BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.geoinfo-lab.org//foss4g-asia-2024//CZCYUY
BEGIN:VTIMEZONE
TZID:+07
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:+07
TZOFFSETFROM:+0700
TZOFFSETTO:+0700
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-asia-2024-NFCUBG@talks.geoinfo-lab.org
DTSTART;TZID=+07:20241216T151500
DTEND;TZID=+07:20241216T153000
DESCRIPTION:In recent years\, the availability of geospatial data has signi
 ficantly increased\, with aerial photographs and Digital Elevation Models 
 (DEMs) becoming widely accessible as open data. Additionally\, the acquisi
 tion of high-resolution image data through drones has become more feasible
  and commonplace. However\, extracting meaningful information from these v
 ast datasets remains a labor-intensive process\, often requiring significa
 nt time and resources.\n\nWhile various deep learning techniques have been
  employed to address this challenge\, they typically demand extensive effo
 rt in collecting and preparing training data. In light of these constraint
 s\, the Segment Anything Model (SAM) has emerged as a promising solution. 
 SAM\, a recent development in the field of fundamental models\, offers the
  advantage of zero-shot classification without the need for specific train
 ing. Moreover\, its Apache-2.0 license ensures accessibility for a wide ra
 nge of applications.\n\nThis presentation aims to demonstrate the potentia
 l of SAM in the realm of geospatial information processing. We will showca
 se practical applications of SAM in analyzing geospatial data\, with a foc
 us on two critical areas: landslide detection and forest canopy mapping. T
 hese case studies will illustrate how SAM can efficiently process and extr
 act valuable insights from complex geospatial datasets\, potentially enhan
 cing the efficiency and effectiveness of our approach to environmental mon
 itoring and disaster risk assessment.
DTSTAMP:20260416T212051Z
LOCATION:Auditorium Hall 2
SUMMARY:Exploring Segment Anything Model's Potential in Geospatial Data: Ca
 se Studies for Landslide and Forest Canopy Detection - Nobusuke Iwasaki\, 
 Ayaka Onohara
URL:https://talks.geoinfo-lab.org/foss4g-asia-2024/talk/NFCUBG/
END:VEVENT
END:VCALENDAR