Filters: Types: Map Service (X) > partyWithName: U.S. Fish and Wildlife Service, Alaska Region (X)
Folders: ROOT > ScienceBase Catalog > US Fish and Wildlife Service (USFWS) > Initiatives ( Show direct descendants )
4 results (8ms)
Location
Folder
ROOT _ScienceBase Catalog __US Fish and Wildlife Service (USFWS) ___Initiatives Filters
Date Range
Extensions Types Contacts Categories Tag Types Tag Schemes |
These are the images associated with the project, including: (1) OriginalImages: original 863 images provided to West Inc from USFWS and others for model training; (2) YoloSliced: 1897 programmatically cropped original images used for training a YOLO Model (300 x 300 pixels); (3) OriginalImages_Box: 785 annotated images; (4) YoloSliced_Box: 1897 annotated sliced images.
Categories: Data,
Image;
Types: Map Service,
OGC WFS Layer,
OGC WMS Layer,
OGC WMS Service;
Tags: ANIMALS/VERTEBRATES,
BIOLOGICAL CLASSIFICATION,
BIRDS,
EARTH SCIENCE,
Image,
The SeaDuckDetectoR is software designed to identify sea ducks and other avian species in aerial photographs. The program is run through R and RStudio. The product includes a .zip file “SeaDuckDetectoR.0.1.0.zip” with the files for installation, and a manual “SeaDuckDetectoR_Manual.docx” explaining how to run the program.
Categories: Data,
Software;
Types: Map Service,
OGC WFS Layer,
OGC WMS Layer,
OGC WMS Service;
Tags: ANIMALS/VERTEBRATES,
BIOLOGICAL CLASSIFICATION,
BIRDS,
EARTH SCIENCE,
Science Keywords,
This is the final report from SDJV Project #157: Automated Sea Duck Counts from Aerial Imagery, conducted by WEST, Inc.
Categories: Data;
Types: Map Service,
OGC WFS Layer,
OGC WMS Layer,
OGC WMS Service;
Tags: ANIMALS/VERTEBRATES,
BIOLOGICAL CLASSIFICATION,
BIRDS,
EARTH SCIENCE,
Report,
This project developed an artificial intelligence system based on a convoluted neural network capable of detecting and counting sea duck individuals in aerial photos and classifying individuals to species and sex when possible, to reduce time and cost commitments associated with processing imagery from aerial surveys. We used a dataset consisting of 810 aerial images containing sea ducks and other birds in offshore and coastal environments. Images were collected from fixed wing aircraft at varying flight heights and image resolution. A biologist reviewed each image identifying and annotating the position of objects of interest (birds) in the image by drawing a bounding box surrounding each object, and assigned species...
Categories: Data,
Project;
Types: Map Service,
OGC WFS Layer,
OGC WMS Layer,
OGC WMS Service;
Tags: ANIMALS/VERTEBRATES,
BIOLOGICAL CLASSIFICATION,
BIRDS,
EARTH SCIENCE,
Project,
|
![]() |