Detecting Movement Type by Route Segmentation and Classification

Karol Waga; Andrei Tabarcea; Minjie Chen; Pasi Fränti

8th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing

Research Article

Detecting Movement Type by Route Segmentation and Classification

Download645 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.4108/icst.collaboratecom.2012.250450,
    author={Karol Waga and Andrei Tabarcea and Minjie Chen and Pasi Fr\aa{}nti},
    title={Detecting Movement Type by Route Segmentation and Classification},
    proceedings={8th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing},
    publisher={IEEE},
    proceedings_a={COLLABORATECOM},
    year={2012},
    month={12},
    keywords={route analysis segmentation classification gps trajectory routes tracks mobile applications second order markov model},
    doi={10.4108/icst.collaboratecom.2012.250450}
}

Karol Waga
Andrei Tabarcea
Minjie Chen
Pasi Fränti
Year: 2012
Detecting Movement Type by Route Segmentation and Classification
COLLABORATECOM
ICST
DOI: 10.4108/icst.collaboratecom.2012.250450

Karol Waga¹, Andrei Tabarcea¹, Minjie Chen¹, Pasi Fränti¹^,*

1: University of Eastern Finland

*Contact email: franti@cs.joensuu.fi

Abstract

Data about people movement is nowadays easy to collect by the GPS technology embedded in smartphones. GPS routes provide information about position, time and speed, but further conclusion requires either prior information or data analysis. We propose a method to detect the movement type by segmentation of the GPS route using speed, direction and their derivatives, and by applying an inference algorithm via a second order Markov model. The method is able to classify most typical moving types such as motor vehicle, bicycle, run, walk and stop.

Keywords: route analysis segmentation classification gps trajectory routes tracks mobile applications second order markov model

Published: 2012-12-14
Publisher: IEEE

: http://dx.doi.org/10.4108/icst.collaboratecom.2012.250450