for each layer represented by the graph's edges. Hence, the vehicle trajectories are distributed among layers such that vehicles entering from the same side with similar motion flows are assigned to the same layer. All multilayer graphs of different views are mapped to the graph of the selected view. Then, tracking is performed on the distinct layers of the mapped multilayer graph by computing min-cost flows. In cases such as vehicle crossing, misdetection, or occlusion, the method can predict the vehicle's tracks by using history, layer neighbourhoods, and other views’ information. Experimental results show a consistency of the ground truth and the analysis obtained using the proposed method in tracking vehicles in the inner part of the intersection.

The extensive use of mobile phones has produced a massive amount of trajectory data and provided the possibility to conduct travel behaviour analyses. In this study, a method of travel behaviour analysis is proposed based on extensive trajectory data obtained from Didi Chuxing, China. The travel time regularity and traffic hot spots are analysed from spatial perspectives for three modes: workday, weekend, and the double 11 shopping festival modes. Then a network analysis of the travel hot spots is conducted to study the regularity of travel behaviours. In addition, the travel regularity has been studied and origin/destination prediction of the hot spots has been conducted based on the multivariate -long short-term memory model. The results indicate that the distribution of the travel time during peak hours and at the travel hot spots can effectively reflect the temporal travel regularity of residents. Additionally, the network can reflect the spatial travel regularity of residents. The results provide reference information for improving urban traffic control.

The increasing availability of historical floating car data (FCD) represents a relevant chance to improve the accuracy of model-based traffic forecasting systems. A more precise estimation of origin–destination (O-D) matrices is a critical issue for the successful application of traffic assignment models. The authors developed a methodology for obtaining demand matrices without any prior information, but just starting from a data set of vehicle trajectories, and without using any assignment model, as traditional correction approaches do. Several steps are considered. A data-driven approach is applied to determine both observed departure shares from origins to destinations and static assignment matrices. Then the O-D matrix estimation problem is formulated as a scaling problem of the observed FCD demand and carried out using as inputs: a set of traffic counts, the FCD revealed assignment matrix and the observed departure shares as an a-priori matrix. Four different optimisation solutions are proposed. The methodology was successfully tested on the network of Turin. The results highlight the concrete opportunity to perform a data-driven methodology that, independently from the reliability of the reference demand, minimises manual and specialised effort to build and calibrate the transportation demand models.

Traffic sign detection and classification is a critical component of intelligent transportation systems, which is applied to inform automatic unmanned driving systems and driving assistance systems about conditions and limits of roads. Although computer vision is widely utilised in traffic sign detection, detection and recognising traffic signs globally remains a great challenge due to the variety of sign types, scale-variance and geometric variations. To address these problems, this study proposes a region-based deep convolutional neural network (CNN) framework for traffic sign detection and classification. Specifically, a multi-branch sample pyramid module is proposed, which is based on multi-branch CNNs for multi-scaled feature exaction. A limited deformable convolutional module is then embedded into the CNN layers to learn the distorted information representation for deformation handing. Moreover, a scale-aware multi-task region proposal network module is applied to detect traffic signs with various scales. The whole network is trained in an end-to-end manner. Finally, experiments are conducted on two public detection data sets to demonstrate the effectiveness of the proposed method.

This comment is presented to identify the drawbacks in a recently published scheme SFVCC by Mishra et al. doi:10.1049/iet-its.2019.0250. In this scheme, a malicious adversary may initiate a replay attack and denial of service attack after eavesdropping the communication. These attacks render the scheme inapplicable for practical deployment.