Traffic Estimation Method Research Articles

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.

Application of Traffic Weighted Multi-Maps Based on Disjoint Routing Areas for Static Traffic Assignment

Urban traffic congestion is a pressing issue, demanding effective and cost-efficient solutions. This paper develops the Traffic Weighted Multi-Maps (TWM) method to solve the Traffic Assignment Problem in Intelligent Transportation Systems (ITS). TWM offers drivers diverse views of the network, promoting path diversity and adaptability. Providing an optimal TWM configuration to the traffic demand in terms of structure and allocation policy is a challenging issue as it usually depends on the size of the network and its complexity. The paper explores TWM generation and assignment by applying routing areas based on semi-disjointed k-shortest paths and allocating them using a per-sub flow optimized assignment policy. This approach allows obtaining a pseudo-optimal solution for static traffic assignment with similar results in terms of total travel time compared to the direct solution of calculating optimal map weights and the theoretical system optimum. It offers a cost-effective solution valid for wide urban areas, as the TWM calculation depends on the variety of the traffic flows and the number of semi-disjoint routing areas considered instead of the network complexity and size. Urban network experiments with synthetic traffic demands are studied under different TWM adoption rates, comparing results with existing traffic assignment policies and estimation methods. It highlights its potential for enhancing urban traffic management. Overall, TWM presents a promising approach to addressing urban traffic congestion efficiently.

MVCV-Traffic: multiview road traffic state estimation via cross-view learning

Fine-grained urban traffic data are often incomplete owing to limitations in sensor technology and economic cost. However, data-driven traffic analysis methods in intelligent transportation systems (ITSs) heavily rely on the quality of input data. Thus, accurately estimating missing traffic observations is an essential data engineering task in ITSs. The complexity of underlying node-wise correlation structures and various missing scenarios presents a significant challenge in achieving high-precision estimation. This study proposes a novel multiview neural network termed MVCV-Traffic, equipped with a cross-view learning mechanism, to improve traffic estimation. The contributions of this model can be summarized into two parts: multiview learning and cross-view fusing. For multiview learning, several specialized neural networks are adopted to fit diverse correlation structures from different views. For cross-view fusing, a new information fusion strategy merges multiview messages at both feature and output levels to enhance the learning of joint correlations. Experiments on two real-world datasets demonstrate that the proposed model significantly outperforms existing traffic speed estimation methods for different types and rates of missing data.

Traffic Density Estimation Methods for Uninterrupted Roadway Facilities: Review and Guidelines

Traffic density is an essential parameter for assessing the performance of uninterrupted facilities during planning, design and operations. This study reviews and evaluates existing density estimation methods. The density estimation methods are classified into two categories: definition of concept (DOC) methods and automated methods. The traditional approach includes aerial photographic, fundamental traffic-flow equation, Edie’s, and cumulative input-output methods. The automated approach includes the occupancy method, filtering method, and integrated method. In addition, the strengths, weaknesses, opportunities, and threats (SWOT) analysis for the preceding methods is conducted. The SWOT analysis will be helpful to researchers and practitioners in selecting the appropriate density estimation method based on its relative merits. Finally, guidelines for using various density methods for heterogeneous and homogeneous traffic are presented.

Sequence-to-Sequence Recurrent Graph Convolutional Networks for Traffic Estimation and Prediction Using Connected Probe Vehicle Data

Traffic estimation is imperative for conducting fundamental transportation engineering tasks such as transportation planning and traffic safety studies. Additionally, traffic prediction is vital for many data-driven intelligent transportation system applications. Most traffic estimation and prediction methods rely on infrastructure-based sensors to collect traffic parameters. However, infrastructure-based data collection can be costly and time consuming to set up and maintain. Additionally, the spatial distribution of the collected traffic data is limited by the location of the deployed hardware sensors. Probe vehicle data can be used to overcome these limitations. Traffic modeling for estimation and prediction is a complex task due to the stochastic nonlinear spatiotemporal dependencies exhibited by traffic parameters. In this paper, a deep learning-based sequence-to-sequence architecture called Seq2seq GCN-LSTM was proposed to estimate and predict network-wide traffic volume and speed. The proposed method utilizes short-term historical traffic data collected from a low-penetration rate probe vehicle fleet to estimate and predict traffic parameters up to 60-minutes ahead. The method utilizes Graph Convolutional Networks for spatial dependency extraction and Long Short-Term Memory networks to model temporal dependencies. The proposed method generated superior traffic results compared to the baseline models. Additionally, the model demonstrated robustness against perturbations caused by the low rate. Furthermore, the probe vehicle penetration rate was varied to test its effect on the proposed method’s modeling capability. The model was able to maintain traffic volume and speed estimation and prediction performance within a reasonable margin of error using penetration rates as low as 1.5% and 0.5%, respectively.

WSNet: A local–global consistent traffic density estimation method based on weakly supervised learning

The available traffic density estimation methods mainly rely on label maps generated by manual annotation to train a network model and enhance the ability of the network model to extract traffic flow feature information. This fully supervised approach requires a lot of manual annotation, which is a time-consuming and laborious task. To solve this problem, this paper proposes a local–global consistent traffic density estimation method based on weakly supervised learning (WSNet). This method extracts the global traffic flow feature information through a trans-traffic module, solves the problem that the traffic flow feature cannot be fully extracted due to the limited receptive fields of convolutional neural networks (CNNs), extracts the local traffic flow feature information through a feedback module, enhances the local representation ability of the traffic flow feature information, and solves the problem of CNNs lacking inductive bias capability due to the use of a transformer only. This method extracts the global traffic flow feature information through the trans-traffic module and the local traffic flow feature information through the feedback module. In addition, a local–global consistency loss function (Lc) is added into the training process and combined with the L1 loss function to strengthen the constraints on traffic density estimation, which effectively improves the accuracy of traffic density estimation. The experimental results show that this method significantly reduces the gap between fully supervised traffic density estimation and weakly supervised traffic density estimation, and the MAE and MSE values of this method are reduced to 4.33 and 5.82, respectively, on the TRANCOS dataset and to 3.90 and 5.8 on the VisDrone2019 Vehicle dataset.

Link-Based Traffic Estimation and Simulation for Road Networks Using Electronic Registration Identification Data

Traffic estimation and traffic simulation are essential parts of the intelligent transportation system. In recent years, massive traffic data has brought many data-based traffic estimation methods, but few are utilized in traffic simulation. The cause is that the data-based traffic simulation has high requirements for data quality, needing the trip information of all vehicles, not met by common traffic data. Fortunately, the electronic registration identification (ERI) data of the vehicle can satisfy. Therefore, we utilize ERI data to study the traffic estimation and simulation for the road network. The core of this research is the travel time estimation model, which is constructed by combining traffic theory models and the deep neural network. The traffic theory models are a group of linear models, which represent the relationship between traffic flow or traffic density and travel time. The deep neural network can extract the temporal and spatial characteristics of the road network traffic by Moving Average Convergence-Divergence (MACD) and Graph Convolutional Network (GCN), respectively. We named the travel time estimation model MGCN. Then, we employed MGCN for traffic simulation. In the experiment section, we employed Chongqing ERI data to verify the research content. Compared with some baseline methods, our method is superior in travel time estimation and traffic simulation.

Le-SKT: Lightweight traffic density estimation method based on structured knowledge transfer

