BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20171029T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20170326T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RDATE:20180325T020000
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.12436.field_data.0@www.open.diag.uniroma1.it
DTSTAMP:20260407T230910Z
CREATED:20170831T104317Z
DESCRIPTION: Depth cameras are becoming key tools for computer vision tasks
  ranging from hand\, body or object tracking\, 3D reconstruction and simul
 taneous localization and mapping. Almost all these tasks need to solve a *
 tracking* problem i.e. each new frame of depth and image data is correlate
 d to the previous\, and this temporal information allows for faithful pose
  and/or geometry reconstruction over time. However\, this reliance on temp
 oral information\, makes tracking problems hard to solve when using sensor
 s running at 30fps\, due to susceptibility to high frame-to-frame scene mo
 tions and artifacts such as motion blur. Using high speed depth cameras wo
 uld greatly simplify these problems and make them more tractable\, but des
 pite significant research efforts\, no existing high framerate and high qu
 ality depth algorithm\, and hence camera exists.In this talk I am going to
  demonstrate a 3D capture system for high speed and high quality depth est
 imation\, and show its advantages in a variety of computer vision tasks. O
 ur hardware and software depth pipeline can run at 1.1msec with modern GPU
 s and readily procurable camera and illumination components. Short BioSean
  Ryan Fanello has received his Bachelor and Master degrees from Sapienza w
 here he worked on 3D Reconstruction and Gesture Recognition. He received h
 is PhD in Robotics from Italian Institute of Technology where he designed 
 and implemented the iCub perception system. In particular\, he worked on a
 lgorithms for 3D estimation\, hand-eye calibration\, egomotion estimation\
 , action recognition and object recognition. After his PhD\, he spent 3 ye
 ars at Microsoft Research. His research is mainly focusing on the intersec
 tion among Machine Learning\, Computer Vision and Natural User Interfaces.
  At Microsoft he has developed new technologies for 3D estimation that hav
 e been deployed on the Microsoft Hololens headset. He was one of the leadi
 ng members of important projects like Holoportation where they showed the 
 first 3D telepresence system with HD quality. Holoportation\, enables real
 -time ''teleportation'' of people from anywhere in the world allowing them
  to communicate fully in 3D. Recently he is a founding team member of perc
 eptiveIO. At perceptiveIO he is developing novel 3D sensing capabilities\,
  natural user interfaces and computer vision applications.  
DTSTART;TZID=Europe/Paris:20170912T110000
DTEND;TZID=Europe/Paris:20170912T110000
LAST-MODIFIED:20191008T082902Z
LOCATION:Aula Magna
SUMMARY:Low Compute and Fully Parallel Computer Vision with HashMatch  - Se
 an Ryan Fanello
URL;TYPE=URI:http://www.open.diag.uniroma1.it/node/12436
END:VEVENT
END:VCALENDAR