2003 | OriginalPaper | Buchkapitel
Acquiring Multi-View Video with an Active Camera System
verfasst von : Robert T. Collins, Omead Amidi, Takeo Kanade
Erschienen in: Multisensor Surveillance Systems
Verlag: Springer US
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
For applications in human identification, activity recognition, 3D reconstruction, entertainment and sports, it is often desirable to capture a set of synchronized video sequences of a person from multiple camera viewpoints (see Figure 8-1). One way to achieve this is to set up a ring of cameras all statically aimed at a single point in space, and to have an actor perform at this fixation point while the video footage is shot. This is the method used to create spectacular special effects in the movie The Matrix, where playing back frames from a single time step, across all cameras, yields the appearance of freezing the action in time while a virtual camera flies around the scene. However, in surveillance or sports applications it is not possible to predict beforehand the precise location where an interesting activity will occur, and therefore it is necessary to dynamically adjust the fixation point of multiple camera views. We have developed a system that tracks a person in real-time and adjusts the pan, tilt, zoom and focus of each camera to acquire synchronized multi-view video of a person moving through the scene.