The traffic density estimation algorithm usually runs on an embedded platform, and its efficiency is very important to the implementation of applications. However, most of the existing methods rely on heavy backbone networks, require high-performance hardware platform support and take a long time to calculate, which are difficult prerequisites to apply in practice. In consideration of the aforementioned problems, this paper proposes a lightweight traffic density estimation method based on structured knowledge transfer (Le-SKT). This method consists of a teacher network and student network. In the teacher network, in order to solve the problem of variable vehicle scales in video images, a multiscale fusion structure is designed, which can fully fuse the low-level and high-level features of an image. To solve the problem of background interference in video images, a fusion module based on an attention mechanism is constructed to enhance the useful traffic flow feature information and suppress the background information. At the same time, the fused traffic flow feature information is dilated convoluted to expand the receptive field and obtain richer contextual vehicle feature information, which generates a trained teacher network. Finally, a lightweight student network is generated by using the structured knowledge of the teacher network, which solves the problems of long computing times and high hardware requirements. The MAE and GAME of this method are reduced to 3.92 and 5.69, respectively in the TRANCOS dataset and 3.74 and 5.57, respectively in the VisDrone2019 vehicle dataset, respectively; The parameter quantity of the student network is only 0.65% of that of the teacher network, which greatly reduces the scale of the neural network model and is suitable for an embedded computing platform with low performance.

Spatiotemporal Traffic Density Estimation Based on ADAS Probe Data

This study aims to develop a spatiotemporal traffic density estimation method based on the advanced driver assistance system (ADAS) Probe data. This study uses the vehicle trajectory data collected from the ADAS equipped on the sample probe vehicles. Such vehicle trajectory data are used firstly to estimate the distance headway between the vehicles on a specific road section, and the postprocessed distance headway data are finally used to estimate the spatiotemporal traffic density. The innovation aspect of the proposed methodology in this study is that traffic density can be estimated in high accuracy only with a small size of data points in support of ADAS. On the other hand, existing density estimation method requires a large number of probe vehicles and its numerous data sets including either the global positioning system data or the dedicated short-range communication data. To verify the proposed methodology, a two-step evaluation is performed: the first step is a numerical evaluation that estimates the spatiotemporal traffic density based on the simulated vehicle trajectory data, and the second step is an empirical evaluation that estimates the density based on the real-road data in both peak and nonpeak periods. Beyond the methodology development, this study verified the estimation reliability of traffic density under various traffic conditions based on the sampling rate of ADAS-equipped vehicles. Consequently, the traffic density estimation error decreased as the sampling rate increased. Estimation accuracy of 90% or higher was observed in all scenarios when the sampling rate was 50% or higher. It indicates that fairly accurate traffic density estimation is feasible using probe vehicles that correspond to half of the vehicles driven on the road. Therefore, this practical approach is expected to mitigate the burden of density estimation, particularly in future road systems in which ADAS and autonomous vehicles are prevalent.

A DNN-based estimate of the PRACH traffic load for massive IoT scenarios in 5G networks and beyond

The massive Internet of Things (IoT) scenario refers to a huge number of Machine Type Communications (MTC) characterized by sporadic transmissions of small-sized packets. In order to manage the uplink radio resource allocation in cellular networks, several access schemes have been proposed. These schemes are mainly based on a grant-based Random Access (RA) procedure and proper load-aware access controls, e.g., Access Class Barring (ACB) techniques, dynamic uplink radio resource allocation, and so on. The development of an efficient approach to estimate the traffic load is extremely important for the proper functioning of these access schemes. With the ever-increasing number of transmitting MTC devices, expected with Beyond 5G (B5G) and 6G networks, additional challenges to obtain a correct real-time traffic load estimation are posed. Deep learning techniques, in this context, offer learning ability and optimization capability to properly support this scenario. In this paper, we propose a current access attempts estimation, based on Deep Neural Network (DNN), which accepts as input only the information really available at the next generation Node B (gNB). The network was trained and tested with a dataset properly created and composed by more than 21 million points. The DNN-based traffic load estimation method is then compared with other benchmark schemes available in the literature, in terms of regression accuracy, both in a static analysis, which considers a stand-alone RA cycle, and through a long-term analysis with a time-varying offered load. The latter analysis was performed both by adopting a theoretical arrival process proposed by 3GPP, and by using traces of real traffic data.

