Detecting the anomaly of human behavior is paramount to timely recognizing endangering situations, such as street fights or elderly falls. However, anomaly detection is complex since anomalous events are rare and because it is an open set recognition task, i.e., what is anomalous at inference has not been observed at training. We propose COSKAD, a novel model that encodes skeletal human motion by a graph convolutional network and learns to COntract SKeletal kinematic embeddings onto a latent hypersphere of minimum volume for Video Anomaly Detection. We propose three latent spaces: the commonly-adopted Euclidean and the novel spherical and hyperbolic. All variants outperform the state-of-the-art on the most recent UBnormal dataset, for which we contribute a human-related version with annotated skeletons. COSKAD sets a new state-of-the-art on the human-related versions of ShanghaiTech Campus and CUHK Avenue, , with performance comparable to video-based methods. Source code and dataset will be released upon acceptance.

Contracting skeletal kinematics for human-related video anomaly detection / Flaborea, Alessandro; D'Amely di Melendugno, Guido Maria; D'Arrigo, Stefano; Sterpa, Marco Aurelio; Sampieri, Alessio; Galasso, Fabio. - (2024). [10.1016/j.patcog.2024.110817].

Contracting skeletal kinematics for human-related video anomaly detection

Flaborea, Alessandro
;
D'Amely di Melendugno, Guido Maria;D'Arrigo, Stefano;Sterpa, Marco Aurelio;Sampieri, Alessio;Galasso, Fabio
2024

Abstract

Detecting the anomaly of human behavior is paramount to timely recognizing endangering situations, such as street fights or elderly falls. However, anomaly detection is complex since anomalous events are rare and because it is an open set recognition task, i.e., what is anomalous at inference has not been observed at training. We propose COSKAD, a novel model that encodes skeletal human motion by a graph convolutional network and learns to COntract SKeletal kinematic embeddings onto a latent hypersphere of minimum volume for Video Anomaly Detection. We propose three latent spaces: the commonly-adopted Euclidean and the novel spherical and hyperbolic. All variants outperform the state-of-the-art on the most recent UBnormal dataset, for which we contribute a human-related version with annotated skeletons. COSKAD sets a new state-of-the-art on the human-related versions of ShanghaiTech Campus and CUHK Avenue, , with performance comparable to video-based methods. Source code and dataset will be released upon acceptance.
2024
Pattern Recognition Letters
Anomaly detection; Open set recognition; Hyperbolic geometry; Kinematic skeleton; Graph convolutional networks
02 Pubblicazione su volume::02a Capitolo o Articolo
Contracting skeletal kinematics for human-related video anomaly detection / Flaborea, Alessandro; D'Amely di Melendugno, Guido Maria; D'Arrigo, Stefano; Sterpa, Marco Aurelio; Sampieri, Alessio; Galasso, Fabio. - (2024). [10.1016/j.patcog.2024.110817].
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1726559
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact