BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20210314T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20201101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20201213T042039Z UID:0E583B43-563F-4059-BC0B-F91AAB21DDFB DTSTART;TZID=America/New_York:20201211T120000 DTEND;TZID=America/New_York:20201211T130000 DESCRIPTION:Uniting the Computer Vision and Remote Sensing Communities with Open Source Competitions\n\nThe computer vision community has made great strides in the last decade\, due in large part to the growth of deep learn ing. The application of advanced computer vision techniques to the remote sensing domain has lagged considerably\, however\, due to a number of a fa ctors such a lack of labeled data\, disparate object sizes\, and the sheer scale of remote sensing datasets. We describe efforts to accelerate the a pplication of advanced computer vision techniques to the remote sensing da ta via the SpaceNet initiative. SpaceNet is inspired by the highly success ful ImageNet competition series that helped spur many of the advances in c omputer vision applied to traditional imagery. Accordingly\, the SpaceNet partners have released a large\, high quality dataset containing high-reso lution satellite imagery and hand-labeled objects of interest. On top of t his dataset\, the SpaceNet partners run a series of open competitions that showcase the use cases of computer vision and data science techniques wit h satellite imagery. We discuss some of the lessons learned from early com petitions that focused on foundational mapping techniques such as building footprint extraction and road network detection. Further\, we discuss exi sting capability gaps and plans for future competitions that will address such issues as seasonal variability\, robust change detection\, and fusion with non-imagery datasets.\n\nAdam Van Etten is the Technical Director of CosmiQ Works\, an In-Q-Tel Lab. In this role\, he applies machine learnin g and computer vision techniques to satellite imaging data\, focused on pr oblems of interest to the US Government. Adam has focused on helping run t he SpaceNet initiative\, and on researching rapid computer vision techniqu es that readily scale to the enormous sizes of satellite imagery corpora. Prior to In-Q Tel\, Adam was a Data Scientist for Data Tactics working at DARPA headquarters developing tools and scalable algorithms for big data a nalysis on a variety of projects. Adam received his Ph.D. in physics from Stanford University and bachelors in physics and astronomy from the Univer sity of Washington.\n\nSpeaker(s): Adam Etten\, \n\nGreenbelt\, Maryland\, United States\, Virtual: https://events.vtools.ieee.org/m/250676 LOCATION:Greenbelt\, Maryland\, United States\, Virtual: https://events.vto ols.ieee.org/m/250676 ORGANIZER:zhuosen.wang@nasa.gov SEQUENCE:1 SUMMARY:IEEE Geoscience and Remote Sensing Society (GRSS) Washington\, DC & Northern VA Chapter Virtual Industry Distinguished Lecturer Webinar URL;VALUE=URI:https://events.vtools.ieee.org/m/250676 X-ALT-DESC:Description: <br /><p>Uniting the Computer Vision and Remote Sen sing Communities with Open Source Competitions</p>\n<p>The computer vision community has made great strides in the last decade\, due in large part t o the growth of deep learning. The application of advanced computer vision techniques to the remote sensing domain has lagged considerably\, however \, due to a number of a factors such a lack of labeled data\, disparate ob ject sizes\, and the sheer scale of remote sensing datasets. We describe e fforts to accelerate the application of advanced computer vision technique s to the remote sensing data via the SpaceNet initiative. SpaceNet is insp ired by the highly successful ImageNet competition series that helped spur many of the advances in computer vision applied to traditional imagery. A ccordingly\, the SpaceNet partners have released a large\, high quality da taset containing high-resolution satellite imagery and hand-labeled object s of interest. On top of this dataset\, the SpaceNet partners run a series of open competitions that showcase the use cases of computer vision and d ata science techniques with satellite imagery. We discuss some of the less ons learned from early competitions that focused on foundational mapping t echniques such as building footprint extraction and road network detection . Further\, we discuss existing capability gaps and plans for future compe titions that will address such issues as seasonal variability\, robust cha nge detection\, and fusion with non-imagery datasets.</p>\n<p><br />Adam V an Etten is the Technical Director of CosmiQ Works\, an In-Q-Tel Lab. In t his role\, he applies machine learning and computer vision techniques to s atellite imaging data\, focused on problems of interest to the US Governme nt. Adam has focused on helping run the SpaceNet initiative\, and on resea rching rapid computer vision techniques that readily scale to the enormous sizes of satellite imagery corpora. Prior to In-Q Tel\, Adam was a Data S cientist for Data Tactics working at DARPA headquarters developing tools a nd scalable algorithms for big data analysis on a variety of projects. Ada m received his Ph.D. in physics from Stanford University and bachelors in physics and astronomy from the University of Washington.</p> END:VEVENT END:VCALENDAR