Home > Research > Publications & Outputs > A Real-time Approach for Novelty Detection and ...

Research

Associated organisational units

Links

Text available via DOI:

Keywords

View graph of relations

A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems. / Sadeghi-Tehran, Pouria; Angelov, Plamen.
Evolving and Adaptive Intelligent Systems (EAIS), 2012 IEEE Conference on . IEEE, 2012. p. 108-113.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Sadeghi-Tehran, P & Angelov, P 2012, A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems. in Evolving and Adaptive Intelligent Systems (EAIS), 2012 IEEE Conference on . IEEE, pp. 108-113. https://doi.org/10.1109/EAIS.2012.6232814

APA

Sadeghi-Tehran, P., & Angelov, P. (2012). A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems. In Evolving and Adaptive Intelligent Systems (EAIS), 2012 IEEE Conference on (pp. 108-113). IEEE. https://doi.org/10.1109/EAIS.2012.6232814

Vancouver

Sadeghi-Tehran P, Angelov P. A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems. In Evolving and Adaptive Intelligent Systems (EAIS), 2012 IEEE Conference on . IEEE. 2012. p. 108-113 doi: 10.1109/EAIS.2012.6232814

Author

Sadeghi-Tehran, Pouria ; Angelov, Plamen. / A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems. Evolving and Adaptive Intelligent Systems (EAIS), 2012 IEEE Conference on . IEEE, 2012. pp. 108-113

Bibtex

@inproceedings{04e88dfacf664341b661ee36640630a9,
title = "A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems",
abstract = "In this paper, we present a novel approach for automatic object detection and also using on-line trajectory clustering for RT anomaly detection in video streams. The proposed approach is based on two main steps. In the first step, a recently introduced approach called Recursive Density Estimation (RDE) is used for novelty detection. This method is using a Cauchy type of kernel which works on a frame-by-frame basis and does not require a pre-defined threshold to identify objects. In the second step, multifeature object trajectory is clustered on-line to identify anomalies in video streams. To identify an anomaly, first the trajectories are transformed into a set of features in a space to which eClustering approach identifies the modes and the corresponding clusters. At the end, by using cluster fusion the final common pattern is estimated and any sparse trajectories are considered as anomalous. ",
keywords = "trajectory analysis, behaviour analysis, video analytics",
author = "Pouria Sadeghi-Tehran and Plamen Angelov",
year = "2012",
doi = "10.1109/EAIS.2012.6232814",
language = "English",
isbn = "978-1-4673-1728-3",
pages = "108--113",
booktitle = "Evolving and Adaptive Intelligent Systems (EAIS), 2012 IEEE Conference on",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems

AU - Sadeghi-Tehran, Pouria

AU - Angelov, Plamen

PY - 2012

Y1 - 2012

N2 - In this paper, we present a novel approach for automatic object detection and also using on-line trajectory clustering for RT anomaly detection in video streams. The proposed approach is based on two main steps. In the first step, a recently introduced approach called Recursive Density Estimation (RDE) is used for novelty detection. This method is using a Cauchy type of kernel which works on a frame-by-frame basis and does not require a pre-defined threshold to identify objects. In the second step, multifeature object trajectory is clustered on-line to identify anomalies in video streams. To identify an anomaly, first the trajectories are transformed into a set of features in a space to which eClustering approach identifies the modes and the corresponding clusters. At the end, by using cluster fusion the final common pattern is estimated and any sparse trajectories are considered as anomalous.

AB - In this paper, we present a novel approach for automatic object detection and also using on-line trajectory clustering for RT anomaly detection in video streams. The proposed approach is based on two main steps. In the first step, a recently introduced approach called Recursive Density Estimation (RDE) is used for novelty detection. This method is using a Cauchy type of kernel which works on a frame-by-frame basis and does not require a pre-defined threshold to identify objects. In the second step, multifeature object trajectory is clustered on-line to identify anomalies in video streams. To identify an anomaly, first the trajectories are transformed into a set of features in a space to which eClustering approach identifies the modes and the corresponding clusters. At the end, by using cluster fusion the final common pattern is estimated and any sparse trajectories are considered as anomalous.

KW - trajectory analysis

KW - behaviour analysis

KW - video analytics

U2 - 10.1109/EAIS.2012.6232814

DO - 10.1109/EAIS.2012.6232814

M3 - Conference contribution/Paper

SN - 978-1-4673-1728-3

SP - 108

EP - 113

BT - Evolving and Adaptive Intelligent Systems (EAIS), 2012 IEEE Conference on

PB - IEEE

ER -