Multi-models machine learning methods for traffic flow estimation from Floating Car Data

Traffic flow measurement is very important for traffic management systems. However, the existing traditional measurement approaches are highly time-consuming and expensive to continuously gather the required data and to maintain the corresponding equipment, such as loop detectors and video cameras. On the other hand, many services on the web propose to estimate automobile travel time taking into account traffic conditions thanks to crowd sourced data (Floating Car Data). This work proposes to reconstruct, from estimated travel time, traffic flows using machine learning method. In particular, we evaluate the capacity of Gaussian Process Regressor (GPR) to address this issue. After obtaining estimated travel time on a given route, a clustering process shows that travel duration profiles in each day can be associated to different “types of day”. Then, different regressors are trained in order to estimate traffic flows from travel duration. In the “multi-model” variant, we trained a Regressor for each type of day. Conversely, in the “single model” variant, only one Regressor is trained (the type of day is not taken into account). This is an innovative work to estimate and reconstruct the traffic flow in transportation networks with machine learning method from aggregated Floating Car Data (FCD). A series of experiments are conducted to compare the estimated traffic flows, obtained by the proposed single model and multi-model, and the real ones from actual sensors. The obtained results show that both single model and multi-models can capture the tendency of real traffic flows. Furthermore, the performance can be improved by regulating parameters in GPR machine learning model, such as half width of sample window and sample size (a whole week or only weekdays), and multi-models can highly increase the performance compared with the single model. Therefore, the proposed GPR machine learning and FCD based new method can replace those traditional loop detectors for the measurement of traffic flow.

A novel image-based convolutional neural network approach for traffic congestion estimation

Traditional image-based traffic congestion estimation methods generally include two steps, which first extract the vehicles from the surveillance images, then calculate the congestion index using the vehicle counts. When working with vast amount of video frames, these approaches are time-consuming and hardly guarantee the real time detection of traffic congestion. In this study, firstly a specific and accurate definition of traffic congestion is proposed to quantify the level of traffic congestion. Then we construct an image-based traffic congestion estimation framework, in which a traffic parameter layer is integrated to the basic convolutional neural network (CNN) model. The proposed framework can directly perform traffic congestion calculation and estimation, which shortens the processing time and avoids the complicated postprocessing. A dataset of 1400 traffic images including 66,890 vehicles is collected for training the proposed CNN model. Another new dataset of 2400 traffic images including 113,516 vehicles is collected to test the proposed method on estimating traffic congestion. Experimental results show that our proposed approach has better efficiency and stability in both free flow and congested traffic conditions, as well as sunny and rainy scenes.

A traffic flow estimation method based on unsupervised change detection

With the rapid development of intelligent transportation, the video surveillance system as its important component has been achieved much attention. Traffic condition closely related to people’s lives needs to be tracked in time. Some methods estimate traffic flow by analyzing the pictures taken by fixed cameras. However, they can only estimate the traffic condition of particular roads. Different from the traditional traffic flow estimation methods, the proposed method explores the video information rather than traffic images acquired by sensing remote-sensing sensors in this letter. More specifically, the highlights of our work include the following parts: first, change detection is performed on analyzing the difference between one frame image extracted from Unmanned Aerial Vehicle (UAV) videos and an updated background image for the sake of recognizing the whole profile of every moving object. Second, a modified fuzzy c-means method is engaged in the process of change detection, which segments the road regions to enhance the profiles of moving objects and eliminate the noise of complex backgrounds. Finally, the estimation of traffic flow can be achieved by analyzing the change detection result. Besides, the videos shot by UAV on a crossroad are used to analyze the effectiveness of the proposed method. Experimental results on a series of binary images and proportion illustrations demonstrate the promising performance of the proposed method in terms of human visual perception and segmentation accuracy.

A Fast Vehicle Counting and Traffic Volume Estimation Method Based on Convolutional Neural Network

Vehicle counting and traffic volume estimation on traffic videos has gained extensive attention from multimedia and computer vision communities. Recent vehicle counting and volume estimation methods, including detection based and time-spatial image (TSI) based methods have achieved significant improvements. However, how to balance the accuracy and speed is still a challenge to this task. In this paper, we design a fast and accurate vehicle counting and traffic volume estimation method. Firstly, traffic videos are converted to TSIs and we annotate the vehicle locations in TSIs manually. Then, we design a simple TSI density map estimation network which utilizes attention mechanism to strengthen the features in the traffic locations for vehicle counting. Finally, we use the parameters obtained from the vehicle counting network to further estimate the traffic volume. Experiments on UA-DETRAC dataset demonstrate that the vehicle counting network not only takes a balance between counting accuracy and speed, but also well estimates the traffic volume when the video data is insufficient.

