Visible to the public Dynamic Camera Network Reconfiguration for Crowd Surveillance

TitleDynamic Camera Network Reconfiguration for Crowd Surveillance
Publication TypeConference Paper
Year of Publication2018
AuthorsBisagno, Niccoló, Conci, Nicola, Rinner, Bernhard
Conference NameProceedings of the 12th International Conference on Distributed Smart Cameras
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-6511-6
Keywordscamera control, crowd surveillance, Human Behavior, Metrics, PTZ, pubcrawl, Resiliency, Smart camera network, UAV, video surveillance

Crowd surveillance will play a fundamental role in the coming generation of video surveillance systems, in particular for improving public safety and security. However, traditional camera networks are mostly not able to closely survey the entire monitoring area due to limitations in coverage, resolution and analytics performance. A smart camera network, on the other hand, offers the ability to reconfigure the sensing infrastructure by incorporating active devices such as pan-tilt-zoom (PTZ) cameras and UAV-based cameras, which enable the adaptation of coverage and target resolution over time. This paper proposes a novel decentralized approach for dynamic network reconfiguration, where cameras locally control their PTZ parameters and position, to optimally cover the entire scene. For crowded scenes, cameras must deal with a trade-off among global coverage and target resolution to effectively perform crowd analysis. We evaluate our approach in a simulated environment surveyed with fixed, PTZ, and UAV-based cameras.

Citation KeybisagnoDynamicCameraNetwork2018