Skip to main navigation Skip to search Skip to main content

Vehicle Trajectory Similarity: Models, Methods, and Applications

  • Universidade Federal de Minas Gerais

Research output: Contribution to journal › Article › peer-review

103 Scopus citations

Abstract

The increasing availability of vehicular trajectory data is at the core of smart mobility solutions. Such data offer us unprecedented information for the development of trajectory data mining-based applications. An essential task of trajectory analysis is the employment of efficient and accurate methods to compare trajectories. This work presents a systematic survey of vehicular trajectory similarity measures and provides a panorama of the research field. First, we show an overview of vehicle trajectory data, including the models and some preprocessing techniques. Then, we give a comprehensive review of methods to compare trajectories and their intrinsic properties. We classify the methods according to the trajectory representation and features such as metricity, computational complexity, and robustness to noise and local time shift. Last, we discuss the applications of vehicular trajectory similarity measures and some open research problems.

Original languageEnglish
Article number3406096
JournalACM Computing Surveys
Volume53
Issue number5
DOIs
StatePublished - 30 Sep 2021
Externally publishedYes

Keywords

  • Datasets
  • mobility
  • trajectory
  • vehicle

Fingerprint

Dive into the research topics of 'Vehicle Trajectory Similarity: Models, Methods, and Applications'. Together they form a unique fingerprint.

Cite this