Learning Based Methods for Traffic Matrix Estimation From Link Measurements

Network traffic matrix (TM) is a critical input for capacity planning, anomaly detection and many other network management related tasks. The TMs are often computed from link load measurements. The TM estimation problem is the determination of the TM from link load measurements. The relationship between the link loads and the TM that generated the link loads can be modeled as an under-determined linear system and has multiple feasible solutions. Therefore, prior knowledge of the traffic demand pattern has to be used in order to find a potentially feasible TM. In this paper, we consider the TM estimation problem with limited prior information. Unlike previous methods that require past measurements of complete TMs, which are hard to obtain or protected by regulations, our method works even if only the distribution of TMs is known. We develop an iterative projection based algorithm to solve this problem. If large number of past TMs can be measured, we propose a Generative Adversarial Network (GAN) based approach for solving the problem. We compare the strengths of the two approaches and evaluate their performance for several networks using varying amounts of past data.

Anomaly-Aware Network Traffic Estimation via Outlier-Robust Tensor Completion

Accurately estimating network traffic from the partial measurements plays a crucial role in network management. However, the potential anomaly existing in real networks usually makes this goal difficult to achieve. Existing network traffic estimation methods generally impute network traffic independent of anomaly detection, which incurs significant performance degradation with network anomaly. To address this issue in the realistic network scenario, we propose a novel anomaly-aware network traffic estimation method to recover network traffic data concurrently with network anomaly detection. Specifically, by exploiting the inherent spatio-temporal characteristics, we first formulate the network traffic estimation as a low-rank tensor completion problem. Then, an outlier-robust tensor completion (OrTC) model is constructed by introducing both L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2,1</sub> -norm regularization and L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</sub> -norm regularization, which can not only well fit the intrinsic low-rank property of real traffic data, but also is robust against both the dense noise and the sparse anomaly. Furthermore, an effective optimization algorithm OrTC-AM is designed to solve the non-convex and non-smooth OrTC model based on the popular alternating minimization method. Finally, the extensive experiments performed on the public dataset demonstrate that our proposed OrTC-AM method outperforms the previously widely used network traffic estimation methods.

A tensor decomposition method for cycle-based traffic volume estimation using sampled vehicle trajectories

Cycle-based traffic volume estimation is important for the dynamic evaluation and optimization of signal control schemes at intersections. With the development of intelligent mobility and connected vehicle technologies, massive high-resolution vehicle trajectory data have become available, which can provide a rich source of information for estimating traffic flow parameters at signalized intersections. Existing methods for traffic volume estimation using sampled vehicle trajectories are commonly driven by shockwave or probabilistic models, in which the traffic volume estimation is usually modelled as a parameter estimation problem. These methods commonly require certain assumptions for the vehicle arrival distribution and a First-In-First-Out (FIFO) queuing rule. However, these model-driven methods have limitations when the vehicle arrival distribution is unknown or when there is more than one lane for the same movement at an intersection approach, as the FIFO rule is no longer true. In addition, the accuracy and stability of these models remain challenging under low penetration rates. In this paper, we propose a tensor decomposition method to estimate cycle-based traffic volume at signalized intersections using sampled vehicle trajectories. Unlike the existing model-driven methods, the proposed method is purely data-driven and does not rely on any prerequisite assumptions for the arrival distributions and queuing rules. In the proposed method, the traffic volume of each cycle is first divided into a known part and an unknown part, based on the queuing position of the last queued sample vehicle. Then, these two parts of the volume as a whole, along with two relevant traffic observations (i.e., the number of sampled vehicles and the observation duration), are then integrated into a three-dimensional tensor. This tensor can effectively preserve the temporal correlations between adjacent cycles and the interrelationships among the traffic observations. Finally, the problem of cycle-based traffic estimation is transformed into a tensor completion problem, and the Tucker decomposition method is adopted to solve the completion problem. The proposed method is evaluated using both empirical and simulation data. The results indicate that the proposed method is capable of producing accurate and reliable estimates for cycle-based traffic volumes even under low penetration rates, i.e., less than 5%.

