Abstract
Abstract. Constrained by road network structure, travel choice and city function zoning, GPS trajectory data exhibits significant spatiotemporal correlation. Unveiling the clustering and distribution patterns of GPS trajectory can help to better understand the travel behaviour as well as the corresponding spatial and temporal characteristics. This paper proposes an approach to identify and visualize the aggregation pattern from GPS trajectory data. Firstly, slow feature trajectory sequences are extracted from raw taxi trajectory data. Together with taxi states information, these sequences are processed as shorter length tracks for faster discovery of cluster similarity. Thereafter, the temporal and spatial similarity and dissimilarity metrics between the trajectories are established, and the temporal and spatial distances between the trajectories are defined to form a space-time cylinder model. Next, based on the idea of density clustering, the DBSCAN spatiotemporal expansion of trajectory data is proposed. Feature trajectory sequences are then clustered into groups with high similarity. Finally, for a more intuitive understanding of the trajectory aggregate distribution, time dimension info of each point in the sequences is used as Z axis, thus the sequences are stretched on the map in different colour for 3D visualization. The proposed method is validated by a case study of taxi trajectory data analysis in Wuhan City, China.
Highlights
With the rapid development of positioning and communication technologies, increasing amount of traffic information has been collected in diverse ways
Considering that the time information of the trajectory sequence is simplified to [t1, tn], this paper proposes a method for calculating temporal similarity S and Dissimilarity D based on time overlapping in the time dimension
In this paper, a method is proposed to identify and visualize the aggregation pattern from spatiotemporal trajectories. This method draws on the idea of space-time cylinder model and DBSCAN algorithm, defines the temporal and spatial distance metrics for similarity measurement, expands the density-based clustering algorithm in spatiotemporal trajectory, and stretches the time dimension of the trajectory sequences for 3D visualization
Summary
With the rapid development of positioning and communication technologies, increasing amount of traffic information has been collected in diverse ways. Traffic patterns, especially aggregation patterns, can be more accurately identified to find hot spot, congestion, accident and all other types of sudden gathering behaviour. Uncovering the aggregation patterns behind them can help increase safety, optimize urban planning and providing guidance for traveling route selection. To generate traffic information for every road segment, speed and position information of floating cars is usually collected at regular time intervals (e.g., 30s). With attached information about the states of passenger and car’s engine, floating car data enables us to identify feature subtrajectory of specific meanings like getting-on/drop-off hotspot (Zhao et al, 2015) and traffic congestion (Liu et al, 2015). We focus on slow sub-trajectory sequences, these shorter length tracks can help faster discover similarity and find clusters
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
