Detecting traffic congestion propagation in urban environments – a case study with Floating Taxi Data (FTD) in Shanghai (original) (raw)

Spatio-temporal clustering for non-recurrent traffic congestion detection on urban road networks

Transportation Research Part C: Emerging Technologies, 2014

Non-Recurrent Congestion events (NRCs) frustrate commuters, companies and traffic operators because they cause unexpected delays. Most existing studies consider NRCs to be an outcome of incidents on motorways. The differences between motorways and urban road networks, and the fact that incidents are not the only cause of NRCs, limit the usefulness of existing automatic incident detection methods for identifying NRCs on urban road networks. In this paper we propose an NRC detection methodology to support the accurate detection of NRCs on large urban road networks. To achieve this, substantially high Link Journey Time estimates (LJTs) on adjacent links that occur at the same time are clustered. Substantially high LJTs are defined as those LJTs that are greater than a threshold. The threshold is calculated by multiplying the expected LJTs with a congestion factor. To evaluate the effectiveness of the proposed NRC detection method, we propose two novel criteria. The first criterion, high-confidence episodes, assesses to what extent substantially high LJTs that last for a minimum duration are detected. The second criterion, the Localisation Index, assesses to what extent detected NRCs could be associated with incidents. The proposed NRC detection methodology is tested for London's urban road network. The optimum value of the congestion factor is determined by sensitivity analysis by using a Weighted Product Model (WPM). It is found out those LJTs that are at least 40% higher than their expected values should belong to an NRC; as such NRCs are found to maintain the best balance between the proposed evaluation criteria.

Detecting vehicle traffic patterns in urban environments using taxi trajectory intersection points

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.

How Travel Demand Affects Detection of Non-Recurrent Traffic Congestion on Urban Road Networks

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Occurrence of non-recurrent traffic congestion hinders the economic activity of a city, as travellers could miss appointments or be late for work or important meetings. Similarly, for shippers, unexpected delays may disrupt just-in-time delivery and manufacturing processes, which could lose them payment. Consequently, research on non-recurrent congestion detection on urban road networks has recently gained attention. By analysing large amounts of traffic data collected on a daily basis, traffic operation centres can improve their methods to detect non-recurrent congestion rapidly and then revise their existing plans to mitigate its effects. Space-time clusters of high link journey time estimates correspond to non-recurrent congestion events. Existing research, however, has not considered the effect of travel demand on the effectiveness of non-recurrent congestion detection methods. Therefore, this paper investigates how travel demand affects detection of non-recurrent traffic conges...

Characterizing the Traffic Density and Its Evolution through Moving Object Trajectories

2009

Managing and mining data derived from moving objects have become an important issue in recent years. In this paper, we are interested in mining trajectories of moving objects, such as vehicles in the road network. We propose a method for discovering dense routes by clustering similar road sections according to both traffic and location in each time period. The traffic estimation is based on the collected spatiotemporal trajectories. We also propose a characterization approach of the temporal evolution of dense routes by a graph connecting dense routes over consecutive time periods. This graph is labeled by a degree of evolution. We have implemented and tested the proposed algorithms, which have shown their effectiveness and efficiency.

Discovering Patterns in Traffic Sensor Data

We maintain a one of a kind, large-scale and high resolution (both spatially and temporally) traffic sensor dataset collected from the entire Los Angeles County road network. Traffic sensors (installed under the road pavement) are used to measure real-time traffic flows through road segments. In this paper, we exploit this dataset to rigorously verify two popular instinctive understandings about traffic flows on road segments: 1) each road segment has a typical traffic flow (known by local travelers) and one can often categorize road segments based on the similarity of their traffic flows, and 2) the road segments within each category not only have similar traffic flows but also are similar in their other characteristics (such as locality, connectivity). Toward this end, we developed a hypothesis analysis framework based on a variety of clustering and correlation evaluation techniques and leveraged this framework to respectively show the following. First, the set of road segments can indeed be partitioned into a set of distinct subpartitions with similar traffic flows, and there is a limited number of signature traffic patterns/labels each of which can accurately represent all traffic flows of a subpartition of the road segments. Second, all segments within each subpartition (represented by one signature) are also highly similar in three other characteristics, namely, direction, connectivity and locality. Our experiments verify our observations with high confidence.

