BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:US/Central
BEGIN:DAYLIGHT
DTSTART:20220313T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20221031T013450Z
UID:417ED593-ADDC-4510-9E63-6F8CB8E35306
DTSTART;TZID=US/Central:20220922T173000
DTEND;TZID=US/Central:20220922T183000
DESCRIPTION:Small Unmanned Aircraft Systems (sUAS) are expected to prolifer
 ate in low-altitude airspace and will require flight near buildings and ov
 er people. Robust urgent landing capabilities including landing site selec
 tion are critical for safety. However\, conventional fixed-wing emergency 
 landing sites such as open fields and empty roadways are rare in and aroun
 d cities. Our work uniquely considers a city's many unoccupied flat roofto
 ps as possible nearby landing sites. We propose novel methods to identify 
 flat rooftop buildings\, isolate their flat surfaces\, and find touchdown 
 points that maximize distance to obstacles. We model flat rooftop surfaces
  as polygons that capture their boundaries and obstructions. We process sa
 tellite images\, airborne LiDAR point clouds\, and map building outlines t
 o generate rooftop maps with a multi-stage machine learning pipeline. We p
 ropose a computational geometry method (Polylidar3D) that reliably extract
 s flat rooftop surfaces from archived data sources. We model risk as an in
 novative combination of landing site and path risk metrics and conduct a m
 ulti-objective Pareto front analysis for sUAS urgent landing in cities. A 
 high-fidelity simulated city is constructed in the Unreal game engine with
  a statistically-accurate representation of rooftop obstacles. Fusion of P
 olylidar3D and RGBD semantic segmentation output shows improved intersecti
 on-over-union (IOU) accuracy in landing site identification compared to us
 ing LiDAR data only.\n\n1PDH will be awarded to the attendees\n\nSpeaker(s
 ): Ella Atkins\, \n\nLincoln\, Nebraska\, United States\, 68588\, Virtual:
  https://events.vtools.ieee.org/m/310043
LOCATION:Lincoln\, Nebraska\, United States\, 68588\, Virtual: https://even
 ts.vtools.ieee.org/m/310043
ORGANIZER:mvvrmkr@gmail.com
SEQUENCE:18
SUMMARY:Environment Mapping and Urgent Landing Planning for Low-Altitude UA
 S Operations
URL;VALUE=URI:https://events.vtools.ieee.org/m/310043
X-ALT-DESC:Description: <br /><p>Small Unmanned Aircraft Systems (sUAS) are
  expected to proliferate in low-altitude airspace and will require flight 
 near buildings and over people. Robust urgent landing capabilities includi
 ng landing site selection are critical for safety. However\, conventional 
 fixed-wing emergency landing sites such as open fields and empty roadways 
 are rare in and around cities. Our work uniquely considers a city's many u
 noccupied flat rooftops as possible nearby landing sites. We propose novel
  methods to identify flat rooftop buildings\, isolate their flat surfaces\
 , and find touchdown points that maximize distance to obstacles. We model 
 flat rooftop surfaces as polygons that capture their boundaries and obstru
 ctions. We process satellite images\, airborne LiDAR point clouds\, and ma
 p building outlines to generate rooftop maps with a multi-stage machine le
 arning pipeline. We propose a computational geometry method (Polylidar3D) 
 that reliably extracts flat rooftop surfaces from archived data sources. W
 e model risk as an innovative combination of landing site and path risk me
 trics and conduct a multi-objective Pareto front analysis for sUAS urgent 
 landing in cities. A high-fidelity simulated city is constructed in the Un
 real game engine with a statistically-accurate representation of rooftop o
 bstacles. Fusion of Polylidar3D and RGBD semantic segmentation output show
 s improved intersection-over-union (IOU) accuracy in landing site identifi
 cation compared to using LiDAR data only.</p>\n<p>&nbsp\;</p>\n<p><span st
 yle="font-size: 14pt\; color: #e03e2d\;"><strong>1PDH will be awarded to t
 he attendees</strong></span></p>
END:VEVENT
END:VCALENDAR