Towards real-time density estimation using vehicle-to-vehicle communications

Traffic state estimation is a fundamental task of Intelligent Transportation Systems (ITS). Recent advances in sensor technology and emerging computer and vehicular communications paradigms have brought the task of estimating traffic state parameters in real time within reach. Recognizing this, the US-DOT started promoting the Connected Vehicles (CV) initiative. By using wireless connectivity between the vehicles participating in the traffic, the CV initiative aims to promote an increased awareness of real-time traffic conditions and, as a result, to reduce the number and severity of crashes.A number of recent papers have proposed CV-based approaches to estimating traffic state parameters including density and flow. However, virtually all the CV-based approaches for density estimation also rely on communication with stationary detectors and other pre-deployed roadside infrastructure. This assumption is problematic since such infrastructure is often not available.The main contribution of this paper is to propose a simple and easy to implement real-time traffic density estimation method that uses only vehicle-to-vehicle communications and the on-board sensing capabilities of present-day vehicles. In our method, using their on-board devices, vehicles maintain a tally that keeps track of the difference between the number of times other vehicles pass them and the number of times they pass other vehicles. Notice that since vehicles may vary their speed as they please, they may pass and be passed by the same vehicle multiple times and, consequently, maintaining a correct tally is a non-trivial task. We show that the tallies computed by vehicles relate, in an interesting way, to traffic density.We provide a detailed proof of our method using techniques that avoid the use of common simplifications inherent to visual time-space traffic diagrams. Furthermore, we demonstrate the accuracy of our method through extensive simulations using real NGSIM traffic traces along with SUMO-generated synthetic traffic traces.

Traffic Data Imputation Using Deep Convolutional Neural Networks

We propose a statistical learning-based traffic speed estimation method that uses sparse vehicle trajectory information. Using a convolutional encoder-decoder based architecture, we show that a well trained neural network can learn spatio-temporal traffic speed dynamics from time-space diagrams. We demonstrate this for a homogeneous road section using simulated vehicle trajectories and then validate it using real-world data from NGSIM. Our results show that with probe vehicle penetration levels as low as 5\%, the proposed estimation method can provide a sound reconstruction of macroscopic traffic speeds and reproduce realistic shockwave patterns, implying applicability in a variety of traffic conditions. We further discuss the model's reconstruction mechanisms and confirm its ability to differentiate various traffic behaviors such as congested and free-flow traffic states, transition dynamics, and shockwave propagation.

Various methods for queue length and traffic volume estimation using probe vehicle trajectories

The rapid development of connected vehicle technology and the emergence of ride-hailing services have enabled the collection of a tremendous amount of probe vehicle trajectory data. Due to the large scale, the trajectory data have become a potential substitute for the widely used fixed-location sensors in terms of the performance measures of transportation networks. Specifically, for traffic volume and queue length estimation, most of the trajectory data based methods in the existing literature either require high market penetration of the probe vehicles to identify the shockwave or require the prior information about the queue length distribution and the penetration rate, which may not be feasible in the real world. To overcome the limitations of the existing methods, this paper proposes a series of novel methods based on probability theory. By exploiting the stopping positions of the probe vehicles in the queues, the proposed methods try to establish and solve a single-variable equation for the penetration rate of the probe vehicles. Once the penetration rate is obtained, it can be used to project the total queue length and the total traffic volume. The validation results using both simulation data and real-world data show that the methods would be accurate enough for assistance in performance measures and traffic signal control at intersections, even when the penetration rate of the probe vehicles is very low.