Abnormal Pedestrian Trajectory analysis based on arbitrary-length clustering

Research output: Chapter in Book/Report/Conference proceedingConference contribution

567 Downloads (Pure)

Abstract

This papers examines the use of trajectory distance measures and clustering techniques to define normal and abnormal trajectories in the context of pedestrian tracking in public spaces. In order to detect abnormal trajectories, what is meant by a normal trajectory in a given scene is firstly defined. Then every trajectory that deviates from this normality is classified as abnormal. By combining Dynamic Time Warping and a modified K-Means algorithms for arbitrary-length data series, we have developed an algorithm for trajectory clustering and abnormality detection. The final system performs with an overall accuracy of 83% and 75% when tested in two different standard datasets. 
Original languageEnglish
Title of host publicationIrish Machine Vision & Image Processing Conference Proceedings 2016
EditorsN. Devaney
PublisherIrish Pattern Recognition & Classification Society
Pages17-24
Number of pages8
ISBN (Print)978-0-9934207-1-9
Publication statusPublished - 26 Aug 2016
EventIrish Machine Vision and Image Processing Conference - NUIG , Galway, United Kingdom
Duration: 24 Aug 201626 Aug 2016
Conference number: 5th
http://optics.nuigalway.ie/IMVIP2016/

Conference

ConferenceIrish Machine Vision and Image Processing Conference
Abbreviated titleIMVIP
CountryUnited Kingdom
CityGalway
Period24/08/201626/08/2016
Internet address

Fingerprint Dive into the research topics of 'Abnormal Pedestrian Trajectory analysis based on arbitrary-length clustering'. Together they form a unique fingerprint.

  • Cite this

    Murdock, D., & Martinez del Rincon, J. (2016). Abnormal Pedestrian Trajectory analysis based on arbitrary-length clustering. In N. Devaney (Ed.), Irish Machine Vision & Image Processing Conference Proceedings 2016 (pp. 17-24). Irish Pattern Recognition & Classification Society. https://aran.library.nuigalway.ie/handle/10379/6136