BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:CET
BEGIN:DAYLIGHT
DTSTART:20180325T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20171029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190214T194500Z
UID:BA66FCE5-8CBA-4C86-97C7-C3BA6A471E41
DTSTART;TZID=CET:20180103T120000
DTEND;TZID=CET:20180103T131500
DESCRIPTION:This presentation shows a pedestrian detection system with enha
 nced object segmentation procedure working on a far infrared (FIR) video. 
 To make the object detection more accurate on the FIR images\, we propose 
 an enhanced segmentation procedure with two thresholds and the region enla
 rgement. This combination allowed a significant reduction of the region of
  interests (ROIs) for further processing. Experiments performed on demandi
 ng public dataset show a significant increase of the pedestrian detection 
 performance (up to 33 frames per second) with the accuracy comparable with
  state-of-the-art algorithms.\n\nSpeaker(s): Karol Piniarski\, \n\nRoom: 2
 30\, Bldg: Centre of Mechatronics\, Biomechanics and Nanoengineering\, Poz
 nan University of Technology\, Poznan\, Wielkopolskie\, Poland
LOCATION:Room: 230\, Bldg: Centre of Mechatronics\, Biomechanics and Nanoen
 gineering\, Poznan University of Technology\, Poznan\, Wielkopolskie\, Pol
 and
ORGANIZER:tomasz.marciniak@put.poznan.pl
SEQUENCE:0
SUMMARY:Effective pedestrian classification in the thermovision image
URL;VALUE=URI:https://events.vtools.ieee.org/m/192627
X-ALT-DESC:Description: <br /><p>This presentation shows a pedestrian detec
 tion system with enhanced object segmentation procedure working on a far i
 nfrared (FIR) video. To make the object detection more accurate on the FIR
  images\, we propose an enhanced segmentation procedure with two threshold
 s and the region enlargement. This combination allowed a significant reduc
 tion of the region of interests (ROIs) for further processing. Experiments
  performed on demanding public dataset show a significant increase of the 
 pedestrian detection performance (up to 33 frames per second) with the acc
 uracy comparable with state-of-the-art algorithms.</p>
END:VEVENT
END:VCALENDAR