Analysis of Road Safety Speed from Floating Car Data

Floating car data (FCD) is an important source of traffic data for the design and management of an intelligent transportation system, and the efficiency and accuracy of FCD map-matching influences the application of FCD. Most map-matching algorithms are very time-consuming because many links need to be evaluated as to whether they are the correct link for the travelling floating car, especially in urban areas where most FCD are collected. In fact, the highest degree of map-matching a link for an FCD is not always the correct link, so the use of candidate links is proposed here. In this study, candidate links are defined as those that fall within the FCD error. We propose a novel algorithm for quickly identifying accurate candidate links on the basis of a vector to raster road map conversion approach. First, a road buffer is constructed based on the size of the confidence region by taking into account the position error of the FCD and the width of the link. Second, all link buffers are converted to a raster map with resolution in metres, each pixel position of the raster map corresponding to a geographical coordinate. A pixel can have one or more values, which represent the link ID whether the link buffer covers the pixel; so a spatial index map between geographical coordinate and link ID is built in this way. Then, candidate links are calculated rapidly in the next three steps: (1) Selecting a link ID from the spatial index map that, according to the FCD positioning fix coordinate, must fall within the confidence region of the FCD. The number is very small and this step is very fast because it does not include a traverse process. (2) Getting data for selected link from the road networks vector map by the link ID. This step uses a binary search and is very fast. (3) Calculating the degree of map-matching of these links to identify candidate links of the FCD. This algorithm is far less time-consuming than earlier approaches. The algorithm was tested using more than 13 million real-world FCD collected in Wuhan City, China, and the performance was shown to be satisfactory.

Research on the Real-time Traffic Status Identification of Signalized Intersections Based on Floating Car Data

With advances in information technologies, floating car data (FCD) (e.g. trajectories of taxis) becomes an important data source for collecting traffic information in urban road networks. Due to the low sampling frequency of FCD, it is a challenge to obtain accurate and reliable travel time estimation based on FCD. This paper presents a location-speed method for accurately estimating travel times in signalized road networks based on FCD. The proposed model utilizes trajectories of probe vehicles on the upstream and downstream of signalized intersections in order to estimate delays caused by traffic signals. A large-scale case study using real-world FCD in Wuhan is carried to validate the proposed method. The results of case study show that the proposed method can obtain satisfied estimation of travel times in signalized road networks.

Floating Car Data (FCD) is a kind of emerging data in the field of traffic engineering. There are three problems in its application of the traffic state discrimination: First, the existing traffic state discrimination model is only for road segment detection; Second, the road-segment based discrimination model is not conducive to the spatial-temporal evolution analysis of traffic state. Third, the existing road segment traffic state discrimination model directly adopts the prototypical Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, and the detection result is limited in accuracy. We proposed a multi-dimensional traffic state discrimination method. Firstly, the traffic state of the road segment is determined based on the improved DBSCAN algorithm. The dynamic segmentation technology is used to realize the visualization of the road traffic state. Then, the traffic incident point discrimination model is constructed according to the spatial-temporal evolution pattern of the road conditions under traffic incidents. The visualization results show that the proposed method can achieve relatively fine multidimensional traffic state discrimination.

The ultimate goal of a Traffic Information System (TIS) consists in properly informing vehicles about road traffic conditions in order to reduce traffic jams and consequently CO2 emission while increasing the user comfort. Therefore, the design of an efficient aggregation protocol that combines correlated traffic information like location, speed and direction known as Floating Car Data (FCD) is of paramount importance. In this paper, we introduce a new TIS data aggregation protocol called Smart Directional Data Aggregation (SDDA) able to decrease the network overload while obtaining high accurate information on traffic conditions for large road sections. To this end, we introduce three levels of messages filtering: (i) filtering all FCD messages before the aggregation process based on vehicle directions and road speed limitations, (ii) integrating a suppression technique in the phase of information gathering in order to eliminate the duplicate data, and (iii) aggregating the filtered FCD data and then disseminating it to other vehicles. The performed experiments show that the SDDA outperforms existing approaches in terms of effectiveness and efficiency.

Adaptive signal control is a method that dynamically adjusts signal phases based on real-time traffic conditions, aiming to improve the efficiency of intersection light control. However, in practical applications, obtaining complete traffic spatiotemporal states at intersections is challenging given the limited data sources. To address this issue, this paper presents a novel deep reinforcement learning model, namely 3DQN-PSTER, which combines Dueling Deep Q Network, Double Deep Q Network, and Priority SumTree Experience Replay technology. This model effectively extracts traffic states from sampled floating car data (FCD) and achieves optimal timing schemes. To evaluate its performance, the proposed model is tested in a simulated intersection environment using actual intersection data. The model interacts with the environment by adjusting signal phases, updating traffic states, and obtaining optimal timing schemes. Simulation results demonstrate that the proposed model exhibits higher convergence efficiency and outperforms benchmark models. When applied, the reinforcement learning single control (RLSC) based on the 3DQN-PSTER model outperforms fixed-time signal control schemes and actuated signal control (ASC) schemes. Even in scenarios with low penetration ratios of FCD, RLSC still significantly outperforms ASC. Therefore, the signal timing optimization method proposed in this paper could greatly enhance intersection operation efficiency in both ideal overall data environments and partial states.

Urban arterials in Shanghai usually have high intersection densities, which can lead to frequent and severe congestion. Research in this area of study focuses on urban arterial operating speed and its relationship with road geometry, traffic control, and traffic volume, and more study is needed before remedies to the congestion problems can be identified. In Shanghai, an opportunity exists to investigate urban arterial operating speed by accessing continuously updated global positioning system (GPS) data from taxis, hereafter called floating car data (FCD). With more than 50,000 taxis equipped with GPS running in the Shanghai road network, it is feasible to acquire comprehensive, citywide arterial speed measurements throughout the network. In this study, 45 arterials in Shanghai, which comprised of 177 two-direction segments bounded by signalized intersections, were selected for study. GPS data from taxis were captured during peak and off-peak hours to enable the calculation of the mean operating speed for each selected segment. Information of road geometry, traffic control, and traffic volume data was also acquired to examine their influence on operating speed. Multilevel linear regression models were utilized to analyze operating speed with the arterial level’s unobserved heterogeneity accounted for as well. It was identified that roadway design variables, including segment length, number of lanes, and horizontal degree of curvature, left-turn lane types, and presence of median along with saturation degree, are all significantly related to the operating speed. The results of this study shed some light on roadway design, roadway improvement, and traffic management.

Detecting and describing movement of vehicles in established transportation infrastructures is an important task. It helps to predict periodical traffic patterns for optimizing traffic regulations and extending the functions of established transportation infrastructures. The detection of traffic patterns consists not only of analyses of arrangement patterns of multiple vehicle trajectories, but also of the inspection of the embedded geographical context. In this paper, we introduce a method for intersecting vehicle trajectories and extracting their intersection points for selected rush hours in urban environments. Those vehicle trajectory intersection points (TIP) are frequently visited locations within urban road networks and are subsequently formed into density-connected clusters, which are then represented as polygons. For representing temporal variations of the created polygons, we enrich these with vehicle trajectories of other times of the day and additional road network information. In a case study, we test our approach on massive taxi Floating Car Data (FCD) from Shanghai and road network data from the OpenStreetMap (OSM) project. The first test results show strong correlations with periodical traffic events in Shanghai. Based on these results, we reason out the usefulness of polygons representing frequently visited locations for analyses in urban planning and traffic engineering.

Abstract. Floating car technology is widely applied in traffic information collection and has become a common method for real-time and dynamic monitoring of urban traffic conditions. Using floating car data from Shanghai as the research object, this paper analyzes the positioning error of floating cars and finds that most errors are within 15 meters. The error is significantly affected by vehicle speed but less by time, and the error decreases as the road grade increases. Speed and travel time ratio are used as parameters to assess the spatiotemporal traffic state, exploring the spatial distribution and temporal evolution of speed, as well as the spatiotemporal distribution of traffic congestion. In the spatial distribution of speed, clustering analysis is used to deduce the temporal distribution pattern of speed on the same road segment. Based on this, corresponding traffic management measures can be applied to different road segments and at different times.

Vehicles' trajectory prediction is a topic with growing interest in recent years, as there are applications in several domains ranging from autonomous driving to traffic congestion prediction and urban planning. Predicting trajectories starting from Floating Car Data (FCD) is a complex task that comes with different challenges, namely Vehicle to Infrastructure (V2I) interaction, Vehicle to Vehicle (V2V) interaction, multimodality, and generalizability. These challenges, especially, have not been completely explored by state-of-the-art works. In particular, multimodality and generalizability have been neglected the most, and this work attempts to fill this gap by proposing and defining new datasets, metrics, and methods to help understand and predict vehicle trajectories. We propose and compare Deep Learning models based on Long Short-Term Memory and Generative Adversarial Network architectures; in particular, our GAN-3 model can be used to generate multiple predictions in multimodal scenarios. These approaches are evaluated with our newly proposed error metrics N-ADE and N-FDE, which normalize some biases in the standard Average Displacement Error (ADE) and Final Displacement Error (FDE) metrics. Experiments have been conducted using newly collected datasets in four large Italian cities (Rome, Milan, Naples, and Turin), considering different trajectory lengths to analyze error growth over a larger number of time-steps. The results prove that, although LSTM-based models are superior in unimodal scenarios, generative models perform best in those where the effects of multimodality are higher. Space-time and geographical analysis are performed, to prove the suitability of the proposed methodology for real cases and management services.

The recent intelligent transportation system has yielded remarkable progress on traffic data collection, resource allocation and intelligent programming. However, development on traffic real-time data processing and prediction still remains limited. In pursuit of real-time prediction on road section average speed, we introduced a prediction method, which mines GIS floating car data with support vector regression algorithm. The result indicated our proposed method was superior in comparison with other commonly used algorithms including linear regression, artificial neural network, Bayesian regression and ridge regression. Besides, the quick convergence and well fitting confirmed the plausibility of our method in this domain.

Understanding the response of a transportation system to disruptive events is significant for evaluating the resilience of the system. However, data collection during such events is always challenging, and the data volume is insufficient for building a robust model. Transfer learning provides an effective solution to this problem. In this study, we propose a floating car data (FCD) driven transfer learning framework for predicting the resilience of target transportation systems to similar disruptive events to those that have ever occurred in the source systems. The core of the framework is an unsupervised pattern extractor that combines the k-Shape clustering and Bayes inference methods for extracting resilience patterns from the FCD collected in the source systems during the disruption period. The extracted patterns can then be used to assist in the prediction of the resilience of the target systems. We examine the effectiveness of the proposed framework by conducting a case study under the context of the COVID-19 pandemic, in which the source domain cities include Antwerp and Bangkok, and the target domain city is Barcelona. Results show that the extracted resilience patterns can improve the prediction performance of transfer learning neural networks with less pre-event information and limited data volume.

Heterogeneous cellular and DSRC networking for Floating Car Data collection in urban areas

Empirical analysis of impact of multi-class commercial vehicles on multi-lane highway traffic characteristics under mixed traffic conditions

Urban network traffic state estimation using a data-based approach