BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Warsaw
BEGIN:DAYLIGHT
DTSTART:20170326T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20161030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20170126T194835Z
UID:F35F92B7-E5B6-11E7-833E-0050568D7F66
DTSTART;TZID=Europe/Warsaw:20161123T120000
DTEND;TZID=Europe/Warsaw:20161123T130000
DESCRIPTION:An analysis of object classification during the process of dete
 ction of pedestrians in night vision infrared images was presented. The cl
 assical solution with one classifier was tested and some methods for incre
 asing the performance are proposed. A modified multi-branch classifier is 
 presented to increase performance of the pedestrian detection system. The 
 solution is accurate\, fast\, and especially good suited for all real-time
  applications where pedestrians may appear in many distances to the camera
 . The obtained results show an increased efficiency of the classification 
 process (by up to 3%) with similar processing time in comparison to a sing
 le classifier. All tests were conducted using the Adaboost classifier\, bu
 t generally\, the results should be consistent also for other types of cla
 ssifiers.\n\nPoznan\, Wielkopolskie\, Poland
LOCATION:Poznan\, Wielkopolskie\, Poland
ORGANIZER:adam.dabrowski@put.poznan.pl
SEQUENCE:0
SUMMARY:[Legacy Report] Performance of object classification for detection 
 of pedestrians
URL;VALUE=URI:https://events.vtools.ieee.org/m/143653
X-ALT-DESC:Description: <br /><p>An analysis of object classification durin
 g the process of detection of pedestrians in night vision infrared images 
 was presented. The classical solution with one classifier was tested and s
 ome methods for increasing the performance are proposed. A modified multi-
 branch classifier is presented to increase performance of the pedestrian d
 etection system. The solution is accurate\, fast\, and especially good sui
 ted for all real-time applications where pedestrians may appear in many di
 stances to the camera. The obtained results show an increased efficiency o
 f the classification process (by up to 3%) with similar processing time in
  comparison to a single classifier. All tests were conducted using the Ada
 boost classifier\, but generally\, the results should be consistent also f
 or other types of classifiers.</p>
END:VEVENT
END:VCALENDAR