BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.osgeo.org//foss4g-asia-2023//speaker//KFNZKQ
BEGIN:VTIMEZONE
TZID:KST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:KST
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-asia-2023-9HDAEL@talks.osgeo.org
DTSTART;TZID=KST:20231129T164000
DTEND;TZID=KST:20231129T165000
DESCRIPTION:In the majority of cases\, I find that deep learning of point c
 loud data\, e.g.\, in the case of classification\, learning with datasets 
 available on the Internet is not accurate enough when trying to solve our 
 specific practical problems. We are then forced to manually label the poin
 t cloud\, which can be time consuming and difficult to achieve accuracy in
  detail when processing on a 2D display\, as point cloud data is generally
  not highly visible.\nTherefore\, I am trying to speed up the labeling of 
 point clouds using VR. I would like to share my idea with you this time.
DTSTAMP:20260818T233917Z
LOCATION:Seoul Archive
SUMMARY:Accelerate labeling of original point cloud data for deep learning 
 in VR with Unreal Engine. - TAISEI NAKAMURA
URL:https://talks.osgeo.org/foss4g-asia-2023/talk/9HDAEL/
END:VEVENT
END:VCALENDAR