With a huge volume of trajectories being collected and stored in databases, more and more researchers try to discover outlying trajectories from trajectory databases. In this article, we propose a novel framework called relative distance-based trajectory outliers detection (RTOD). In
RTOD, we first employed relative distances to measure the dissimilarity between trajectory segments, and then formally defined the outlying trajectories based on distance measures. In order to improve the time performance, we proposed an optimization method that employs R-tree and local feature
correlation matrix to eliminate unrelated trajectory segments. Finally, we conducted extensive experiments to estimate the advantages of the proposed approach. The experimental results show that our proposed approach is more efficient and effective at identifying outlying trajectories than
existing algorithms. Particularly, we analyzed the effect of each parameter in theory.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
outlying trajectories mining;
Document Type: Research Article
Department of Computer Science and Technology,Ningbo University of Technology, Ningbo, PR China
Department of Computer Science and Technology,Southwest Jiaotong University, Chengdu, PR China
Publication date: 01 October 2012
More about this publication?