Detail publikace

Methods for Trajectory Outlier Detection in Surveillance Video

PEŠEK, M.

Originální název

Methods for Trajectory Outlier Detection in Surveillance Video

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

Outlier detection in trajectory data extracted from surveillance video is a useful data analysis task, which can reveal anomalous or suspicious behaviour of moving objects. This paper deals with the description, evaluation and comparision of two methods for the trajectory outlier detection. Firstly, TOP-EYE algorithm, which gradually computes and accumulates outlying score of a trajectory. Secondly, a model-based method which uses the Gaussian mixture model (GMM) and identifies trajectories not following the learned model as outliers.

Klíčová slova

data mining, outlier detection, moving objects data, trajectory, surveillance video, TOP-EYE, GMM

Autoři

PEŠEK, M.

Vydáno

26. 4. 2012

Nakladatel

Brno University of Technology

Místo

Brno

ISBN

978-80-214-4462-1

Kniha

Proceedings of the 18th Conference STUDENT EEICT 2012

Edice

Volume 3

Strany od

474

Strany do

478

Strany počet

5

URL

http://www.feec.vutbr.cz/EEICT/2012/sbornik/03doktorskeprojekty/11inteligentnisystemy/03-xpesek07.pdf

BibTex

@inproceedings{BUT192806,
  author="Martin {Pešek}",
  title="Methods for Trajectory Outlier Detection in Surveillance Video",
  booktitle="Proceedings of the 18th Conference STUDENT EEICT 2012",
  year="2012",
  series="Volume 3",
  pages="474--478",
  publisher="Brno University of Technology",
  address="Brno",
  isbn="978-80-214-4462-1",
  url="http://www.feec.vutbr.cz/EEICT/2012/sbornik/03doktorskeprojekty/11inteligentnisystemy/03-xpesek07.pdf"
}