loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Jinsong Liu ; Ivan Nikolov ; Mark P. Philipsen and Thomas B. Moeslund

Affiliation: Visual Analysis and Perception Laboratory, CREATE, Aalborg University, 9000 Aalborg, Denmark

Keyword(s): Surveillance, Anomaly Detection, Autoencoder, Long-term, Weighted Reconstruction Error, Background Estimation.

Abstract: In surveillance systems, detecting anomalous events like emergencies or potentially dangerous incidents by manual labor is an expensive task. To improve this, anomaly detection automatically by computer vision relying on the reconstruction error of an autoencoder (AE) is extensively studied. However, these detection methods are often studied in benchmark datasets with relatively short time duration — a few minutes or hours. This is different from long-term applications where time-induced environmental changes impose an additional influence on the reconstruction error. To reduce this effect, we propose a weighted reconstruction error for anomaly detection in long-term conditions, which separates the foreground from the background and gives them different weights in calculating the error, so that extra attention is paid on human-related regions. Compared with the conventional reconstruction error where each pixel contributes the same, the proposed method increases the anomaly detection rate by more than twice with three kinds of AEs (a variational AE, a memory-guided AE, and a classical AE) running on long-term (three months) thermal datasets, proving the effectiveness of the method. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.145.168.203

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Liu, J.; Nikolov, I.; Philipsen, M. and Moeslund, T. (2022). Detecting Anomalies Reliably in Long-term Surveillance Systems. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5; ISSN 2184-4321, SciTePress, pages 999-1009. DOI: 10.5220/0010907000003124

@conference{visapp22,
author={Jinsong Liu. and Ivan Nikolov. and Mark P. Philipsen. and Thomas B. Moeslund.},
title={Detecting Anomalies Reliably in Long-term Surveillance Systems},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={999-1009},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010907000003124},
isbn={978-989-758-555-5},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Detecting Anomalies Reliably in Long-term Surveillance Systems
SN - 978-989-758-555-5
IS - 2184-4321
AU - Liu, J.
AU - Nikolov, I.
AU - Philipsen, M.
AU - Moeslund, T.
PY - 2022
SP - 999
EP - 1009
DO - 10.5220/0010907000003124
PB - SciTePress