C
Claudio Piciarelli
Researcher at University of Udine
Publications - 79
Citations - 2091
Claudio Piciarelli is an academic researcher from University of Udine. The author has contributed to research in topics: Anomaly detection & Object detection. The author has an hindex of 21, co-authored 72 publications receiving 1680 citations.
Papers
More filters
Journal ArticleDOI
Trajectory-Based Anomalous Event Detection
TL;DR: The proposed work addresses anomaly detection by means of trajectory analysis, an approach with several application fields, most notably video surveillance and traffic monitoring, based on single-class support vector machine (SVM) clustering, where the novelty detection SVM capabilities are used for the identification of anomalous trajectories.
Journal ArticleDOI
On-line trajectory clustering for anomalous events detection
TL;DR: A trajectory clustering algorithm suited for video surveillance systems that clusters are organized in a tree-like structure that can be used to perform behaviour analysis, since it allows the identification of anomalous events.
Proceedings ArticleDOI
Trajectory clustering and its applications for video surveillance
TL;DR: A trajectory clustering method suited for video surveillance and monitoring systems that is dynamic and built in real-time as the trajectory data is acquired, without the need of an off-line processing step.
Proceedings ArticleDOI
VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization
TL;DR: In this article, a transformer-based image anomaly detection and localization network is proposed, which combines a reconstruction-based approach and patch embedding to preserve the spatial information of the embedded patches, which is later processed by a Gaussian mixture density network to localize the anomalous areas.
Journal ArticleDOI
Dynamic Reconfiguration in Camera Networks: A Short Survey
TL;DR: This paper proposes a reference framework for network reconfiguration and presents a short survey of some of the most relevant state-of-the-art works in this field, showing how they can be reformulated in this framework.