BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-2022//speaker//NRESQB
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-2022-NWCQRX@talks.staging.osgeo.org
DTSTART;TZID=CET:20220824T164500
DTEND;TZID=CET:20220824T171500
DESCRIPTION:Assigning semantic labels to points within a point cloud aids i
 n both visual interpretation of the data and as a preprocessing step to ot
 her forms of analysis like building footprint extraction\, hydrological mo
 deling\, and biomass estimation. Our talk will focus primarily on earth ob
 servation data and airborne lidar data sources in particular\, where label
 s are commonly aligned with those classes specified in the ASPRS LAS speci
 fication (e.g.\, ground\, vegetation\, and building)\, but we are also beg
 inning to explore the extension of these same methods to data generated by
  commodity\, consumer-grade devices like iPhones. For many years\, hand-tu
 ned models have been developed for this segmentation task\, building on re
 asonable assumptions about the data. For example\, ground points should in
 clude those lowest elevation returns within a local window or building seg
 ments should typically be planar. Within the past decade\, we have seen a 
 surge in AI/ML powered models that are able in many cases of outperforming
  the prior methods\, being able to learn novel features and adapt to the i
 ntrinsic variability of data. We will provide an overview of the open sour
 ce ecosystem powering this trend\, from benchmark datasets like US3D and D
 ALES to machine learning frameworks (i.e.\, PyTorch and Tensorflow) and ke
 y libraries such as PDAL\, Open3D\, and PyG.
DTSTAMP:20260403T232645Z
LOCATION:Auditorium
SUMMARY:Open Source Point Cloud Semantic Segmentation Using AI/ML - Brad Ch
 ambers
URL:https://talks.staging.osgeo.org/foss4g-2022/talk/NWCQRX/
END:VEVENT
END:VCALENDAR