BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Capture of dynamic scene using multiple cameras provides rich spat
 ial-temporal information that can be used for solving challenging computer
  vision problems. - Tali Basha\, Tel-Aviv University
DTSTART:20120907T130000Z
DTEND:20120907T140000Z
UID:TALK39286@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Indeed\, multi-view systems have been used by various computer
 -vision methods in the last decade\, where the setting of cameras depends 
 on the application. In this talk\, I will discuss the use of multi-view sy
 stems in two “distant” setups: First\, I will present the use ofcalibr
 ated and synchronized camera-array for solving the problem of dense 3D str
 ucture and 3D motion estimation. Then\, I will consider the scenario of a 
 group of people capturing asynchronously a dynamic scene\, using probably 
 the most popular means of photographing today – cellphones. The combined
  data obtained this way can be regarded as the output of a new type of ext
 ended camera\, which we call a crowd-based camera (or CrowdCam).  Using th
 is new setup introduced us with a novel problem of photo-sequencing -- tem
 porally ordering a set of still images taken by a CrowdCam\, and a geometr
 y-based solution\, as I will present. We believe that photo sequencing is 
 an essential step for analysis of a dynamic scene form a set of still imag
 es.
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR