BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-it-2023//talk//W3NYLQ
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-it-2023-W3NYLQ@talks.staging.osgeo.org
DTSTART;TZID=GMT:20230614T151500
DTEND;TZID=GMT:20230614T153000
DESCRIPTION:This study presents a novel approach to monitor oil spills and 
 ships using Synthetic Aperture Radar (SAR) raw data and deep learning tech
 niques. The proposed methodology involves several steps including pre-proc
 essing (focusing\, filtering and land sea mask)\, semantic segmentation\, 
 and classification using a deep convolutional neural network (DCNN) model\
 , as well as real-time (FFT-based) processing to ensure a fast response. \
 n\nTo train the DCNN model\, the study combined three datasets: CleanSeaNe
 t\, TenGeoP-SARwv\, and GAP_OilSpill_DB. The first two datasets are public
 ly available\, while the third dataset was specifically built by the autho
 rs by integrating known and documented case studies from news articles and
  cases identified in the sea area in front of the port of Brindisi (Southe
 rn Italy)\, internally validated by expert GAP operators.  \n\nData augmen
 tation techniques were also utilized to improve the model's performance by
  generating additional training data. The DCNN model uses DeepLab v3+ base
 d on ResNet-18 and is trained on a large dataset of SAR images that includ
 es various types of oil spills\, look-alikes\, novelty objects\, and ships
 . \n\nThe proposed system is optimized to process data on board the satell
 ite to ensure a real-time response. The system transmits images to the gro
 und segment only if there is an event of interest (e.g. a novelty object o
 r an oil spill detected eventually involving the nearest ships).  \n\nThe 
 study demonstrates that the proposed approach provides a promising solutio
 n for real-time monitoring of oil spills\, ships and novelty objects using
  satellite SAR raw data. The use of deep learning and data augmentation te
 chniques can significantly improve the accuracy and speed of detection\, w
 hich can ultimately lead to better environmental management and oil spill 
 response. .Additionally\, the proposed approach can be applied to a variet
 y of SAR datasets and has the potential to be integrated with existing oil
  spill response systems.  \n\nAcknowledgments  \n\nThis work was carried
  out in the framework of the APP4AD project (“Advanced Payload data Proc
 essing for Autonomy & Decision”\, Bando ASI “Tecnologie Abilitanti Tra
 sversali”\, Codice Unico di Progetto F95F21000020005)\, funded by the It
 alian Space Agency (ASI). ERS\, ENVISAT and Sentinel-1 data are provided b
 y the European Space Agency (ESA).
DTSTAMP:20260522T060747Z
LOCATION:Sala Biblioteca @ PoliBa
SUMMARY:Real-Time Oil Spill Detection by Using SAR-Based Machine Learning T
 echniques - Davide Oscar Nitti\, Alberto Morea\, Khalid Tijani\, Nicolò R
 icciardi\, Raffaele Nutricato
URL:https://talks.staging.osgeo.org/foss4g-it-2023/talk/W3NYLQ/
END:VEVENT
END:VCALENDAR