Crowd surveillance plays a key role to ensure safety and security in public areas. Surveillance systems traditionally rely on fixed camera networks, which suffer from limitations, as coverage of the monitored area, video resolution and analytic performance. On the other hand, a smart camera network provides the ability to reconfigure the sensing infrastructure by incorporating active devices such as pan-tilt-zoom (PTZ) cameras and UAV-based cameras, thus enabling the network to adapt over time to changes in the scene. We propose a new decentralised approach for network reconfiguration, where each camera dynamically adapts its parameters and position to optimise scene coverage. Two policies for decentralised camera reconfiguration are presented: a greedy approach and a reinforcement learning approach. In both cases, cameras are able to locally control the state of their neighbourhood and dynamically adjust their position and PTZ parameters. When crowds are present, the network balances between global coverage of the entire scene and high resolution for the crowded areas. We evaluate our approach in a simulated environment monitored with fixed, PTZ and UAV-based cameras.
Dynamic camera reconfiguration with reinforcement learning and stochastic methods for crowd surveillance / Bisagno, N.; Xamin, A.; De Natale, F.; Conci, N.; Rinner, B.. - In: SENSORS. - ISSN 1424-8220. - 20:17(2020), pp. 1-15. [10.3390/s20174691]
Dynamic camera reconfiguration with reinforcement learning and stochastic methods for crowd surveillance
Bisagno N.;De Natale F.;Conci N.;
2020-01-01
Abstract
Crowd surveillance plays a key role to ensure safety and security in public areas. Surveillance systems traditionally rely on fixed camera networks, which suffer from limitations, as coverage of the monitored area, video resolution and analytic performance. On the other hand, a smart camera network provides the ability to reconfigure the sensing infrastructure by incorporating active devices such as pan-tilt-zoom (PTZ) cameras and UAV-based cameras, thus enabling the network to adapt over time to changes in the scene. We propose a new decentralised approach for network reconfiguration, where each camera dynamically adapts its parameters and position to optimise scene coverage. Two policies for decentralised camera reconfiguration are presented: a greedy approach and a reinforcement learning approach. In both cases, cameras are able to locally control the state of their neighbourhood and dynamically adjust their position and PTZ parameters. When crowds are present, the network balances between global coverage of the entire scene and high resolution for the crowded areas. We evaluate our approach in a simulated environment monitored with fixed, PTZ and UAV-based cameras.File | Dimensione | Formato | |
---|---|---|---|
Journal_Dynamic_Cameras_Reconfig.pdf
accesso aperto
Tipologia:
Pre-print non referato (Non-refereed preprint)
Licenza:
Creative commons
Dimensione
8.56 MB
Formato
Adobe PDF
|
8.56 MB | Adobe PDF | Visualizza/Apri |
sensors-20-04691.pdf
accesso aperto
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Creative commons
Dimensione
8.48 MB
Formato
Adobe PDF
|
8.48 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione