An Attribute-based Method for Video Anomaly Detection

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Reiss, Tal, Hoshen, Yedid
Format: Preprint
Publié: 2022
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912203981979648
author Reiss, Tal
Hoshen, Yedid
author_facet Reiss, Tal
Hoshen, Yedid
contents Video anomaly detection (VAD) identifies suspicious events in videos, which is critical for crime prevention and homeland security. In this paper, we propose a simple but highly effective VAD method that relies on attribute-based representations. The base version of our method represents every object by its velocity and pose, and computes anomaly scores by density estimation. Surprisingly, this simple representation is sufficient to achieve state-of-the-art performance in ShanghaiTech, the most commonly used VAD dataset. Combining our attribute-based representations with an off-the-shelf, pretrained deep representation yields state-of-the-art performance with a $99.1\%, 93.7\%$, and $85.9\%$ AUROC on Ped2, Avenue, and ShanghaiTech, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2212_00789
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle An Attribute-based Method for Video Anomaly Detection
Reiss, Tal
Hoshen, Yedid
Computer Vision and Pattern Recognition
Machine Learning
Video anomaly detection (VAD) identifies suspicious events in videos, which is critical for crime prevention and homeland security. In this paper, we propose a simple but highly effective VAD method that relies on attribute-based representations. The base version of our method represents every object by its velocity and pose, and computes anomaly scores by density estimation. Surprisingly, this simple representation is sufficient to achieve state-of-the-art performance in ShanghaiTech, the most commonly used VAD dataset. Combining our attribute-based representations with an off-the-shelf, pretrained deep representation yields state-of-the-art performance with a $99.1\%, 93.7\%$, and $85.9\%$ AUROC on Ped2, Avenue, and ShanghaiTech, respectively.
title An Attribute-based Method for Video Anomaly Detection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2212.00789