How to automatically monitor wide critical open areas is a challenge to be addressed. Recent computer vision algorithms can be exploited to avoid the deployment of a large amount of expensive sensors. In this work, we propose our object tracking system which, combined with our recently developed anomaly detection system. can provide intelligence and protection for critical areas. In this work. we report two case studies: an international pier and a city parking lot. We acquire sequences to evaluate the effectiveness of the approach in challenging conditions. We report quantitative results for object counting, detection, parking analysis, and anomaly detection. Moreover, we report state-of-the-art results for statistical anomaly detection on a public dataset.
Deep Learning Based Surveillance System for Open Critical Areas / Francesco Turchini, Lorenzo Seidenari,Tiberio Uricchio, Alberto Del Bimbo. - In: INVENTIONS. - ISSN 2411-5134. - ELETTRONICO. - 3:(2018), pp. 1-13. [10.3390/inventions3040069]
Deep Learning Based Surveillance System for Open Critical Areas
Francesco Turchini;Lorenzo Seidenari
;Tiberio Uricchio;Alberto Del Bimbo
2018
Abstract
How to automatically monitor wide critical open areas is a challenge to be addressed. Recent computer vision algorithms can be exploited to avoid the deployment of a large amount of expensive sensors. In this work, we propose our object tracking system which, combined with our recently developed anomaly detection system. can provide intelligence and protection for critical areas. In this work. we report two case studies: an international pier and a city parking lot. We acquire sequences to evaluate the effectiveness of the approach in challenging conditions. We report quantitative results for object counting, detection, parking analysis, and anomaly detection. Moreover, we report state-of-the-art results for statistical anomaly detection on a public dataset.File | Dimensione | Formato | |
---|---|---|---|
inventions-03-00069.pdf
accesso aperto
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Open Access
Dimensione
1.09 MB
Formato
Adobe PDF
|
1.09 MB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.