With the rapid pace of urbanization, the number of vehicles traveling between cities has increased significantly. Consequently, many traffic-related problems have emerged, such as traffic jams and ...excessive numbers and types of vehicles. To solve traffic problems, road data collection is important. Therefore, in this paper, we develop an intelligent traffic-monitoring system based on you only look once (YOLO) and a convolutional fuzzy neural network (CFNN), which record traffic volume, and vehicle type information from the road. In this system, YOLO is first used to detect vehicles and is combined with a vehicle-counting method to calculate traffic flow. Then, two effective models (CFNN and Vector-CFNN) and a network mapping fusion method are proposed for vehicle classification. In our experiments, the proposed method achieved an accuracy of 90.45% on the Beijing Institute of Technology public dataset. On the GRAM-RTM data set, the mean average precision and F-measure (F1) of the proposed YOLO-CFNN and YOLO-VCFNN vehicle classification methods are 99%, superior to those of other methods. On actual roads in Taiwan, the proposed YOLO-CFNN and YOLO-VCFNN methods not only have a high F1 score for vehicle classification but also have outstanding accuracy in vehicle counting. In addition, the proposed system can maintain a detection speed of more than 30 frames per second in the AGX embedded platform. Therefore, the proposed intelligent traffic monitoring system is suitable for real-time vehicle classification and counting in the actual environment.
One of the world’s challenges is the amount of traffic on the roads. Waiting for the green light is a major cause of traffic congestion. Low throughput rates and eventual congestion come from many ...traffic signals that are hard coded, irrespective of the volume of the amount of traffic. Instead of depending on predefined time intervals, it is essential to build a traffic signal control system that can react to changing vehicle densities. Emergency vehicles, like ambulances, must be given priority at the intersection so as not to spend more time at the traffic light. Computer vision techniques can be used to improve road traffic signal control and reduce real-time traffic delays at intersections without the requirement for substantial infrastructure analysis. Long wait times and significant energy consumption are just two of the problems of the current traffic signal control system. To optimal efficiency, the traffic signal’s duration must be dynamically changed to account for current traffic volume. To lessen congestion, the approach taken in this research focuses on modifying traffic signal time determined by the density of vehicles at the crossroads. The main purpose of this article is to demonstrate heavy traffic and emergency vehicle prioritization from all directions at the traffic intersection for a speedy passage. Using the Pygame tool, the proposed method in this study, which includes a mechanism for estimating traffic density and prioritization by counting vehicles at a traffic junction, is demonstrated. The vehicle throughput for the adaptive traffic light built using Pygame is compared with the vehicle pass rate for the adaptive traffic light built using Simulation of Urban Mobility (SUMO). The simulation results show that the adaptive traffic light built using Pygame achieves 90% throughput compared to the adaptive traffic light built using SUMO. A Two-Dimensional Convolutional Neural Network (2D-CNN) is implemented using Tensorflow for vehicle classification. The 2D-CNN model demonstrated 96% accuracy in classifying vehicles using the test dataset. Additionally, emergency vehicles, such as ambulances, are given priority for quick passing.
► An analytically tractable Gaussian model of (stochastic) first-order traffic flow. ► Analysis of Lipschitz continuity and (weak-sense) differentiability of disjunctive flux functions. ► A recipe ...for computing large state covariance matrices using few parameters and discussion of their properties. ► A preliminary validation of the model using Kalman filtering in a real-world setting.
A Gaussian approximation of the stochastic traffic flow model of Jabari and Liu (2012) is proposed. The Gaussian approximation is characterized by deterministic mean and covariance dynamics; the mean dynamics are those of the Godunov scheme. By deriving the Gaussian model, as opposed to assuming Gaussian noise arbitrarily, covariance matrices of traffic variables follow from the physics of traffic flow and can be computed using only few parameters, regardless of system size or how finely the system is discretized. Stationary behavior of the covariance dynamics is analyzed and it is shown that the covariance matrices are bounded. Consequently, Kalman filters that use the proposed model are stochastically observable, which is a critical issue in real time estimation of traffic dynamics. Model validation was carried out in a real-world signalized arterial setting, where cycle-by-cycle maximum queue sizes were estimated using the Gaussian model as a description of state dynamics. The estimated queue sizes were compared to observed maximum queue sizes and the results indicate very good agreement between estimated and observed queue sizes.
