Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty
Many wildlife species inhabit inaccessible environments, limiting researchers ability to conduct essential population surveys. Recently, very high resolution (sub-metre) satellite imagery has enabled remote monitoring of certain species directly from space; however, manual analysis of the imagery is...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2020
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs12122026 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/12/12/2026/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/12/12/2026/ 2023-08-20T04:10:18+02:00 Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty Ellen Bowler Peter T. Fretwell Geoffrey French Michal Mackiewicz agris 2020-06-24 application/pdf https://doi.org/10.3390/rs12122026 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/rs12122026 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 12; Issue 12; Pages: 2026 WorldView-3 convolutional neural network VHR satellite imagery wildlife monitoring observer uncertainty Wandering Albatross Text 2020 ftmdpi https://doi.org/10.3390/rs12122026 2023-07-31T23:40:58Z Many wildlife species inhabit inaccessible environments, limiting researchers ability to conduct essential population surveys. Recently, very high resolution (sub-metre) satellite imagery has enabled remote monitoring of certain species directly from space; however, manual analysis of the imagery is time-consuming, expensive and subjective. State-of-the-art deep learning approaches can automate this process; however, often image datasets are small, and uncertainty in ground truth labels can affect supervised training schemes and the interpretation of errors. In this paper, we investigate these challenges by conducting both manual and automated counts of nesting Wandering Albatrosses on four separate islands, captured by the 31 cm resolution WorldView-3 sensor. We collect counts from six observers, and train a convolutional neural network (U-Net) using leave-one-island-out cross-validation and different combinations of ground truth labels. We show that (1) interobserver variation in manual counts is significant and differs between the four islands, (2) the small dataset can limit the networks ability to generalise to unseen imagery and (3) the choice of ground truth labels can have a significant impact on our assessment of network performance. Our final results show the network detects albatrosses as accurately as human observers for two of the islands, while in the other two misclassifications are largely caused by the presence of noise, cloud cover and habitat, which was not present in the training dataset. While the results show promise, we stress the importance of considering these factors for any study where data is limited and observer confidence is variable. Text Wandering Albatross MDPI Open Access Publishing Four Islands ENVELOPE(-108.218,-108.218,56.050,56.050) Remote Sensing 12 12 2026 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
WorldView-3 convolutional neural network VHR satellite imagery wildlife monitoring observer uncertainty Wandering Albatross |
spellingShingle |
WorldView-3 convolutional neural network VHR satellite imagery wildlife monitoring observer uncertainty Wandering Albatross Ellen Bowler Peter T. Fretwell Geoffrey French Michal Mackiewicz Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty |
topic_facet |
WorldView-3 convolutional neural network VHR satellite imagery wildlife monitoring observer uncertainty Wandering Albatross |
description |
Many wildlife species inhabit inaccessible environments, limiting researchers ability to conduct essential population surveys. Recently, very high resolution (sub-metre) satellite imagery has enabled remote monitoring of certain species directly from space; however, manual analysis of the imagery is time-consuming, expensive and subjective. State-of-the-art deep learning approaches can automate this process; however, often image datasets are small, and uncertainty in ground truth labels can affect supervised training schemes and the interpretation of errors. In this paper, we investigate these challenges by conducting both manual and automated counts of nesting Wandering Albatrosses on four separate islands, captured by the 31 cm resolution WorldView-3 sensor. We collect counts from six observers, and train a convolutional neural network (U-Net) using leave-one-island-out cross-validation and different combinations of ground truth labels. We show that (1) interobserver variation in manual counts is significant and differs between the four islands, (2) the small dataset can limit the networks ability to generalise to unseen imagery and (3) the choice of ground truth labels can have a significant impact on our assessment of network performance. Our final results show the network detects albatrosses as accurately as human observers for two of the islands, while in the other two misclassifications are largely caused by the presence of noise, cloud cover and habitat, which was not present in the training dataset. While the results show promise, we stress the importance of considering these factors for any study where data is limited and observer confidence is variable. |
format |
Text |
author |
Ellen Bowler Peter T. Fretwell Geoffrey French Michal Mackiewicz |
author_facet |
Ellen Bowler Peter T. Fretwell Geoffrey French Michal Mackiewicz |
author_sort |
Ellen Bowler |
title |
Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty |
title_short |
Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty |
title_full |
Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty |
title_fullStr |
Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty |
title_full_unstemmed |
Using Deep Learning to Count Albatrosses from Space: Assessing Results in Light of Ground Truth Uncertainty |
title_sort |
using deep learning to count albatrosses from space: assessing results in light of ground truth uncertainty |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2020 |
url |
https://doi.org/10.3390/rs12122026 |
op_coverage |
agris |
long_lat |
ENVELOPE(-108.218,-108.218,56.050,56.050) |
geographic |
Four Islands |
geographic_facet |
Four Islands |
genre |
Wandering Albatross |
genre_facet |
Wandering Albatross |
op_source |
Remote Sensing; Volume 12; Issue 12; Pages: 2026 |
op_relation |
https://dx.doi.org/10.3390/rs12122026 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs12122026 |
container_title |
Remote Sensing |
container_volume |
12 |
container_issue |
12 |
container_start_page |
2026 |
_version_ |
1774724396586369024 |