Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zaheer, Muhammad Zaigham, Mahmood, Arif, Astrid, Marcella, Lee, Seung-Ik
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912086413541376
author Zaheer, Muhammad Zaigham
Mahmood, Arif
Astrid, Marcella
Lee, Seung-Ik
author_facet Zaheer, Muhammad Zaigham
Mahmood, Arif
Astrid, Marcella
Lee, Seung-Ik
contents Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous events in the training data. We propose a weakly supervised anomaly detection system which has multiple contributions including a random batch selection mechanism to reduce inter-batch correlation and a normalcy suppression block which learns to minimize anomaly scores over normal regions of a video by utilizing the overall information available in a training batch. In addition, a clustering loss block is proposed to mitigate the label noise and to improve the representation learning for the anomalous and normal regions. This block encourages the backbone network to produce two distinct feature clusters representing normal and anomalous events. Extensive analysis of the proposed approach is provided using three popular anomaly detection datasets including UCF-Crime, ShanghaiTech, and UCSD Ped2. The experiments demonstrate a superior anomaly detection capability of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2203_13704
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos
Zaheer, Muhammad Zaigham
Mahmood, Arif
Astrid, Marcella
Lee, Seung-Ik
Computer Vision and Pattern Recognition
Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous events in the training data. We propose a weakly supervised anomaly detection system which has multiple contributions including a random batch selection mechanism to reduce inter-batch correlation and a normalcy suppression block which learns to minimize anomaly scores over normal regions of a video by utilizing the overall information available in a training batch. In addition, a clustering loss block is proposed to mitigate the label noise and to improve the representation learning for the anomalous and normal regions. This block encourages the backbone network to produce two distinct feature clusters representing normal and anomalous events. Extensive analysis of the proposed approach is provided using three popular anomaly detection datasets including UCF-Crime, ShanghaiTech, and UCSD Ped2. The experiments demonstrate a superior anomaly detection capability of our approach.
title Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2203.13704