Drastic changes into city road traffic may impact in large portions of the city, then hypothetical scenarios have to be analyzed to identify the best solutions to maintain high quality of city ...services. In this paper, a solution for unexpected or planned events is proposed and validated with the major focus on traffic flow fields. In order to mitigate the effects on wide area, assessments are needed to evaluate the city changes impact on traffic flow in short time. The proposed solution takes into account static, historical, real-time/dynamic, and forecasting information, with long terms and range of Traffic Flow Reconstructions (multiple simulations, predictions and data transformations) integrated with a specific assessment model to provide support for decision makers. Such a solution dynamically reshapes the road network with many connected critical areas and it automatically computes multiple traffic reconstructions in consecutive time slots, while considering the evolution of traffic flow data according to the related traffic re-distribution at junctions, solving their indeterminacy. Each scenario can be grounded for different road graph solutions, and each solution is evaluated by means of specific indicators taking into account traffic flow criticisms, and topological road graph features. The solution herein presented has been developed into the Snap4City framework for Sii-Mobility national mobility and transport action of the Italian Ministry of Innovation and Research.
Cities around the world are inundated by cars and suffer traffic congestion that results in excess delays, reduced safety and environmental pollution. The interplay between road infrastructure and ...travel choices defines the level and the spatio-temporal extent of congestion. Given the existing infrastructure, understanding how the route choice decisions are made and how travellers interact with each other is a crucial first step in mitigating traffic congestion. This is a problem with fundamental importance, as it has implications for other limited supply systems where agents compete for resources and reach an equilibrium. Here, we observe the route choice decisions and the traffic conditions through an extensive data set of GPS trajectories. We compare the actual paths followed by travellers to those implied by equilibrium conditions (i) at a microscopic scale, where we focus on individual path similarities, and (ii) at a macroscopic scale, where we perform network-level comparison of the traffic loads. We present that non-cooperative or selfish equilibrium replicates the actual traffic (to a certain extent) at the macroscopic scale, while the majority of individual decisions cannot be reproduced by neither selfish nor cooperative equilibrium models.
We investigate if the vehicle travel time after 6 h on a given street can be predicted, provided the hourly vehicle travel time on the street in the last 19 h. Likewise, we examine if the traffic ...status (i.e., low, mild, or high) after 6 h on a given street can be predicted, provided the hourly traffic status of the street in the last 19 h. To pursue our objectives, we exploited historical hourly traffic data from Google Maps for a main street in the capital city of Jordan, Amman. We employ several machine learning algorithms to construct our predictive models: neural networks, gradient boosting, support vector machines, AdaBoost, and nearest neighbors. Our experimental results confirm our investigations positively, such that our models have an accuracy of around 98-99% in predicting vehicle travel time and traffic status on our study's street for the target hour (i.e., after 6 h from a specific point in time). Moreover, given our time series traffic data and our constructed predictive models, we inspect the most critical indicators of street traffic status and vehicle travel time after 6 h on our study's street. However, as we elaborate in the article, our predictive models do not agree on the degree of importance of our data features.
Urban transport traffic surveillance is of great importance for public traffic control and personal travel path planning. Effective and efficient traffic flow prediction is helpful to optimize these ...real applications. The main challenge of traffic flow prediction is the data sparsity problem, meaning that traffic flow on some roads or of certain periods cannot be monitored. This paper presents a transport traffic prediction method that leverages the spatial and temporal correlation of transportation traffic to tackle this problem. We first propose to model the traffic flow using a fourth-order tensor, which incorporates the location, the time of day, the day of the week, and the week of the month. Based on the constructed traffic flow tensor, we either propose a model to estimate the correlation in each dimension of the tensor. Furthermore, we utilize the gradient descent strategy to design a traffic flow prediction algorithm that is capable of tackling the data sparsity problem from the spatial and temporal perspectives of the traffic pattern. To validate the proposed traffic prediction method, case studies using real-work datasets are constructed, and the results demonstrate that the prediction accuracy of our proposed method outperforms the baselines. The accuracy decreases the least with the percentage of missing data increasing, including the situation of data being missing on neighboring roads in one or continuous multi-days. This certifies that the proposed prediction method can be utilized for sparse data-based transportation traffic surveillance.
