BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Automated as-built modelling using machine learning  - Ioannis Ana
 gnostopoulos - PhD Student
DTSTART:20150227T150000Z
DTEND:20150227T153000Z
UID:TALK57373@talks.cam.ac.uk
CONTACT:Lorna Everett
DESCRIPTION:Building Information Models are currently used by 36% of Europ
 ean contractors\, with approximately 42% of them using BIMs for as-built m
 odelling. Three-dimensional representation of the as-is conditions of a bu
 ilding can be achieved by laser scanning the facility. Laser scanning give
 s an accurate 3D representation through point clouds. However\, point clou
 ds are raw spatial information that contain no structured building knowled
 ge.  Consequently\, converting them into 3D models requires manipulation b
 y experienced personnel\, which can be tedious and time-consuming. Therefo
 re\, an accurate automated procedure is needed which will decrease modelli
 ng time and costs. The state of practice along with the current research e
 fforts will be presented.
LOCATION:Cambridge University Engineering Department\, LR5
END:VEVENT
END:VCALENDAR