Discovering Congestion Propagation Patterns in Spatio-Temporal Traffic Data

IEEE Transactions on Big Data, 2017

Congestion is the condition of the road in the traffic networks which is characterised as slow speed and long travel time. The detection of unusual traffic patterns including congestions is an significant research problem in the data mining and knowledge discovery community. However, to the best of our knowledge, the discovery of propagation, or causal interactions among detected traffic congestions has not been appropriately investigated before. In this research, we introduce algorithms which construct causality trees based on temporal and spatial information of identified congestions. Frequent substructures of these causality trees reveal not only recurring interactions among spatio-temporal congestions, but potential bottlenecks or flaws in the design of existing traffic networks. Our algorithms are validated by experiments on a large real-time travel time data in an urban road network.

Spatio-Temporal Congestion Patterns in Urban Traffic Networks

Transportation Research Procedia, 2016

Traffic congestion in urban areas is a big issue for cities around the world. Thus, studying congestion and respective counter measures is of high importance for the increasing urbanization of society. Congestion analysis and forecast is most of the times done either on a link-wise network or on a networkwide level. Though, due to bottlenecks in the infrastructure and similar commuting patterns by road users, usually the same parts of an urban traffic network get congested. The idea is to observe and investigate primarily these most vulnerable parts of the network, which are denoted as congestion clusters, as they are crucial to both, drivers and operators. A methodology for determining congestion clusters is described, which provides a significant amount of flexibility to be able to meet different needs for different applications or cities. Based on a five months set of Floating Car (FC) data, the suggested methodology is tested. First analyses are conducted to understand up to which degree these clusters are able to represent the congestion level of the entire network. Besides, correlations between the clusters are investigated on a statistical basis and conclusions are drawn. The results provide a basis for potential traffic estimation and forecast systems.

12 Years of Mining Road Traffic Data

2018

Predicting traffic congestion is an important tool for users, authorities, fleet management companies, and road planners. Typically road traffic authorities know the long-term demands on road sections, however, the shorter-term prediction is a research problem. That said, algorithms, data, and processing have advanced to a point where new road analysis can be done, which is very much the topic of this contribution. This paper applies big data practices on 12 years of data from the Swedish road traffic authority to predict traffic flow congestion around the city of Stockholm. We present a simple transparent model to detect traffic build up in space and time, and hence find the end of any queue. An important insight in this work is the use of traffic density as a different measure for congestion detection, rather than the average velocity or flow values. Ian Marsh RISE SICS Γ ian.marsh@ri.se Ahmad Al-Shistawy RISE SICS Γ ahmad.al-shistawy@ri.se Cosar Ghandeharioon KTH Γ cosarg@kth.se ...

Understanding Taxi Driving Behaviors from Movement Data

Lecture Notes in Geoinformation and Cartography, 2015

Understanding taxi mobility has significant social and economic impacts on the urban areas. The goal of this paper is to visualize and analyze the spatiotemporal driving patterns for two income-level groups, i.e. high-income and low-income taxis, when they are not occupied. Specifically, we differentiate the cruising and stationary states of non-occupied taxis and focus on the analysis of the mobility patterns of these two states. This work introduces an approach to detect the stationary spots from a large amount of non-occupied trajectory data. The visualization and analysis procedure comprises of mainly the visual analysis of the cruising trips and the stationary spots by integrating data mining and visualization techniques. Temporal patterns of the cruising trips and stationary spots of the two groups are compared based on the line charts and time graphs. A density-based spatial clustering approach is applied to cluster and aggregate the stationary spots. A variety of visualization methods, e.g. map, pie charts, and space-time cube views, are used to show the spatial and temporal distribution of the cruising centers and the clustered and aggregated stationary spots. The floating car data collected from about 2000 taxis in 47 days in Shanghai, China, is taken as the test dataset. The visual analytic results demonstrate that there are distinctive cruising and stationary driving behaviors between the high-income and low-income taxis.

Application of clustering algorithms for spatio-temporal analysis of urban traffic data

Transportation Research Procedia, 2020

The large vehicle movement traffic datasets offer a lot of great opportunities for the evolution of new methodologies for the analysis of the transportation system. However, deriving relevant traffic patterns from such a vast amount of historical dataset is challenging. In this paper, several data mining techniques have been applied to obtain more understanding about urban traffic patterns by analyzing hourly and daily variation in urban traffic flow dataset. A model has been developed for the analysis of spatial and temporal patterns in urban traffic data. Model development involves the formulation of algorithms to be applied to the data and choice of various metrics to evaluate the clustering algorithm. Furthermore, these techniques have been applied to the traffic dataset of Aarhus, the second-largest city of Denmark. Finally, results are analyzed to determine the various factors that affect the traffic flow patterns in an urban area.