Evaluating Thermal and Color Sensors for Automating Detection of Penguins and Pinnipeds in Images Collected with an Unoccupied Aerial System

Estimating seabird and pinniped abundance is central to wildlife management and ecosystem monitoring in Antarctica. Unoccupied aerial systems (UAS) can collect images to support monitoring, but manual image analysis is often impractical. Automating target detection using deep learning techniques may...

Full description

Saved in:
Bibliographic Details
Published in:Drones (Basel) 2022-09, Vol.6 (9), p.255
Main Authors: Hinke, Jefferson T., Giuseffi, Louise M., Hermanson, Victoria R., Woodman, Samuel M., Krause, Douglas J.
Format: Article
Language:English
Subjects:
Aircraft
Algorithms
Annotations
Antarctica
automated detection
Automation
Cameras
census
Color imagery
Data acquisition
Deep learning
Distribution
drone
Drone aircraft
Ecological monitoring
Environmental aspects
Ground stations
Image acquisition
Image analysis
Image classification
Image processing
Infrared imaging
Machine learning
Marine environment
Marine mammals
Methods
Neural networks
Penguins
Sensors
Software
Target detection
Technology application
Tracking and trailing
Wildlife management
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Estimating seabird and pinniped abundance is central to wildlife management and ecosystem monitoring in Antarctica. Unoccupied aerial systems (UAS) can collect images to support monitoring, but manual image analysis is often impractical. Automating target detection using deep learning techniques may improve data acquisition, but different image sensors may affect target detectability and model performance. We compared the performance of automated detection models based on infrared (IR) or color (RGB) images and tested whether IR images, or training data that included annotations of non-target features, improved model performance. For this assessment, we collected paired IR and RGB images of nesting penguins (Pygoscelis spp.) and aggregations of Antarctic fur seals (Arctocephalus gazella) with a small UAS at Cape Shirreff, Livingston Island (60.79 °W, 62.46 °S). We trained seven independent classification models using the Video and Image Analytics for Marine Environments (VIAME) software and created an open-access R tool, vvipr, to standardize the assessment of VIAME-based model performance. We found that the IR images and the addition of non-target annotations had no clear benefits for model performance given the available data. Nonetheless, the generally high performance of the penguin models provided encouraging results for further improving automated image analysis from UAS surveys.
ISSN:2504-446X
2504-446X
DOI:10.3390/drones6090255