•The model denoising stacked autoencoders for traffic data imputation is proposed.•The model performance changes with temporal and spatial factors.•An efficient model realization with hierarchically ...training algorithm is developed.
Traffic data provide the basis for both research and applications in transportation control, management, and evaluation, but real-world traffic data collected from loop detectors or other sensors often contain corrupted or missing data points which need to be imputed for traffic analysis. For this end, here we propose a deep learning model named denoising stacked autoencoders for traffic data imputation. We tested and evaluated the model performance with consideration of both temporal and spatial factors. Through these experiments and evaluation results, we developed an algorithm for efficient realization of deep learning for traffic data imputation by training the model hierarchically using the full set of data from all vehicle detector stations. Using data provided by Caltrans PeMS, we have shown that the mean absolute error of the proposed realization is under 10veh/5-min, a better performance compared with other popular models: the history model, ARIMA model and BP neural network model. We further investigated why the deep leaning model works well for traffic data imputation by visualizing the features extracted by the first hidden layer. Clearly, this work has demonstrated the effectiveness as well as efficiency of deep learning in the field of traffic data imputation and analysis.
As a result of a fast-growing population, an increasing number of vehicles on the road, and inadequate public policies, metropolitan areas in Latin America are dealing with significant traffic ...congestion problems. Most cities do not have real-time urban traffic control systems. Therefore, the use of simulation software is a cost-effective solution to evaluate and reduce congestion in metropolitan areas. This paper seeks to assess urban traffic performance using the Urban Mobility Simulator (SUMO) on Fernandes Lima Avenue, the most important thoroughfare in Maceio, Alagoas, Brazil, which features distinctive characteristics such as a dedicated lane for public transportation and three segments with pedestrian traffic lights. Comparing the real observations with the simulation results, it was confirmed that the model provided accurate estimates, with errors of less than 5% for vehicle traffic volume and 10% for total travel time. After conducting experimental studies on four different scenarios, including the current state (1), no blue lane (2), no pedestrian traffic lights (3), and no blue lane and no pedestrian traffic lights (4), it was found that significant improvements in efficiency indicators, such as travel time, waiting time, fuel consumption, and carbon dioxide emissions, could be achieved. Scenarios 2, 3, and 4 were particularly effective, resulting in volumetric increases of 9.95%, 7.88%, and 10.77%, respectively, in vehicle traffic.
The population is increasing rapidly, due to which the number of vehicles has increased, but the transportation system has not yet developed as development occurred in technologies. Currently, the ...lowest capacity and old infrastructure of roads do not support the amount of vehicles flow which cause traffic congestion. The purpose of this survey is to present the literature and propose such a realistic traffic efficiency model to collect vehicular traffic data without roadside sensor deployment and manage traffic dynamically. Today’s urban traffic congestion is one of the core problems to be solved by such a traffic management scheme. Due to traffic congestion, static control systems may stop emergency vehicles during congestion. In daily routine, there are two-time slots in which the traffic is at peak level, which causes traffic congestion to occur in an urban transportation environment. Traffic congestion mostly occurs in peak hours from 8 a.m. to 10 a.m. when people go to offices and students go to educational institutes and when they come back home from 4 p.m. to 8 p.m. The main purpose of this survey is to provide a taxonomy of different traffic management schemes for avoiding traffic congestion. The available literature categorized and classified traffic congestion in urban areas by devising a taxonomy based on the model type, sensor technology, data gathering techniques, selected road infrastructure, traffic flow model, and result verification approaches. Consider the existing urban traffic management schemes to avoid congestion and to provide an alternate path, and lay the foundation for further research based on the IoT using a Mobile crowd sensing-based traffic congestion control model. Mobile crowdsensing has attracted increasing attention in traffic prediction. In mobile crowdsensing, the vehicular traffic data are collected at a very low cost without any special sensor network infrastructure deployment. Mobile crowdsensing is very popular because it can transmit information faster, collect vehicle traffic data at a very low cost by using motorists’ smartphone or GPS vehicular embedded sensor, and it is easy to install, requires no special network deployment, has less maintenance, is compact, and is cheaper compared to other network options.