Churchill Beluga Boat Drone Imagery
Aerial imagery surveys are commonly used in marine mammal research to determine population size, habitat distribution and habitat use. Analysis of aerial photos involves hours of manually identifying individuals present in each image and converting raw counts into useable biological statistics. Our...
Format: | Dataset |
---|---|
Language: | unknown |
Published: |
2022
|
Subjects: | |
Online Access: | https://search.dataone.org/view/sha256:b9e6eceec94b5e51b5797877a8727bb34d126926c291c12545c623fab4d3498f |
id |
dataone:sha256:b9e6eceec94b5e51b5797877a8727bb34d126926c291c12545c623fab4d3498f |
---|---|
record_format |
openpolar |
spelling |
dataone:sha256:b9e6eceec94b5e51b5797877a8727bb34d126926c291c12545c623fab4d3498f 2024-10-03T18:46:00+00:00 Churchill Beluga Boat Drone Imagery 2022-01-01T00:00:00Z https://search.dataone.org/view/sha256:b9e6eceec94b5e51b5797877a8727bb34d126926c291c12545c623fab4d3498f unknown Beluga Unmanned Aerial Vehicle kayak boat AERIAL PHOTOGRAPHS video Churchill estuary Dataset 2022 dataone:urn:node:CANWIN 2024-10-03T18:18:51Z Aerial imagery surveys are commonly used in marine mammal research to determine population size, habitat distribution and habitat use. Analysis of aerial photos involves hours of manually identifying individuals present in each image and converting raw counts into useable biological statistics. Our research proposes the use of deep learning algorithms as an assistive technology to increase the efficiency of the marine mammal research workflow. To test the feasibility of this proposal, the existing YOLOv4 convolutional neural network model was trained to detect belugas, kayaks and motorized boats in unmanned aerial vehicle (UAV) imagery. Computer-based object detection achieved an average precision of 61.17% for belugas, 98.58% for boats, and 95.97% for kayaks. We then tested the performance of computer vision tracking of belugas and manned watercraft in UAV videos using the DeepSORT tracking algorithm, achieving a multiple object tracking accuracy (MOTA) ranging from 37% – 88% and multiple object tracking precision (MOTP) between 63% – 86%. Results from this research indicate that deep learning technology can perform at a similar caliber as human annotators in beluga and watercraft detection and tracking, allowing for larger datasets to be processed within a fraction of the time. Dataset Beluga Beluga* Unknown Kayak ENVELOPE(103.217,103.217,71.533,71.533) |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
dataone:urn:node:CANWIN |
language |
unknown |
topic |
Beluga Unmanned Aerial Vehicle kayak boat AERIAL PHOTOGRAPHS video Churchill estuary |
spellingShingle |
Beluga Unmanned Aerial Vehicle kayak boat AERIAL PHOTOGRAPHS video Churchill estuary Churchill Beluga Boat Drone Imagery |
topic_facet |
Beluga Unmanned Aerial Vehicle kayak boat AERIAL PHOTOGRAPHS video Churchill estuary |
description |
Aerial imagery surveys are commonly used in marine mammal research to determine population size, habitat distribution and habitat use. Analysis of aerial photos involves hours of manually identifying individuals present in each image and converting raw counts into useable biological statistics. Our research proposes the use of deep learning algorithms as an assistive technology to increase the efficiency of the marine mammal research workflow. To test the feasibility of this proposal, the existing YOLOv4 convolutional neural network model was trained to detect belugas, kayaks and motorized boats in unmanned aerial vehicle (UAV) imagery. Computer-based object detection achieved an average precision of 61.17% for belugas, 98.58% for boats, and 95.97% for kayaks. We then tested the performance of computer vision tracking of belugas and manned watercraft in UAV videos using the DeepSORT tracking algorithm, achieving a multiple object tracking accuracy (MOTA) ranging from 37% – 88% and multiple object tracking precision (MOTP) between 63% – 86%. Results from this research indicate that deep learning technology can perform at a similar caliber as human annotators in beluga and watercraft detection and tracking, allowing for larger datasets to be processed within a fraction of the time. |
format |
Dataset |
title |
Churchill Beluga Boat Drone Imagery |
title_short |
Churchill Beluga Boat Drone Imagery |
title_full |
Churchill Beluga Boat Drone Imagery |
title_fullStr |
Churchill Beluga Boat Drone Imagery |
title_full_unstemmed |
Churchill Beluga Boat Drone Imagery |
title_sort |
churchill beluga boat drone imagery |
publishDate |
2022 |
url |
https://search.dataone.org/view/sha256:b9e6eceec94b5e51b5797877a8727bb34d126926c291c12545c623fab4d3498f |
long_lat |
ENVELOPE(103.217,103.217,71.533,71.533) |
geographic |
Kayak |
geographic_facet |
Kayak |
genre |
Beluga Beluga* |
genre_facet |
Beluga Beluga* |
_version_ |
1811923103907840000 |