Browse by author
Lookup NU author(s): Dr Federico Angelini,
Dr Mohsen Naqvi
This is the authors' accepted manuscript of an article that has been published in its final definitive form by The Institution of Engineering and Technology, 2022.
For re-use rights please refer to the publisher's terms and conditions.
Human activity anomaly detection plays a crucial role in the next generation of surveillance and assisted living systems. Most anomaly detection algorithms are generative models and learn features from raw images. This work shows that popular state-of-the-art autoencoder-based anomaly detection systems are not capable of effectively detecting human posture and object-positions related anomalies. Therefore, a human pose-driven and object detector based deep learning architecture is proposed, which simultaneously leverages human poses and raw RGB data to perform human activity anomaly detection. We demonstrate that pose-driven learning overcomes the raw RGB based counterpart limitations in different human activities classification. Extensive validation is provided by using popular datasets. Then, we demonstrate that with the aid of object detection, the human activities classification can be effectively used in human activity anomaly detection. Moreover, novel challenging datasets, i.e. BMbD, M-BMbD and JBMOPbD, are proposed for single and multi-target human posture anomaly detection and joint human posture and object position anomaly detection evaluations.
Author(s): Yang Y, Angelini F, Naqvi SM
Publication type: Article
Publication status: Published
Journal: IET Image Processing
Pages: epub ahead of print
Online publication date: 22/10/2022
Acceptance date: 12/10/2022
Date deposited: 12/10/2022
ISSN (print): 1751-9659
ISSN (electronic): 1751-9667
Publisher: The Institution of Engineering and Technology
ePrints DOI: 10.57711/d611-fk15
Altmetrics provided by Altmetric