Deep Learning for Automated Detection and Classification of Waterfowl, Seabirds, and other Wildlife from Digital Aerial Imagery

Archived

Geological Survey

Description

The Bureau of Ocean Energy Management (BOEM), and the US Fish and Wildlife Service (USFWS) Division of Migratory Bird Management (DMBM), Branch of Migratory Bird Surveys, and US Geological Survey (USGS) are funding and collaborating on studies to develop deep learning algorithms that automate the process of detecting and classifying waterfowl, seabirds, and other marine wildlife species. BOEM has prioritized the use of Outer Continental Shelf Program funds by USGS in FY19, FY20, and FY21 to advance development of an imagery and annotation database and development of deep learning algorithms (DLA) (https://www.boem.gov/Environmental-Stewardship/Environmental-Studies/Partnerships/Partner-USGS.aspx). This project will advance the application of computer vision and deep learning methods to automated detection and classification of waterfowl, seabirds, and other marine wildlife species from digital aerial imagery.

Who can apply

  • Public and State controlled institutions of higher education

Contact

Desiree T Santa <br/>Grant Specialist <br/>Phone 703-648-7382
dsanta@usgs.gov

Key dates & funding
  • PostedJun 7, 2019
  • ClosesJun 17, 2019
  • Award floor$85,000
  • Award ceiling$85,000
  • Program funding$85,000
  • Expected awards1
  • CFDA15.808
Categories

Pro insight

Edit and export this grant’s proposal template, plus deadline reminders, similar-grant suggestions, and funder history — all available with Pro.

Unlock with Pro