BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20220327T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260424T192953Z
UID:62a1b2b4b5113891884701@ist.ac.at
DTSTART:20220620T110000
DTEND:20220620T120000
DESCRIPTION:Speaker: Cornelia Fermüller\nhosted by Christoph Lampert\nAbst
 ract: Visual motion interpretation is the core of many real-world AI appli
 cations\, including self-driving cars\, robotics\, augmented reality\, and
  human motion analysis. Classical computational approaches are based on co
 mputing correspondence\, i.e.\, matching image points\, in consecutive ima
 ge frames which are then used to reconstruct scene models. However\, in bi
 ology\, we find systems with low computational power that do not compute c
 orrespondence but are very efficient in using visual motion. Their princip
 les have not been translated to our computational approaches yet. I have e
 xplored the cue of visual motion from three different angles. First\, neur
 omorphic event-based sensors which do not record image frames but temporal
  information about scene changes provide us with data in the form of point
  clouds in space time that approximate continuous motion. Exploiting the a
 dvantages of this data\, we developed scene segmentation algorithms that f
 unction in the most challenging scenarios. Second\, by changing the sequen
 ce of computations\, and estimating 3D motion from robust filter output\, 
 we have developed optimization and machine learning algorithms that are ro
 bust and generalize better to new scenarios. Third\, I show experiments on
  visual illusions that give an indication of the motion computations in th
 e early visual processes in nature and point to directions for improving c
 urrent motion computations.
LOCATION:Mondi Seminar Room 3\, Central Building\, ISTA
ORGANIZER:kharppre@ist.ac.at
SUMMARY:Cornelia Fermüller: Neuromorphic Visual Motion Analysis
URL:https://talks-calendar.ista.ac.at/events/3823
END:VEVENT
END:VCALENDAR